# Research Papers — 2026-08 · bundle page 16 of 240

> Full-text markdown of papers #751–800 of 11995 published in 2026-08, newest first. AI-readable mirrors of the full 11995-paper 2026-08 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-08/page/16
[← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/15.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-08/page/17.md)

### Designing for the Next Click: Bandits for Real-Time Page Layout

Authors: Bhavtosh Rath, Harshith Narasimhamurthy, Bob Eisinger, Cole Stiegler, Adnan Awow, Amit Pande
Published: 2026-08-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2608.29850v1

E-commerce platforms increasingly personalize user experiences through machine learning, yet page layout decisions remain dominated by static rules and manual curation. We present a scalable bandit-based system that optimizes product page layouts in real time while preserving human control over design intent. A contextual bandit model dynamically selects the most effective layout for each session using user, item, and category-level features. The system leverages a LinUCB-based policy to balance exploration and exploitation as it learns from live user interactions. The architecture is designed for seamless integration into large-scale web serving stacks, supporting low-latency inference and continuous model updates. The system was first tested on entry product pages. In online A/B deployments on a major retail platform, our approach achieved positive lifts in session-level performance metrics over a strong heuristic baseline. Our results demonstrate that contextual bandits can effectively optimize visual and structural aspects of product discovery for user engagement, providing a scalable path toward learning-to-design the web.

---

### ContextBias: Controlled Evaluation of Bias Persistence Under Context Shift in Text-to-Image Models

Authors: Shaghayegh Kolli, Sina Emami, Moreno D'Incà, Pouyan Nejadi, Nicu Sebe, Massimiliano Mancini, Jana Diesner
Published: 2026-08-30
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2608.29847v1

Text-to-image models learn associations between concepts - in the case of this paper, people's professions, which we refer to as roles - and visual attributes. These associations can underpin many observed forms of stereotypical bias. A key open question in this area is whether these associations are stable or change when visual representations of people in professional roles are placed in different prompted contexts. We introduce ContextBias, a controlled evaluation framework, and ContextBench, a benchmark spanning 92 roles and 1,656 semantically controlled prompts, designed to isolate the effect of contextual variation on role-linked visual representations. Evaluating four state-of-the-art models on 66,240 generated images, we find that placing a role in a semantically unrelated context does not suppress role-linked attributes; instead, cross-role attribute concentration increases (pooled BI $+0.047$). Demographic cues, characteristic garments, and role-specific tools remain highly prevalent across context-free, related, and unrelated conditions, and are robust to semantic prompt reformulation. Scene composition and camera framing show the greatest context-sensitivity. These findings reveal a form of stereotypical persistence that remains largely invisible to context-free evaluations, highlighting the need for controlled contextual variation in bias benchmarking. Code and dataset: https://huggingface.co/datasets/shaghayegh/ContextBias , https://github.com/Sina-Emami/ContextBias

---

### Influence-Directed Distillation: Solving the Diversity Bottleneck in Sampled-Token On-Policy Distillation

Authors: Run Yang, Runpeng Dai, Jie Sun, Jielei Zhang, Fan Zhou, Hongtu Zhu, Peiyi Li, Longwen Gao
Published: 2026-08-30
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2608.29846v1

Sampled-token on-policy distillation (OPD) efficiently transfers capabilities from teacher to student using student-generated tokens, requiring teacher probabilities only for sampled tokens. Yet it frequently suffers from diversity distillation failure: the student's pass@1 improves while its pass@$k$ plateaus, failing to inherit the teacher's diversity. To explain this, we introduce First-Order Local Entropy Influence, a signed first-order proxy that decouples each update's entropy effect into the teacher--student log-probability gap and the student's local probability structure, and empirically links entropy contraction to negative-influence positions. Motivated by this, we propose Influence-Directed Adaptive On-Policy Distillation (IDA-OPD): rather than relying on costly full-vocabulary Forward-KL objectives, it preserves entropy-expanding updates while replacing entropy-contracting ones with divergence-adaptive advantage shrinkage, using only the teacher's sampled-token log-probability. Experiments on reasoning-oriented distillation show IDA-OPD consistently improves pass@$k$, inheriting the teacher's diversity through distillation, matches the strongest teacher-informed methods at strictly lower cost, and broadly maintains vanilla OPD's pass@1, all without full-vocabulary teacher information.

---

### The Price of Intelligence: A Quality-Adjusted Price Index for AI Services

Authors: Louis Yiven Zhu
Published: 2026-08-30
Categories: econ.GN, cs.LG
arXiv: https://arxiv.org/abs/2608.29843v1

Posted prices for AI inference have fallen steadily since 2024, yet the measured speed of that fall depends almost entirely on the method of measurement. This paper constructs quality-adjusted price indices for the AI inference market from public data. The panel assembles 21,024 posted-price observations across 3,208 models and 86 providers and joins them to 4,605 benchmark scores through a latent quality index estimated from benchmark response patterns, so the quality ladder of the hedonic tradition is built here from evaluations in place of product characteristics. Measured by the matched-model methods that statistical agencies apply to software, inference prices fell at 0.10 log points a year. The quality-adjusted index fell at 0.73, so 87% of the decline is invisible to current methods, with direct consequences for measured competition, concentration and productivity in this market. Counted per completed task, moreover, the buyer's price stopped falling. Reasoning models raised token consumption faster than token prices fell, and the seller's and buyer's prices accordingly diverged. A pre-registered validity audit disciplines the quality measure and yields the sharpest result. Excluding contamination-flagged benchmarks leaves model rankings intact at 0.998 yet moves the index by 0.49 log points a year, so the leaderboard-stability arguments standard in AI evaluation offer no defence of economic statistics built on benchmarks. Prices, quality and the audit are fully reproducible from public sources at zero cost.

---

### SkillForge: Compositional Skill Synthesis with Verification-in-the-Loop for Generating Formally Verified Dafny Programs

Authors: Yanming Liu, Xinyue Peng, Jiannan Cao, Xinyi Wang, Jinbo Su
Published: 2026-08-30
Categories: cs.CL, cs.PL
arXiv: https://arxiv.org/abs/2608.29841v1

Generating formally verified programs from natural language remains challenging: existing approaches either produce code in a single pass without recourse when verification fails, or rely on open-ended agentic reasoning that is non-deterministic and opaque. We introduce SKILLFORGE, a framework that decomposes formal code synthesis into a library of atomic, reusable skills, each targeting a specific subtask such as specification inference, body synthesis, invariant generation, error diagnosis, or targeted repair, and defined by a prompt template, tool binding, and decidable success criterion. A verification-driven harness orchestrates these skills: it submits candidates to the Dafny verifier, diagnoses failures into structured categories, deterministically routes to the appropriate repair skill, and iterates until formal correctness is proved or a budget is exhausted. On a curated benchmark of natural language to Dafny specification pairs, SKILLFORGE substantially outperforms both state-of-the-art agentic approaches (including ReAct-style agents, MCTS-based repair, and RL-guided verification) and traditional iterative baselines, while requiring fewer tokens and lower latency. Ablation studies confirm that every skill contributes measurably, and the harness converges rapidly with the majority of programs verified on the first attempt.

---

### EVAR: Evidence-Validated Hypothesis Admission for Budget-Aware Narrative Reasoning

Authors: Peilin Liu, Zhiquan Ji, Jinglong Ping
Published: 2026-08-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2608.29835v1

Large language models (LLMs) often produce fluent but weakly grounded conclusions when reasoning over non-interactive, long-form narratives. A central failure mode is that unsupported intermediate hypotheses can enter the reasoning trajectory and contaminate subsequent inference, especially when evidence is scattered across distant parts of the story. To address this problem, we propose EVAR, an evidence-validated hypothesis admission framework for budget-aware narrative reasoning. EVAR first compiles the narrative into an immutable evidence store of source-linked atomic claims and assigns an instance-specific inference budget from unresolved gaps and uncertainty signals. During refinement, EVAR directly proposes candidate hypotheses for unresolved gaps, constructs hypothesis-conditioned validation challenges, and verifies each candidate against the locked store before admission: supported hypotheses enter the answer-supporting state, unverifiable ones are quarantined, and contradictory ones are discarded. A sufficiency-based stopping mechanism further avoids unnecessary refinement. Experiments on NarraCrime and multiple public reasoning benchmarks show that EVAR improves both task performance and evidence faithfulness while maintaining controllable inference cost.

---

### You Know What I Mean: A Benchmark for Agentic Conversational Reference Grounding

Authors: Karen Fuchs, Uri Katz, Yoav Goldberg
Published: 2026-08-30
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2608.29834v1

Collaborative conversations frequently contain references whose targets are indirect rather than named: resolving "this looks like the fix discussed yesterday" requires combining conversational context with evidence from the surrounding workspace which is accessible through APIs or user interfaces. We formalize this problem as Conversational Reference Grounding (CoRG): using a given set of tools to resolve a reference in conversation to the unique external item intended by the speaker. CoRG is challenging because it combines lexical, semantic, and temporal cues distributed across the conversation and the external workspace. Agents must translate these heterogeneous signals into effective tool use: formulating strategies, discovering plausible candidates, inspecting their metadata and content, and ruling out close alternatives. We study CoRG through RepoRef, a benchmark of 400 developer-chat segments grounded in GitHub issues, pull requests, and commits across 92 repositories. Unlike single-shot retrieval tasks, RepoRef often requires multi-step tool use. Our results show that CoRG remains challenging for current agents, even the best agent reaches only 67.0% success rate, leaving one third of references unresolved. These findings position CoRG as a concrete benchmark for studying how agents search, inspect, and verify information in realistic multi-tool environments.

---

### A^2Agent: Action-Aware Reinforcement Learning for Repository-Level Code Localization Agents

Authors: Doyeon Kim, Suyoung Bae, Yumin Lee, Jee-Hyong Lee
Published: 2026-08-30
Categories: cs.CL, cs.SE
arXiv: https://arxiv.org/abs/2608.29831v1

Localizing issue-relevant code regions is a critical step in automated software engineering. However, due to their reliance on sparse trajectory-level signals, existing methods cannot identify which per-turn actions are effective and often discover correct code regions during exploration but fail to commit them. To address these limitations, we propose an action-aware reinforcement learning method that combines a per-turn reward sequence rewarding both the discovery and commitment of gold code regions with an action-level advantage estimation scheme that isolates each action's credit by grouping turns sharing the same exploration context. Extensive evaluations show that our method improves the average F1 over the state-of-the-art (SOTA) by 1.58% on SWE-Bench Verified and 8.55% on SWE-Bench Pro, with our 4B model outperforming baselines up to 8x larger. Our code is available at https://github.com/donian00/A2Agent.

---

### Null-Space Diffusion Restoration with Adaptive Uncertainty-Guided Fusion for Ultrasound Speckle Reduction

Authors: Juneyong Lee, Jaeyoung Choi
Published: 2026-08-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.29820v1

Ultrasound B-mode imaging commonly suffers from speckle noise and artifacts, requiring a delicate balance between contrast, resolution, and preservation of anatomical structures. Although recently developed despeckling methods have achieved some progress, supervised learning approaches remain fundamentally limited by the ground truth paradox, which arises from the absence of noise-free, ground truth reference images in in vivo scenarios. Existing unsupervised diffusion-based methods typically enforce data consistency directly in the nonlinear log-compressed domain, which can disproportionately amplify background artifacts when mapped back to the envelope domain. To overcome these limitations, we propose an uncertainty-guided null-space diffusion (UGNS) framework, a novel label-free solution that enforces consistency correction on a stabilized positive-envelope proxy obtained via inverse log compression. The proposed UGNS introduces several technical novelties: (a) extraction of a structural prior in the stabilized envelope domain to produce a robust signal envelope that preserves anatomical structure, (b) development of an adaptive range-null reconstruction mechanism that uses an adaptive weight mask to preserve tissue regions via range-space projection, and (c) introduction of uncertainty-guided fusion in an adaptive way to mitigate sampling variability. Extensive and comparative experiments were conducted using the PICMUS benchmark and in vivo datasets. The results demonstrate that UGNS achieves competitive generalized contrast-to-noise ratio (gCNR) values across diverse datasets. In addition, it is successfully validated that UGNS effectively suppresses speckle noise while preserving fine spatial resolution. Code is available at https://github.com/yousirong/UGNS.git.

---

### PhasorNet: Learning Structure from Frequency for Real-Time Stereo Matching

Authors: Md Raqib Khan, Santosh Kumar Vipparthi, Subrahmanyam Murala
Published: 2026-08-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.29819v1

Accurate stereo matching remains challenging in ill-posed regions such as fine structures, reflective, or transparent objects, where appearance cues are often ambiguous or unreliable. To tackle this, we propose PhasorNet, a lightweight yet powerful framework that boosts geometric discrimination via frequency-domain cues. At its core, the Phase-Augmented Transformer (PAT) injects Fourier-derived phase information into the attention mechanism, yielding photometrically robust, structure-preserving features that prioritize structural consistency in difficult areas. Additionally, we develop a Geometry-Context Fusion Refinement Module (GCFRM) that combines a full-resolution convolutional stream with a lightweight attention-based stream (leveraging WQA and CDGA blocks) to efficiently preserve fine details and object boundaries without excessive overhead. Training is further enhanced by a multi-scale Edge-guided High-Error Region (EHR) loss that adaptively focuses optimization on high-error and edge regions, guiding hierarchical cost volume refinement. With only 5.3M parameters, PhasorNet achieves state-of-the-art performance on the challenging ETH3D benchmark while exhibiting excellent cross-domain generalization on KITTI, delivering an efficient and practical solution for accurate real-time stereo matching.

---

### Structure Aware Neural Architecture Search for Mixture of Experts

Authors: Petr Babkin, Oleg Bakhteev
Published: 2026-08-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2608.29817v1

Neural Architecture Search (NAS) has so far rarely been applied to Mixture-of-Experts (MoE) models, and existing MoE designs leave the alignment between experts and the structure of the data to emerge on its own. We propose an architecture search framework that makes this alignment an explicit search variable: the assignment of data clusters to experts is optimised jointly with the per-expert architectures. We cast the joint problem as a cluster-aware likelihood maximisation, show that it coincides with the incomplete-data maximum likelihood of a latent-variable mixture, and solve it by a generalised Expectation-Maximisation procedure whose otherwise intractable expert-quality term is supplied by an adaptively refined surrogate. We prove that the iterates converge whenever the surrogate errors are summable, and that at every limit point no candidate the search produces improves the true objective. On a heterogeneous image-classification mixture the method recovers the underlying domain partition on 95% of clusters without ever observing domain labels, and on that benchmark and a four-domain time-series forecasting one alike it outperforms the MoE and NAS baselines that likewise use no label information.

---

### FRAMEWORKERS: A Dynamic Multi-Agent Framework for AI-Generated Video Production

Authors: Zhendong Li, Lei Sun, Letian Shi, Deheng Zhang, Ruibo Ming, Mengshun Hu, Dannong Xu, Jian Wang, Danda Paudel, Luc Van Gool, Jinjin Gu
Published: 2026-08-30
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.29814v1

Modern video generators excel at synthesizing individual clips, but complete video production requires coordinating a long sequence of interdependent creative steps, including scripting, storyboarding, generation, and editing. It further demands persistent asset management and dynamic task orchestration as intermediate outputs, dependencies, and execution states evolve over time. Existing automated systems typically rely on rigid pipelines that are difficult to adapt to diverse inputs and changing workflows, while general-purpose large language models (LLMs) remain unreliable for long-horizon orchestration and multimodal asset routing. We introduce FRAMEWORKERS, a task-centric and workspace-grounded multi-agent framework for open-ended video production. A central Director formulates video creation as dynamic task management, continuously editing a Task Stack to determine which subtask to execute next and which sub-agent to invoke. An Assistant serves as the execution layer, grounding each selected task in a shared Workspace, retrieving the required assets and context, invoking the assigned sub-agent, and persisting the resulting artifacts. Execution capabilities are exposed through modular sub-agents with registered descriptors, allowing new sub-agents to be integrated without redesigning the orchestration workflow. To improve orchestration reliability, we fine-tune the Director via supervised fine-tuning (SFT) followed by Group Relative Policy Optimization (GRPO) for descriptor-conditioned task routing. Experiments show that FRAMEWORKERS outperforms strong LLM planners in routing accuracy, recovers reliably from runtime failures, generalizes to unseen sub-agents without retraining, and achieves higher end-to-end video quality and broader task coverage than fixed pipelines, single-agent systems, and prior multi-agent approaches.

---

### RegionCache: Semantic-Aware Region Reuse for Efficient Multi-Turn Image Generation

Authors: Peizheng Li, Xin Ai, Hanyuan Liu, Qiange Wang, Yanfeng Zhang
Published: 2026-08-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.29809v1

Real-world image generation often involves multi-turn editing, where users iteratively modify small regions while most image content remains unchanged. However, existing diffusion transformer (DiT)-based editing pipelines recompute the entire image at every turn, causing substantial redundant computation. Existing DiT acceleration methods further ignore semantic correspondence across prompts, leading to unnecessary recomputation or unsafe reuse that harms editing quality. To address this, we propose RegionCache, a semantic-aware reuse framework for multi-turn image editing that selectively reuses diffusion states from unchanged regions. RegionCache detects reusable regions through semantic overlap between consecutive prompts and cross-attention localization, and adopts an adaptive reuse schedule based on prompt similarity and contextual consistency. Experiments on PixArt-alpha demonstrate that RegionCache achieves 1.43x--2.55x end-to-end speedup while maintaining comparable image quality. Code is available at https://github.com/hebutBryant/RegionCache.

---

### Beyond Global Realism: Virtual Try-On Evaluation and Optimization with Dimension-wise Garment Fidelity Assessment

Authors: Kaidong Zhang, Yukang Ding, Xiaoyu Liu, Ying Chen
Published: 2026-08-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.29804v1

Virtual try-on (VTON) requires not only realistic generation but also faithful preservation of garment characteristics. However, existing evaluation metrics such as PSNR, SSIM, KID and FID struggle to measure the consistency between the generated and reference garments, particularly in capturing the multi-dimensional characteristics of garment fidelity. To address this, we propose DAT: a Dimension-wise Assessment framework for virtual Try-on, which decomposes garment consistency into seven interpretable dimensions: silhouette, color, neckline and sleeve shape, major decoration and structure, material texture, fine-detail fidelity, and logo preservation, each formulated as a discrete attribute-level prediction task. To train this specialized assessment model, we adopt a two-stage learning paradigm comprising large-scale weak supervision on 50K samples, followed by refinement on 10K higher-quality annotations obtained via multi-model voting. Furthermore, we employ weighted cross-entropy loss to mitigate the severe label imbalance inherent across evaluation dimensions. Beyond its role as an evaluation framework, the assessment model can be integrated into reinforcement learning optimization of Qwen-Image-Edit for VTON, where dimension-wise rewards are adaptively aggregated to emphasize under-optimized aspects during training. Experimental results show that our method (8B parameters) achieves state-of-the-art performance in terms of balanced accuracy, SROCC, and PLCC, outperforming strong proprietary models such as Gemini-3.1, Qwen3.7-plus, and GPT-5.5, while also serving as an effective optimization signal for reward-guided VTON generation

---

### Do LLMs Change Their Minds Like Humans? Diagnosing Human--LLM Divergence in Single-Turn Persuasion Judgments

Authors: Lin Chen, Yitong Chen, Yong Li
Published: 2026-08-30
Categories: cs.CY, cs.CL
arXiv: https://arxiv.org/abs/2608.29803v1

Large language models (LLMs) are increasingly deployed as proxies for human participants in social simulations, yet whether they update their beliefs in response to persuasive arguments, as humans do, remains poorly understood. We conduct a systematic comparison using a naturally occurring online persuasion corpus in which original posters explicitly verify whether a reply changed their view. Our results show that LLMs achieve only slight agreement with humans (Cohen's kappa ranging from 0.079 to 0.178). Content-level analyses show that humans and LLMs agree on the strongest persuasion cues but diverge on finer ones: humans are more swayed by novel content and assertive language, whereas LLMs favor topical similarity and surface-level formatting. At the level of persuasion strategy, LLMs underweight emotional appeals and overweight credibility signals relative to humans, while the type of proposition under debate exerts no measurable effect on the degree of divergence. Furthermore, switching from first-person role-playing to third-person observation shifts all models toward greater resistance to persuasion, with the effect varying across persuasion strategies and textual features. These findings highlight the risk of treating LLM judgments as faithful proxies for human belief updating and point to structural differences in how LLMs and humans process persuasive discourse. Our code is available at https://github.com/tsinghua-fib-lab/LLM-belief-update-cmv.

---

### Foundation and Multimodal Large Language Models for Face Presentation and Morph Attack Detection

Authors: Hatef Otroshi Shahreza, Asif Hussain Khan, Peter Lorenz, Alain Komaty, Sébastien Marcel
Published: 2026-08-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.29802v1

Face recognition systems are increasingly deployed in security-critical applications, yet they remain vulnerable to presentation and morph attacks. Presentation attack detection (PAD) and morphing attack detection (MAD) are therefore essential components of trustworthy face biometrics. Despite advancements in PAD and MAD methods, existing detectors suffer from limited generalization and degrade in cross-dataset evaluation. In this paper, we systematically investigate whether general-purpose foundation models (FMs) and multimodal large language models (MLLMs) encode PAD-relevant and MAD-relevant information, and how such models can best be deployed for both tasks. We study five approaches with increasing access to the internal information of the model: (i) zero-shot prompting of off-the-shelf MLLMs; (ii) training a shallow model on the next-token logit probabilities at the output of the MLLM; (iii) parameter-efficient fine-tuning on task-specific question-answer data, yielding two specialized MLLMs, called PADLLM and MADLLM, which additionally provide textual reasoning for their decisions; (iv) linear probing of frozen vision encoders; and (v) fine-tuning of vision encoders of FMs and MLLMs. We benchmark 16 open-weight MLLMs and 30 vision encoder backbones on four PAD datasets (MSU-MFSD, CASIA-FASD, Replay-Attack, and OULU-NPU) and four MAD datasets (FFHQ, FRGC, FRLL, and FERET). Our experiments show that FMs and MLLMs can achieve significant performance for PAD and MAD. In addition, the fine-tuned models achieve state-of-the-art detection performance in cross-dataset evaluation, indicating that general-purpose pretrained representations carry substantial attack-relevant information. Source code of all our experiments will be publicly released.

---

### Source-Dependent Deference in Medical Imaging Agents Under Falsified Findings: A Pilot Audit

Authors: Ridam Roy, Md Shahriar Rashid, Md. Rajib Mia
Published: 2026-08-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.29800v1

Tool-using agents are being proposed for medical imaging, and their behaviour when a tool returns a false finding is largely unmeasured. We audit whether a ReAct-style tool-calling agent abandons an answer it has already given correctly once a falsified finding arrives, and whether that depends on how the finding is presented. On 20 VQA-RAD closed questions across four vendor-designated model tiers, the agent commits to an answer from the image alone; a negated finding is then delivered either as JSON from an analyze_image tool the agent invokes itself, or as quoted prose attributed to a radiologist. Our outcome is the commission-error rate over cases answered correctly without any tool. Deference is much higher under the prose-attributed claim: at the strongest tier the agent revised its correct answer in 10 of 13 cases against 1 of 13 under the tool (exact McNemar p=0.0039, Holm-adjusted 0.012). We do not claim this isolates the source label. Attribution travels with the delivery channel in our design, and exposure differs because the tool claim reaches the agent only when it calls the tool. The finding is a joint source-and-delivery asymmetry from a small-scale pilot whose pre-specified stopping rule was not met.

---

### R$^2$A: Learning Persona Policies Through Persona Representation Learning and Runtime Alignment

Authors: Mohan Zhang, Chengsong You, Xiaoyu Cao, Zhen Sun, Xiaohan Jia, Junwei Zhou, Yongchao Chen
Published: 2026-08-30
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2608.29798v1

The same Persona behavior can be beneficial in one context but harmful in another, causing static Persona elicitation to perform inconsistently across tasks. We introduce the Persona Selection--Realization Framework, which models behavior generation through a latent Persona state and decomposes it into Persona Selection and Persona Realization. The discrepancies between static Persona elicitation and an ideal Persona policy in these two components define the Selection Gap and Realization Gap, respectively. Building on this framework, we propose R$^2$A, a two-stage approach for learning Persona policies. Persona Representation Learning uses structured Who--How--What presentations to encode the target Persona's objective, conditional behavioral principles, and trajectory-level manifestations. Persona Runtime Alignment then removes the explicit Persona specification and jointly calibrates behavior selection and trajectory realization using task feedback. Across 12 evaluation settings covering the four principles of the Accountable-Professional Persona studied in this work, R$^2$A overall outperforms both the base model and static Persona elicitation. Ablation results further show that Persona Representation Learning is critical for preventing Runtime Alignment from producing behaviorally imbalanced policies and for achieving more stable Persona policy learning.

---

### GridFlow: Structured Latent Flow for Seamless City-Scale 3D Point Cloud Generation

Authors: Xinyu Wang, Muhammad Ibrahim, Atif Mansoor, Ajmal Mian
Published: 2026-08-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.29793v1

Generating realistic 3D city environments from remote sensing data is important for simulation, urban planning, and mixed reality, yet existing point cloud generation methods are limited to single objects or bounded indoor scenes and cannot handle the scale, seamless tiling, and partial observability challenges of city-scale generation. We present \ours{}, a multi-stage framework that generates dense, colored point clouds ($10^5$ points per $150\text{m}{\times}150\text{m}$ tile) at city scale, conditioned on satellite imagery, semantic segmentation maps, and digital surface models (DSM). A \emph{Grid-Aligned VAE} encodes each tile into a topology-preserving latent grid where tokens correspond to fixed spatial regions, enabling spatially coherent multi-modal conditioning and compact latent-space edge consistency that implicitly aligns thousands of boundary points for seamless cross-tile generation. A conditional rectified flow model synthesizes geometry latents from the fused multi-modal conditions, and an orientation-aware diffusion colorizer separately handles satellite-visible horizontal surfaces and occluded vertical façades. To support standardized evaluation, we build on public 3D data sources to introduce \emph{City3D-MultiGen}, a benchmark of $163$K densely annotated tiles from Melbourne and London with aligned point clouds, satellite images, semantic maps, and elevation data. Experiments show that \ours{} outperforms adapted point cloud generation baselines across all geometry metrics and produces visually coherent colored point clouds with seamless boundaries over arbitrarily large urban extents. Our benchmark details are available at https://huggingface.co/datasets/e32/City3D-MultiGen

---

### HiVe: Beyond Static Prompts for Multitask Learning via Hierarchy-based Vertical Mixture-of-Experts

Authors: Hyeonjik Bae, Minyeol Kim, Susik Yoon
Published: 2026-08-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2608.29790v2

As large language models (LLMs) continue to scale, parameter-efficient fine-tuning (PEFT) has become a practical alternative to full-parameter adaptation. Prompt tuning is effective, but existing approaches either use flat prompt structures or hierarchical structures with fixed prompt composition, limiting adaptive prompt specialization. To address this limitation, we propose HiVe, a prompt tuning framework that models prompts at multiple levels and enables input-dependent specialization. HiVe constructs a prompt hierarchy by leveraging inter-task relationships during training, and employs a vertical mixture-of-experts (V-MoE) mechanism at inference time to compose prompts up to the level of specialization required for each input. Experiments show that HiVe consistently outperforms strong prompt tuning baselines across diverse tasks.

---

### A Unified Perspective on Conformal Prediction and Wasserstein Distributionally Robust Optimization for Uncertainty Quantification

Authors: Kehan Long, Yiqi Zhao, Pol Mestres, Lars Lindemann, Nikolay Atanasov, Jorge Cortés
Published: 2026-08-30
Categories: math.OC, cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2608.29789v1

Uncertainty quantification from finite data is central to machine learning, optimization, and automation systems, where decisions must remain reliable under limited samples and test-time distribution shift. Conformal prediction (CP) and distributionally robust optimization (DRO) offer two complementary approaches: CP constructs data-dependent prediction sets with distribution-free finite-sample validity under exchangeability, while DRO optimizes worst-case performance over an ambiguity set around an empirical distribution. We develop a unified probabilistic perspective on CP and DRO by viewing both as ways to turn finite calibration data into a data-dependent quantile estimator that a test score falls below with high probability. From this perspective, CP and DRO correct the empirical quantile along two coordinates of the same family of estimators: CP inflates the quantile level, whereas DRO shifts the quantile value through an ambiguity radius. Both methods provide the same calibration-conditional guarantee for the true distribution, requiring the target coverage to hold with high probability over the calibration sample. Their constructions differ, however: CP uses a closed-form, distribution-free level correction, while DRO uses a value-space correction whose certified radius depends on properties of the unknown distribution and additionally guarantees coverage uniformly over the ambiguity set. This distinction emerges in the tails of the score distribution. Because CP relies on sparse upper-tail order statistics of the calibration samples, its level inflation barely moves the estimator when those samples are dense near the target quantile but overshoots when they are sparse, whereas a well-chosen DRO radius corrects in value space and may avoid this overshoot.

---

### InspectorGPT: A Comparative Reasoning Enhanced VLM for Comprehensive Industrial Anomaly Detection

Authors: Weifei Chen, Honghao Zhang, Zhiyuan You, Xinyi Le
Published: 2026-08-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.29783v1

Industrial anomaly detection is a critical component of modern manufacturing. Most traditional unsupervised methods rely on modelling normal feature distributions, inherently limiting generalization to unknown categories. To improve generalizability, some recent methods incorporate vision-language models (VLMs) for zero-shot detection via text prompts. However, we observe that reasoning-oriented post-training can cause anomaly discrimination to collapse, with some fine-tuned models performing worse than their base VLMs. Existing methods also provide only textual decisions or coarse boxes, without pixel-level segmentation. A more explicit detection principle comes from human inspection: anomalies are identified by comparing a query image with a defect-free reference. Inspired by this, we propose InspectorGPT, a VLM framework centered on comparative reasoning. Given a normal reference and a query image, InspectorGPT compares them to identify discrepancies and perform multiple inspection tasks with detailed reasoning. We internalize this capability through Chain-of-Thought (CoT) fine-tuning and Group Relative Policy Optimization (GRPO) with tailored, verifiable rewards. We further introduce InspectorGPT-Seg for pixel-level anomaly masks. Segmentation supervision improves anomaly discrimination but weakens semantic reasoning, while joint training fails to balance them. We therefore train the two branches separately and combine them through task-vector fusion. Extensive experiments demonstrate superior multi-dimensional performance and generalization to unseen benchmarks, validating comparative reasoning for comprehensive industrial inspection.

---

### PruneShift: A Framework for Evaluating Decision Reliability in Structured Pruning

Authors: Hao Ye, Gaopeng Zhang
Published: 2026-08-30
Categories: cs.LG, cs.NE
arXiv: https://arxiv.org/abs/2608.29765v1

Structured pruning uses surrogate objectives because direct task evaluation over every feasible mask is too expensive. Most evaluations report average surrogate error or rank correlation on broadly sampled masks. These summaries do not directly test the mask chosen by the surrogate. We introduce PruneShift, an evaluation framework that separates broad predictive fidelity, fidelity near selector outputs, and the quality of the selected pruning decision. We first prove that Spearman and Kendall agreement can approach one while normalized selection regret remains maximal. We then derive sufficient conditions based on uniform error, selector suboptimality, decision margin, density ratio, and comparison mass. The analysis also yields a finite pool certificate with an explicit excess cost bound. Four studies test different links in this argument. External TextbookQA confirmation is heterogeneous: 7 of 20 simultaneous intervals favor the surrogate-selected mask, 6 favor its fixed comparator, and 7 cross zero. On a fixed Natural Questions pool, strict improvement holds in one of four settings. A controlled QQP experiment supports the proposed coverage mechanism in all 16 prespecified endpoints, although the sufficient bounds are conservative. Finally, a restricted OSSCAR reconstruction study on OPT-125M shows better local than broad fidelity in 68 of 75 primary endpoints. Independent fixed-mask confirmation is inconclusive in 24 of 25 endpoints and favors the comparator in one. These results show why predictive fit, decision reliability, and pruning method quality require separate evidence.

---

### ECA-BLS: An Efficient Complex-Augmented Broad Learning System

Authors: A. Rahaman, A. Quadir, M. Sajid, M. Akhtar, M. Tanveer
Published: 2026-08-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2608.29763v1

Broad Learning System (BLS) is an efficient alternative to deep architectures due to its fast training, analytical learning, and strong generalization under limited data. However, existing BLS variants are confined to real-valued representations, restricting their ability to capture nonlinear interactions and second-order statistical dependencies inherent in real-world data. Notably, no prior BLS model fully exploits the complete second-order statistics that naturally emerge when data are embedded in the complex domain. To address this limitation, this paper introduces the first complex augmented Broad Learning System (CA-BLS), which transforms real-valued inputs into phase-encoded complex representations and adopts widely linear modeling to jointly leverage covariance and pseudo-covariance information via complex conjugate augmentation. This enables effective modeling of latent nonlinearities, coherence structures, and second-order dependencies inaccessible to conventional BLS formulations. To mitigate the additional computational cost of complex augmentation, an Efficient Complex Augmented BLS (ECA-BLS) is further developed, reformulating CA-BLS entirely in the real domain while preserving its exact decision function, achieving up to 75\% fewer multiplications and over 60\% fewer additions. A rigorous theoretical analysis proves the mathematical equivalence between CA-BLS and ECA-BLS, ensuring zero theoretical loss. Extensive experiments on 26 benchmark datasets from the UCI and KEEL repositories demonstrate that ECA-BLS consistently outperforms classical BLS and recent state-of-the-art randomized neural networks in accuracy, average rank, and statistical significance, establishing augmented second-order modeling as a critical and previously missing dimension of BLS research.

---

### SynCrash: A Multi-Stage Pipeline for Zero-Shot Accident Detection and Localization in Traffic Surveillance Video

Authors: Arkya Jyoti Bagchi, Ritul Jangir, Varun Raskar
Published: 2026-08-30
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2608.29759v1

We present SynCrash, a multi-stage pipeline for zero-shot accident detection, spatial localization, and collision-type classification in fixed-view CCTV surveillance video. Our approach addresses the ACCIDENT at CVPR 2026 Challenge, which requires predicting when an accident occurs, where in the frame the impact happens, and what type of collision it is, all without access to labeled real-world training data. The pipeline operates in three decoupled stages: (1) Temporal localization via a VideoMAEv2-giant backbone fine-tuned on CARLA-based synthetic clips with metadata-aware embeddings and dense sliding-window inference; (2) Spatial localization using YOLO for object detection combined with a physics-informed hybrid heuristic that leverages bounding-box overlap and trajectory-based reasoning to predict the impact point; and (3) Collision-type classification using a lightweight rule-based strategy derived from the number and configuration of detected vehicles. The key insight is that temporal understanding benefits from supervised fine-tuning on synthetic data, whereas spatial understanding is better served by pretrained object detectors and physics priors that transfer naturally across domains.

---

### GraM-Diff: A Unified Graph-Mamba Diffusion Framework for EEG-Based Alzheimer's Disease Data Generation and Diagnosis

Authors: M. Tanveer, Ayush Singh Rana, Sanskriti Jain, Arnav Kumar, Aryaman Tiwari, A. Rahaman, A. Quadir, M. Sajid
Published: 2026-08-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2608.29755v1

Electroencephalography (EEG) is a promising, non-invasive, and cost-effective modality for Alzheimer's disease (AD) detection, but deep learning methods are limited by small and imbalanced clinical datasets. Generative augmentation offers a solution, yet existing approaches rely on inefficient class-specific models or fail to capture complex spatial and temporal brain dynamics. To address this, we propose GraM-Diff, a unified classifier-guided Graph-Mamba diffusion framework for EEG synthesis. It embeds Graph Convolutional Networks within a diffusion U-Net to model inter-electrode connectivity and Bidirectional Mamba state-space blocks for linear-complexity long-range temporal modeling. Latent-space classifier guidance lets a single model generate both healthy and pathological EEG within a shared representation, avoiding fragmented per-cohort pipelines. Across four EEG-based AD benchmarks, synthetic augmentation improves classification, yields superior Context-FID and correlation scores over strong generative baselines, and enhances robustness in data-scarce settings.

---

### PAGE-RAG: Provenance-Aware Graph Evidence Promotion for Fixed-Budget Multi-hop Retrieval-Augmented Generation

Authors: Haokun Deng, Xunkai Li, Hongchao Qin, Rong-Hua Li
Published: 2026-08-30
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.29753v1

Multi-hop question answering in retrieval-augmented gener?ation (RAG) often benefits from retrieving beyond the few candidates that will finally be read: narrow retrieval can miss an indispensable hop, while expanded retrieval introduces topical distractors. This challenge is not tied to a particu?lar knowledge-base format. Candidate pools may come from standalone retrievers, standard RAG backends, or graph-based retrieval pipelines. What is needed is a query-aware selection layer that can use relational structure to filter candidates be?fore generation. PAGE-RAG addresses this setting by using a graph as a temporary selection structure, rather than assum?ing a graph-structured knowledge base. It builds a query-local graph over retrieved candidates, records why candidates are connected, and treats each connection as a support hypothe?sis rather than support itself. We identify the resulting failure mode as a connectivity-support gap: connected candidates do not necessarily support the answer. We propose PAGE-RAG, a Provenance-Aware Graph Evidence promotion method that scores candidate paths with relevance, source-tracing meta?data, specificity, hubness, noise, and coherence signals, and applies minimal sufficient selection to promote supporting facts into a compact reader context. PAGE-RAG can serve as a complete retrieval-to-reading pipeline, and the same promo?tion stage can be inserted after existing retrieval or RAG sys?tems without replacing their upstream retrieval logic. Across three multi-hop QA benchmarks under the same final bud?get, PAGE-RAG improves support F1 and answer F1 by 10.4 and 3.3 points on a weighted average over a strong retriever. As a plug-in, PAGE-RAG further improves all reported RAG backends, including reasoning-oriented, compression-based, graph-based, and document/chunk-level systems.

---

### ReTrace: Rejected-Trajectory Conditioning for Speculative Decoding

Authors: Luxi Lin, Zhanpeng Zeng, Shuang Peng, Songwei Liu, Rongrong Ji
Published: 2026-08-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2608.29748v2

Speculative decoding accelerates autoregressive language model inference by having a lightweight draft model propose multiple candidate tokens, which are then verified in parallel by a larger target model. However, after the first rejection, standard prefix-based verification discards the remaining draft suffix, so the computation spent generating and verifying those positions does not contribute to decoding progress. Focusing on DFlash, we show that rejected positions in a rejected suffix may still align with the target continuation, indicating that the draft model can retain useful semantic and structural information despite local token-level errors. Motivated by this observation and inspired by conditional diffusion, we introduce ReTrace, a rejected-trajectory conditioning method that conditions each draft block on the rejected suffix from the previous round rather than generating it from fresh mask placeholders alone. ReTrace retains the hidden representations of the rejected suffixes, aligns them with the next draft block, refines them using target-aware correction signals from the same verification pass, and admits them into the drafter's input embeddings through gated residual fusion. Because rejected tokens are never committed and target-side verification remains unchanged, ReTrace preserves the lossless property of speculative decoding without requiring an additional model forward pass. Experiments with Qwen3 models across mathematical reasoning, code generation, and open-ended dialogue demonstrate that ReTrace consistently improves average acceptance length and end-to-end decoding speed over its DFlash backbone. By introducing cross-round conditioning without modifying within-round proposal generation, ReTrace is largely orthogonal to existing drafting improvements and might be combined with them for further gains.

---

### Drift Calibration in Geometric Eye Tracking Systems

Authors: Jiaqi Liu, Zixuan Wang, Yuhong Zhang, Dingkang Liang, Jane Hanqi Li, Tzyy-Ping Jung, Gert Cauwenberghs
Published: 2026-08-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.29739v1

Geometric eye trackers can provide the spatial accuracy required for gaze-based interaction and multimodal studies, but their measurements remain sensitive to residual session-specific calibration error. Research on correcting this error is difficult to compare because methods are typically evaluated with different devices, target layouts, and error definitions. We present a calibration-focused dataset containing 163 trials from 12 participants, with separate 18-point fitting and 32-point test grids, and use it to evaluate global, local, and composite correction functions under a common spatial-extrapolation protocol. We further introduce a lightweight neural refiner that combines ranked predictions from complementary calibrators. On this controlled dataset, post-vendor correction reduces the mean angular error from $1.53^\circ$ to $1.03^\circ$ with the strongest classical composite and to $0.96^\circ$ with the refiner. In a closed-loop gaze task, lower residual error is associated with higher performance across four online correction conditions. These results provide a reproducible data-quality benchmark for using gaze as a behavioral signal in interactive modeling.

---

### Evaluating the Capabilities of LLMs for Persuasive Dialogue

Authors: Jordan Robinson, Angus R. Williams, Katie Atkinson, Anthony G. Cohn
Published: 2026-08-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2608.29738v1

Large language models (LLMs) can generate apparently highly persuasive text, but does sounding persuasive mean arguing well? We introduce \textsc{Persuasio}, a multi-agent dialogue platform grounded in a formal argumentation-based theory of persuasion dialogues that adjudicates logical winners during free-text debates. Using this system, we generated 192 debates on a UK political topic between humans and LLMs, and evaluated 22 interlocutors through both automated adjudication and 9,702 crowdsourced pairwise judgements across 1{,}386 annotation instances. We observed a consistent decoupling between subjective and formal persuasiveness: LLMs dominated the subjective ranking yet performed substantially worse under argumentation-theoretic adjudication, where humans remained competitive. Multi-agent and retrieval-augmented variants further widened this divergence. These findings reveal a systematic gap between rhetorical fluency and formal argumentative strength in LLM-based persuasive dialogues.

---

### XDG: Accelerated Visual Disambiguation

Authors: Gonglin Chen, Ben Southall, Hanyuan Xiao, Wenbin Teng, Haolin Xiong, Tianwen Fu, Junyi Ouyang, Kshitij Singh Minhas, Supun Samarasekera, Rakesh Kumar, Yajie Zhao
Published: 2026-08-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.29733v2

Visual aliasing, also known as the doppelganger problem, remains a key challenge for structure-from-motion (SfM): visually similar but physically distinct surfaces can produce incorrect image matches and degrade reconstruction quality. Previous work mitigates this issue with geometry-aware foundation-model features, but places a heavy transformer classifier on top of the backbone, making large-scale disambiguation expensive. We introduce XDG, an efficient visual disambiguation model designed for scalable SfM. Our key observation is that a 3D foundation model already performs the cross-view geometric reasoning necessary for visual disambiguation, so doppelganger classification should adapt the backbone representation directly rather than relearn pair reasoning in a separate heavy decoder. XDG fine-tunes Depth Anything 3 with lightweight LoRA adapters and repurposes its camera tokens as compact pair-level classification tokens. A compact MLP head predicts whether a candidate image pair observes the same 3D surface. Extensive experiments show that XDG provides a favorable accuracy-efficiency tradeoff: it remains competitive with the state-of-the-art disambiguation method across pairwise and reconstruction benchmarks and delivers more than a 3x inference speedup. On individual LaMAR scenes containing thousands of images, XDG saves more than 10 hours of visual disambiguation processing. Code is available at https://github.com/xtcpete/xdg.

---

### Higher-Dimensional Rotary Position Embedding

Authors: Yixing Li, Ruobing Xie, Yudong Zhang, Yushi Bai, Samm Sun, Yu Cheng
Published: 2026-08-30
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2608.29715v1

Transformers rely on position embedding mechanisms in long context modeling in most cases. Rotary Position Embedding (RoPE) embeds positional information with independent 2D rotations, forming relative position terms in self-attention. However, its pairwise, block-based, and decoupled structure limits deep mixing and robustness across channels. We propose HD-RoPE, which extends RoPE from independent 2D rotations to higher-dimensional rotations and introduces a Paley-I orthogonal basis to obtain balanced, isotropic, and dense phase mixing within each rotation subspace. This significantly enhances channel coupling and rotational degrees of freedom while maintaining orthogonal stability and the relative position closure property. Furthermore, HD-RoPE is easily optimized for engineering efficiency without introducing additional trainable parameters. We have conducted extensive evaluation results demonstrating that HD-RoPE achieves significant performance improvements over standard RoPE across various popular benchmarks and in both long and short contexts.

---

### Neural ODE enhanced linear mixed effect models for estimating complex association patterns of time-varying covariates with the marker trajectory

Authors: Zhe Aurore Li, Quentin Clairon, Cécilia Samieri, Rodolphe Thiébaut, Mélanie Prague, Cécile Proust-Lima
Published: 2026-08-30
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2608.29714v1

Longitudinal cohort studies produce repeated data that enable the assessment of time-varying association patterns between exposures and health outcomes. Classical linear mixed-effects models (LMMs) can accommodate a large variety of association patterns while accounting for the irregularly spaced, partially observed measurement. But they require the analyst to pre-specify the functional form linking the exposure history to the outcome. We propose the Neural ODE-LMM, which embeds a Neural Ordinary Differential Equation (Neural ODE) within the linear mixed-effects framework: a learned vector field encodes covariate trajectories into a continuous-time latent state that drives both the fixed- and random-effect design, while preserving the standard LMM observation model. This retains classical likelihood-based inference while learning complex, potentially cumulative, covariate effects flexibly. All parameters are estimated by maximising a penalised marginal likelihood. To quantify covariate effects, we introduce contrasts of counterfactual predictions that compare the expected outcome under alternative covariate trajectories with variance estimated via the delta method. In simulations, the model recovers both instantaneous and cumulative-burden effects without prior specification of the functional form. Applied to the Trois-Cités (3C) cohort, a population-based study of 7{,}324 participants, the method reveals trajectory-dependent associations of BMI and fasting glucose with cognitive decline.

---

### DVBench: Benchmarking MLLMs for Understanding Dynamic Charts and Narratives in Data Videos

Authors: Bomiao Wang, Zekai Shao, Jiexiang Lan, Xiaoliang Fu, Xingchen Zeng, Siming Chen
Published: 2026-08-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2608.29711v1

While MLLMs have made significant strides in chart comprehension and video understanding, current evaluations largely isolate these capabilities, leaving a critical gap in understanding temporally evolving structured visual information. To address this gap, we introduce DVBench, a benchmark for evaluating MLLMs on data videos, a storytelling medium that integrates dynamic charts with structured narratives. We decompose data video understanding into five dimensions. DVBench comprises 300 real-world data videos and 1,000 human-verified QA pairs curated through a rigorous semi-automated pipeline. Extensive evaluations of nine MLLMs show that Gemini-3.1-Pro achieves the best overall performance, while Kimi-k2.5 is the strongest open-source model. We further identify two notable phenomena: open-source model performance does not scale strictly with parameter size, and narrative proficiency does not guarantee visual capability. Fine-grained analyses and ablation studies further reveal dimension-specific weaknesses and the effects of frame configurations and subtitle inputs, informing future MLLM development. DVBench is publicly available at https://bomiaowang.github.io/DVBench/.

---

### The Depth Flow of Token Representations Is Nonlinear and Does Not Descend Its Own Density

Authors: Alexandre Quemy
Published: 2026-08-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2608.29706v1

A token's representation is carried through the network layer by layer. The whole vocabulary carried together forms a flow. We fit this flow's equation of motion as a discrete Langevin model over corpus-mean trajectories of Pythia-160M and Pythia-410M, and score the predicted steps on held-out tokens. Linear maps are often used as cheap surrogates for a layer. The flow they summarize is not linear: a quadratic drift beats the linear linear map at every transition of both models, and the Kramers--Moyal estimator agrees wherever its neighborhoods stay local. We then characterize the flow further. First, we show that it does not descend its own log-density. The drift instead descends a potential that is not the density. Second, the rotational component is not negligible, $4$ to $45\%$ of the explainable drift, and the circulation shows in what the flow preserves: a token keeps its angular rank across all thirteen layers while its norm rank is shuffled and its concentration rank is reversed by the last block.

---

### A Calibration Audit of Confidence in Feed-Forward 3D Reconstruction Models

Authors: Nanxing Nick Deng, Qing Cheng, Niclas Zeller, Daniel Cremers
Published: 2026-08-30
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2608.29705v3

Feed-forward 3D reconstruction models output a per-pixel confidence that is used by downstream systems as an uncertainty signal. The confidence is trained to serve as a weight in the training loss of models. Whether the confidence can be used as an uncertainty magnitude has not been measured. We audit seven backbones on 13 datasets and score the confidence on four properties, i.e., ranking of error, ratio of error to uncertainty on average, slope of this ratio across the confidence range, and coverage of the implied error distribution. Although the confidence ranks error quite well, the uncertainty decoded from the confidence is too small compared to the actual error. The uncertainty has the right size only under the exact training conditions. The median case is off by at least 2.4x across all seven models, while the uncertainty is further off the more confident the model is. Our work shows that the overconfidence appears on unseen scenes even when the model reaches its loss's optimum. As a post-hoc repair we fit a power law on the confidence with two constants per backbone--dataset pair. The repair brings all four audited properties to target at the dataset level, while leaving ranking untouched. Fitted with the target dataset held out, the constants bring the median case from 2.4x off to 1.35x. The repair does not hold below the dataset level, where two-thirds of held-out scenes are still more than five points off in coverage. We attribute what the repair cannot reach to the model, which carries neither the scale of the error nor the shape of its distribution across predictions. We release the audit protocol, its results, and the fitted constants per backbone-dataset pair.

---

### A Hub of Short Rows Inflates Intrinsic Dimension Estimation of Token Embeddings

Authors: Alexandre Quemy
Published: 2026-08-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2608.29702v1

A token-embedding table holds a hub of short rows near its origin, and we show that this cluster biases what nearest-neighbor intrinsic-dimension (ID) estimators report. Because of the concentration of measure, a token is closer to the central cluster than to any other token, so its first two neighbors are both hub rows at nearly the same distance. As a result, the ID estimators such as TwoNN return a dimension far above the real ID. Measured one token at a time, dimension is a heavy-tailed distribution. Measured on the full vocabulary, it grows with the model's parameter count. However, when we remove the hub, the heavy tail disappears and the measured dimension collapses to a narrow range for eleven models, from GPT-2 to models such as K3 and GLM-4.7. The hub acts as a switch: a few hundred rows are enough to fully inflate the estimate. We reproduced an experiment stating that the intrinsic dimension (ID) of Pythia's token-embedding table grows with the parameter count, from $27$ to $122$ between 160M and 12B parameters. We show that this result disappears when the hub is removed: the table then reads $10$ to $17$ at every size. The hub contains a subset of the population that under-trained-token detectors flag, but on Pythia the hub that we detected and removed as a whole was updated during training: what seem to characterize these rows is simply their length, not an absence of updates. Finally, we show that normalizing the rows instead of removing them gives the same lower reading.

---

### Ideation Arena: Evaluating LLM Generated Research Ideas with Battle-style Human Expert Assessment

Authors: Zhiyu Chen, Keyu Zhao, Jigao Fu, Dong Liang, Yanbiao Wu, Jiaoyang Li, Haidong Xue, Xinhua Zeng, Yuanyi Zhen, Fengli Xu, Yong Li
Published: 2026-08-30
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.29696v1

Evaluating research ideas generated by LLMs is difficult because their scientific value cannot be fully determined by objective criteria, and no single reference answer specifies what counts as a good idea. To address this challenge, we introduce Ideation Arena, a battle style platform that evaluates research ideas through pairwise human assessment. Ideation Arena evaluates ideas generated by 14 frontier LLMs and 5 research agent architectures built on 2 base models. To ensure a common starting point, Ideation Arena builds shared literature contexts from papers familiar to the participating researchers and provides the same contexts to all LLMs and agents. We collect over 6,000 double blind pairwise comparisons from 105 active computer science researchers and construct an Elo rating leaderboard of proposal-stage expert preferences in computer science under a shared closed-context protocol. We validate the rankings through interrater agreement and robustness analyses, showing that the leaderboard remains stable under changes in annotator composition and domain coverage. Our results show substantial variation in agent effectiveness, with some frameworks improving ideation quality over their backbones and others offering little benefit or even underperforming their base models. We further construct Ideation Arena Eval, a benchmark for assessing whether automated evaluators align with human preferences in research ideation. Experiments with current LLM judges show that they still cannot reliably reproduce expert preferences, with the best judge reaching 72.56% Soft Accuracy on Overall Quality. Our code, data, and leaderboards are available at https://github.com/foss12138/Research-Ideation-Arena.

---

### Transformer-Based Flow Shop Scheduling Using MILP-Generated Training Data

Authors: Roderich Wallrath
Published: 2026-08-30
Categories: math.OC, cs.LG
arXiv: https://arxiv.org/abs/2608.29690v1

Advances in machine learning (ML) have created new opportunities to complement traditional operations research (OR) methods. In particular, transformer models can capture complex interactions in token sequences by mapping tokens into a high-dimensional embedding space and propagating contextual information via attention. This makes them a candidate to model non-permutation flow shop scheduling with secondary resources as a next-token prediction task, where tokens represent job-machine-secondary resource tuples. For training, mixed-integer linear programming (MILP)-generated schedules are tokenized and used as next-token prediction data. During inference, partial token sequences (prefixes) are randomly generated and completed by the trained transformer through constrained decoding. A computational study is conducted on a flow shop with 8 jobs, 4 machines, and 3 secondary resources, where jobs are selected from a fixed pool of 20 jobs that is sampled during training and provides the candidates during prefix completion. The transformer achieves better solution quality (smaller makespans) compared to a genetic algorithm (GA), the NEH heuristic, and random search. It is outperformed only by the MILP model and the iterated greedy (IG) heuristic. The study concludes that transformer models can, to some extent, learn patterns from MILP-optimized non-permutation flow shop schedules and that transformer-based scheduling represents an interesting direction for future research, particularly in settings with a fixed, recurring job set.

---

### Last Step Matters: Early Uncertainty Cannot Predict Failure in Long-Horizon Agents

Authors: Zongyue Li, Chengyue Yu, Lei Zang, Chenyi Zhuang, Linjian Mo, Leilei Gan
Published: 2026-08-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2608.29685v1

Early failure prediction is important for long-horizon agents, as it enables timely intervention and can reduce inference and tool-use costs. Uncertainty quantification, such as verbal confidence and perplexity, offers a promising approach to detecting agent failures; however, it has not been explored whether these signals retain their discriminative power during the intermediate stages of long-horizon execution. We evaluate mainstream uncertainty signals on deep-research tasks and find that verbal confidence reliably distinguishes failures at trajectory completion, achieving a mean AUROC of 0.85, whereas all evaluated signals offer limited predictive value earlier in execution, with none exceeding a mean AUROC of 0.60 at 50% trajectory progress. We identify an underlying mechanism explaining this gap: path switching, where agents frequently abandon their current search direction in-trajectory, breaking the link between early signal and final outcome. These findings challenge the assumption that intermediate uncertainty can reliably guide early intervention. They also motivate a practical recommendation for agent harnesses in deep-research settings: use final-step confidence to decide whether to restart, an approach that our experiments find more effective than in-trajectory intervention.

---

### GeoRay: Gauge-Aware Feed-Forward Satellite 3D Reconstruction in the Geodetic Frame

Authors: Zhe Dong, Wanqing Wu, Yuzhe Sun, Haochen Jiang, Yuchen Ma, Lecheng Ren, Tianzhu Liu, Yanfeng Gu
Published: 2026-08-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.29680v1

Feed-forward 3D foundation models reconstruct perspective scenes in one pass. Satellite photogrammetry needs a different product, one that domain adaptation alone does not deliver: dense surface height in an absolute geodetic frame under non-central rational polynomial cameras (RPCs). Perspective-pretrained features are not reliably observable along RPC height rays, absolute elevation carries a low-order height--datum gauge exchangeable with sensor bias to first order, and monocular and multi-view cues fail in different regions. \method{} treats all three. Lightweight ray-consistent adapters make a frozen backbone matchable along native RPC rays. An explicit datum mechanism separates relief from absolute level and is equivariant to the vertical origin by construction, so one trained model serves zero-, one-, and sparse-control inference. Calibrated inverse-variance fusion combines the two relief streams. \bench{}, our absolute-frame benchmark of eighteen systems across in-domain, cross-dataset, and cross-city tiers, scores absolute placement without registration or test-reference leakage. On 26 held-out US3D tiles, \method{} attains $2.99$\,m absolute MAE at $91.9\%$ coverage, improves completeness-aware accuracy by $46.4$ points over the strongest compliant feed-forward baseline, remains the most accurate such system under both transfer shifts, and runs in $24$\,s model-forward time per tile. Code and models will be released at https://github.com/HIT-SIRS/GeoRay

---

### MedSegBenchmarker: A Raw-Count-First Framework for Controlled 2D Medical Image Segmentation Benchmarks

Authors: Vanessa Borst, Lukas Horn, Daniel Grillmeyer, Thomas Prantl, Samuel Kounev
Published: 2026-08-30
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2608.29677v1

Despite rapid advances in MIS, fair and reproducible comparisons of segmentation models remain challenging due to heterogeneous datasets, inconsistent evaluation protocols, and rapidly evolving architectures. In particular, comparisons often implicitly assume that model rankings are invariant to data partitioning, preprocessing, metric aggregation, uncertainty estimation, and computational constraints. The lack of extensible and unified evaluation frameworks further limits systematic investigation of new models, datasets, and training paradigms. We present MEDSEGBENCHMARKER (MSB), a configuration-driven framework for controlled benchmarking of 2D MIS. It integrates duplicate and near-duplicate image detection, group-aware data splitting, YAML study specifications, resumable training, hyperparameter optimization, cross-validation, and checkpoint-based evaluation. Rather than retaining only aggregate performance measures, MSB exports sample- and class-level pixel counts and predictions together with the evaluation context. These elementary artifacts enable post-hoc analyses without repeated inference. We demonstrate MSB in a case study involving three heterogeneous 2D datasets and multiple MIS and general-purpose vision models evaluated at 256- and 512-pixel input resolutions. Reaggregation of identical predictions changes the top-ranked architecture in three of six dataset-resolution settings, despite high rank correlations between aggregation strategies. Increasing input resolution produces model- and dataset-dependent performance gains and losses that must be considered alongside empirically measured inference complexity. These results show that seemingly minor choices in evaluation and experimental setup can affect benchmark conclusions. MSB, available at GitHub, provides a practical and extensible basis for making benchmark conditions and evaluation choices explicit and reproducible.

---

### Cost-Effective Repository Exploration for Agentic Issue Localization

Authors: Mohammad Nour Al Awad, Sergey Ivanov
Published: 2026-08-30
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2608.29675v1

Repository exploration is a distinct and costly stage of coding-agent pipelines: before generating a patch, an agent must identify which repository files are likely to matter. We study whether this stage can be delegated to lower-cost models while retaining useful localization quality. Using our IssueLoc-Bench, we evaluate five explorer models under the same read-only interactive interface on 499 SWE-bench Verified-derived tasks and 500 tasks from 153 additional repositories. We measure early candidate discovery, top-three gold-file coverage, strict file-set recovery, agent time, and token usage, with paired instance-level uncertainty and repository-clustered sensitivity analysis. The highest-quality explorer leads across localization metrics, but substantially cheaper operating points emerge: depending on the model and evaluation arm, lower-cost explorers retain approximately 78-94% of the reference Hit@3 and 73-92% of its F1 while reducing mean agent time by 41-88% and token usage by 84-95%. The preferred operating point depends on how localization is consumed downstream: ranking and coverage metrics characterize recoverable candidate handoffs, whereas F1 and exact match characterize restrictive file gates. These results support treating repository exploration as an independently measurable and budgetable stage of modular coding agents, with explorer selection guided by the downstream handoff contract.

---

### Creation begins with understanding: LLMs as strategy designers for privacy-preserving tabular data synthesis

Authors: Jinmeng Li, Quan Zhang, Hangting Ye, He Zhao, Firas Laakom, Dandan Guo, Jürgen Schmidhuber
Published: 2026-08-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2608.29674v1

Sharing tabular data in high-stakes domains is constrained by privacy regulations. Synthetic data offer a promising alternative, but deep generative models are costly to train and difficult to audit, while LLM-based methods often serialize records as text, obscuring tabular structure and exposing sensitive data. We introduce Tabular Synthesis Strategy Designer (TabSSD), which uses an LLM to design synthesis procedures rather than directly generate records. TabSSD provides the LLM with tree-derived summaries of variable dependence rather than raw records, which produces Python programs for local execution and evaluation. Across twelve datasets, TabSSD strikes a favourable balance among statistical fidelity, predictive utility, and empirical privacy risk, achieving the best average rank across six metrics among ten methods. Moreover, it substantially reduces local computation and token consumption relative to the compared methods. By enabling human-guided refinement and eliminating user-side model tuning, TabSSD lowers the expertise and infrastructure barriers to transparent tabular data synthesis.

---

### A Target-Centric Survey of Quantization-Aware Training

Authors: Jiamin Song, Mengjie Zhao, Zijing Wang, Yongkang Liu, Qian Li, Shi Feng, Feiliang Ren, Daling Wang, Hinrich Schütze
Published: 2026-08-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2608.29667v1

The rapid development of LLMs incurs prohibitive memory footprints and intensive computational demands. Quantization-Aware Training (QAT) techniques have emerged as a promising solution to address these challenges by explicitly simulating quantization effects during model training, yielding low-bit models that achieve accuracy comparable to their full-precision counterparts. In this work, we provide a target-centric survey of QAT, aimed at clarifying both its theoretical foundations and its evolving implementation landscape. We systematically review existing QAT methods through a target-centric taxonomy and synthesize cross-target differences in error characteristics, numerical formats, and strategy transferability. We further summarize QAT evaluation paradigms and discuss challenges in optimization and deployment, outlining potential directions for future research.

---

### PhysVR: Vision-Language Model Guided Interference-aware Temporal Feature Refinement for Remote Physiological Measurement

Authors: Zixu Li, Jianjun Qian, Hang Shao, Daoheng Li, Lei Luo, Jian Yang
Published: 2026-08-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.29663v1

Remote photoplethysmography (rPPG) enables contactless physiological measurement from facial videos, yet its subtle pulse-related variations are easily affected by illumination variation, head motion, facial blur, and region-of-interest instability. Existing methods mainly suppress interference during feature learning, while whether the learned temporal features remain affected by interference and how to further suppress such interference before rPPG estimation are rarely examined. To address this limitation, we propose PhysVR, a vision-language model guided interference-aware temporal feature refinement framework for rPPG estimation. Specifically, a physiological backbone produces global temporal features and a coarse rPPG prediction, from which signal-derived physiological reliability evidence is constructed from local temporal characteristics. In parallel, a frozen vision-language model processes sampled facial frames under an interference-oriented prompt, and an evidence head extracts visual interference evidence from the VLM output. Temporal cross-attention integrates the physiological and visual evidence with the global temporal features to construct interference-aware temporal context. Guided by this context, a shared temporal correction unit performs general refinement, while four interference-specific experts selectively suppress different interference through adaptive routing. The refined temporal features are then used for final rPPG estimation. Extensive experiments on five public benchmarks demonstrate that PhysVR consistently outperforms representative methods under both intra-dataset and cross-dataset evaluation protocols.

---

### ACTD: Anchor-Based Cross-Tokenizer Distillation with Residual Regularization

Authors: Huiyi Zhang, Zijian Li, Xiaocheng Feng, Weitao Ma, Xiaoliang Yang, Yichong Huang, Bing Qin
Published: 2026-08-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2608.29662v1

Knowledge distillation effectively transfers reasoning capabilities from large language models to lightweight student models. To enable knowledge transfer across disparate model families, researchers increasingly explore cross-tokenizer distillation. However, cross-tokenizer distillation remains challenging due to vocabulary and sequence misalignment, while approximate vocabulary alignment can introduce additional noise into distillation. To address these challenges, we propose Anchor-Based Cross-Tokenizer Distillation with Residual Regularization (ACTD). ACTD bridges structural heterogeneity through vocabulary and sequence alignment, while mitigating alignment noise via a novel anchor loss with residual regularization. We further extend this framework to a multi-teacher setting. Evaluated across five reasoning benchmarks with three distinct teacher models, ACTD achieves state-of-the-art performance. Moreover, its multi-teacher extension outperforms the strongest single-teacher and multi-teacher baselines, further demonstrating the robustness of our method.

---

### ButterMamba: Butterworth-Enhanced Spatial-Temporal Mamba for Efficient Traffic Flow Prediction

Authors: Limiao Zhang, Yuhui Lu, Jie Gao, Hao Jiang, Haiping Ma, Xingyi Zhang
Published: 2026-08-30
Categories: physics.soc-ph, cs.LG, physics.data-an
arXiv: https://arxiv.org/abs/2608.29658v1

Accurate traffic flow prediction is fundamental to intelligent transportation systems, playing a pivotal role in urban mobility optimization and smart city development. While Graph Neural Networks (GNNs) integrated with time series forecasting have emerged as promising solutions, two critical limitations persist: (1) the quadratic complexity of attention-based architectures hinders real-time deployment in large-scale networks, and (2) high-frequency noise in sensor data significantly degrades prediction reliability. These challenges are particularly acute in metropolitan scenarios where both computational efficiency and noise robustness are paramount. To address these limitations, we introduce \textbf{ButterMamba}, a novel and efficient framework based on State Space Models (SSMs). ButterMamba consists of two key components: (1) a Butterworth Spectral Filtering module that preprocesses the data by removing high-frequency noise, allowing the model to focus on significant underlying trends, and (2) a Spatial-Temporal State Mixer that uses a parallel Mamba architecture to efficiently capture both long-range temporal dependencies and complex spatial correlations across the road network. By decoupling noise filtering from spatial-temporal modeling, ButterMamba achieves superior predictive accuracy with linear computational complexity. Extensive experiments on three public datasets demonstrate that ButterMamba not only outperforms existing state-of-the-art models in terms of prediction accuracy but also considerably reduces training time and memory usage.

---

### Reward-guided Fine-Tuning of One-Step Generative Models via Wasserstein Gradient Flow

Authors: Hoseong Hwang, Woorim Han, Joungin Chun, Jinseong Park, Jaewoong Choi
Published: 2026-08-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2608.29647v1

To mitigate the time complexity of generative models, one-step generative models have recently emerged through direct mapping from noise to data in a single forward pass. However, the reward-guided fine-tuning method of one-step generative models remains largely unexplored. To address this, we consider one-step generators from an optimal transport view, investigating Wasserstein Gradient Flow (WGF) for modeling smooth and controlled distributional evolution in probability space. We then propose a novel reward-guided fine-tuning of a one-step generative model via WGF. We derive a practical training method that requires no reward gradients, thereby handling both non-differentiable and differentiable rewards. Moreover, our method provides smooth and stable reward-guided distributional updates while mitigating reward hacking and mode collapse. Experiments on 2D synthetic data, CIFAR-10, and ImageNet 256$\times$256 with diverse rewards, including JPEG (in)compressibility, class probability, Black-and-White and CLIP alignment, show that our method achieves better reward alignment compared to baselines.

---

### Detect Before You Attribute: Cascade Failure Attribution for Multi-Agent Systems

Authors: Jiayi Zhang, Zexin Wang, Degang Sun, Changhua Pei, Fei Sun, Gaogang Xie, Jingjing Li
Published: 2026-08-30
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2608.29646v1

Large language model (LLM)-based agents have shown strong potential in solving complex tasks through multi-step reasoning, yet they remain vulnerable to execution failures. Accurate failure attribution is therefore critical for improving agent reliability. Existing topology- and spectrum-based methods exploit trajectory structures but often overlook fine-grained semantics, while LLM-based attribution methods capture semantic cues but suffer from long-context degradation over lengthy trajectories. To address these challenges, we propose DUOTRACE, a plug-and-play detection filter for LLM-based failure attribution. DUOTRACE follows a detect-before-attribute paradigm: it first detects anomalous executions and then supplies focused trajectory evidence to downstream LLM-based attribution methods. For effective VAE-based anomaly detection on agent trajectories, DUOTRACE integrates dual-view semantic-structural node representations, a Tree-LSTM-based trajectory encoder, and prefix-chain- and LLM-based data augmentation to handle heterogeneous nodes, hierarchical execution structures, and limited failure data. Experiments with six LLM-based attribution baselines show that DUOTRACE improves agent-level and step-level attribution accuracy by 8.7% and 7.0%, respectively.

---