# Research Papers — 2026-10 · bundle page 122 of 156

> Full-text markdown of papers #6051–6100 of 7799 published in 2026-10, newest first. AI-readable mirrors of the full 7799-paper 2026-10 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-10/page/122
[← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/121.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-10/page/123.md)

### JEV versus LLMs: Accuracy, Cost and Calibration on Seven Political Science Replications

Authors: Steven Denney, Matthew DiGiuseppe
Published: 2026-10-05
Categories: cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2610.06625v2

Large language models (LLMs) annotate and scale political text or constructs by generating text tokens. A new class of models, which TypeSafe markets as "System One" models, instead returns decisions and probability distributions across a user-supplied fixed answer set. A commercial model, JEV, is advertised as having a dramatic cost and speed advantage over traditional LLMs along with better calibrated decisions. As such, it might be useful for social scientists looking to quickly and cost-effectively annotate or scale large corpora of text and have a reliable indicator of a classifier's uncertainty. Yet, the accuracy of these claims and the broader model accuracy in social science text-based tasks are not yet established. In this paper, we do just that and hope to establish the suitability of JEV for social science tasks. We compare JEV with LLMs and human coders from published research, and with a current mid-tier commercial LLM (GPT-6 Luna) and an open-weight alternative (Qwen3.8-27B). We find that JEV matches, or comes close to, the capabilities of both LLMs in a variety of tasks. However, we find no cost advantage over GPT-6 Luna at OpenAI's batch prices. Further, we find that, when each question is asked once, JEV's probabilities are better calibrated than GPT-6 Luna's token probabilities, but not consistently better than Qwen3.8-27B's. We conclude that unless researchers have a need for speed, JEV's only obvious advantage is ease of parsing the underlying choice probabilities.

---

### JEV versus LLMs: Accuracy, Cost and Calibration on Seven Political Science Replications

Authors: Matthew DiGiuseppe, Steven Denney
Published: 2026-10-05
Categories: cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2610.06625v1

Large language models (LLMs) annotate and scale political text or constructs by generating text tokens. A new class of models, which TypeSafe markets as "System One" models, instead returns decisions and probability distributions across a user-supplied fixed answer set. A commercial model, JEV, is advertised as having a dramatic cost and speed advantage over traditional LLMs along with better calibrated decisions. As such, it might be useful for social scientists looking to quickly and cost-effectively annotate or scale large corpora of text and have a reliable indicator of a classifier's uncertainty. Yet, the accuracy of these claims and the broader model accuracy in social science text-based tasks are not yet established. In this paper, we do just that and hope to establish the suitability of JEV for social science tasks. We compare JEV with LLMs and human coders from published research, and with a current mid-tier commercial LLM (GPT-6 Luna) and an open-weight alternative (Qwen3.8-27B). We find that JEV matches, or comes close to, the capabilities of both LLMs in a variety of tasks. However, we find no cost advantage over GPT-6 Luna at OpenAI's batch prices. Further, we find that, when each question is asked once, JEV's probabilities are better calibrated than GPT-6 Luna's token probabilities, but not consistently better than Qwen3.8-27B's. We conclude that unless researchers have a need for speed, JEV's only obvious advantage is ease of parsing the underlying choice probabilities.

---

### Large Language Model-Guided Discovery of Weight-Five Bivariate Bicycle Codes

Authors: Juan Cruz-Benito
Published: 2026-10-05
Categories: quant-ph, cs.AI
arXiv: https://arxiv.org/abs/2610.06623v1

Building on our earlier program-evolution workflow guided by large language models (LLMs), we study weight-five bivariate bicycle (BB) and perturbed bivariate bicycle (PBB) codes. The resulting catalogue contains 1,142 distinct code proposals, including 1,081 nonbaseline proposals attributable to LLM-generated programs. Across the catalogue, we certify connected Calderbank--Shor--Steane (CSS) realizations ((96,4,10)), ((140,6,10)), and ((180,4,14)). A post-search comparison certifies seven imported Lin--Pryadko archive constructions. For leading parameter triples also represented in that archive, we provide exact distance evidence, explicit bivariate presentations, and verified component reductions. A basis-independent connectivity analysis identifies 409 of the 1,142 catalogue entries as disconnected and shows that 73.1\% of the classes with exact distance certificates contain repeated connected components. Algebraic analysis organizes the connected CSS classes into order-3, order-7, and order-15 cyclotomic-kernel strata. The strongest exact connected PBB parameter point is ((216,4,10)), attained by two distinct component classes. Among the 936 distinct CSS proposals from the LLM-guided campaign with a recorded positive distance, 816 (87.18\%) are certified at $d\geq5$. For comparison, three random-search controls each sample 6,444 CSS code proposals uniformly without replacement, using the same per-lattice and encoded-dimension sample counts as the LLM-guided campaign. In these controls, 4,672--4,785 proposals (72.50--74.26\%) meet the same criterion. The LLM-guided campaign has the higher certified yield, while the random controls cover more connected classes. Together, these results extend LLM-guided discovery to a more constrained code family and provide a reproducible structural and exact-distance account of its strongest candidates.

---

### Frozen Factor or Spectral Band? Disentangling Two Choices in Low-Rank LoRA

Authors: Adnan Slimane Ali, Ayoub Belfatmi, David Ngwe Pouth
Published: 2026-10-05
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2610.06621v1

Spectral variants of low-rank adaptation (LoRA) choose both a subspace and which factor to freeze. We separate these choices by freezing the input factor A or output factor B on the top or bottom singular directions of pretrained weights, with learning rates selected separately. At rank 2, the same-band advantage of freezing A is larger than either within-factor band difference on all four task-model pairs with complete comparisons. Freezing B also trails comparable-budget free LoRA by 8-18 percentage points on five pairs spanning a formatting task and OpenBookQA. The A-frozen advantage persists in a single-GPU-model replication and within individual MLP module groups, including controls with equal or greater trainable counts for B frozen, and when A is frozen on a random orthonormal basis. The factor contrast weakens with rank. On OpenBookQA / Qwen2.5-1.5B at rank 16, PEFT's MiCA implementation trails comparable-budget LoRA by 3.08 points under a shared training recipe transferred from the MiCA paper. A trained oracle output subspace largely removes the low-rank deficit; partial warm-up gains recur across three direction seeds. The factor-versus-band ordering is descriptive; an approximate multiplicity audit weakens several earlier significance claims. These results extend known factor asymmetry by showing how its magnitude depends on spectral placement, rank and training conditions.

---

### RealtimeWAM: One-Step Asynchronous World Action Models

Authors: Chengtao Lv, Jinyang Du, Shuyi Feng, Yang Yong, Shiqiao Gu, Shunzi Yang, Ruihao Gong, Shen Ren, Tianwei Zhang, Wenya Wang
Published: 2026-10-05
Categories: cs.CV, cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2610.06617v1

World Action Models (WAMs) incorporate visual representations from video generation backbones to guide action prediction. Recent efficient WAMs adopt Mixture-of-Transformers (MoT) architectures and compute video representations once for reuse by the action expert. However, intra-expert iteration (\ie, multi-step action denoising) and inter-expert waiting (\ie, sequential execution of the video and action experts) still limit inference efficiency. To this end, we present RealtimeWAM, an extremely efficient WAM variant with one-step action generation and asynchronous inference, addressing these two bottlenecks. To reduce intra-expert iteration, we propose Teacher-Anchored Consistency Distillation (TACD) to address a local-global error gap: low local consistency error alone does not guarantee accurate final actions. TACD supplements local consistency with explicit supervision from the frozen teacher's multi-step rollout endpoint, enabling accurate one-step action generation. Additionally, we propose Cross-Expert Wavefront Pipelining (CEWP) to eliminate unnecessary expert-level waiting. It overlaps the two experts through block-wise sharing of the video KV cache, synchronizing only immediately before the corresponding action attention consumes it. Extensive experiments across diverse benchmarks (\eg, LIBERO, LIBERO-Plus and RoboTwin) and model variants (\eg, Fast-WAM and Faster-WAM) demonstrate the superiority of RealtimeWAM. Notably, RealtimeWAM maintains near-lossless performance (\ie, $<1\%$ drop) across these benchmarks while delivering significant end-to-end speedup (\eg, $\sim25\times$ on H100). Our code and checkpoints are available via this \href{https://github.com/ModelTC/LightX2V/tree/main/examples/realtimewam}{link}.

---

### Video Encoders Built on Image Representations

Authors: Jusheng Zhang, Wenhao Wang, Longqi Cai, Liangzhe Yuan, Yuxiao Wang, Ming-Hsuan Yang
Published: 2026-10-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.06616v1

The design of a video encoder determines when frames begin to interact and which frame-specific visual evidence remains accessible to the language model. Native video pathways couple neighboring frames during visual encoding, whereas image pathways preserve independently computed frame representations but incur a much larger visual-token cost when all image tokens are forwarded. We ask a basic question: whether a compact video encoder can instead be built on image representations. To answer this question, we separate three operations that are often coupled: per-frame representation, cross-frame token allocation, and temporal interaction. A frozen image encoder first produces frame-specific candidates. A question-aware selector then allocates a fixed token budget across frames using relevance, diversity, and cross-frame correspondence, after which a lightweight learned refiner reads neighboring-frame context and writes residual updates only to the retained anchors. This preserves source positions and keeps the visual output at the fixed budget. Across 13 benchmarks and three vision-language backbones, the resulting pathway matches full-image aggregate performance while using only about 28%-35% of its visual tokens. Specifically, on Qwen3-VL-8B, it achieves a 13-benchmark macro-average of 62.75 with 1,535 visual tokens, compared with 62.58 for the full Image pathway at 4,424 tokens and 59.49 for native Conv3D at 2,212 tokens. On Qwen3-VL-32B, it reaches a 13-benchmark macro-average of 66.28, compared with 66.09 for Image, while providing a 2.16x end-to-end speedup. These results show that compact video encoding does not require early temporal mixing: frame-specific evidence can be preserved first, allocated jointly, and temporally contextualized after selection.

---

### COMPASS 2.0: psychometric representational similarity analysis distinguishes symptom structure from personal signal

Authors: Baihan Lin
Published: 2026-10-05
Categories: q-bio.NC, cs.CL
arXiv: https://arxiv.org/abs/2610.06615v1

Language models can score psychiatric questionnaires from speech, but agreement with self-report may reflect the questionnaire rather than the person. We introduce psychometric representational similarity analysis, a framework for comparing the structure of speech-derived scores, self-report, item wording and theory, and implement it alongside person-level construct scoring in COMPASS 2.0. We show how similarly worded items induce covariance without psychological signal. In pre-registered discovery and confirmation analyses of clinical interviews from 275 participants, language-derived symptom geometry resembled wording more than self-report, with no structure beyond wording detected by the registered tests. Geometric agreement with self-report survived assigning participants someone else's answers, whereas person-paired scores captured distress more than specific symptoms. Complementary analyses examined counselling quality and wording structure across 34 instruments and the Research Domain Criteria (RDoC) framework. These findings distinguish agreement about psychological structure from evidence that language-derived assessments track individual people.

---

### FREA: A Multi-Source Expert Benchmark for Reaction Feasibility Verification

Authors: Botao Yu, Bo Zhou, Daniel Adu-Ampratwum, Frazier N. Baker, Ziru Chen, Reza Averly, Ye Liu, Wenhao Gao, Xia Ning, Huan Sun
Published: 2026-10-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.06614v1

As generative models and AI agents propose chemical reactions at a scale beyond expert review, feasibility verifiers decide which proposals enter synthesis planning. But do their decisions agree with chemists across different kinds of candidates? We introduce FREA, a benchmark of 751 reactions labeled by expert chemists under an explicit feasibility criterion, drawn from retrosynthesis model proposals, zero-yield experimental records, edits by large language models (LLMs), and five negative candidate generation methods. Our evaluation finds that no verifier leads across all sources: LLMs given only the criterion are competitive with dedicated verifiers, while forward models perform best on retrosynthesis proposals but reject most feasible edits of recorded reactions at the evaluated operating points. Looking beyond aggregate scores, both forward models perform below chance when separating infeasible alternative disconnections from feasible generated candidates. To study whether negative supervision addresses these weaknesses, we also release a corpus of over 14 million recorded reactions and generated negative candidates. In matched training comparisons, adding a mixture of generated negatives to forward training raises mean AUROC across sources, but these gains do not extend to retrosynthesis proposals. Varying the generation method further shows that the largest gain on generated candidates coincides with worse proposal screening. These findings motivate evaluating verifiers against experts across sources and designing negatives for transfer to model proposals.

---

### Lens3D: Target-Conditioned Visual Foveation for Fine-Grained 3D Understanding

Authors: Junming Huang, Zini Chen, Shuaiying Hou, Chi Wang, Qiang Dai, Weiwei Xu
Published: 2026-10-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.06611v1

Existing 3D large language models often overlook fine-grained attributes and less visually salient objects and parts, even when relevant evidence is present in scene videos. We introduce Lens3D to improve fine-grained object understanding through external visual assistance and knowledge transfer. Its LensUnd pipeline adopts 3D localization to select informative, complementary views for an external 2D vision-language model, supporting fine-grained object captioning, small-object grounding, and fine-grained object question answering. LensDistill transfers the resulting fine-grained knowledge to 3D LLMs through detailed caption supervision, enabling captioning from native inputs without external VLM calls. We also construct LensBench, a held-out evaluation set of 2,068 objects with three silver-standard reference descriptions per object. Experiments with Video-3D LLM and 3DRS demonstrate that LensDistill substantially improves fine-grained object captioning while preserving existing grounding and scene-level QA performance. These results establish the feasibility of transferring externally acquired fine-grained knowledge into native 3D LLMs.

---

### The Surrogate Is Not the Reward: Post-Surrogate Primary-Outcome Acquisition in Contextual Bandits

Authors: Kyungbok Lee, Michael R. Kosorok
Published: 2026-10-05
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2610.06610v1

We study contextual bandits in which a surrogate is observed after the action but before the learner decides whether to acquire the primary outcome that defines action value and regret. The value of acquiring the primary outcome depends on both decision relevance (how much the current outcome matters for comparing policies) and the residual uncertainty after observing the surrogate. The Audited Surrogate Bandit (ASB) learns a contextual policy while allocating a budget of $B$ primary-outcome acquisitions over $T$ rounds. ASB sets a pre-surrogate acquisition level from current decision relevance and, after observing the surrogate, redistributes that level using an estimate of that residual uncertainty. For a finite class of $N$ policies over $K$ actions, ASB incurs $\widetilde O(\sqrt{KT\log N}\{1+\sqrt{T/B}\})$ regret relative to the best policy in the class. In a two-action family where the surrogate does not reveal the better action, a learner that observes the surrogate before deciding whether to acquire can achieve bounded regret, whereas any learner that must decide before seeing the surrogate incurs $Ω(T/B)$ worst-case regret under the same budget. Synthetic experiments show that both acquisition factors matter: ASB has lower regret than variants using only decision relevance or only residual uncertainty. On a KuaiRec benchmark of user-video interactions, the regret gap relative to relevance-only acquisition widens and then narrows as the budget grows.

---

### Separators Make Carry Propagation Learnable:The Geometry of Latent Carry in a Multiplication Transformer

Authors: Sama Satariyan, Raphael Cousin, G{é}rard Biau
Published: 2026-10-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.06605v1

Transformers asked to multiply multi-digit numbers in a single forward pass often fail, and interpretability studies of pretrained language models find arithmetic solved by input-range heuristics rather than by an explicit carry. We train small Llama-style transformers from scratch on 4x4 multiplication without chain of thought and find that the input format is decisive: inserting a space token between digits raises exact-match accuracy from 1% to 89%. Output positions are learned in carry-chain order, with the middle digits, which have the longest-range dependencies, learned last. Inside the model, the separator token that predicts each digit (its prediction slot) encodes the carry-in as an angle on a ring in the residual stream; examples with more distinct carry values fill more of the ring. Activation patching between examples matched on the column sum shows that this state is causally used before the last layer: patching the prediction slot alone transfers the source carry in up to 84% of cases after block 4 for one middle column of our best model, while for other columns the carry is first assembled at the neighboring answer slot before reaching its own. Remaining errors are almost always off by one, consistent with a small error on the carry or on the circular digit code.

---

### Word-Level Text Unmixing via Evidence-Preserving Ownership Routing with Language Models

Authors: Jinglin He, Siyang Jiang, Lixing He, Guoliang Xing, Hongkai Chen
Published: 2026-10-05
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2610.06603v1

Text from multiple sources can become interleaved into a single sequence when attribution metadata is lost, such as overlapping speech transcripts, document reading flows, or concurrent agent streams. We formalize this challenge as Word-Level Text Unmixing: given an interleaved lexical stream and source count K, recover the original source sequences while preserving every word occurrence and its within-source order exactly. Directly generating separated texts with LLMs can omit, duplicate, or hallucinate words, violating this exact-reconstruction objective. We therefore propose Evidence-Preserving Ownership Routing (EPOR), which decouples source-ownership prediction from reconstruction. EPOR adapts a causal LLM to predict canonical ownership routes conditioned on the mixed stream and prior routing decisions. At inference, completion-safe constrained decoding is combined with deterministic indexed reconstruction, yielding structurally valid K-source partitions that preserve every observed occurrence exactly once. We also introduce UNMIXBENCH, covering controlled synthetic mixtures, timestamp-derived speech from AMI and ICSI, layout-derived document streams from ReadingBank, and simulated concurrent digital outputs. Across five evaluation tracks, a 4B EPOR model achieves the lowest mean minimum-permutation word error rate among finetuned baselines, reducing the five-track mean by 22.3% relative to compact source-array generation and remaining competitive with zero-shot frontier LLMs. These results show that when lexical evidence is fully observed, separating ownership inference from lexical regeneration provides a reliable alternative to direct generation.

---

### Multitask Conditional Generative Adversarial Network Enables Automatic Whole Knee Cartilage and Menisci Segmentation and Reliable $T_{1ρ}$ and $T_2$ Quantification Without High-Resolution Morphological Images

Authors: Ahmed Tahseen Minhaz, Richard Lartey, Zhiyuan Zhang, Jeehun Kim, Kunio Nakamura, Mingrui Yang, Jiasen Zhang, Weihong Guo, Naveen Subhas, Carl S. Winalski, Xiaojuan Li
Published: 2026-10-05
Categories: cs.CV, eess.IV
arXiv: https://arxiv.org/abs/2610.06602v2

Early osteoarthritis detection through quantitative MRI (qMRI) requires accurate cartilage and meniscus segmentation, traditionally necessitating time-consuming, costly 3D high-resolution Double Echo Steady-State (DESS) MRI scans. This study developed a multi-task conditional generative adversarial network (MT-cGAN) to simultaneously synthesize DESS-like images and segment tissues directly from qMRI echo images. This retrospective study evaluated 508 knee MRI volumes from 361 subjects (mean age: $40.4 \pm 12.2$ years; 179 female) across three cohorts. Ground truth segmentation masks were generated from DESS images using a pretrained model with manual correction, and $T_{1ρ}$ and $T_2$ maps were computed from magnetization-prepared angle-modulated partitioned $k$-space spoiled gradient echo snapshots (MAPSS) echo images. MT-cGAN was trained to jointly synthesize DESS-like images and segment cartilage and meniscus directly from echo images. Model performance was evaluated using Dice score for segmentation accuracy and coefficient of variation (CV) for $T_{1ρ}$ and $T_2$ quantification. MT-cGAN achieved the highest segmentation performance, mean Dice score 0.84 (range: 0.80--0.86) across all cartilage and meniscus compartments and significantly outperformed the state-of-the-art conditional GAN model with transfer learning (mean Dice, 0.82; $p < 0.001$, Wilcoxon signed-rank test). For relaxometry quantification, MT-cGAN demonstrated the highest consistency with the reference DESS protocol, yielding the lowest CV ($T_{1ρ}$: 1.84%, $T_2$: 1.81%). The proposed MT-cGAN accurately segmented cartilage and menisci while providing reliable $T_{1ρ}$ and $T_2$ quantification directly from echo images. By eliminating the need for separate morphological DESS scans, this workflow reduces required scan times to facilitate the clinical translation of qMRI.

---

### Multitask Conditional Generative Adversarial Network Enables Automatic Whole Knee Cartilage and Menisci Segmentation and Reliable T1\r{ho} and T2 Quantification Without High-Resolution Morphological Images

Authors: Ahmed Tahseen Minhaz, Richard Lartey, Zhiyuan Zhang, Jeehun Kim, Kunio Nakamura, Mingrui Yang, Jiasen Zhang, Weihong Guo, Naveen Subhas, Carl S. Winalski, Xiaojuan Li
Published: 2026-10-05
Categories: cs.CV, eess.IV
arXiv: https://arxiv.org/abs/2610.06602v1

Early osteoarthritis detection through quantitative MRI (qMRI) requires accurate cartilage and meniscus segmentation, traditionally necessitating time-consuming, costly 3D high-resolution Double Echo Steady-State (DESS) MRI scans. This study developed a multi-task conditional generative adversarial network (MT-cGAN) to simultaneously synthesize DESS-like images and segment tissues directly from qMRI echo images. This retrospective study evaluated 508 knee MRI volumes from 361 subjects (mean age: $40.4 \pm 12.2$ years; 179 female) across three cohorts. Ground truth segmentation masks were generated from DESS images using a pretrained model with manual correction, and $T_{1ρ}$ and $T_2$ maps were computed from magnetization-prepared angle-modulated partitioned $k$-space spoiled gradient echo snapshots (MAPSS) echo images. MT-cGAN was trained to jointly synthesize DESS-like images and segment cartilage and meniscus directly from echo images. Model performance was evaluated using Dice score for segmentation accuracy and coefficient of variation (CV) for $T_{1ρ}$ and $T_2$ quantification. MT-cGAN achieved the highest segmentation performance, mean Dice score 0.84 (range: 0.80--0.86) across all cartilage and meniscus compartments and significantly outperformed the state-of-the-art conditional GAN model with transfer learning (mean Dice, 0.82; $p < 0.001$, Wilcoxon signed-rank test). For relaxometry quantification, MT-cGAN demonstrated the highest consistency with the reference DESS protocol, yielding the lowest CV ($T_{1ρ}$: 1.84%, $T_2$: 1.81%). The proposed MT-cGAN accurately segmented cartilage and menisci while providing reliable $T_{1ρ}$ and $T_2$ quantification directly from echo images. By eliminating the need for separate morphological DESS scans, this workflow reduces required scan times to facilitate the clinical translation of qMRI.

---

### Molecules of a Story: Community Detection in PMI-weighted Narrative Networks

Authors: Kasper Fyhn, Rebekah Baglini
Published: 2026-10-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.06600v1

Automatically extracted narrative networks -- graphs with entities as nodes and their relations as edges -- have proven useful for revealing central narrative structures through salient entities and their connections (Tangherlini et al. 2020; Labatut and Bost 2019). But a narrative is more than those central structures that everything else revolves around. This work is concerned with the everything else: brief sub-plots, small clusters of descriptions, or associations between minor characters that go under the radar at the macro-level. We present an approach to unearth such peripheral structures. They involve rare entities with limited textual presence, overshadowed by dominant entities and lost among each other in the long tail of many but rare entities (Baayen 2001). We leverage the known tendency of pointwise mutual information (PMI, Church and Hanks 1990) to inflate for rare events, turning its weakness into a strength by weighting edges with PMI to foreground peripheral entity configurations. Communities extracted from the resulting network are structural traces of underlying narrative elements. We demonstrate the approach on The Lord of the Rings. From measures of how concentrated or dispersed a community's activations are across the text, a typology emerges that reveals that peripheral structures form more than a single class: episodic passages, echoing long-distance connections, and recurring threads each surface as distinct configurations. The approach is conceptually simple and surfaces fine-grained narrative details that are lost in abundance, though its deliberate amplification of weak signals comes with inherent sensitivity -- best understood as a lens for exploration rather than a robust extraction pipeline.

---

### SimForcing: Distilling Simulation Motion Priors into Real-Domain Robot World Models

Authors: Xiaodong Wang, Tianle Li, Chuanxin Song, Junliang Xie, Zhanmi Zhong, Suiying Wu, Peixi Peng
Published: 2026-10-05
Categories: cs.RO, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2610.06598v1

Action-conditioned robot world models must respond precisely to robot trajectories while preserving realistic visual dynamics, yet learning both from heterogeneous robot videos remains challenging. Simulation offers structured motion supervision, but appearance differences hinder direct transfer, and inaccurate simulation predictions can misguide real-video generation. We present SimForcing, a simulation-guided framework that uses simulation both as a source of transferable motion knowledge and as a controllable reference for prediction. First, we transfer motion knowledge from a simulation teacher through latent-motion distillation, aligning temporal changes in latent space to internalize motion priors while mitigating the influence of appearance differences. Second, we introduce multi-block simulation conditioning with condition dropout to exploit predicted simulation trajectories without relying excessively on their accuracy. Our simulation-conditioning classifier-free guidance scheme unifies these two ideas by balancing predictions based on internalized motion knowledge with those additionally guided by simulation latents. The jointly trained student generates both simulation conditions and real-domain videos, requiring no additional world model at inference. On Bridge, SimForcing achieves the best PSNR, SSIM, LPIPS, and FVD among the compared methods without external embodied pretraining. Evaluation on InternData-A1 further supports its applicability across robot datasets. Moreover, using our trained world model to initialize a vision-language-action model improves LIBERO success, suggesting its utility for downstream policy learning. \url{https://github.com/Wang-Xiaodong1899/SimForcing}

---

### Can Agent Harnesses and Inference Engines Hear Each Other? The HEAR Protocol for Agentic LLM Serving

Authors: Jiaqi Zhao, Haodong Chen, Jitai Hao, Wei Zhao, Jinghao Pang, Qiang Huang, Jun Yu
Published: 2026-10-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.06597v1

LLM agents increasingly execute complex workflows involving multi-turn reasoning, tool use, and parallel agents. Efficient serving requires decisions that span two layers with complementary information: the agent harness understands workflow dependencies, context lifecycles, and execution objectives, whereas the inference engine observes request queues, KV-cache state, resource pressure, and execution capabilities. Existing interfaces do not systematically connect these views, limiting workflow-aware execution. HEAR, a bidirectional Harness--Engine Pairing protocol for agentic LLM serving. HEAR standardizes how the harness communicates workflow intent and execution requirements and how the engine returns runtime state, capabilities, and outcomes. By separating protocol semantics from optimization policies, HEAR supports diverse coordination strategies without changing workflow or model semantics. We instantiate HEAR for online cache-aware runtime coordination and workload-aware execution-mode selection for agent roles. Across four conversational and research-agent benchmarks under memory-constrained, concurrent serving, HEAR achieves a $1.61\times$ batch speedup and reduces median time-to-first-token by $2.23\times$ on SCBench. Mooncake shows that workflow intent and live engine state provide complementary benefits across load regimes. On BrowseComp-Plus and DeepResearchBench, workload-specific configurations yield $1.23\times$ and $2.45\times$ end-to-end speedups, respectively, without observed task-quality degradation. These results establish HEAR as a reusable coordination substrate for efficient agentic LLM serving.

---

### Analysis of SWIR Imaging Detection Performance Under Adverse Environmental Conditions for Autonomous Driving Systems

Authors: Rohan Mehra, Alexandre Riffard, Yannis Loumouamou, Mathieu Labussière
Published: 2026-10-05
Categories: cs.CV, eess.IV
arXiv: https://arxiv.org/abs/2610.06596v1

Short-wave infrared (SWIR) imaging has emerged as a promising modality for autonomous driving, yet its practical benefits over RGB remain poorly characterized across diverse conditions. This paper presents a systematic comparative study of paired RGB and SWIR object detection on the RASMD dataset, covering four weather conditions and two real-time detection architectures, with various fine-tunings evaluated against a unified ground truth. Overall, RGB demonstrates comparable or superior performance in most scenarios, while RF-DETR exhibits greater robustness across varying conditions. Beyond aggregate metrics, we propose a sensor-dominance mining framework that combines multi-model agreement with targeted manual inspection to identify scenarios where one sensing modality provides more reliable detections using largely unannotated paired data. This analysis reveals that SWIR offers clear advantages in four safety-critical situations, including windshield glare, water droplets on the windshield, low-contrast object visibility, and long-range vehicle detection. The findings suggest that SWIR should be viewed as a complementary modality that enhances perception in rare but challenging conditions. The datasets will be available upon request, and all code and trained model weights are publicly released at https://github.com/comsee-research/swir-adverse-env-analysis.

---

### VGGT-Bridge: Beyond Sequential Pose Graphs via Coarse-Stride Skip Edges

Authors: Sungjae Choi, Hanna Bae, Sunghyun Baek, Junmo Kim
Published: 2026-10-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.06594v1

Feed-forward visual geometry transformers such as VGGT reconstruct dense 3D structure from images in a single forward pass, simplifying multi-view 3D reconstruction. However, their quadratic attention complexity makes them difficult to scale to long sequences with thousands of frames. Chunk-and-align frameworks address this by splitting a long sequence into overlapping chunks and stitching their local reconstructions into a pose graph. Yet existing methods connect only sequentially adjacent chunks, so small per-frame errors accumulate along the chain into large-scale drift. To move beyond sequential edges, we propose VGGT-Bridge, which adds long-range skip edges that directly constrain non-adjacent chunks without retraining. By running VGGT on sparsely sampled coarse chunks, each coarse chunk bridges distant fine chunks into a single direct constraint. We further turn VGGT's first-frame scale bias into a drift correction by feeding selected coarse chunks in reverse, and a loop-aware policy keeps this reversal compatible with existing loop closures. VGGT-Bridge reduces ATE by 28.3% on KITTI Odometry, 18.8% on Virtual KITTI, and 10.0% on Waymo Open over the SwiftVGGT baseline, achieving the best performance among all chunk-and-align methods.

---

### The Review Lottery: Benchmarking an Observational Estimator of Peer-Review Noise (ICLR 2017-2025)

Authors: Feilian Huang
Published: 2026-10-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.06591v2

How much of a conference accept/reject decision would change if the same paper were reviewed by a different set of reviewers? Running a second independent program committee is the gold standard for answering this, but it is prohibitively expensive: done only twice (NeurIPS 2014 and 2021). We build an observational estimator of this quantity from public review data alone, calibrate it twice, and apply it to nine years of ICLR (2017-2025; 36,113 papers, 134,912 reviews). The estimator decomposes scores with a Bayesian ordered-probit model into paper quality and reviewer noise, maps scores to decisions with a logistic model, and simulates two independent committees (posterior draws B=1,000; committee sizes k=2,3,4). Estimated disagreement rates are 23-30% at k=2 and 18-24% at k=4; 30-50% of accepted papers would be rejected. External calibration: at the NeurIPS 2021 reviewer-count caliber (k=3), the simulated 2021 disagreement rate is 23.3% (21.7%, 25.0%) vs. reported 23.0% (bias +0.3pp); accept precision and committee correlation agree within 5pp and 0.04. Internal calibration: on 18,740 papers with 4+ reviews, random model-free 2+2 reviewer splits agree with the k=2 simulation within 1pp in 2018 and 2021-2025. Longitudinally, we find no robust time trend in reviewer noise over 2017-2025. The high accepted-paper flip rates of 2020 and 2021 have distinct mechanisms: the 2020 four-point scale compressed scores (23.7% of papers had zero within-paper variance), and a counterfactual shows coarsening the scale raises disagreement by about 7pp; 2021 instead combined the lowest signal-to-noise ratio in the sample with the most threshold-crowded acceptances. For the LLM era, a 2023 breakpoint test on within-paper score variance finds no break, but the design has almost no power, and no post-2022 review text or confidence data exist, so no LLM attribution is attempted.

---

### The Review Lottery: Calibrating an Observational Estimator of Peer-Review Noise (ICLR 2017-2025)

Authors: Feilian Huang
Published: 2026-10-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.06591v1

How much of a conference accept/reject decision would change if the same paper were reviewed by a different set of reviewers? Running a second independent program committee is the gold standard for answering this, but it is prohibitively expensive: done only twice (NeurIPS 2014 and 2021). We build an observational estimator of this quantity from public review data alone, calibrate it twice, and apply it to nine years of ICLR (2017-2025; 36,113 papers, 134,912 reviews). The estimator decomposes scores with a Bayesian ordered-probit model into paper quality and reviewer noise, maps scores to decisions with a logistic model, and simulates two independent committees (posterior draws B=1,000; committee sizes k=2,3,4). Estimated disagreement rates are 23-30% at k=2 and 18-24% at k=4; 30-50% of accepted papers would be rejected. External calibration: at the NeurIPS 2021 reviewer-count caliber (k=3), the simulated 2021 disagreement rate is 23.3% (21.7%, 25.0%) vs. reported 23.0% (bias +0.3pp); accept precision and committee correlation agree within 5pp and 0.04. Internal calibration: on 18,740 papers with 4+ reviews, random model-free 2+2 reviewer splits agree with the k=2 simulation within 1pp in 2018 and 2021-2025. Longitudinally, we find no robust time trend in reviewer noise over 2017-2025. The high accepted-paper flip rates of 2020 and 2021 have distinct mechanisms: the 2020 four-point scale compressed scores (23.7% of papers had zero within-paper variance), and a counterfactual shows coarsening the scale raises disagreement by about 7pp; 2021 instead combined the lowest signal-to-noise ratio in the sample with the most threshold-crowded acceptances. For the LLM era, a 2023 breakpoint test on within-paper score variance finds no break, but the design has almost no power, and no post-2022 review text or confidence data exist, so no LLM attribution is attempted.

---

### Keepsake: Selective Spatial Memory for Long-Horizon Video Generation

Authors: Abdul Mohaimen Al Radi, Kunyang Li, Yuzhang Shang, Mubarak Shah, Yu Tian
Published: 2026-10-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.06588v1

Long-horizon camera-controlled video generation relies on persistent memory to maintain scene consistency. Existing systems follow two strategies to achieve this consistency. Full-history approaches retain all generated observations, causing unbounded storage and retrieval costs. Selective-construction approaches reduce redundancy, but make one-time retention decisions that are never revisited, even as an observation's value changes with the evolving memory bank. Both strategies leave a shared question unresolved: as the generated history evolves, which stored observations should still remain in memory? Our key insight is that the value of a stored observation is not fixed, but relational: it depends on the alternatives currently available in the memory bank. A view supported by many geometrically and visually similar substitutes can be relinquished with little loss of coverage, whereas an observation with few viable alternatives should remain regardless of age. We introduce Keepsake, an online, training-free controller for fixed-capacity spatial memory. At each update, Keepsake constructs a pose-appearance graph over retained and newly generated observations, combining camera-pose proximity with visual similarity. A retention priority jointly captures the number of strong substitutes and the similarity of the closest alternative, allowing Keepsake to continually reassess memory value, preserve observations with little alternative support, and evict highly replaceable ones under a fixed budget. The controller modifies only the persistent-memory update; the host generator, denoising schedule, and retrieval rule remain unchanged. Across MemCam and WorldMem, Keepsake improves FVD and LPIPS under a fixed memory budget. On 180-second MemCam trajectories, it retains only 32 of 5,397 frames while reducing FVD by 35.1%.

---

### Mind the Accent Gap: British Accent Robustness in Speech-Driven Financial Voice Assistants

Authors: Aadam Haq, Oggi Rudovic, Malcolm Chadwick, Jay Rainey, Shucong Zhang, Ricardo Guerrero, Sourav Bhattacharya, Maja Pantic
Published: 2026-10-05
Categories: cs.SD, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2610.06587v1

AI voice assistants often use Automatic Speech Recognition (ASR) with LLM-based reasoning, yet existing systems struggle with regional British accents, including Scottish, Irish, and Welsh accents, since most ASR models are trained predominantly on American English voice data. Consequently, errors can carry through to the LLM stage, corrupting tool-call arguments and producing wrong or missing responses, which is especially costly in finance. Deployable ASR must also meet tight latency and memory budgets, making an accent-robust model choice even harder. We introduce CavaBench, the first internally collected benchmark of spoken financial queries, and use it to evaluate a range of ASR models and their end-to-end ASR-LLM pipeline behaviour across self-reported British accents. We find that WER strongly predicts downstream tool-calling accuracy ($r = -0.93$) but can fail to reflect task-level performance, with accent-related failures varying substantially across models and acoustic conditions. These findings guide the design of more inclusive, reliable voice-based financial assistants.

---

### Does AI Help Cyber Attackers or Defenders? Evidence from Nonpublic Vulnerabilities and Subsequent Attacks

Authors: Tobias Heldt, Matt Turk, Christoph Landolt, Mario Fritz
Published: 2026-10-05
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2610.06584v1

The release decision for frontier AI systems increasingly relies on cyber capability benchmarks, yet public vulnerability benchmarks can expose agents to previously published advisories, exploits, and fixes, making it difficult to distinguish prior exposure from capability on unseen vulnerabilities. We evaluate open-weight and proprietary AI models on exploit generation, vulnerability repair and subsequent attacks in five nonpublic software environments, including vulnerabilities we privately disclosed while they remained unpatched. Researcher-developed and reviewed deterministic graders, not LLM judges, determine task scores. Comparisons with 209 disclosed vulnerabilities and cryptographic challenges reveal substantial variation across systems and vulnerability types. Repair scores exceed attack scores in two nonpublic environments and fall below them in three. Passing an initial security test is also insufficient: another exploit succeeds in 92 of 524 non-independent defender test intervals after the initial exploit is stopped. These results motivate vulnerability-specific attack-repair comparisons and subsequent resistance tests.

---

### Mind the Execution Gap: Action-Semantic Mismatch in World-Model Control

Authors: Shengtao Wen, Xiang Chen, Yu Tian, Lingbing Guo, Lina Gong, Sheng-Jun Huang
Published: 2026-10-05
Categories: cs.AI, cs.CL, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2610.06582v1

World-model controllers rely on action-conditioned dynamics for prediction and planning, yet real control systems often execute commands asynchronously due to communication delay, packet loss, reordering, and actuator buffering. We study how asynchronous execution changes the action semantics assumed within world-model controllers, rather than treating it only as an external control disturbance. Through controlled interventions, we identify two architecture-dependent failure modes: planning-based controllers such as TD-MPC2 suffer from a future-action timeline mismatch between imagined and executed action sequences, while recurrent world models such as DreamerV3 can attribute observed transitions to commands that were not actually applied. Our analysis shows that TD-MPC2 requires the correct future action sequence during latent dynamics rollout, whereas DreamerV3 requires timely attribution of each transition to the action that generated it. Based on these findings, we introduce two lightweight execution-consistent interfaces, Future-Sequence for TD-MPC2 and Applied-Action Feedback for DreamerV3, that correct these mismatches without modifying the pretrained world models. Experiments across delays, packet loss, reordering, multiple control domains, measured network traces, and a process-separated asynchronous stack consistently support both diagnoses and the corresponding architecture-specific corrections.

---

### LinearPFN: Amortized Variable Selection for Linear Models with Interactions

Authors: Louis Schiekiera, Max Zimmer, Christophe Roux, Manuel Arnold, Sebastian Pokutta, Fritz Günther
Published: 2026-10-05
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2610.06580v1

Spike-and-slab regression is a standard Bayesian formulation of variable selection: it returns a posterior distribution over which candidate effects are active rather than a single selected subset, so that every candidate effect carries an inclusion probability. Its cost grows exponentially with the number of candidate effects, so the posterior can be enumerated exactly only when the number of predictors is small. Beyond that reach, the posterior has to be approximated, typically by Markov chain Monte Carlo over the model space, which requires a fresh run for every dataset and, within a fixed budget of steps, may fail to converge. We present LinearPFN, a prior-data fitted transformer network that amortizes spike-and-slab inference for linear models with main effects and pairwise interactions. The network is pretrained once on synthetic datasets, drawn from an explicitly specified prior, and a single forward pass over a new dataset returns posterior inclusion probabilities, posterior-mean coefficients and posterior predictive distributions with no per-dataset fitting. The prior is conjugate by design, so that the posterior for each fixed set of active effects has a closed form, and wherever the exact posterior is still computable by enumeration we verify the network's outputs against it. On real predictor matrices from published social-science datasets, with outcomes drawn from the prior so that the true active set is known, LinearPFN attains a higher per-dataset selection AUC and a higher F1 under the median probability model rule than five classical baselines. The lead holds when the coefficients, the interactions or the noise depart from the prior. Code: https://github.com/schiekiera/LinearPFN. Trained model: https://huggingface.co/schiekiera/LinearPFN.

---

### DGA-Muon: Decoupled Geometry-Aligned Adaptive Scaling for Muon

Authors: Wenpeng Zhang, Runsheng Yu
Published: 2026-10-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.06578v2

While NorMuon has achieved strong empirical performance in pretraining, its underlying adaptive mechanism remains largely heuristic and poorly understood. In this work, we provide the first systematic theoretical analysis of NorMuon's adaptivity, revealing that it primarily arises from orthogonalization-induced geometry rather than genuine optimization dynamics, serving to offset the resulting geometric non-uniformity. Under exact orthogonalization, the adaptive scaling factors degenerate into a single global scalar for square and wide matrices, while for tall matrices their variation results from unevenly distributed row energy after orthogonalization. Under approximate orthogonalization, the orthogonality residuals introduce additional variation into the scaling, giving rise to a counterintuitive Orthogonalization--Adaptivity Paradox: more accurate orthogonalization weakens adaptivity. We further show that NorMuon's rigid row-wise scaling is geometrically misaligned with the one-sided orthogonal structure of tall matrices by distorting column orthogonality. Motivated by these limitations, we propose two core design principles that a desirable adaptive mechanism for Muon should satisfy. First, adaptive scaling should be decoupled from orthogonalization, with the scaling factors computed directly from raw gradients. Second, adaptive scaling should be aligned with the shape-dependent orthogonal structure of the polar factor, using row-wise scaling for wide matrices and column-wise scaling for tall matrices. We prove that this geometry-aligned scaling preserves the orthogonal structure of the update. By incorporating several other techniques, we obtain Decoupled Geometry-Aligned Muon (DGA-Muon). We establish convergence guarantees for DGA-Muon and empirically validate both our theoretical characterization of NorMuon's scaling degeneration and the superiority of DGA-Muon.

---

### Before Agent Tells The Lie: Has Deception Already Been Represented?

Authors: Xinling Li, Dadi Guo, Qingyu Liu, Qinghua Mao, Yi R. Fung, Na Zou, Xia Hu, Dongrui Liu
Published: 2026-10-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.06576v1

Large language model (LLM)-based agents can exhibit deceptive behavior during task execution, including hiding failures, fabricating results, or falsely signaling task completion. Existing monitoring approaches mainly detect deception after it appears in observable actions or outputs. In this paper, we investigate whether deceptive behavior can be predicted from an agent's internal representations before it becomes externally visible. We frame deception monitoring as a trajectory-level representation analysis problem and align agent trajectories around key decision points. Using hidden states extracted before these points, we show that future honest and deceptive outcomes can be reliably distinguished, with predictive signals remaining detectable several model calls before the final decision. We further characterize the temporal evolution of these signals: deception-related representations are weak early in execution but become increasingly identifiable as trajectories progress, while transferable structure can emerge before the strongest decision-adjacent signals appear. Finally, we intervene on the identified honest-deceptive representation directions during inference and find that activation steering reduces downstream deceptive behavior, suggesting that these representations influence agent decisions. Our findings indicate that agent deception is an evolving internal process that can be detected and potentially mitigated before it is expressed externally.

---

### FrontVeg V2: A Training-Free Software Framework for Foreground-Aware Zero-Shot Plant Trait Segmentation in High-Resolution Images of Trellised Crops

Authors: Abdoul Djalil Ousseini Hamza, Herearii Metuarea, Corentin Lothod{é}, Morgane Roth, Jacem Ben Hamden, Eric Duch{ê}ne, Lionel Ley, David Alletru, David Rousseau
Published: 2026-10-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.06575v1

FrontVeg V2 is an open-source, training-free software framework for foregroundaware zero-shot segmentation of plant traits in high-resolution images of trellised crops. The pipeline combines monocular depth estimation, automatic foreground extraction using Valley-Aware Depth Thresholding, tiled zero-shot segmentation, Graph-Based Mask Assembly, and geometry-aware fusion. This design enables plant organs and disease symptoms to be segmented while reducing detections arising from neighboring vegetation rows. The current implementation integrates Depth Anything V2 (DAV2) and SAM3 and can be used through both command-line batch processing and a Napari graphical interface. FrontVeg V2 provides a reusable framework for multi-crop, multi-trait digital phenotyping without task-specific model retraining.

---

### BrainTRACE: Tracing Longitudinal, Multimodal, and Volumetric Evidence in Brain MRI Clinical Reasoning

Authors: Qizhen Lan, Mengchen Fan, Hang Zhang, Jingwei Duan, Moule Lin, Jialin Chen, Baocheng Geng, Xiaoqian Jiang
Published: 2026-10-05
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2610.06571v1

Brain MRI interpretation is a longitudinal clinical reasoning problem: radiologists compare serial studies, integrate information across MRI sequences, localize findings within volumetric anatomy, and translate this evidence into report-grounded assessments. Existing medical VQA and 3D imaging benchmarks capture important parts of this workflow, but often evaluate brain MRI through isolated images, static volumes, or ungrounded report-style answers, thereby obscuring failures in the evidence chain that support clinical validity. We introduce BrainTRACE, a report-grounded benchmark for evaluating whether vision-language models can trace the evidence structure required for longitudinal brain MRI interpretation. BrainTRACE contains 7,273 scored VQA instances derived from 1,778 longitudinal patients, 7,299 MRI studies, and approximately 29k co-registered 3D MRI sequence volumes. The benchmark is organized by five levels of clinical reasoning, from acquisition recognition to case-level synthesis, and by evidence demands covering longitudinal comparison, report-grounded references, multi-sequence integration, and volumetric spatial evidence. BrainTRACE supports rendered inputs compatible with standard VLM interfaces, a 3D-evidence condition, and a decomposed case-reasoning track that audits six steps in a longitudinal evidence chain. Evaluation of 20 VLM configurations shows that current systems can identify isolated visual cues but rarely compose them into grounded longitudinal interpretations. We release the benchmark specification, evaluation lists, scoring implementation, scoring rubrics, and audit-record format to support reproducible progress in brain MRI VLM evaluation.

---

### HERA: Harness-Environment Co-Evolution for Reliable Agentic Abstention

Authors: Han Luo, Bingbing Wen, Guang Yang, Zora Zhiruo Wang, Pan Lu, Lucy Lu Wang
Published: 2026-10-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.06563v1

Large language model (LLM) agents are increasingly capable of acting in complex tool-use environments, yet they often fail to recognize when tasks are infeasible and no valid solution exists. Recent work has formalized this reliability gap as the problem of agentic abstention, and existing approaches typically optimize a model or agent harness against a fixed set of tasks, leading to limited generalization to unseen failure modes. We introduce HERA, a framework for harness-environment co-evolution for agentic abstention. HERA consists of (i) a pipeline to automatically construct verifiable pairs of feasible and infeasible tasks by applying controlled environment mutations that transform solvable tasks into cases requiring abstention, and (ii) a co-evolution procedure in which performance failures on previous tasks are used to drive harness adaptation and generate new execution environments and tasks geared towards previous weaknesses. On held-out evaluation tasks, an evolved harness from HERA improves abstention accuracy from 61.7% to 83.3% while improving feasible-task completion from 68.3% to 76.7%, achieving the highest abstention and feasible-task completion among the compared methods. The resulting best harness transfers across 19 other LLMs, improving abstention accuracy by 15.3 percentage points on average without any model-specific optimization, and enabling smaller models to match the performance of more powerful models at an estimated 85% lower cost.

---

### Synthetic Cultural Agents from Aggregate Anchors

Authors: Augusto Gonzalez-Bonorino, Kseniia Biriukova, Monica Capra
Published: 2026-10-05
Categories: econ.GN, cs.CL
arXiv: https://arxiv.org/abs/2610.06562v1

Population prompts are widely used to generate synthetic survey responses, but they combine information supplied at inference with associations already encoded during pretraining. We introduce an alternative construction that maps declared aggregate preference anchors into group-indexed choice policies. For each population, the signs of six Global Preferences Survey (GPS) coordinates deterministically label a shared bank of paired synthetic responses, and Direct Preference Optimization fits a parameter-efficient adapter to those comparisons. We evaluate the adapters on candidate World Values Survey (WVS) items using prompts that omit country names and distinguish four questions: recovery of the imposed labels, transfer of the anchor signal to new text, coherence between the GPS anchors and human WVS responses, and agreement between adapter and human scores. The adapters recover the imposed pairwise labels. On a purposively selected sixteen-country development panel, adapter trust scores completely separate the two GPS-sign groups and have a rank correlation of (0.74) with continuous GPS trust scores. Human-GPS and adapter-human associations remain unresolved on the same panel, and results for the other preference dimensions are heterogeneous. These findings show that an anchored policy can retain a declared aggregate signal without thereby reproducing human response patterns. The contribution is therefore both an inspectable construction and an evaluation framework that separates anchor transfer from human criterion agreement.

---

### MIRT: Transformers for Truthful Generative Auctions with Whole-feed Permutation Externalities

Authors: Ali Elahi, Ermis Soumalias, Jason Cheuk Nam Liang, Daniel Yao, Michael J. Curry
Published: 2026-10-05
Categories: cs.GT, cs.LG
arXiv: https://arxiv.org/abs/2610.06559v1

Modern online platforms commonly rank ads and organic content separately before blending them into a feed displayed to the user, overlooking externalities: an item's click-through rate depends on its surrounding content, not only on its own position. Recent learning-based feed generation mechanisms model some of these cross-type interactions to globally optimize for the whole feed's welfare. However, these approaches either fix the ordering of organic content, or lack exact strategyproofness guarantees for bidders. To combat these shortfalls, we introduce the Maximal-in-Range Transformer (MIRT) mechanism class, which uses a transformer to generate a range of candidate feeds that jointly order ads and organic content, and selects the welfare-maximizing feed in the range. However, there is a tension: strategyproofness requires the generated range to be bid-independent, even though a candidate feed's welfare depends linearly on the bids. Our key technical contribution is a reinforcement learning approach that incorporates both candidate generation and bid-aware selection into training, enabling a bid-independent transformer to learn to generate high-welfare ranges by accounting for both individual feed quality and the collective quality of the range. Additionally, we bound the pseudo-dimension of the MIRT class under hard attention, showing that near-optimal expected welfare is learnable with sample complexity polynomial in the transformer size and only logarithmic in the range size. Empirically, MIRT outperforms the previous non-strategyproof state-of-the-art feed models while remaining exactly strategyproof. Our results show that transformer-based auctions can deliver externality-aware whole-feed optimization without sacrificing exact incentive compatibility, removing a major obstacle to their practical deployment.

---

### Signature-Based Feature Learning for Human Activity Recognition: A Reproducible Machine Learning Study of Representation, Depth, and Model Choice

Authors: Kamal Jarrar, Jacky Cresson, Christian Paroissin
Published: 2026-10-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.06553v1

Human activity recognition (HAR) relies on transforming sensor signals into informative representations for classification. Although deep learning and handcrafted features are widely used, the role of representation itself is often not systematically isolated. Signature transforms provide a mathematically grounded way to encode temporal order and cross-channel interactions, but their value for HAR under a fully reproducible and leakage-aware framework remains unclear. To evaluate whether signature-based feature learning improves HAR performance compared with raw-signal baselines, and to assess the effects of embedding strategy, truncation depth, model choice, and sensor configuration. Experiments were conducted on the UCI HAR dataset using a fully reproducible pipeline with the original train--test split preserved and subject-disjoint validation to prevent leakage. Three representations were compared: raw flattened signals, time-augmented paths, and lead--lag transformed paths. Signature features were computed at multiple truncation depths and evaluated using multilayer perceptron (MLP) and Random Forest (RF) classifiers under identical preprocessing and validation procedures. A prior K-means-based feature reduction study was also reproduced for comparison. Signature-based representations improved performance when paired with RF models, the best configuration was time-augmented six-channel signatures at depth 6 using entropy-based RF achieving 0.858 accuracy and 0.859 macro F1, outperforming the strongest raw baseline (0.816 accuracy). Lead--lag representations were competitive at moderate depths but did not surpass the best time-augmented models. MLP models did not exceed raw baselines. Signature-based feature learning can improve HAR, but its benefit depends on alignment between representation design and classifier choice.

---

### Proof-Grounded Patient-Specific Clinical Explanations from Knowledge-Graph Reasoning

Authors: Surajit Das
Published: 2026-10-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.06549v1

Clinical decision-support outputs can lack an au- ditable link between patient observations, encoded knowledge, conclusions, and recommendations. We present the CKG Clinical Explanation Engine, a downstream layer for a frozen, training-free clinical knowledge-graph reasoner that converts patient inference states and disease knowledge into typed facts, explicit rule-application traces, provenance-linked conclusions, and policy-licensed recommendations. The design separates measurement availability, representation completeness, and disease-specific activation; consequently, observed zero-activation evience is not treated as missing and partial representation is distinct from unobserved evidence. Optional language generation is restricted to symbolically licensed content. Across five usable workbooks (6,720 patients; 20,160 patient-disease traces; 1,021,440 feature-evidence rows), IG-range validity and knowledge provenance were 100%, numerical cross-sheet fidelity was 100% (120,960/120,960), and exported logical/report trace completeness was 100% (20,160/20,160). Availability representation consistency was 99.7028% (1,018,404/1,021,440); all 3,036 disagreements were confined to three systematic feature-cohort patterns. The corpus contained 86,783 observed zero-activation and 139,949 observed partially represented instances. A separate seeded 25-patient end-to-end audit completed without execution failure and passed all pre-specified trace, licensing, provenance, and state-consistency checks. These results establish structural and implementation auditability, not clinical correctness or utility.

---

### Empirical Variational Autoencoder

Authors: Kaede Shiohara
Published: 2026-10-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.06545v1

We present Empirical Variational Autoencoder, a general generative framework for continuous-valued (i.e., non-vector-quantized) sequences. EVA is based on the evidence lower bound of the Variational Autoencoder (VAE) but learns autoregressive latent priors empirically from training data, which can be implemented only by an additional single linear layer on top of VAEs. By replacing the conventional standard-Gaussian constraint with the self-predicted priors, EVA significantly alleviates the latent distribution gap between prior and posterior which is typically observed in conventional VAEs, and leads to high-fidelity ancestral sampling for sequential data generation. Extensive experiments on image and sound synthesis demonstrate that EVA achieves competitive generation quality with autoregressive diffusion baselines despite its much faster inference time.

---

### A Fine-Grained Analysis of the LoRA Fine-Tuning Landscape with Implications for Data Selection

Authors: Bowen Zhang, Changrui Fang, Xinsong Ma, Jiaye Teng, Ziye Ma
Published: 2026-10-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.06542v1

Low-Rank Adaptation (LoRA) has become a standard approach for parameter-efficient fine-tuning, yet a fundamental practical question remains unresolved: how should the adapter rank be chosen? An overly small rank may lead to a poorly conditioned optimization landscape, whereas an unnecessarily large rank sacrifices the efficiency that motivates LoRA in the first place. Existing theoretical analyses provide only limited guidance on this trade-off, and their guarantees are typically established under restrictive theoretical settings. We address this gap by developing a substantially sharper landscape theory for LoRA, building on modern results from nonconvex low-rank matrix sensing. Our central insight is that the appropriate adapter rank should depend on the quality of the data-induced optimization geometry, rather than on the model alone. To formalize this connection, we introduce LoRA-RIP, a data-dependent restricted-isometry metric that characterizes the conditioning of the cross-entropy (CE) objective along LoRA-relevant low-rank directions. We prove that sufficient rank over-parameterization, with the required rank explicitly determined by the LoRA-RIP constant, eliminates spurious local minima, thereby extending existing RIP-based guarantees beyond the classical 1/3 regime. This characterization further enables principled data selection under a fixed rank budget. Experiments across language and vision tasks support these theoretical predictions, showing that rank and data quality are two coupled resources that should be jointly considered for more efficient and reliable LoRA fine-tuning.

---

### WaveGSSM: Graph Wave State Space Models for Propagating Spatio-Temporal Patterns

Authors: Junyou Zhu, Fenying Cai, Ping Xiong, Christian Nauck, Langzhou He, Chao Gao, Jürgen Kurths, Frank Hellmann
Published: 2026-10-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.06540v1

Spatio-temporal graph models typically encode each snapshot with a GNN and then connect the resulting representations through a temporal module. This space-then-time design is effective, yet it does not explicitly represent how a pattern moves across the graph. We show empirically that, for a propagating process, the same present field can lead to different futures when its recent rate of change differs, motivating an explicit representation of motion in the predictive state. We introduce WaveGSSM, a second-order graph state-space model that maintains two coupled latent states at each node, one for the current pattern and one for its temporal rate of change. A graph-wave transition updates the motion state through graph interactions and uses it to advance the pattern state, coupling spatial propagation and temporal evolution within a single rollout. We evaluate WaveGSSM on four temporal-graph benchmarks and global weather forecasting. It consistently achieves the best mean performance across the temporal-graph benchmarks and reduces the geopotential RMSE by 20.2% on average for 1- to 5-day weather forecasts relative to a backbone-matched snapshot model, while better preserving large-scale atmospheric patterns.

---

### Symmetry and AI-assisted discovery of magic-state factories

Authors: Shubham P. Jain, Adam Wills, Shraddha Singh
Published: 2026-10-05
Categories: quant-ph, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2610.06535v1

Magic-state distillation is a major resource cost in fault-tolerant quantum computing. The cost of a magic-state factory depends strongly on its failure rate, which grows with the number of input magic states. Although symmetry-restricted methods have recently made distance two searches tractable, distance three and above have remained elusive at moderate input counts. We develop symmetry- and AI-assisted methods to search this regime. We present a unified binary-matrix formulation encompassing both triorthogonal-code and direct circuit searches. We show that distance at least three is equivalent to nonzero, pairwise distinct syndromes, separating the choice of syndromes from the search for compatible output gates. We restrict the syndrome search using group symmetry and language-model agents, followed by deterministic solving and independent verification. Our searches yield 699 factory classes, including 564 new ones. These include factories for pure-T states and factories with entangled outputs comprising combinations of T, CS, and CCZ magic states. The pure-T factories ((63, 11, 3)) and ((850, 128, 6)) achieve the lowest overhead exponents we know among protocols with at most 100 and 1000 inputs, respectively, with $γ= 1.589$ and $γ= 1.057$. Our ((1715, 287, 6)) factory, with $γ= 0.998$, is the smallest known pure-T factory with $γ< 1$. We also provide a context directory of search briefs and campaign notes with which readers can train their own agents and tailor the search to their requirements. With these results, we begin constructing an active, open-source repository of magic-state distillation protocols for the quantum community, supplemented by our methods and data, for the practical fault-tolerant quantum computing regime.

---

### Anatomy of LLM Sycophancy: What a Flip Rate Hides

Authors: Haonan Huang
Published: 2026-10-05
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2610.06522v1

A model under pushback can correct itself, capitulate, or hold, and one flip rate counts a correction and a capitulation alike. Using SycoLens, a modular replay protocol, we test how user pressure and evaluation settings shape measured flip rates. Each measurement is one stateless replay of an item, a committed answer, and one scripted user line in a fixed form. Every effect is read against a matched control with the line deleted. Pushback wording, committed text, answer format, boundary distance, and ground truth become factors of one instrument; earlier instruments vary one to three of them. Across eleven frontier models from three providers and about 760,000 controlled replays, which models look sycophantic depends on how the user pushes back. Lines that assert the opposite verdict and lines that challenge the answer without asserting one rank the models almost unrelatedly. Flip effects grow several-fold near a model's boundary, yet items answered identically in every screening draw still carry about half of the most-affected totals. On arithmetic tasks where the truth is known, one model re-derives and corrects itself under pressure while another abandons correct answers without written work. On the model tested, a planted derivation lowers release of the answer it argues for, true or wrong, where a bare stated value does not; the wrong answer is corrected much more often than the true one is abandoned. Under a yes/no readout the rankings come closer, entangled with a pressure-induced shift toward "no". One score per model therefore compares different behaviours across models and benchmarks. We condense these dependencies into a reporting profile; the instrument, records, and analyses will be released upon publication.

---

### Conditional Flow Matching for Single-Neuron Electrophysiology: Capturing Multimodal Responses Across Stimuli

Authors: Cameron Schofield, Luca Ghafourpour, Philip H. Wong, Costas A. Anastassiou, Richard E. Turner
Published: 2026-10-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.06520v1

Neurons of the brain exhibit a rich repertoire of electrophysiology dynamics with the same repeated stimulus eliciting very different voltage responses from the same cell. One common approach in biophysically detailed models is to capture this variability through ensembles of deterministic parametrizations, at a cost of hundreds of thousands of CPU hours. Existing machine learning surrogates inherit the same limitation, where a stimulus is mapped to a single voltage response. We address this challenge by learning a conditional generative model for single-neuron electrophysiology, using flow matching with a velocity field conditioned on the input current. On biophysically detailed models of two human cortical interneuron types, the generated responses closely reproduce the electrophysiological feature distributions, spike-time structure, and excitability profiles, even matching the experimental recordings from the corresponding human cortical neurons. Near the firing threshold, firing and non-firing responses coexist at the same stimulus amplitude, and at high amplitudes, ensembles may split into low- and high-firing modes near depolarization block. We show that our model recovers both modes in each case, while a neural operator baseline suppresses spiking near threshold and blurs the gap between modes at depolarization block.

---

### GCTAuto-encoder: A Cross modal Framework for Security Flaw Detection in IoT Networks

Authors: Najmieh Sadat Safarabadi
Published: 2026-10-05
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2610.06517v1

IoT encompasses diverse physical entities, from smart home devices to autonomous vehicles, creating a complex environment with heterogeneous security models. This heterogeneity makes IoT sub-systems vulnerable to various network attacks. Modern security systems must therefore be more robust to ensure security and privacy for IoT applications. A highly secure IoT system also demands real time insight, requiring data collection at the edge of the computing layer. This diversity calls for a unified security model applied at the foundational level. Edge intelligence offers a direct approach to handling device diversity. A key goal of edge intelligence in IoT is to extract insight from local data; security models can then use this data to build local node protections, and integrating AI models yields an advanced security solution. This research proposes a novel deep learning algorithm for effective intrusion detection at the edge, supported by a cloud-based IoT framework. We evaluate the proposed cross modal deep learning algorithm against baseline models. The contribution is a cross domain Deep Neural Network (DNN) algorithm for intrusion detection. The objective is to assess a multi-method deep learning model to detect intrusions in IoT systems at the edge via community detection with modeled attention. We evaluate GCT auto-encoder, a novel framework integrating edge intelligence to identify security flaws. The model significantly improves performance and efficiency. On a network intrusion IoT dataset covering multiple attack scenarios, it achieved 0.908 accuracy, reduced learning loss to 0.00156, and outperformed existing approaches.

---

### Test-Time Adaptation of Reasoning Strategies with Bayesian Nonparametric Memory

Authors: Keshav Ramji, Tahira Naseem, Ramón Fernandez Astudillo
Published: 2026-10-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.06516v1

While modern large language models (LLMs) have been trained to reason through verbalized chains-of-thought, the generation cost grows substantially due to suboptimal paths to reach the final answer. Furthermore, as new insights are discovered while observing various input queries (e.g. through self-reflection), limited mechanisms exist for carrying forward these findings to be applied to subsequent problems. One can view the list of such strategies or behaviors as a growing cheatsheet, with elements retrieved from this memory module at inference-time. In this work, we consider structured cheatsheets, with learned clusters of behaviors. We introduce a Hierarchical Dirichlet Process Gaussian Mixture Model (HDP-GMM) over behavior embeddings, which shares components across domains while allowing domain-specific mixing weights, and uses the posterior predictive to retrieve relevant behaviors for a query; we call this a $\textit{Bayesian Cheatsheet}$. This mechanism allows for cheap adaptation in an online test-time training (TTT) setting, softly updating the mixture's sufficient statistics following each sample and enabling the creation of new components when the synthesized behaviors are sufficiently novel. We demonstrate that Bayesian Cheatsheet achieves clear performance gains relative to existing memory modules across reasoning benchmarks such as AIME'25, Omni-MATH, and PhysReason, even in the cold-start setting. We show that the Bayesian Cheatsheet is an adaptively reorganizing memory module, as behaviors can be re-assigned to components through a single step of collapsed Gibbs sampling. Our findings highlight the value of Bayesian-inspired memory modules for effective test-time adaptation and the role of structure in metacognitive reasoning.

---

### ANT: A Multi-Granularity Network Traffic Dataset and Benchmark for Agents Behavior Auditing

Authors: Fan Li, Xiangyu Gao, Zixuan Liu, Tong Li, Chuanpu Fu, Ziqiang Wang, Ke Xu
Published: 2026-10-05
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2610.06514v1

The growing adoption of large language model (LLM) agents creates a need for network administrators and security teams to audit agent behavior within organizational networks without inspecting private user content. Network traffic offers an observable source of evidence, but how much it reveals about agent tasks and operations remains unclear. Existing traffic datasets lack the joint task and stage annotations needed to evaluate this question. We introduce ANT (Agent Network Traffic), a dataset providing agent behavior information at risk, scenario, and behavior primitive granularities alongside network traffic. ANT contains 3,114 execution episodes across 20 tasks and five scenarios, comprising 276,417 bidirectional flows and 40,049 behavior primitive segments organized into 47 macro groups. We establish a benchmark for agent risk identification, scenario recognition, and behavior primitive classification using 13 representative traffic analysis baselines. The results show that existing methods recover useful but uneven behavioral signals. They struggle to identify risk when malicious workflows resemble benign tasks and to distinguish scenarios with similar traffic patterns. Primitive classification is more reliable for frequent macro groups and those with distinctive traffic patterns than for rare or semantically similar groups. ANT provides a common basis for developing more precise auditing and forensic analysis of agent behavior from network traffic. Our data and code are available at https://anonymous.4open.science/r/ant-main-suite-7BC0/.

---

### SOL: Measuring Gaps between Text Distributions by Double Sliced Wasserstein Metrics

Authors: Gregor Kornhardt, Moritz Piening, Jannis Chemseddine, Gabriele Steidl
Published: 2026-10-05
Categories: cs.CL, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2610.06513v2

Evaluating text generation requires measuring how well the generated distribution matches the data distribution. For autoregressive models, this is done by the perplexity. Diffusion and flow-based language models can only provide a likelihood bound, whose tightness differs between model families. Sample-based substitutes such as generative perplexity with entropy do not consider the distribution fit. We propose SOL, a distance between text distributions. Each sequence is represented by the empirical measure of its hidden states under a fixed transformer and the distributions of these measures are compared by the double sliced Wasserstein distance. We prove that SOL is a metric if the transformer is injective. Experiments show that SOL detects distributional failures, recovers expected model trends, and provides stable sample-based estimates. We put forward SOL to fill the gap in the current evaluation protocol used for non auto-regressive models. As a first step we use SOL to re-evaluate a variety of models trained on OpenWebText.

---

### ArtifactArena: Evaluating Models by What They Build in the Physical World

Authors: Kushagra Tiwary*, David Mayo*, Nikhil Behari, Xiangzhou Sun, Abdulrahman Alabdulkareem, Isaac Galatzer-Levy, Boris Katz, Brian Cheung
Published: 2026-10-05
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2610.06511v1

To evaluate the frontier, we must measure models not by what they say, but by what they can engineer and build in grounded physical environments. We introduce \textsc{ArtifactArena}, an open-ended platform where models face a physically grounded hardware-software co-design challenge: engineering fully functional robots to compete in a simulated arena. We evaluate a frontier model's zero-shot, verifier guided refinement, and open-ended physical design capabilities through three harnesses that refine their bot artifacts based on text descriptions, physics simulator feedback, and gameplay data. We benchmark these capabilities with an Elo ranking of frontier models derived from head-to-head tournaments between their artifacts. By releasing this framework and tournament infrastructure for ongoing community submissions, we establish a living, non-saturating testbed to continuously measure the expanding limits of open-ended intelligence in the physical world. Please visit \href{https://artifactarena.ai}{https://artifactarena.ai} for more information.

---

### Xaurora: Generative Weather Forecasting with Denoising Stochastic Interpolants from a Foundation Model Prior

Authors: Eliot Walt, Miltiadis Kofinas, Nikolaj Mücke, Efstratios Gavves, Dim Coumou
Published: 2026-10-05
Categories: cs.LG, physics.ao-ph
arXiv: https://arxiv.org/abs/2610.06509v1

Deep learning has revolutionised weather forecasting in recent years, especially through atmospheric foundation models, which offer competitive skill for a fraction of the computational costs of classic physics-based models. However, most existing foundation models are deterministic, limiting the generation of large ensembles for accurate uncertainty quantification, extreme weather risk assessment, and long-range weather forecasting. Furthermore, these models incur a large, often prohibitive, computational overhead to train from scratch. To address these shortcomings, we turn a pretrained deterministic prior model, namely the Aurora foundation model, into a generative ensemble-prediction model. To that end, we introduce a novel generative method, Denoising Stochastic Interpolants, combined with a replay buffer for Stochastic Differential Equation (SDE) rollout, enabling probabilistic training of SDE trajectories. Our stochastic foundation model, Xaurora, is finetuned from the small Aurora version, yet it approaches the state-of-the-art on global ensemble metrics and is competitive with the large version of Aurora. Our method is parameter and sample efficient, and generates skilful 15-day forecasts in 13 minutes. Our results demonstrate that deterministic foundation models can be efficiently extended into even stronger stochastic models.

---

### A General Pipeline for Dense Illuminant Estimation via Physically Based Synthetic Data

Authors: Luca Cogo, Gianmarco Corti, Simone Bianco, Raimondo Schettini
Published: 2026-10-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.06508v1

Illuminant estimation is a fundamental problem in computational photography, as it enables the correction of color shifts induced by varying lighting conditions. While learning-based methods have demonstrated strong performance, their progress is hindered by the limited availability of large-scale datasets with accurate illuminant ground-truth. In this work, we propose a general and reusable pipeline to derive dense illuminant chromaticity maps from physically based 3D-rendered scenes. By repurposing an existing 3D scene collection, our approach enables the systematic generation of pixel-wise illuminant annotations under controlled lighting conditions, effectively lowering the barrier to data acquisition for learning-based illuminant estimation. Using this pipeline, we generate a large-scale synthetic set of 74,321 images, which we employ for pre-training both single- and multi-illuminant estimation models. Extensive experiments with state-of-the-art architectures show that synthetic pre-training consistently improves performance, with gains of up to 28% for single-illuminant estimation and up to 57% for multi-illuminant estimation, particularly in data-scarce regimes. These findings demonstrate that synthetic data generation pipelines offer an effective and scalable solution for the pre-training of illuminant estimation methods.

---

### Improving Proactive AI Assistance with Hierarchical Procedural Understanding

Authors: Jin-Seop Lee, TaeYeon Won, SeongJun Jung, JungHoon Kim, Boyang Albert Li, JinYeong Bak, Jaehong Yoon, Jee-Hyong Lee
Published: 2026-10-05
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2610.06505v2

Proactive AI assistants continuously observe a user's activity and decide whether to provide new guidance or remain silent. They should provide appropriate guidance for the task, determine when to provide the next guidance based on task progress, and adjust the guidance level to the user's expertise and needs. Supporting these capabilities requires training and evaluation data that reflect procedural structure and capture how guidance should adapt to task progress and user needs. However, existing datasets either focus on detection-based proactive understanding or provide procedural guidance at a fixed granularity. Fixed-granularity guidance provides limited information about fine-grained progress and broader procedural context, making it difficult to determine completion and adapt guidance granularity. To address these limitations, we introduce the ProactiveCoach suite, comprising ProactiveCoach-Instruct for training, ProactiveCoachBench for evaluation, and fine-tuned VLMs with an adaptive guidance system. ProactiveCoach-Instruct provides hierarchically structured guidance at the phase, step, and action levels for learning task progress and procedural context. ProactiveCoachBench evaluates whether models provide appropriate guidance at the right time across different guidance levels and adapt when the requested level changes. We fine-tune pretrained VLMs on ProactiveCoach-Instruct and demonstrate its effectiveness across backbones. Compared with fixed-granularity supervision, hierarchical supervision improves overall performance across backbones by up to 9.6%p. We further build an adaptive guidance system by combining our fine-tuned model with a lightweight guidance router. Without additional fine-tuning, our system outperforms the in-context adaptation baseline by 57.1%p across four guidance-level transitions. Our project page is available at https://jinsuby.github.io/ProactiveCoach/.

---

### Harmful Content Generation in Text-to-Image Models: Capabilities and Moderation Limitations

Authors: Paschalis Giakoumoglou, Manos Schinas, Symeon Papadopoulos
Published: 2026-10-05
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2610.06503v1

Text-to-image generative models can produce highly realistic imagery but also raise concerns about harmful misuse. While safety mechanisms exist, systematic evaluations of their effectiveness against realistic attacks remain limited. We present a systematic evaluation of harmful content generation across five open text-to-image models using an automated pipeline that transforms legitimate news captions into unsafe prompts targeting sexually explicit content, violence/gore, harmful stereotypes, self-harm, and hate speech. We evaluate both standard models with built-in safety mechanisms and community fine-tuned variants that bypass content restrictions. A human evaluation of 1,500 generated images shows high harmful-content generation rates: 89.2% for gore-related prompts, 47.6% for sexually explicit content, 43.6% for harmful stereotypes, 46.0% for hate speech, and 34.5% for self-harm, predominantly through graphic violence. Models show substantial capability for generating violent and stereotypical content, while community fine-tuned variants are particularly vulnerable to sexually explicit prompts. Generation quality is largely preserved under harmful prompting, producing imagery of sufficient fidelity to pose risks for disinformation and abuse; FLUX.1-dev produces clearly realistic harmful images in 30.9% of cases. We further evaluate automated moderation systems and find substantial detection gaps that allow unsafe images to evade filtering. Finally, we assess synthetic image detectors and show that models trained only on benign datasets perform worse on explicit content, while more diverse training data improves detection, highlighting semantic distribution gaps in current approaches. These findings expose limitations in current generation safeguards, moderation systems, and synthetic image detection, highlighting the need for stronger defenses against misuse at scale.

---