# Research Papers — 2026-10 · bundle page 83 of 156

> Full-text markdown of papers #4101–4150 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/83
[← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/82.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-10/page/84.md)

### From Video Clips to Creation Trajectory: Sora100K for AI-Native Video Creation

Authors: Sicong Yang, Ruihuan Yang, Jian Lu, Jianfei Yuan, Xiaodong Cun, Xiuli Bi
Published: 2026-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.11770v1

AI-Native video creation is shifting from isolated video clips toward iterative video creation workflows. However, existing datasets remain largely video clips, representing video generation and editing as separate tasks rather than connected stages of a video creation workflow. In this paper, we introduce Sora100K, a dataset that represents the AI-Native video creation workflow as a structured video creation trajectory. Specifically, we first identify video creation trajectories and decompose them into three subsets according to their structural roles: text-to-video generation records as roots, single-turn video editing records as editing edges, and multi-turn video editing records as complete trajectories. Then, we use a VLM to assign semantic annotations for generation roots and editing-operation annotations for editing edges. A strict construction pipeline further reconstructs source-to-edit lineage, editing order, and intermediate video states while ensuring data quality. Finally, we perform lightweight adaptation on LTX-2 models to assess the supervision value of Sora100K. The results show improvements in visual quality, multi-shot generation, and cross-shot consistency, while successive-turn evaluation reveals that following multi-turn editing instructions remains challenging. Sora100K establishes a new data foundation for AI-Native video creation beyond isolated video clips and toward structured video creation trajectory. The dataset and supplementary materials are publicly available at https://huggingface.co/datasets/ysicong/Sora100K.

---

### Narrow and Deep: An Ontology Tower as the Knowledge of an LLM Agent for an Industrial Equipment System

Authors: Younghwan Joo, Sung-il Kim
Published: 2026-10-08
Categories: eess.SY, cs.AI
arXiv: https://arxiv.org/abs/2610.11768v1

Large language model (LLM) agents are beginning to operate industrial energy equipment, and what they get right depends on what they are told about the plant. Established building ontologies name many kinds of points across many sites, whereas an industrial equipment system needs few entities with much knowledge about each. This study proposes the ontology tower, a narrow-and-deep ontology of a single equipment system whose knowledge deepens in two ways: through quantities derived from the measured points by physical relations, and through lessons from the operating journal incorporated as knowledge nodes. On a real low-humidity air-handling test plant operated daily through a programmable logic controller, agents received a text projected from its tower in a preregistered evaluation of nine tasks replayed from the plant's records, using four open-weight models from 9 to about 750 billion parameters. This knowledge raised the rate at which the agents avoided the most plausible misjudgment of each task by about 20 percentage points, and the overall task score of the 9-billion-parameter model as much as that of the largest. Operating lessons were used when incorporated into the tower or placed in the prompt as records, but seldom when left in the journal behind a search tool. In live runs through an invariant safety layer, the agents brought the controlled variable into its target band in 12 of 14 runs. An ontology narrow in entities but deep in what is known about them can thus supply the knowledge that an agent for an industrial equipment system needs.

---

### Same Outcome, Different Evidence: Intent Recovery in LLM Safety Evaluation

Authors: Haitong Jiang, Chunlin Liu, Sihan Tang, Chan Wu, Xiaoqing Su, Yuhong Feng
Published: 2026-10-08
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2610.11766v1

Safety evaluations of large language models commonly summarize harmful-output behavior with attack success rate (ASR). Yet the same non-harmful outcome can arise for very different reasons. A model may recover a harmful task and refuse it, fail to recover the task, or respond to something else entirely. Distinguishing these cases becomes especially important under intent-obscuring prompts, where a low ASR does not reveal whether the evaluated task was actually engaged. To make this distinction explicit, we pair ASR with operative understanding rate (UR), which measures whether a response both identifies the evaluated task and treats it as the task to be answered. Across interfaces, this paired view reveals substantial variation hidden by ASR: similar ASR values can correspond to sharply different recovery rates. Controlled English reconstructions show that recovery consistently improves as compressed prompts become more explicit, whereas ASR does not follow the same pattern. A complementary contrast comes from FormalLogic, where high recovery can still coincide with frequent harmful assistance. Together, these results show that non-harmful outcomes are not equally informative about model safety, motivating the joint reporting of intent recovery and ASR in LLM safety evaluation. Code and experiment inputs are available at https://github.com/kevinjiang0121-cyber/IRIS.

---

### Thinking Inertia: LLMs Keep Thinking When Told Not To

Authors: Dianqiao Lei, Kevin Qinghong Lin, Pan Lu, Philip Torr, James Zou
Published: 2026-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.11765v1

Large Language Models (LLMs) increasingly ship with explicit "thinking modes", yet their counterpart, "no-thinking", has received far less attention. We study LLMs' no-thinking behavior along two axes. a. How to measure no-thinking? Prior work typically defines no-thinking through proxies such as a disabled thinking mode or the absence of long traces. These proxies are unreliable: disabled thinking modes may still emit reasoning, while long traces may contain filler rather than genuine inference. We instead normalize each response into a pre-answer trace and final answer, and evaluate it at three levels: (i) Empty-Thinking Rate for strict answer-only compliance; (ii) instruction-aware Question-Pre-answer Relevance for similarity between the question and pre-answer trace; and (iii) LLM-as-judge Explicit Inference Rate for visible explicit inference. Together, these metrics distinguish answer-only output, relevant but non-inferential text, and explicit inference. b. How does no-thinking vary across tasks and models? We evaluate six prompting interventions on six LLMs across Boolean, multiple-choice, and open-ended questions. We find that explicit no-think controls cannot reliably eliminate visible inference. Models instead exhibit "Thinking Inertia": explicit inference persists even under strict controls and becomes more prevalent as the answer space opens. Accuracy remains stable on Boolean and multiple-choice tasks, whereas open-ended tasks reveal a trade-off between answer-only compliance and task accuracy. Rewriting the same questions across answer spaces shows that supplying candidate answers makes answer-only responses easier to produce. These findings establish no-thinking as a non-trivial capability: stopping explicit reasoning cannot be assumed from model settings or instructions alone and deserves systematic evaluation alongside reasoning ability.

---

### RAGenome: Scaling Retrieval-Based Genomic Language Models to Long Contexts

Authors: Frederikke Isa Marin, Panagiotis Antoniadis, Dionysia Danai Brilli, Andreas Bjerregaard, Rachael DeVries, Yan Li, Ole Winther, Wouter Boomsma
Published: 2026-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.11761v1

The genome holds the blueprint that governs the biological properties of the cell. Consequently, advancing our knowledge of genomic function is crucial both for a broader understanding of biology and for continued biomedical advances. The success of large language models on natural language and protein sequences has motivated similar efforts on genomic data. However, standard genomic language models (gLMs) often require extremely large computational resources and still fall behind traditional methods on some downstream tasks. Recently, MSA-based pretraining has been proposed as an efficient alternative, but existing models are limited to short input contexts, restricting their use to short-range tasks, such as variant effect prediction. In this work, we present RAGenome, the first retrieval-based gLM that scales pretraining to longer contexts (100$\times$ longer than existing MSA-based gLMs), allowing it to capture both across-species evolutionary relationships and within-species longer-range interactions. Trained on whole-genome alignments from 100 vertebrates, RAGenome substantially improves the long-range capabilities of MSA-based gLMs, raising gene finding performance from 0.45 to 0.60, while remaining competitive on purely evolutionary-based tasks like prioritizing pathogenic variants. RAGenome provides competitive gLM performance at a fraction of the training cost, unifying evolutionary modeling and long-range capabilities within a single, flexible, scalable framework. Code is available at https://github.com/PanosAntoniadis/RAGenome.

---

### Beyond QAOA: A Review of AI and Quantum Computing for Adaptive Combinatorial Optimization

Authors: Hoong Chuin Lau
Published: 2026-10-08
Categories: quant-ph, cs.LG, math.OC
arXiv: https://arxiv.org/abs/2610.11759v2

Near-term quantum approaches to combinatorial optimization are limited by qubit counts, circuit fidelity, sampling cost, and the difficulty of encoding constraints, while machine learning is increasingly used to configure and control quantum optimization workflows. We call such workflows adaptive: decisions conventionally fixed in advance, from formulation and penalties to shot budgets, backends, and whether to invoke a quantum processor at all, are made by learned policies that respond to the instance, the progress of the solve, or the hardware. This review examines three paradigms, AI for quantum optimization, quantum for AI-driven optimization, and AI-quantum co-optimization, and organizes the literature by the decision being learned rather than by application. A structured search identified a 119-paper corpus, of which 67 papers form an evidence core coded in detail. The evidence is considerably stronger for AI-assisted quantum optimization than for the reverse direction: learning already reduces quantum evaluations, improves initialization, supports decomposition and penalty control, and mitigates noise, whereas evidence that quantum computation improves learned optimizers remains largely confined to small-scale simulation. Experimental controls are thin: of 52 studies in the three paradigms, 22 include no classical baseline, the quantum contribution is fully isolated in 10 of 24 where an ablation applies, and the median largest experiment uses 16 qubits. We introduce an M0-M5 evidence hierarchy, from simulation to practical quantum advantage, and find no broadly convincing result at the highest level. We argue that scaling is increasingly a systems problem: the question is not only whether a problem fits on a quantum processor, but how classical and quantum resources should be allocated across the optimization process.

---

### Memory Forcing: Attendable Mid-Horizon History for Streaming Video Generation

Authors: Jiaming Zhang, Xinyu Wang, Huafeng Shi, Gangshan Wu, Limin Wang
Published: 2026-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.11756v2

Autoregressive video diffusion enables causal video streaming without a bidirectional pass over the full clip, but existing few-step systems usually retain only the opening and most recent frames in a fixed-size KV cache. Once an event leaves this window, later frames can no longer attend to it, a failure we term mid-horizon forgetting. We present Memory Forcing, a few-step streaming method that preserves this missing history without increasing the cache size. Its Archive \& Working Banks partition the cache into sink, archive, and working regions, retaining diverse intermediate events alongside recent motion under fixed memory. Because absolute temporal indices drift outside the training range, Bank-aware RoPE reassigns indices at attention time so each bank remains distinguishable. At 1.3B, Memory Forcing leads on longer clips, shows the smallest drop from 5s to 60s among methods reporting all four lengths, and preserves subjects and scenes through leave-and-return. The same design scales to Wan2.2 5B, producing more physically plausible, realistic, and dynamic videos and, to our knowledge, the first public 5B model on this forcing line.

---

### SR-TTA: Spatial-Redundancy Test-Time Adaptation for Interference-Robust Respiration Sensing

Authors: Jingyuan Liu, Zheng Chang, Haoqiu Xiong, Zhuangzhuang Cui, Sofie Pollin
Published: 2026-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.11755v1

Future 6G networks aim to expose sensing as a native service by reusing communication infrastructure. We study respiration sensing on a cell-free massive multiple-input multiple-output (MIMO) base station, where a 64-antenna channel must be fused into a breathing waveform. The state-of-the-art hand-crafted fusion is near-optimal in benign conditions. It collapses, however, under strong in-band motion interference, whose frequency falls inside the respiration band. We show that a learned complex-weight beamformer recovers respiration by spatial nulling, and that the remaining gap to a per-recording oracle can be closed at deployment by label-free test-time adaptation. Crucially, we identify which label-free signal makes this work. Frequency- and variance-based criteria cannot separate an in-band interferer from breathing. Our spatial-redundancy test-time adaptation (SR-TTA), which maximizes consistency across random antenna subsets under an out-of-band spectral veto, preserves benign performance in our tests. The respiration-rate error drops from 5.8 to 0.8 breaths per minute (bpm) under simulated in-band interference, and the pipeline maps onto the Open Radio Access Network (O-RAN) architecture as O-RAN distributed-unit (O-DU) range-gating, an adaptation xApp, and a calibration rApp. On real testbed recordings, a one-time cross-subject calibration plus SR-TTA reduces failures from 47% to 7%, drawing level with the hand-crafted combiner using label-free test-time adaptation.

---

### What Output-Only Review Cannot Verify: Study Contracts for Research Agents

Authors: Eitan Waks, Ben Glocker
Published: 2026-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.11754v1

Some defects in an AI-generated study can be identified from its artifacts; others require knowledge of what was approved before execution. We propose study contracts that bind declared experimental choices, run obligations and claim scope to recorded execution evidence, and distinguish this contract-relative verification from scientific truth. A diagnostic using eight self-authored clean/mutated pairs illustrates the information boundary. A deterministic checker applying a registered, fault-specific rule to approved and executed objects detected all eight registered mutations. Across eighteen recorded judge aliases given individual metadata-filtered packages without pair context or the registry-selected fault label, 104 of 144 mutated evaluation cases received defect flags; the remaining cases comprised 32 abstentions and eight terminal failures, with no explicit clean decisions on mutated cases. Some packages retained approval and execution fields, including digests. The prompt instructed judges to abstain when evidence was insufficient. These results characterize a deliberately information-asymmetric development setting; they do not isolate the effect of authoritative information from differences in task specification and rule selection, and they are not comparative verifier quality or agent reward hacking. We identify full-information comparisons, legitimate-adaptation controls and closed-loop agent evaluations as necessary tests of whether contract checks improve useful compliant completion under optimization.

---

### Dino Forcing Flow Models: Do not denoise what you can predict

Authors: Arijit Ghosh, Lucas Degeorge, Paul Couairon, Alexei A Efros, Vicky Kalogeiton, David Picard
Published: 2026-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.11751v1

Co-denoising pretrained representations such as DINO can substantially improve the training speed and quality of flow matching models, but it introduces a second denoising trajectory and requires carefully designed schedules. We propose a simpler alternative: predict the pretrained representation directly, then condition the model on its own prediction. This removes the need for a second ODE and any representation-specific denoising schedules, while retaining the benefits of representation guidance. Our approach converges substantially faster and achieves better generation quality as measured by FID score. On ImageNet, it outperforms the state of the art in latent space at 2x fewer epochs than prior methods; in pixel space, it improves FID over comparable prior methods by more than 20%. These results support a simple principle: do not denoise what you can predict. Our code is openly available at https://github.com/arijit-hub/dino_forcing.

---

### Where Draft Trees Lose Target Mass: Exit-Guided Speculative Decoding

Authors: Shijing Hu, Xuancheng Ren, Zhihui Lu, Pan Zhou
Published: 2026-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.11750v1

Tree-based speculative decoding verifies multiple draft continuations in one target-model pass, but finite trees built from draft scores face a fundamental draft-target mismatch. We ask whether better exact verification can increase acceptance on a fixed tree and how target feedback can improve the tree itself. Through a target-flow view, we identify a canonical exit law and prove that one plus target coverage sharply bounds the expected output-block length, including the bonus token, of any exact path verifier. All optimal verifiers share the same exit and bonus-token law, already attained by representative predraw-and-follow and sequential residual verifiers. This yields Tree Exit Verification (TEV), an exact, level-parallel procedure using one exit-node decision and one bonus-token decision. The exit law also identifies missing target probability, providing node-level feedback for Exit-Guided Draft-Tree Training (ExitTrain) on inference-time draft trees. Experiments across dialogue, code, and mathematical reasoning validate fixed-tree equivalence: ExitTrain increases average output-block length by 13%, while TEV reduces verifier-stage latency by 15%, yielding a 14% end-to-end speedup over DDTree. Our results distinguish two opportunities: better draft trees for higher acceptance and more direct verification for lower latency. Code: https://github.com/hsj576/TEV.

---

### DEX: Digit-Level Early Exit for Energy-Efficient MSDF Neural Network Inference

Authors: Yousef Sadegheih, Dorit Merhof, Muhammad Usman
Published: 2026-10-08
Categories: cs.AR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2610.11748v1

U-Net inference for brain-tumor segmentation requires billions of multiply-accumulate operations, motivating hardware that can reduce computation dynamically rather than relying only on fixed precision or static model compression. Most-significant-digit-first (MSDF) arithmetic exposes the leading digits of a result during computation, enabling output-dependent decisions before the full value is generated. This paper presents an MSDF accelerator for quantized U-Net segmentation with a two-stage grouped processing element supporting signed INT8 operands and in-stream bias accumulation. Four runtime mechanisms operate directly on the output digit stream: exact early negative detection (END) in ReLU layers, exact sign-only decision making in the segmentation head, calibrated low-order-digit skipping, and calibrated pruning. The two approximate mechanisms are selected offline under an accuracy constraint, while execution requires only lightweight control and does not modify the stored weights. On a residual U-Net trained with nnU-Net for BraTS, the proposed mechanisms reduce digit cycles by 38.38\% while achieving a mean Dice score of 80.58\% on 73 held-out cases, compared with 81.20\% for the floating-point model; the exact mechanisms alone reduce cycles by 18.79\% without altering the quantized output. Synthesized in 45~nm, the processing element operates at 500~MHz, occupies 0.858~mm$^2$, and consumes 0.726~mJ per $192\times192$ patch under switching-activity-annotated power analysis. A projected eight-output accelerator with shared activation delivery achieves 16.6~ms latency and 1.67~mJ per patch.

---

### Streaming-Aware Diffusion for Real-Time Video Super-Resolution via Cross-Step Attention

Authors: Harris Partaourides, Sotirios Chatzis
Published: 2026-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.11746v1

Real-time video super-resolution requires high spatio-temporal fidelity under strict latency constraints, challenging diffusion models due to their iterative sampling cost and limited temporal coordination. We propose a streaming-aware framework that adapts pretrained single-image latent diffusion models for efficient video super-resolution (VSR) by exploiting the sequential structure of video streams. Our Cross-Step Attention mechanism reuses intermediate denoising features across adjacent frames and diffusion steps, enabling temporal information exchange without explicit temporal modeling. We further introduce Trajectory-Coupled Diffusion Scheduling, which aligns adjacent diffusion states and provides cleaner intermediate representations for cross-step conditioning, improving temporal coherence. These components are integrated into a streaming inference pipeline that incrementally propagates latent states across frames, reducing the effective computational complexity from $O(N \cdot S)$ to $O(N + S)$ for $N$ frames and $S$ diffusion steps. Experiments on REDS4 and YouHQ40-Test demonstrate improved perceptual quality and temporal realism while maintaining frame-wise stability. Our method achieves over 40 FPS at $512 \times 512$ resolution after cold start, enabling real-time VSR without explicit temporal modeling.

---

### The Ball and the Box: Two Geometries of Computation in Superposition

Authors: Xiaoyu Li, Lequan Lin, Dai Shi, Jiaojiao Jiang, Junbin Gao, Andi Han
Published: 2026-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.11744v1

Neural representations can encode more features than they have dimensions, a phenomenon known as superposition. We study the dimension needed to compute Boolean gates from such representations. For a single threshold layer with a Gaussian random dictionary and uniformly random sparse Boolean inputs, we derive sharp dimension thresholds under two error criteria. A vanishing expected error count can require more dimensions than correctness of every output with high probability. Shared reads explain the gap: rare realizations can produce many errors at once. The expected-count threshold has ball geometry, while joint reliability has box geometry when a gate is evaluated on every feature tuple. Optimizing shared readout weights and biases gives explicit thresholds for conjunction, disjunction, and majority. For pairwise conjunction, the analysis also describes the transition near the threshold, in agreement with exact simulations.

---

### TraceRelay: Attention-Aligned Recurrence over Rolling Traces

Authors: Sungwoo Goo, Hwi-yeol Yun, Sangkeun Jung
Published: 2026-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.11743v1

We present TraceRelay, an attention-aligned recurrent architecture that distributes persistent representations over a rolling sequence of low-dimensional traces. Local right looking attention forms increments from lower-layer representations; delivery is delayed until all attended inputs are in the causal past. A fixed additive phase recurrence accumulates the delayed increments, and left-looking attention reads the resulting residual augmented stream. A stride-wise prefix sum supports parallel prefill and bounded-buffer continuation. We study 36 small-model runs on Equal Repeats, bounded Dyck closing-type prediction, and causal Most-Freq generation, using three seeds per setting. At trained length 256, Equal Repeats models with recurrent phase inheritance reach 98.81-99.69% accuracy versus 50.73-51.63% for separately trained variants without inheritance, despite the latter receiving more updates. Accuracy drops sharply at lengths beyond the training range. At the longest evaluated lengths, models with more dimensions in the middle layer's recurrent traces perform better on Dyck (76.34% versus 55.49% close accuracy at length 4096), whereas models with fewer trace dimensions perform better on five-symbol Most-Freq (70.74% versus 55.60% exact generation at length 1024). These contrasting cases motivate further study of how the size of recurrent representations should be chosen for different tasks, without establishing a general rule across tasks or model configurations.

---

### Correlational Training of Morphological Neural Networks

Authors: Konstantinos Fotopoulos, Petros Maragos
Published: 2026-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.11740v1

Neural networks are typically trained using first-order methods and back-propagation. It is unclear whether this approach is optimal for morphological layers whose weight Jacobians are sparse and whose resulting parameter gradients can be poor. In this work, we propose a novel weight update method for morphological neural networks inspired from the Multiplicative Weights Update (MWU) scheme. We view each morphological perceptron as an instance of the learning from experts' advice problem in logarithmic space, and use a correlation-based reward that favors inputs aligned with the desired output change, regardless of whether a strong gradient signal has reached their weight. We empirically evaluate our approach by training fully connected layers both as stand-alone models and as parts of larger transformer networks. Across nine benchmarks, correlational training yields improvements on eight, by up to 32.84 percentage points, while substantially reducing run-to-run variability.

---

### Scalable AI Uncertainty Quantification via Generalized Laplace Active Subspaces

Authors: Wouter N. Edeling, Peter V. Coveney
Published: 2026-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.11738v1

Reliable uncertainty quantification (UQ) is essential for deploying neural networks in scientific and high-stakes applications, but full Bayesian inference over the network parameters is computationally infeasible. We propose a low-rank generalized Laplace approximation for neural-network UQ based on a small number of data-informed curvature directions. Starting from a generalized Bayesian posterior defined through an empirical loss, we construct a local Gaussian approximation around a pretrained set of weights in this active curvature subspace. The posterior variances in the retained subspace are available in closed form, and the prior variance is calibrated by an empirical Bayes procedure. The generalized Bayesian formulation allows us to compare two posterior scalings: the standard Bayesian scaling associated with the summed negative log likelihood, and a mean-loss scaling in which the empirical loss is normalized by the number of data. A central finding is that the standard scaling induces a data-size dependent contraction of the posterior variance in the leading active directions. In regression problems, this can force the low-rank framework to retain additional weak-curvature directions in order to achieve nominal coverage of calibration data. When posterior samples are propagated through the non-linear network, these additional directions can degrade the coherence of the predictive intervals and shift the posterior predictive mean away from the pretrained model. In contrast, the generalized mean-loss scaling yields a more stable, lower dimensional active subspace and produces calibrated, coherent predictive confidence intervals. These results indicate that generalized Laplace active subspaces provide a practical and scalable route to calibrated uncertainty quantification in neural networks.

---

### Uncovering and Fixing Collider Bias in Bayesian PINNs

Authors: Michael Obermayr, Robert Peharz
Published: 2026-10-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.11737v1

Bayesian physics-informed neural networks (B-PINNs) are a popular framework for parameter and state inference from sparse or noisy observations. They are commonly formulated via a collider structure, in which physical and trajectory parameters are assumed to be a priori independent and become coupled through virtual likelihoods on differential-equation residuals that enforce physical consistency. We show that this modeling choice can induce severe systematic bias in the posterior over physical parameters: even when the prior is favorably centered on the ground-truth parameters, the resulting posterior can drift away and concentrate far from them. As a remedy, we advocate a hierarchical chain model in which physics generates trajectories, which in turn generate observations. The chain model does not suffer from this posterior bias, but it poses a harder, so-called doubly intractable, inference problem due to a physics-dependent normalization constant. This challenge can be resolved by discretizing the underlying stochastic dynamics, after which the chain posterior can be sampled exactly with particle MCMC. We identify two distinct mechanisms characterizing the collider bias, derive analytical approximations of their magnitudes, and establish diagnostic criteria for predicting when standard B-PINNs remain reliable. Experiments confirm the predicted bias and show that the chain formulation successfully avoids it.

---

### Towards Unified Evaluation of Prompt Enhancers for Video Generation

Authors: Yawen Shao, Yubo Zhu, Ziyun Dai, Zixun Fang, Kai Zhu, Zeyinzi Jiang, Yufeng Ai, Siyang Sun, Haolan Xue, Yu Shang, Yuxiang Bao, Zoubin Bi et al.
Published: 2026-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.11736v1

Modern video generators can realize increasingly complex visual narratives, positioning the prompt enhancer (PE) as a critical bridge from concise user instructions and multimodal references to structured cinematic plans. However, existing PE evaluation relies on rendered videos, imposing substantial computational and human costs, slowing PE training and iteration, and conflating PE quality with downstream generator behavior. To address this gap, we introduce PEBench, the first unified benchmark for direct PE evaluation across text-to-video, image-to-video, and reference-to-video prompt enhancement. It comprises 1,100 expert-verified cases and 1,005 visual assets, spanning 35 fine-grained tasks with diverse temporal, cinematic, audiovisual, and multi-reference requirements. In addition, we develop PEBench evaluation, an evidence-grounded framework that combines modality-aware fact extraction with rubric-based assessment across 24 criteria. Our systematic evaluation of representative open- and closed-source PE methods reveals an emerging shift from fine-grained descriptive expansion toward intent-preserving cinematic planning, while the caption-reconstruction and forward-refinement methods show complementary strengths in cinematic coverage and semantic fidelity or internal coherence, respectively. Human validation shows that PEBench scores align closely with expert judgments of enhanced prompts and downstream videos from Wan3.0 and MiniMax-H3, indicating that prompt-level evaluation reliably reflects downstream utility.

---

### Onboard Marine Anomaly Detection on $Φ$sat-2: From Simulation-Based Development to In-Orbit Demonstration

Authors: Clotilde Szywala, Thomas Goudemant, Marjorie Bellizzi, Benjamin Francesconi, Adrien Girard
Published: 2026-10-08
Categories: cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2610.11735v1

Onboard Artificial Intelligence can improve responsiveness and bandwidth efficiency of Earth Observation systems by processing data directly on the satellite. This paper presents the experience gained from the development, onboard integration, and post-launch adaptation of a lightweight marine anomaly detection pipeline deployed on the European Space Agency's $Φ$sat-2 mission. The application combines sea segmentation, self-supervised feature encoding of marine regions, generic anomaly detection based on deviations from a normal sea state, and optional characterization of selected anomaly types. Before launch, the pipeline was trained and validated on simulated $Φ$sat-2 imagery to assess algorithmic performance and compatibility with resource-constrained onboard hardware. After integration and functional validation in the mission environment, early experiments on real $Φ$sat-2 acquisitions revealed a significant mismatch between simulated and in-orbit data. The pipeline was therefore retrained on real Level-1 imagery using an improved annotation strategy to better handle ambiguous marine regions, substantially enhancing performance. Beyond demonstrating the onboard feasibility of the application, the $Φ$sat-2 experience highlights the importance of robust annotation strategies and sensor-aware design, and shows that simulation-based development is valuable for pre-flight risk reduction, while reliable scientific validation requires representative in-orbit data and should be clearly distinguished from functional validation.

---

### Timer-M1: A Multivariate Time Series Foundation Model via Learning Primitives

Authors: Haoran Zhang, Haixuan Liu, Xingjian Su, Yong Liu, Zhi Chen, Yuxuan Wang, Jianmin Wang, Mingsheng Long
Published: 2026-10-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.11734v1

We introduce Timer-M1, a pretrained multivariate time series foundation model that learns with primitives for zero-shot forecasting. Across domains, time series share elementary temporal and relational patterns, termed primitives, yet differ in how these primitives manifest and evolve across different contexts. Despite progress in zero-shot and task-general forecasting, existing foundation models may still struggle to generalize to complex real-world scenarios. To this end, we develop a primitive-based data synthesis and pretraining pipeline. The synthesis pipeline generates series with temporal primitives shared across domains and then assembles real and generated series into multivariate samples using relational primitives. Afterwards, samples are organized into episodes by assigning distinct channel roles as target variates, past-only covariates, and known-future covariates, ensuring that the model is optimized on predictable variates using available exogenous information. Technically, Timer-M1 further adapts gated two-dimensional Transformer blocks that dynamically allocate cross-variate attention across layers. Across three large-scale forecasting benchmarks, Timer-M1 ranks first on both FEV and TIME and second on GIFT-Eval among most recent time series foundation models. These results support effective primitive-based pretraining as a route to robust general forecasting technique across domains and task settings.

---

### MemTrial: Learning When to Trust Memory in LLM Portfolio Agents

Authors: Guanghao Wu, Zhuo Cai, Shoujin Wang
Published: 2026-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.11732v2

Large language model (LLM) agents for portfolio management learn from experience: they credit each experience in their memory with the outcome of the decisions that used it. In financial markets, however, this outcome mostly reflects the market move shared by all decisions on that date, so the credit tracks the market rather than the experience, and these agents often do worse than simply holding the equal-weight (1/$N$) portfolio. We ask how an agent can credit an experience with what it changes, and answer it by putting memory on trial: drafts of the same decision with and without an experience face the same market, so the outcome they share cancels in their difference. Our agent, MemTrial, drafts each decision with eight combinations of its retrieved experiences, chosen by a fractional factorial design, and credits each experience with its Banzhaf value, the average of these differences. As each date occurs once and each draft is a noisy LLM sample, these credits are noisy and may not hold on new dates. MemTrial therefore pools them across dates and similar experiences with a hierarchical Bayesian model, acts on them only after they have predicted unseen dates, and otherwise stays anchored at a conservative reference such as 1/$N$. On four benchmarks, MemTrial not only benefits from experiences that matter (the best of 15 methods on a semi-synthetic benchmark with known experience quality) but also limits its losses when its values do not hold (at most 2.2\% below 1/$N$ on PortBench and InvestorBench, against 15--38\% for the best experience-learning agent). Averaged over five settings, it improves the utility of the best experience-learning agent by 21.2\%, and with eight LLMs it beats every LLM-based baseline on InvestorBench.

---

### Spectral Weight Decay: Inducing Low-Rank Structure in Neural Network Weights

Authors: Dmitrii Andriianov, Andrey Veprikov, Aleksandr Beznosikov
Published: 2026-10-08
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2610.11730v1

Standard weight decay treats each weight matrix as a vector and ignores its spectral structure. We introduce spectral weight decay, a post-step decoupled nuclear-norm update that applies additive rather than multiplicative spectral shrinkage. We connect the update to approximate proximal descent and show that its sensitivity to update order can exceed that of conventional $\ell_2$ weight decay near rank deficiency. Across LLaMA models with $124$M to $500$M parameters, spectral weight decay lowers effective rank and improves SVD-LLM compression at matched validation loss. At $500$M and a $4\%$ distortion budget, it reaches $1.89\times$ compression and $1.18\times$ GPU inference speedup, compared with $1.14\times$ and $1.01\times$ after standard weight decay. Under fixed-horizon training with $60\%$ label noise, it also improves final mean clean-test accuracy over matched $\ell_2$ regularization by up to $17.8$ points on MNIST and $4.6$ points across four BERT-base tasks. Code is available at https://github.com/brain-lab-research/SpectralWD.

---

### MAP4CS: A Multi-dimensional Data Pruning Framework for Efficient Code Retriever Fine-tuning

Authors: Yuxuan Chen, Mingwei Liu, Guangsheng Ou, Zekai Zhang, Zike Li, Yanlin Wang, Pelin Zheng
Published: 2026-10-08
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2610.11727v1

Retrieval-Augmented Generation (RAG) has become a cornerstone in software engineering for enhancing Large Language Models (LLMs) with domain-specific knowledge. However, adapting retrievers to evolving code repositories remains challenging due to the noise and redundancy inherent in massive code corpora. Standard fine-tuning on the full corpus is computationally expensive and often leads to sub-optimal performance due to negative transfer from low-quality samples. Conversely, simple random sampling fails to guarantee data representativeness. To address these challenges, we propose MAP4CS (Multi-dimensional Awareness Pruning for Code Search), an adaptive data pruning framework. MAP4CS identifies a small, high-quality core subset by integrating syntactic structure, semantic diversity, and distributional representation, followed by a rigorous rule-based filtering pipeline. Extensive experiments on two large-scale datasets demonstrate that MAP4CS consistently outperforms random sampling baselines using only 5% of the training data. Remarkably, it achieves performance comparable to, or even superior to, fine-tuning on the full dataset, validating the ''less is more'' hypothesis in data-centric AI. Furthermore, linguistic analysis reveals an adaptive optimization mechanism: MAP4CS automatically functions as a de-duplicator for redundant corpora and a denoiser for chaotic ones, constructing a training corpus that is both lexically diverse and information-dense.

---

### Addressing Overcommitment in the Reasoning of Gendered Economic Memes under Multimodal Ambiguity

Authors: Kushal Kanwar, Dushyant Singh Chauhan, Kapil Rana, Gopendra Vikram Singh, Nils Lukas
Published: 2026-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.11724v1

Multimodal meme understanding is increasingly used to analyze socially sensitive content, yet existing models often exhibit biased behavior when interpreting economic dependence and social roles under ambiguity. Many memes express economic relationships through sparse text or symbolic visual cues, providing insufficient evidence for gendered attribution. In such underspecified settings, models tend to rely on pretraining correlations, leading to hallucinated and stereotypical economic role assignments. In this work, we study gendered economic dependence in image-text memes through the lens of contextual sufficiency and identify epistemic overcommitment-inferring roles without adequate evidence-as a primary source of bias. We propose CGER-Net, a context-grounded multimodal framework that estimates whether the input provides sufficient evidence for gendered economic reasoning and applies evidence-gated inference to enable confident attribution when cues are explicit while favoring principled abstention otherwise. We evaluate CGER-Net on EconMeme-GE, a curated dataset of image-text memes annotated as Men, Women, Neutral, or Ambiguous. Across strong contemporary multimodal baselines, CGER-Net reduces Gender Overcommitment Rate by up to 44% on ambiguous instances while maintaining comparable accuracy on unambiguous cases. Human evaluation further shows that 79% of generated rationales are judged as epistemically aligned with the available evidence. These results highlight the importance of modeling when not to infer for reliable and responsible multimodal analysis.

---

### MultiWorldBench: Do Independently Controlled Views Describe One Shared World?

Authors: Zhangbo Xu, Ruoxi Zhang, Rui Hu, Yisong Wang, Xitong Li
Published: 2026-10-08
Categories: cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2610.11723v2

Multiplayer world models must ensure that independently controlled views remain consistent with one shared and persistent world. We introduce MultiWorldBench, a diagnostic Minecraft benchmark containing 495 case configurations across seven task suites and ten capabilities, including independent control, cross-view motion, shared-state synchronization, persistence, structural reasoning, concurrent interaction, and delayed revisit. We evaluate Solaris, Gamma-World, and MineWorld, using Engine GT as a reference. Gamma-World achieves the highest ten-capability average among the generated systems at 21.39, followed by Solaris at 20.88 and MineWorld at 1.89, while Engine GT reaches 91.69. Gamma-World performs better on several control, shared-state, and revisit capabilities, whereas Solaris leads in cross-view motion and race-condition consistency. Nevertheless, all generated systems score at most 8.00 on state persistence and 1.33 on structural consistency, and none succeeds in spatial reasoning or building-identity preservation. Human preferences produce the same overall ranking and show strong alignment with the automatic evaluation, with a mean dimension-level Spearman correlation of 0.96. These results show that plausible individual views do not yet constitute a coherent multiplayer world.

---

### 4-Tensor Attention Model for Semantic Physical Reality

Authors: Jongwook Kim, Sangheon Yun
Published: 2026-10-08
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2610.11716v1

We describe a 4-tensor attention model that predicts the next semantic state of a scene, for video generation and robot planning. A window of states has positions (x, t) and two fibers, a semantic fiber and a temporal-context fiber, and one softmax normalizes attention jointly over the window. Frames and an agent's situation are written as those states; the encoder, the renderer, and the planner remain outside the update. To test the update on its own, we train on ROCStories, where each window poses the same next-sentence task at the semantic layer. On the validation split, with one seed per setting, the last-sentence cross-entropy on the three matched settings is lower for the 4-tensor model than for a free-running one-dimensional transformer by 5.3% at H=2, L=2, by 2.6% at H=4, L=2, and by 2.4% at H=4, L=3. At H=4, L=2 the parameter counts are nearly the same, 172.5M and 175.9M. On the same two GPUs that 4-tensor run finished in 2.4 hours and the baseline run in 45.2 hours; the baseline is trained by free-running decoding, one sequential forward pass per target token.

---

### Internalizer: Portable Context-to-Parameter Mapping for Very Large Language Models

Authors: Peter Devine, Nick Ryan, Benjamin Sirb, Alex Chiocchi
Published: 2026-10-08
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2610.11715v1

Hypernetworks that map a context directly to a LoRA adapter let a large language model carry that context in its weights, but prior work has demonstrated them only on base models of up to 14 billion parameters. We present the Internalizer, a state-of-the-art, portable Context-to-Parameter Mapping hypernetwork that generates document-specific LoRA adapters for the frozen 284B-parameter DeepSeek v4 Flash, a target two orders of magnitude larger than in any previous work. Most of its parameters live in a model-agnostic trunk with only thin entry and exit layers per base model, so it trains cheaply against small models before being ported to the large one. On unseen documents of up to 4096 tokens, the generated adapters reach 84.9% top-1 and 97.8% top-5 teacher-forced accuracy against 63.4% and 83.5% for the base model, with nothing in the context window but a three-word instruction. Once the hypernetwork is trained, a single forward pass turns any document into an adapter for such a model, which could be served alone for speed or alongside the document in the window to raise accuracy further.

---

### DeltaReplay: Task-Relative Memory Reuse for Mobile GUI Agents

Authors: Yudong Bai, Yihong Chen, Quanming Yao, Yaqing Wang
Published: 2026-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.11707v1

Memory-augmented mobile GUI agents store successful execution trajectories and reuse them in later tasks, but a stored trajectory rarely matches a new task exactly. The new task may use different parameters, share only some of its steps with a stored trajectory, or have no relevant record in memory. Forcing the agent to use irrelevant memory can mislead it, whereas discarding memory that may still be useful deprives it of guidance from past experience. To address this dilemma, we propose DeltaReplay, a step-level memory reuse framework that decides how to use existing memory without modifying it. We observe that the reusable part of a stored record is determined not by the record itself but by its relation to the new task, mainly through two factors: page-level consistency and action-level generality. We therefore store execution trajectories as paths in a transition graph, whose nodes (pages) and edges (actions between pages) capture these two factors. At reuse time, the action on each edge is split into a task-independent operation and task-specific parameters. DeltaReplay then compares each recorded step with the new task and the current screen, and decides whether to follow it, execute it after replacing its parameters, or leave it to the base agent. On AndroidWorld and SPA-Bench, DeltaReplay improves the task success rate over a base agent with the same backbone by up to 10.3 and 25.0 percentage points, respectively. These results indicate that deciding at each step how to use retrieved memory lets agents benefit even from partially matching trajectories.

---

### Does an Illumination Prior Help Face-Swap Detection? A Controlled Study of Temporal Self-Blended Images

Authors: Danil Davydov, Bader Rasheed, Dmitriy Vatolin
Published: 2026-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.11706v1

Self-blended images are widely used to train face-swap detectors, but primarily capture blending artifacts. We investigate whether adding illumination inconsistencies improves detection. Temporal Self-Blended Images (T-SBI) transfer lighting statistics between frames of the same video, with the mismatch controlled by luminance difference (ΔL). Using five training regimes and a three-seed comparison of high- and low-ΔL training, we find no evidence of illumination-specific improvements. AUC differences remain within seed variability across four datasets, and an analysis of 506,328 attribute-binned samples shows no preferential reduction in errors under harsh lighting. Instead, T-SBI shifts prediction scores, changing optimal thresholds by approximately 0.34 on FaceForensics++ and 0.30 on Celeb-DF, making comparisons at a fixed threshold misleading. However, T-SBI improves robustness to heavy JPEG compression on DFDC (AUC 0.780 versus 0.696), potentially reflecting greater reliance on low-frequency cues. These findings highlight the importance of evaluating training methods against their intended targets and accounting for threshold effects.

---

### Intervention anchors and scientific verification in synthetic vascular predictive representations

Authors: Lingsen You, Yujun Guo, Xinyu Zhong, Zisu Peng, Wentong Wang, Li Shen, Junbo Ge
Published: 2026-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.11704v1

Complete orthogonal predictive coordinates do not by themselves bind a latent direction to a named intervention. We present a mathematical and synthetic audit motivated by vascular device-vessel suitcordance. Capacity-matched least-squares predictors were exactly equivalent under complete fixed output transforms, whereas an anchor-only observer recovered interpretations only within the span of known perturbation signatures. Six three-dimensional configurations across 64 seeds gave a maximum paired prediction discrepancy of 6.7e-15 but a median untransported edit error of 1.513. Coordinate transport removed that error. Noisy and weak anchors constrained calibration stability, and changing the representation basis required recalibration or verified transport. Across 256 additional fits in dimensions 3-24, prediction equivalence persisted within 4.0e-15. We then evaluated nine deliberate runnable fault classes across 64 seeds. All 576 faulty executions completed, but each violated at least one reconstruction, prediction, delivered-edit or scope contract; all 320 valid control records passed. Repeating a faulty implementation gave exact self-agreement despite error against the separately computed simulator expectation. For one omitted-direction defect, probe coverage followed its analytic law, and rank-aware abstention protected unsupported interpretations. Scalar-noise experiments exposed both missed weak faults and excessive rejection under narrow relative tolerances. These controls provide an executable separation of prediction, semantic support and scientific acceptance. They are synthetic numerical audits, not clinical validation, neural JEPA-Anything replication, agent learning or patient treatment-effect estimation.

---

### What is the goal of unsupervised machine learning?

Authors: Aapo Hyvärinen
Published: 2026-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.11697v1

Unsupervised learning is one of the main branches of machine learning. Here I argue that unlike the other branches of machine learning (supervised and reinforcement learning), unsupervised learning is a rather heterogenous field that can serve several different goals. It seems futile to try to define one single goal for unsupervised learning. I identify four different goals for unsupervised learning: 1) Estimating the distribution, 2) Generating new data points, 3) Extracting features for downstream tasks, and 4) Understanding the data.

---

### A 3D Characterization Framework for Intelligent Sequential Decision Making

Authors: Sadig Gojayev, Carolina Fortuna
Published: 2026-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.11696v1

Puzzles are widely used to evaluate the reasoning capabilities of artificial intelligence (AI) systems for sequential decision making, yet approaches originating from different paradigms are rarely compared under unified conditions. To address this gap, we introduce a three-dimensional characterization framework that enables the analysts of AI methods by 1) projecting them to the Markov decision process (MDP) sequential decision making formalism, 2) degree of autonomy through human prior ranking of their designs and, 3) skill and computational cost. Using this framework, we analyze how representative graph-based, reinforcement learning, and large language model (LLM)-based approaches differ in their design choices and performance characteristics, instantiated respectively by Neurosolver, forward-backward reinforcement learning (FBRL), and automated thought-of-search (AutoToS), including a double-agent extension of thought-of-search (DA-ToS). The analysis relies on the Tower of Hanoi puzzle that provides a controlled benchmark with well-defined rules and scalable complexity, enabling consistent comparison across increasing problem sizes. The 3D characterization reveals that LLM-based methods, due to their weakly constrained action-space design, shift complexity from architecture to inference-time verification, leading to substantially higher memory and runtime costs than Neurosolver and FBRL.

---

### Structured Sentiment Analysis Using Sequence Labeling as Dependency Graph Parsing

Authors: Muhammad Imran, Ana Ezquerro, Carlos Gómez-Rodríguez, Anders Søgaard, David Vilares
Published: 2026-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.11695v1

This study addresses the problem of structured sentiment analysis, whose goal is to obtain a fine-grained sentiment graph where the nodes represent spans of sentiment holders, targets, and expressions, while the arcs define the relationships among them. Our proposed approach casts the task as dependency graph parsing, but departs from traditional parsing methods by solving it through sequence labeling. To do so, we leverage recent advances in linearized graph encodings that allow each word in the input to be assigned a label, effectively capturing the structure of the dependency graph. We conducted experiments on seven datasets spanning five languages (English, Spanish, Norwegian, Basque, and Catalan), showing performance competitive with leading, more complex single-model approaches.

---

### Elucidating the Space of Enzymatic Reaction: A Unified Benchmark and Pretrained Model

Authors: Yutong Hu, Tianming Huang, Yanbo Zhao, Qiongyu Zhang, Shixiang Tang, Lei Bai, Ziyi Zhou, Liang Hong, Pan Tan
Published: 2026-10-08
Categories: q-bio.QM, cs.AI
arXiv: https://arxiv.org/abs/2610.11694v1

Existing reaction models primarily learn molecular transformations, whereas enzy- matic reactions depend jointly on molecular structure and catalytic function. We formulate this problem as learning an enzymatic reaction space linking reactants, products, and Enzyme Commission (EC) annotations. To characterize this space, we introduce VenusRX-Bench, a unified benchmark for forward reaction prediction, single-step retrosynthesis, and EC-number prediction. VenusRX-Bench integrates reactions from multiple biochemical databases with standardized curation, leakage- controlled splits, and consistent evaluation. Benchmarking representative chemical and enzymatic models reveals a clear chemical-to-enzymatic domain gap, driven by limited domain data, catalytic-context dependency, and the difficulty of modeling large biomolecular structures. To bridge this gap, we develop VenusRX, a unified T5-style sequence-to-sequence model for enzymatic reactions. VenusRX jointly learns forward prediction, ret- rosynthesis, and reaction reconstruction, with two-stage training on millions of template-expanded reactions followed by real biochemical reactions. In addition, optional EC conditioning incorporates catalytic context, while Molecule Library- Constrained Decoding improves the generation of complex biomolecules. Across benchmark tasks and challenging generalization splits, VenusRX achieves the best or competitive performance on most evaluated settings over representative chem- ical and enzymatic baselines. Moreover, EC information consistently improves reaction prediction, while learned reaction representations support accurate EC prediction, revealing a bidirectional relationship between reaction structure and catalytic function. Together, VenusRX-Bench and VenusRX provide a unified framework for elucidating and modeling enzymatic reaction space

---

### Can Jev be Your Q or Policy in Reinforcement Learning?

Authors: Yi Ma, Tianpei Yang, Yaodong Yang, Weixun Wang, Hongyao Tang
Published: 2026-10-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.11692v1

Foundation models supply reinforcement learning (RL) with priors that mitigate its longstanding weaknesses in sample efficiency and transfer, but their token-by-token generation makes queries sequential and costly. Jev, a recently released decision model, generates nothing and returns calibrated, typed answers in a single forward pass. Existing work studies foundation models in RL either as models to be trained or as generators to be prompted, and Jev belongs to neither category, having so far served only as a black box in single domains. How well such a model decides on its own in RL environments, and how it can improve RL as a component of training, therefore remain unaddressed. To this end, in this paper we first examine the requirements that the objects of an RL system place on the answers they consume, and establish that Jev can fulfill all of them except the cardinal use of a value function. The remaining objects form positions that admit several roles each. We then construct algorithms that employ Jev at three of these positions, as a reference policy, an exploration judge, and a replay rater, to improve sample efficiency, exploration, and learning performance. Across nine MiniGrid tasks and three Atari games, training with Jev outperforms a standard RL learner, including where the learner makes no progress alone, while the model itself remains untrained. To our knowledge, we present the first use of Jev within the RL learning process and establish a frozen decision model as a usable component of RL training, inviting further exploration of how Jev and other advanced decision models can improve RL.

---

### Epistemic Disturbance in the Graph Model for Conflict Resolution: State-Preserving Actions, Four-Valued Assessments, and the Distinction between Capability and Intention

Authors: Yukiko Kato
Published: 2026-10-08
Categories: cs.GT, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2610.11690v1

In the graph model for conflict resolution (GMCR), a decision maker (DM) either moves the conflict to another state or does nothing. The basic definitions leave inaction implicit, so every action that leaves the state unchanged is treated as doing nothing. Yet announcements, exercises, leaks and selective disclosures are neither moves nor inaction: they leave the state unchanged but change what other DMs believe about which moves are available and which moves others would want to make. We introduce such state-preserving actions by augmenting states with the DMs' epistemic states: a physical move changes the physical state, a state-preserving action changes only the epistemic state, and inaction is the absence of a transition. Actions generate evidence through observer-specific interpretation maps. Building on a four-valued extension of GMCR from the author's earlier work, which separates evidence for and against, we show that evidence for a move can only enable perceived moves and evidence against can only disable them, that two of the four reduction operators ignore one kind of evidence, and that contradictory assessments are absorbing under monotone accumulation. With the monotonicity of stability in move sets, this fixes the direction in which any action moves a DM's stability judgements and characterizes when actions can enable provocation or deterrence. Capability assessments affect all sanction-based stability concepts, and on the DM's own side also Nash stability, whereas intention assessments affect only sequential stability. Hedging between two candidate types weakly expands or shrinks an observer's sequentially stable set according to how it reads contradiction. In the 1995 DVD format negotiation, general metarationality cannot distinguish its phases, since the computer industry group could always sanction; sequential stability, which asks whether it would, can.

---

### HI3D 3.0 (Twinkle3D): Object-specific 3D Asset Generation with High Resolution

Authors: Ziying Li, Shengchu Zhao, Huiang He, Yiyang Chen, Jianwen Huang, Bailin Li, Changhao Li, Jianhui Li, Jie Li, Ruiyang Liu, Yibo Luo, Tengjiao Sun et al.
Published: 2026-10-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2610.11685v1

Image-to-3D generation has become increasingly capable of producing objects that closely resemble the input image, and an outstanding challenge is to reproduce the depicted object itself, including the specific geometry that defines it. Inscriptions, brand marks, and repeated structures are frequently distorted or lost, despite being critical to object identity. We present Hi3D 3.0, an image-to-3D generation system targeting object-specific fidelity, with Twinkle3D as its geometry model for generating watertight triangle meshes at $2048^{3}$ resolution. Twinkle3D advances high-fidelity geometry generation along four dimensions. First, while O-Voxel/FaithC offers high representational precision, it often suffers from poor surface quality and non-watertight geometry. We address both issues while retaining its $2048^{3}$-level precision. Second, we scale diffusion generation to sequences of up to 300K geometric tokens through a redesigned DiT architecture and large-scale distributed training optimizations, reducing training time per step from approximately ten minutes to ten seconds. Third, subsequent refinement cannot fully compensate for errors introduced during initial generation; we therefore strengthen both global shape and local detail in the initial generation stage, and the resulting single-stage model surpasses prior two-stage pipelines with $512^{3}$ refinement. Finally, we introduce a fine-grained image-3D cross-modal interaction mechanism that strengthens correspondence between visual evidence and geometric tokens, improving the recovery of object-specific structures. We evaluate geometric fidelity using alignment metrics derived from silhouettes and normal fields. Hi3D 3.0 outperforms four commercial systems across all reported metrics, recovering 82.1% of inscribed characters at 98.2% precision, compared with 21.7% recall for the strongest competitor.

---

### Camera-Noise Residuals for Face-Swap Detection: Redundant, Not Complementary, and Why

Authors: Danil Davydov, Bader Rasheed, Dmitriy Vatolin
Published: 2026-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.11683v1

Fusing a learned camera-noise fingerprint with an RGB appearance backbone is an appealing route to generator-independent deepfake detection, because the noise residual is grounded in image-formation physics rather than in the texture statistics of a particular generator. We test, on FaceForensics++, whether a Noiseprint++ residual channel carries information \emph{complementary} to an RGB Xception backbone for face-swap detection. A three-model ablation (RGB-only, residual-only, late-fusion) shows that fusion does not improve over RGB alone and that the residual branch alone is near chance. A seven-level bottleneck diagnostic localizes the cause: the noise maps do carry a discriminative signal, but it is statistical---carried by the per-sample first and second moments (mean, variance, energy) of the residual---and the per-sample \texttt{InstanceNorm} layer placed at the noise-branch input, following the TruFor template, standardizes exactly those moments away (five-fold cross-validated AUC drops from $0.747$ to $0.554$). A context-crop control rules out cropping geometry, and two fixed-fusion variants that remove the bottleneck recover the statistical signal yet still fail to beat RGB on every dataset. We conclude that, on this manipulation distribution, the noise residual is redundant with RGB rather than complementary, and we give concrete guidance for practitioners adopting noise-residual fusion for face-swap detection.

---

### TRACE: Diagnosing Verifier Brittleness in Agentic Evaluation

Authors: Radhika Gaonkar
Published: 2026-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.11678v1

Verifier scores now serve as both benchmark metrics and training rewards for large language model (LLM) agents, and a change in score is routinely read as a change in capability. It may instead reflect a change in the evaluation. We introduce TRACE, a protocol that turns a score change from a verdict into a testable diagnosis: it applies a targeted change to one part of an evaluation, compares paired runs, checks whether the agent's behavior changed, and rescores unchanged trajectories to test whether the scoring rule is responsible. In a controlled suite of 25 synthetic tasks, renaming tools lowers a scripted agent's score by 0.250 even though it performs exactly the same operations; restoring the original names at scoring time closes the entire gap, while the same mutation exposes a genuine behavioral failure in a second agent. On public $τ^2$-bench tasks with four LLM agents, an initial 30-task study finds mixed reward changes whose one clear effect does not replicate. In a larger follow-up on 88 new tasks with repeated runs per condition, renaming tools or reformatting tool outputs leaves reward unchanged to within $\pm$0.10 for seven of eight agent-change pairs, whereas tool names that deliberately mislead lower every agent's reward by 0.20-0.44, showing that the setup can detect real effects. Identical reruns flip 15-36% of task outcomes, so single-run comparisons cannot separate presentation effects from run-to-run variation. Two frontier LLM judges give consistent verdicts when a fixed trajectory is presented differently, yet disagree with each other on 57% of the same records, largely because one grades procedure rather than outcome. TRACE thus separates what a score change says about the agent from what it says about the measurement.

---

### VESSI - VLM-Enhanced Support for Surveillance and Investigations

Authors: Saverio Cavasin, Pietro Tedeschi, Mattia Tamiazzo, Alessandro Brighente, Simone Milani, Mauro Conti
Published: 2026-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.11674v1

Automated video surveillance analysis has become a critical component of intelligence infrastructures and Law Enforcement agencies. Traditional systems lack the semantic module for comprehensive situational awareness and forensic tasks, limiting their ability to interpret events meaningfully or support post-incident investigations. This slows operational insight and increases the burden on human analysts. Recent advances in Vision-Language Models (VLMs) offer promising pathways to bridge this gap. To address this, we propose VLM-Enhanced Support for Surveillance and Investigations (VESSI), a VLM-based framework designed to enhance automated video surveillance analysis through prompt-driven interrogation of video sequences where salient visual features are converted into textual descriptions. We test our framework with four state-of-the-art models. Since most datasets for this task are unlabeled, we also propose the Composite Model Utility Score (CMUS) to assess VLM performance. Experimental results show that our solution substantially improves the analysis capabilities of human operators and enhances the flexibility of automated surveillance systems. In our evaluation, the most reliable model flagged potentially relevant activity in more than 66% of the videos while reducing review time by more than 85%, offering a practical balance between selectivity and efficiency. The model ordering produced by the reference-free CMUS evaluation was reproduced by the normal-video CMUS evaluation and matched the false-positive-rate ordering obtained from 5,909 manually referenced frames. This agreement supports the operational use of the score within the evaluated setting.

---

### Early Signatures of Memorization in Diffusion Models via Basin Geometry and Cyclic Denoising

Authors: Nikhil Verma, Siddharthan Dileep, Anoop Singh, Srikanth Sastry, Ramya Hebbalaguppe, Sayan Ranu, N. M. Anoop Krishnan
Published: 2026-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.11670v1

Diffusion models generalize early in training and later reproduce individual training samples. Standard tests detect memorization only once one-shot generation produces near-copies, leaving a released model unaudited until its outputs fail. We show that memorization is encoded in the geometry of the learned energy landscape before it appears in generated samples, a state we call latent memorization. Using score divergence and basin volume, we find that localized basins form around training samples and separate them from held-out samples before the first memorized sample appears, with an onset that follows the same $O(n)$ scaling as the memorization time. We probe these basins with cyclic denoising, which repeatedly applies partial noising and denoising. Under the exact empirical score, we prove that cycling started near an isolated training sample recovers it and returns to it over any finite number of cycles with high probability. In trained models, cycling recovers training images from CelebA and CIFAR-10 checkpoints whose one-shot samples contain no copies, and at a CelebA checkpoint with 0.1% one-shot copies, 500 cycles raise the memorized fraction above 30%. Cycling also reveals degenerate attractors that match no single training image and fade as training proceeds, so residence in a basin does not by itself imply memorization. These findings hold on a Gaussian mixture, CelebA, and CIFAR-10 across optimizers, architectures, noise schedules, and training-set sizes, and extend to off-the-shelf Stable Diffusion v1.4, where the cycled conditional-unconditional divergence gap separates memorized from non-memorized prompts with an AUC of 0.944 and a TPR of 0.866 at 1% FPR. More broadly, what a diffusion model has memorized is a property of the geometry and stability of its learned distribution, and assessing it requires examining this structure rather than generated outputs alone.

---

### Perceptually Grounded and Semantics-Aware Evaluation for Holistic Co-Speech Gesture Generation

Authors: Nick Milkin, Lanmiao Liu, Esam Ghaleb, Asli Ozyurek, Zerrin Yumak
Published: 2026-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.11669v1

Holistic and semantics-aware co-speech gesture generation has advanced rapidly, yet evaluation remains behind: objective metrics do not consistently reflect human perception, and semantic appropriateness remains difficult to quantify. We present a perceptually grounded and semantics-aware benchmark that combines standardized model comparison, human-centered metric validation, and fine-grained semantic evaluation. We first curate a list of 13 objective metrics covering different aspects, including distributional similarity, geometric fidelity, kinematic quality, cross-modal synchrony, and semantic appropriateness. For the semantic-appropriateness category, we propose a new metric, Semantic Gesture Preservation (SGP), which measures how far semantic gestures in the ground truth are preserved in the generated gestures. For this, we augment the BEAT2 dataset's annotations using a multi-modal LLM. We then conduct a perceptual study where 101 participants score generated gestures among five dimensions, including human-likeness, motion diversity, absence of animation errors, speech timing and content match. We systematically analyze objective metric--subjective score correlations. Unlike Semantic Score (SC), which shows no significant association with the evaluated perceptual dimensions, SGP is selectively aligned with speech-aware human judgments. We construct five target-specific composite metrics aligned with the subjective dimensions. These composites improve perceptual alignment across all five dimensions, with the largest gains for absence of animation errors and content match, indicating that complementary objective signals can better approximate human judgments than individual metrics alone. Overall, our results show that objective metrics require validation against subjective evaluations.

---

### $σ$Transfer: Uncertainty Transfer from Small to Large Networks under $μ\mathrm{P}$

Authors: Richard Bergna, Fernando Ruiz Mazo, Nicolò Felicioni, José Miguel Hernández-Lobato, Kamil Ciosek
Published: 2026-10-08
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2610.11668v1

Reliable predictive uncertainty in Laplace approximations depends critically on the prior precision, yet selecting it requires a posterior sweep that is prohibitively expensive for neural networks with billions of parameters. Under the Maximal Update Parametrization ($μ\mathrm{P}$), we derive a rescaling of the prior covariance that makes the selected precision stable as model width grows. This leads to $σ\mathrm{Transfer}$: we select the precision on a smaller model and zero-shot transfer it to the much larger model, i.e., without searching for the precision on the larger model at all. We show convergence of the prior kernel, posterior covariance, selected precision, and posterior-derived decisions under explicit conditions, and verify $σ\mathrm{Transfer}$ across regression, image classification, and Transformer readouts. For example, measured precision-sweep speedups reach $\sim 5000\times$ when transferring from width 128 to 4096 on MNIST, at a target-NLL degradation of $0.002$; transferring from a public 1B to 7B model gives a median search speedup of $\sim 2.3\times$ (up to $\sim 330\times$), with a mean measured target-NLL increase below $10^{-4}$ across ten tasks. The same posterior stability also enables transfer of acquisition, OOD-detection, and abstention decisions without constructing a target posterior.

---

### Autoregressive Retriever: Improving Query Understanding from Item Feedback for Universal Multimodal Retrieval

Authors: Jianfei Zhao, Yifan Wang, Feng Zhang, Xin Sun, Chong Feng, Zhixing Tan, Yang Luo, Boyuan Pan, Xu Kai, Yao Hu
Published: 2026-10-08
Categories: cs.IR, cs.CV
arXiv: https://arxiv.org/abs/2610.11666v1

Universal multimodal retrieval typically encodes a query once and ranks independently indexed items by embedding similarity. This design supports efficient search, but leaves the query representation unchanged even when retrieved items could help clarify the information need. We introduce the AutoRegressive Retriever (ARR), a multimodal retrieval model that learns both to select informative items and to use their content to refine subsequent retrieval. ARR alternates between retrieving an item and updating the query embedding, then uses the final embedding to rank the collection. Supervised fine-tuning teaches the encoder to use feedback through stepwise contrastive supervision. Reinforcement learning treats feedback items as actions and optimizes their selection using the final reciprocal rank of a relevant item. A query-side adapter enables this optimization against a fixed item index. ARR demonstrates strong retrieval performance on both in-domain and zero-shot benchmarks, outperforming the compared baselines on average. Further analyses show that feedback improves retrieval at inference time and that training with feedback also improves the initial query embedding, before any item is observed.

---

### Evi-VN: Hard Region Guided Virtual Node Evidence Injection for GNN-Based Fraud Detection

Authors: Jiran Tao, Yifan Wu, Binyan Jiang
Published: 2026-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.11665v1

Online platforms contain growing numbers of bots, deceptive reviewers, and scam accounts that imitate legitimate users. Such camouflage blurs graph neighborhoods and behavioral attributes, making it difficult for graph neural networks (GNNs) to distinguish both well-disguised fraudsters and legitimate users. Across diverse GNNs, we observe overlapping errors on a shared hard region, suggesting the presence of latent fraud evidence that graph topologies and standard features fail to capture. Fraud-specific GNNs can mitigate particular graph pathologies, yet they still make limited use of heterogeneous evidence such as structured records, text, images, and audio; uniform multimodal fusion may also disturb nodes already handled reliably by the graph. We propose Evi-VN to learn and correct these shared blind spots rather than build another fraud detector. To our knowledge, Evi-VN is the first graph fraud detection framework to use feature isolated evidence chains to correct hard regions shared across GNNs. Its evidence chains connect behavior, content, and context across structured, textual, visual, and acoustic sources, helping expose camouflage that graph neighborhoods may miss. Crucially, Evi-VN selectively applies this evidence only to likely hard samples via virtual class nodes, preserving both the reliable predictions and the input design of existing GNNs. Shared hard regions also let Evi-VN enhance generic, fraud-specific, and unseen GNNs even with imperfect evidence models. Experiments across bot, fake-review, refund-evidence, and telecom-fraud tasks validate these advantages.

---

### Constrained Command-Conditioned Reinforcement Learning with Bandit Strategy Selection in Real-Time Strategy Games

Authors: Nick Leenders, Roy Lindelauf, Joost van Oijen, Boris Cule
Published: 2026-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.11663v1

Deep reinforcement learning agents reach strong performance in real-time strategy games but can be brittle against opponents outside their training distribution. Separating strategic command selection from learned unit control allows different strategies to be selected for different opponents while reusing the same execution policy. This requires an executor that can follow different commands and measurable criteria for assessing whether it does so. We introduce a constrained command-conditioned Proximal Policy Optimization (PPO) policy, the executor, for MicroRTS, a real-time strategy environment. Discrete commands specify strategic objectives and behavioral requirements for economy, army composition, military posture, and worker policy over multiple environment steps; the executor determines the unit-level actions used to fulfill them. A Thompson-sampling bandit acts as the strategist, selecting command tuples from an estimate of the opponent's strategy built from in-game observations rather than opponent identity. In a controlled comparison with a flat PPO baseline trained with the same architecture, budget, curriculum and self-play league, the strategist-executor system wins significantly more often against three of the four strongest opponents on a training map, including the two strongest held-out ones (0.55 to 0.97 and 0.01 to 0.34), with no significant difference against the others.

---

### Lamarck's Driving School: Discovering Autonomous Driving Training Strategies through Evolutionary Competition

Authors: Yichun Ye, He Zhang, Ye Tian, Jian Sun
Published: 2026-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.11662v1

Autonomous driving capabilities depend strongly on the distribution of scenarios encountered during training. Existing methods commonly construct or dynamically adapt training scenario distributions using surrogate criteria such as realism, difficulty, or risk. However, these predefined surrogates may misrepresent training value, leading to inefficient use of training resources. To address this limitation, we propose a Lamarckian evolutionary framework that replaces surrogate-based guidance with competition among candidate distributions. We formulate training strategy discovery as a multi-stage bilevel optimization problem and use Lamarckian evolution algorithm to approximate its solution. At the outer level, Darwinian crossover, mutation, and selection explore the scenario distribution space; at the inner level, policy learning acquires new capabilities, and Lamarckian inheritance transfers them to subsequent stages, allowing scenario distributions and policy capabilities to co-evolve. The resulting evolutionary trajectories reveal recurring stage-wise regularities among high-value distributions, characterized by capability accumulation through stage-wise challenge rotation. We further distill these regularities into a lightweight, reusable Lamarckian Training Strategy. Experiments show that, compared with the baseline, the complete framework reduces performance loss by up to 25.07%, while the lightweight strategy still achieves a 19.13% reduction. These results demonstrate that evolutionary competition can both discover effective training strategies and reveal reusable stage-wise patterns in how the value of training distributions changes with policy capability. Code is available on GitHub.

---

### DIAL-OPD: Learning More from Fewer Tokens in On-Policy Distillation

Authors: Anhao Zhao, Haoran Xin, Junlong Tong, Yingqi Fan, Xuan Lu, Ping Nie, Wenjie Li, Xiaoyu Shen
Published: 2026-10-08
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2610.11659v1

On-policy distillation (OPD) supervises student-generated trajectories with token-level teacher signals. Its sampled-token variant avoids the cost of full-vocabulary probabilities. Yet we find that training on fewer tokens can outperform full-token OPD, challenging the intuition that more supervision improves learning. This motivates selecting tokens by learning value. Existing disagreement-based criteria ignore probability scale: tokens assigned negligible probability by both models, termed low-low tokens, can receive large log-ratio rewards and hinder learning. We propose DIAL-OPD, a token-selection method that bridges log-probability and probability spaces by weighting reward magnitude with the logarithmic mean of teacher and student probabilities. A parameter beta controls this weighting, and the highest-scoring tokens are retained. Across 4 teacher-student pairs and 7 mathematical reasoning benchmarks, we compare DIAL-OPD with 9 baselines. Retaining only 40% of tokens, it outperforms Vanilla OPD and its full-token variants, with mean accuracy gains reaching 5.25 percentage points over Vanilla OPD, and doubles AIME25 Pass@16 from 13.33% to 26.67%. It also achieves up to an 18% relative improvement in mean accuracy over the strongest token-selection baseline at matched retention ratios. With a 4B teacher, DIAL-OPD surpasses the strongest full-token baseline using an 8B teacher at both student scales, showing that effective supervision allocation can outweigh teacher scaling. Further analysis shows that moderate beta balances suppressing low-low tokens against preserving useful disagreements. Token-level evidence reveals that DIAL-OPD filters high-reward tokens with limited reasoning value while preserving supervision critical to reasoning correctness.

---

### DisFace3DNet: Explainable Facial Attractiveness Prediction via 3D Component Disentanglement

Authors: Fenggui Rao, Yan Luximon, Jie Zhang
Published: 2026-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.11656v1

Facial attractiveness prediction usually assigns one overall rating, leaving the roles of shape, appearance, and viewing conditions implicit. We propose DisFace3DNet, which uses 3D component disentanglement to learn seven component reference scores from overall ratings with auxiliary weak semantic supervision, without human-labeled component targets. Designated 3D representations and image cues feed jointly learned routes for identity, skin, hair, light, background, expression, and pose. A constrained fit then combines five static and two signed dynamic scores into the overall rating, exposing each component's numerical contribution and supporting component-specific comparisons across images. On SCUT-FBP5500, DisFace3DNet achieves a Pearson correlation of $0.8904\pm0.0063$ (mean $\pm$ standard deviation across five folds) with average human ratings; its component terms reconstruct every held-out prediction to numerical precision. Skin, hair, and facial shape account for the largest component-wise prediction variation. Human evaluation supports the score directions for facial shape, skin, and hair; expression agreement is weaker. DisFace3DNet thus connects overall prediction to quantitative analysis of the facial and contextual cues entering each estimate.

---