# Research Papers — 2026-10 · bundle page 19 of 156

> Full-text markdown of papers #901–950 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/19
[← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/18.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-10/page/20.md)

### Dimension-Optimal Dynamic Regret in Exp-Concave Online Learning

Authors: Yanyi Li, Wendao Wu, Haihan Zhang, Qinshi Wang, Chenheng Zhang, Chunyuan Zheng, Cong Fang, Haoxuan Li, Zhouchen Lin
Published: 2026-10-14
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2610.20187v1

Tracking changing comparators is a central problem in online learning. For exp-concave losses, previous work established the $T^{1/3}P_T^{2/3}$ dependence on the horizon $T$ and Euclidean path length $P_T$ for fixed dimension, while the optimal cost of dimension remained unresolved. We resolve this question by establishing a sharp $d^{1/3}$ curved dimension factor, improving the $d^{2/3}$ factor of recent switching and interval reductions (1, 2). To achieve this improvement, we develop a proper, full-information learner on compact convex subsets of $\mathbb{R}^d$ that adapts to the unknown path length and, under fixed dimension-independent diameter, gradient, and curvature parameters, guarantees $$\operatorname{Reg}_T(u_{1:T}) \le \widetilde{O}\left(d+\min\left\{d^{1/3}T^{1/3}P_T^{2/3},\sqrt{TP_T},T\right\}\right).$$ A matching lower bound on a diameter-one Euclidean ball establishes the minimax frontier up to logarithmic factors when $T\gtrsim d^2$, including the transition from the curved rate to larger path budgets. The lower bound already holds for losses that depend on only one coordinate per round, isolating an unavoidable cost of learning across directions. Our upper bound follows from square-root Gaussian KL control of comparator movement and a cancellation argument that pays for history restarts. The curved learner maintains $O(\log^2 T)$ Gaussian states, uses one gradient per round, and runs in time near-linear in $T$ under a Mahalanobis-projection oracle.

---

### When Occupation-derived Skills Don't Help: On the Limits of Skill-Augmented Career Path Prediction

Authors: Ege Süalp, Elena Senger, Toine Bogers, Barbara Plank
Published: 2026-10-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.20186v1

Skills are widely assumed to play a central role in career transitions, motivating their use in career path prediction (CPP) systems. In this work, we critically examine whether explicit skill representations provide complementary signal beyond text-based job representations. We evaluate multiple strategies for incorporating skills into CPP models, including score fusion and neural architectures, under two conditions: predicted skills and ground-truth ESCO annotations. Surprisingly, across two benchmark datasets, none of these settings yield substantial improvements over strong text-only baselines. Even when using ground-truth skills, gains remain marginal and inconsistent. Through detailed analysis, we identify key factors underlying this result: high redundancy between textual and skill representations, limited discriminative power of ESCO's taxonomy, and representational collapse in skill embeddings. Furthermore, we find that skill prediction difficulty correlates with overall sample difficulty, limiting the potential for complementary signals. Our findings challenge the common assumption that explicit skill modeling inherently benefits career prediction and suggest that dense text representations already capture most skill-relevant information.

---

### Cross-Model In-Context Neurofeedback Reveals (Limited) Activation Control in LLMs

Authors: Davide Baldelli, Robyn Kozierok, Mirko Bronzi, Damiano Fornasiere
Published: 2026-10-14
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2610.20179v1

Probes on activation vectors are widely used to detect misbehavior in language models, but their success relies on the assumption that models cannot control what their activations encode. Humans can learn, through neurofeedback, to control the firing of even single neurons, and recent studies investigated whether this ability extends to language models, reaching conflicting conclusions. No experimental design so far disentangles competence at the task from genuine access to one's own activations. We fill this gap with in-context neurofeedback sessions, in which a "subject" model is asked to maximize (or minimize) a score derived from its activations, shown back to it at every turn. In our first experiment, the sentences are generated either by the subject or by a second "writer" model, while the score always derives from the activations of the subject. We test ten open-weight models from five families, with sizes from 9B to 32B. Some models move their own scores considerably, but no more than a writer of comparable competence moves them. Is this because the task requires no privileged access, or because the subject controls its activations while processing the sentences, whoever wrote them? To answer this, we prefill a fixed sentence as the subject's reply at every turn and ask it to increase or decrease the score. Three out of ten models show small but consistent control effects. We further ask whether models can control their activations to the point of fooling an activation monitor. We make models repeat sentences a monitor would flag, such as a deceptive answer for a deception monitor, and ask them to raise or lower the monitor's score. No model learns to lower it, but one model can raise it. In-context control of a model's own activations might not yet be a threat to activation monitors, but it exists in a few models and needs to be tracked as models evolve.

---

### TreeSpark: Learning to Draft the Trees You Verify for Speculative Decoding

Authors: Jihao Zhao, Qianyu Jiang, Shuaishuai Zu, Pengfei Li, Guanghuan Fang, Ben Feng, Biao Qin, Zhibin Wang, Baochuan Yang
Published: 2026-10-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.20175v1

Parallel drafters such as DFlash and DSpark reduce proposal latency, but early mismatches limit how much of each block can be accepted. Retaining alternatives introduces parent states and candidate choices that reference-conditioned training does not directly supervise. We introduce TreeSpark, a unified training and inference framework extending the semi-autoregressive DSpark architecture. It constructs parent-conditioned candidate trees from one backbone pass and replays their expansion, pruning, and budgeted packing during training. Survival negative log-likelihood weights retained edges by reference-derived path mass, while a capped coverage hinge promotes target-important alternatives near local selection boundaries. Both objectives reuse reference-chain target distributions without additional target forward passes. We evaluate greedy decoding with Qwen3-4B and Qwen3-8B on nine general benchmarks and six writing domains. Across targets and suites, TreeSpark improves mean acceptance length over DSpark by 23.4% to 31.6% and mean single-request throughput by 15.1% to 25.0%. Batched Qwen3-4B throughput improves by 12.6% to 17.2%. At fixed attention capacity and inference policy, the proposed supervision further improves mean acceptance length by approximately 6.4% and mean system throughput by 4.2% to 5.0% on Qwen3-4B.

---

### RM-OPD: On-Policy Distillation for Generative Reward Models

Authors: Qinglin Su, Licheng Pan, Zhen Fang, Jiakang Wang, Qingnan Ren, Yunsheng Lu, Yan Gao, Zhixuan Chu
Published: 2026-10-14
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2610.20174v2

Reinforcement Learning on Mixed-domain preference data (Mix-RL) has become the mainstream approach for training general-purpose Generative Reward Models (GRMs). However, Mix-RL suffers from two critical bottlenecks: the reward sparsity induced by outcome rewards, and the cross-domain interference arising from jointly optimizing heterogeneous capabilities, which together give rise to imbalanced capability acquisition and pervasive reward hacking. Inspired by the success of On-Policy Distillation (OPD) in multi-domain capability integration, we introduce RM-OPD (Reward Modeling via On-Policy Distillation), a two-stage framework that separates specialist acquisition from capability integration. First, we cultivate domain-specialized teacher models via single-domain GRPO fine-tuning, allowing each expert to reach its performance ceiling in isolation; then we consolidate these teachers into one student model through (i) routed on-policy distillation, which provides dense signed token-level supervision on student-generated critiques; (ii) domain contribution reweighting, which reweights token guidance toward target domain shares, preventing specific domains from dominating optimization; and (iii) optional criteria context distillation, which conditions teachers on domain-specific evaluation criteria to sharpen token-level supervision. Across multiple RM benchmarks and two base models, RM-OPD consistently outperforms vanilla Mix-RL and other strong baselines, achieving overall superior performance and exhibiting an emergent "teacher-surpassing" effect. These results establish RM-OPD as a promising paradigm for building generalist GRMs.

---

### MultiPartyTurnBench: Benchmarking Floor Control in Multi-Party Spoken Dialogue

Authors: Puneet Mathur, Dinesh Manocha
Published: 2026-10-14
Categories: cs.SD, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2610.20172v1

Full-duplex speech systems must decide when to enter, hold, or relinquish the conversational floor, even as multiple speakers overlap or backchannel without taking it. Existing evaluations study dyadic turn-taking or end-to-end agent behavior, but lack a unified, controlled evaluation of genuine floor transitions against confusable non-events in multi-party settings. We introduce MultiPartyTurnBench (MPTB), a benchmark of 240 synthetically generated, channel-separated conversations spanning two to five speakers and six interaction types. MPTB evaluates two complementary tasks: End-of-Turn (EOT) detection distinguishes genuine turn completion from temporary holds, while Interruption (INT) detection distinguishes successful floor takeovers from non-floor-taking speech. Exact event-conditioned annotations enable causal evaluation using false-positive-constrained recall and signed latency. Across acoustic, semantic, and turn-projection baselines, we find a stark asymmetry: learned systems achieve 82.5-92.6% EOT recall at 4.3-11.8% false-positive rates, while INT detection suffers from missed takeovers or excessive false activations. This asymmetry extends to five full-duplex agents which achieve 86.1-95.8% balanced accuracy on turn entry, yet perform near chance (46.9-54.7%) on selective interruption handling. Gemini-3.8-Live yields to 97.7% of backchannels, whereas MiniCPM-o-4.5 yields to only 1.4% of genuine interruptions. These findings establish selective floor control as a distinct, unresolved challenge for reliable multi-party voice interaction.

---

### Optimizing Sparse Boolean Rule Networks using Mixed Integer Linear Programming

Authors: Thomas Pammer, Johannes Fürnkranz, Markus Sinnl
Published: 2026-10-14
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2610.20170v1

We study the problem of learning accurate and cognitively simple binary classifiers that are directly interpretable as Boolean rules. We propose mixed integer linear programming (MILP) formulations for training sparse disjunctive normal form (DNF) networks, viewed as small networks with a conjunctive hidden layer and a disjunctive output layer. Contrary to previous work that uses MILP for inductive rule learning, we start with a fixed network structure, for which we then find optimal weights. A regularized objective explicitly trades off misclassification costs against sparsity, yielding globally optimized rule sets. Our main technical contribution is an enhanced formulation that substantially reduces the number of integer decision variables and eliminates redundant constraints, while preserving exact Boolean semantics for all feasible solutions. Furthermore, we develop a combined approach based on initialization and dropout to break symmetries in the weights between rules, mitigating redundancy, and encouraging more diverse and stable rule representations. Experiments on synthetic benchmarks and UCI datasets show that the advanced formulation improves computational efficiency and achieves competitive or superior accuracy compared to established interpretable baselines, including SAT-based DNF learning and well-known rule- and tree-based learners. Overall, our approach provides a principled optimization framework for learning compact Boolean rule sets with explicit control over accuracy and sparsity trade-offs.

---

### Gap Detection: Mitigating Homogenization through Demand and Defensibility

Authors: Xucheng Yu, Haibo Jin, Xiaoqi Wang, Runze Kong, Haohan Wang
Published: 2026-10-14
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2610.20162v1

Language models often produce semantically similar answers to open-ended questions, even when many plausible alternatives exist. Generating useful alternatives requires identifying both what the query calls for and what existing responses already cover. We introduce Gap Detection, a framework that searches for relevant but unoccupied directions in a shared text embedding space. Its objective, GapScore, combines query relevance (Demand) with dissimilarity to the nearest existing item (Defensibility). The framework optimizes this product on the unit sphere, maps candidate directions to concept words with a language model, and uses task-specific filtering and constrained prompting to turn those concepts into text. On five curated topics and 90 INFINITY-CHAT queries, the reported mean relative reductions in output Collision are 12.8% and 10.8%, respectively. We also instantiate the framework for generative engine optimization over four product markets and for iterative synthetic-data augmentation. In the latter setting, with 100 training examples per method, Gap Detection reduces Collision from 0.324 to 0.298 relative to undirected accumulation and increases the Vendi Score from 27.16 to 29.20; the accuracy difference is one example on a 40-example test set. Component ablations expose the trade-off between semantic separation and relevance, while also showing that better direction scores do not uniformly yield better downstream metrics. These results support explicit gap search as a practical mechanism for diversifying content, with task validity checked separately from geometric novelty.

---

### OneLA: Learning Many Worlds from Latent Actions

Authors: Ziyu Zhu, Zhaoxu Sun, Fan Jiang, Chiyu Wang, Junfeng Ni, Mu Xu
Published: 2026-10-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.20160v1

Learning world models across diverse domains calls for a unified control space, yet ac- tion interfaces vary across domains and action annotations are often scarce. Latent ac- tions learned directly from videos offer a promising way to establish such a space without explicit action supervision. However, learning shared latent actions across domains re- mains challenging, as variations in appearance, embodiment, and dynamics can entangle domain-specific visual cues with transferable transition structure. To this end, we intro- duce OneLA, a simple framework that learns continuous latent actions through a shared orthogonal dictionary and a common predictive objective, without task-specific designs or cross-domain alignment losses during latent action pretraining. These latent actions pro- vide a shared conditioning interface for world models, with lightweight adapters mapping native control commands into the same space. Conditioned on latent actions and the cur- rent visual state, the world model predicts context-dependent transitions for controllable rollout. OneLA improves action readout across domains and reduces action cycle-transfer rotation error by 24.8% over the strongest evaluated baseline. A joint-training comparison further shows a 20.5% improvement in Human Preference Score v3 (HPSv3) for real- scene generation. These results suggest a path toward general-purpose world models that learn from diverse videos and support flexible control through latent action space.

---

### Dataset-Level Regularization for Joint-Embedding Self-Supervised Learning

Authors: Konstantinos Almpanakis, Anna Kreshuk
Published: 2026-10-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.20158v1

Self-supervised joint embedding learning aligns representations of augmented views while regularizing their distribution to prevent collapse. Regularization aims to shape the overall representation distribution, but most joint embedding methods restrict its computation to the active minibatch. We propose out-of-batch regularization, which maintains a dataset-level state in CPU memory and uses globally constructed per-instance targets during minibatch training. Evaluated on natural images and biomedical datasets, these anchors approximate the full-dataset regularization gradient more faithfully than conventional minibatch estimation at small batch sizes. Applications to contrastive (SimCLR) and non-contrastive (SIGReg) approaches show consistent improvement over the corresponding in-batch objectives for image classification, minority-class performance under controlled imbalance, instance retrieval, and continued self-supervised pretraining, with the largest gains at small batch sizes. These results suggest that dataset-level regularization can be decoupled from minibatch optimization, making batch size an optimization choice that does not affect the geometry of the regularizer.

---

### LLM-Based Policy Compliance Verification of Loan Applications

Authors: Florentina Voboril
Published: 2026-10-14
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2610.20155v1

Banks rely on extensive internal policy frameworks to ensure that corporate lending decisions comply with regulatory requirements and internal risk standards. Reviewing loan applications against these policies is a largely manual and knowledge-intensive process, which can lead to overlooked policy violations or exceptions. This report presents a prototype of an LLM-based policy checker that automatically verifies loan applications against internal lending policies. The proposed approach follows a two-step architecture. First, compliance-relevant rules are automatically extracted from policy documents and converted into structured, machine-readable representations. Second, loan applications are evaluated against the extracted rules to identify policy exceptions, non-compliant findings, missing information, and cases requiring manual review. Evaluation results demonstrate that the rule extraction process is highly stable across multiple runs and consistently captures rules identified as critical by a domain expert. When evaluated on 11 real loan applications with known policy exceptions, the system successfully detected the majority of these exceptions and identified additional compliance issues that had previously been overlooked during manual reviews. While the approach produces false positives and cannot fully replace human judgement, the results indicate that LLM-based policy compliance verification can provide valuable support in the loan application verification process by highlighting potential compliance risks.

---

### Attention-Based Spatio-Temporal Approach for Fire and Smoke Detection

Authors: Alireza Mirrashid, Mohammad Khoshbin, Ali Atghaei, Hassan Shahbazi
Published: 2026-10-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.20141v1

In various industries, smoke and fire are two of the most important threats in the workplace. One of the common methods for detecting smoke and fire is the use of infrared thermal and smoke sensors, which cannot be used in outdoor applications. Therefore, the use of vision-based methods seems necessary. The problem of smoke and fire detection is spatiotemporal and requires spatiotemporal solutions. This paper presents a method that uses spatial features along with temporal-based features to detect smoke and fire in the scene. It consists of three main parts; the task of each part is to reduce the error of the previous part so that the final model has a robust performance. This method also uses transformer modules to increase the accuracy of the model. The results of our model show the proper performance of the proposed approach in solving the problem of smoke and fire detection and can be used to increase workplace safety.

---

### Sparse Autoencoders for Mechanistic Interpretability in NLP: A Critical Survey of Recoverability, Interpretability, and Utility

Authors: Salima Lamsiyah, Adelaide Danilov, Oleksandr Marchenko Breneur, Aria Nourbakhsh
Published: 2026-10-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.20139v1

Sparse autoencoders (SAEs) have emerged as a promising approach to mechanistic interpretability by decomposing language-model activations into sparse, potentially interpretable features. However, differences in design assumptions, evaluation objectives, and experimental settings complicate conclusions about their effectiveness. We present a critical survey of 138 studies on SAEs in natural language processing. Our contributions are fourfold: (1) we propose a task-grounded taxonomy connecting dictionary design, feature operations, and NLP functions; (2) we examine how sparsity allocation, geometry, data coverage, and inference affect feature recoverability; (3) we assess evidence for semantic interpretability, mechanistic faithfulness, and behavioral utility; and (4) we synthesize findings across multilingual processing, retrieval, reasoning, classification, and behavioral regulation, highlighting the roles of objectives, baselines, supervision, and intervention pipelines. Through comparative analyses of published results, we reconcile apparent disagreements, identify unresolved questions, and propose directions for more rigorous evaluation. An anonymous research register https://anonymous.4open.science/r/sae-research-register-C331/register.html accompanies the survey.

---

### In-Context Batch Black-box Optimization via Flow Matching

Authors: Quoc-Anh Hoang Nguyen, Xinyu Zhang, Daolang Huang, Julien Martinelli, Samuel Kaski
Published: 2026-10-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.20138v2

Batch black-box optimization is important for expensive systems where many candidates can be evaluated in parallel, yet only a few rounds of evaluation are affordable. In this regime, effective batch construction must identify multiple promising regions while avoiding redundant evaluations, and conventional Bayesian optimization can require increasingly difficult batch-selection procedures as the batch size grows. We introduce Flow Matching for Thompson-Sampling Refinement (FMTR), an amortized approach that learns offline a continuous, history-conditioned proposal distribution from which variable-size batches can be sampled. FMTR is trained offline by conditional flow matching on Thompson-sampling argmaxes refined toward high-value regions via a horizon-dependent Langevin pushforward map, adapting the exploration-exploitation tradeoff over the optimization horizon. At test time, the model parameters remain fixed and batch generation requires neither task-specific surrogate refitting nor numerical acquisition optimization. FMTR achieves strong performance against batch BO and in-context baselines on synthetic and real-world benchmarks, while substantially reducing the computational cost of batch selection.

---

### StreamErase: Towards Ultra-Fast Streaming Video Erasing

Authors: Zhuobai Dong, Xiaobing Tu, Xiantao Zhang, Jinkui Ren, Yinggui Wang, Yue Ma, Linfeng Zhang
Published: 2026-10-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.20137v1

Current video object removal methods suffer from prohibitive latency (minutes per video) and non-causal processing that prevents real-time interaction. We present StreamErase, enabling sub-second latency with up to 26 FPS streaming generation on a single GPU. Our approach first augments a text-to-video model with mask input to generate high-quality videos that erase target objects and synthesize coherent backgrounds, but does not perform inference on the fly. As such, we progressively transfer the erasing capability from a powerful bidirectional foundation model to an efficient unidirectional streaming eraser, enabling long-horizon erasing without sacrificing visual fidelity. Several key challenges arise when generating videos over long, potentially infinite horizons: (1) bridging the domain gap from training on finite length and extrapolating to long horizons, (2) sustaining high quality by preventing error accumulation, and (3) maintaining fast inference, without increasing computational cost as the context grows. To address these challenges, we carefully designed sliding-window causal attention with attention sinks. By incorporating self-rollout with attention sinks and KV cache rolling during training, we simulate inference-time extrapolations with a fixed context window, enabling constant-speed generation of arbitrarily long videos. Finally, we establish a dedicated benchmark, LongErase, for streaming long-video object removal. Our model achieves strong performance compared to existing video object erasing models and generalizes well to real-world video scenarios, uniquely enabling infinite-length streaming. With StreamErase, users can input a mask and see the erasing results unfold in real-time, delivering a truly interactive experience.

---

### Seeing at the Edge: Energy Characterization of Vision-Language Model Inference on Edge Platforms

Authors: Junlin Liao, Harshit Kondle, Di Liu, Zonghua Gu
Published: 2026-10-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.20136v1

Vision-language models (VLMs) are moving onto edge devices, but little is known about how much energy they draw on single-board computers with NPU or GPU accelerators, or where that energy goes. We measure total-system energy, latency, and thermal behavior of Qwen2-VL-2B-Instruct and its text-only sibling on a Raspberry Pi 5 with a Hailo-10H NPU and on a Jetson Orin Nano Super, on both CPU and accelerator, and separate the fixed energy of each request from the energy that grows with output length. Because the accelerators use different quantization and serving software, we compare deployment stacks rather than silicon. Three findings stand out. First, NPU offloading makes the Pi a much more efficient VLM platform: it cuts energy per generated token by about two-thirds, leaves the host CPU largely free, and avoids the thermal throttling that the CPU backend reaches in sustained use. Second, an image adds both fixed and per-token energy, but at typical response lengths generating the answer costs far more than processing the image. Third, the Jetson GPU favors short responses through its lower fixed cost per request, whereas the Pi NPU favors longer ones through its lower cost per output token; their energy curves cross near 40 output tokens.

---

### DreamHMR: From Video Generation to Human Motion Modeling via Structural Focusing

Authors: Zhengjie Xu, Ruihao Gong, Xianglong Liu
Published: 2026-10-14
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2610.20124v1

Human mesh recovery (HMR) provides a geometric foundation for understanding human motion, but accurately reconstructing both body motion and fine hand articulation from videos remains challenging, especially in real-world scenes where occlusion and partial visibility are common. Video generation pretraining offers rich spatial and temporal priors for this task, but its focus on visual synthesis leaves a gap between these representations and explicit human geometry. We present DreamHMR, a general framework that adapts video generation priors for complete body-and-hand reconstruction. It follows a global-to-local strategy, first grounding video representations in human geometry and then refining body and hand detail with reliable local evidence. Global Body Representation Transfer trains the video backbone to predict complete human renderings, turning its native prediction task into a means of learning surface correspondence and posed geometry. Local Joint Feature Enhancement combines contextual estimates with reliable local evidence to recover fine body and hand detail, while limiting interference from occluders and background. Experiments on five datasets with four video backbones demonstrate strong reconstruction performance across backbone families. Under a unified evaluation protocol, our best model outperforms the best existing methods on all reported metrics of 3DPW, EMDB-1, and RICH, reducing body MPJPE by 4.2%, 4.7%, and 6.1%, respectively. In more challenging occlusion settings on held-out BEDLAM and EgoBody sequences, DreamHMR reduces overall body and hand MPJPE by 7.0% and 10.0%, respectively. Our code will be made publicly available.

---

### A Bregman Proximal Viewpoint on Neural Operators

Authors: Abdel-Rahim Mezidi, Jordan Patracone, Saverio Salzo, Amaury Habrard, Massimiliano Pontil, Remi Emonet, Marc Sebban
Published: 2026-10-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.20120v1

We present several advances on neural operators by viewing the action of operator layers as the minimizers of Bregman regularized optimization problems over Banach function spaces. The proposed framework allows interpreting the activation operators as Bregman proximity operators from dual to primal space. This novel viewpoint is general enough to recover classical neural operators as well as a new variant, coined Bregman neural operators, which includes the inverse activation operator and features the same expressivity of standard neural operators. Numerical experiments support the added benefits of the Bregman variant of Fourier neural operators for training deeper and more accurate models.

---

### KANLab: TensorFlow Playground for Kolmogorov-Arnold Networks

Authors: Lukas Niehaus, Robin Rawiel, Ulf Krumnack
Published: 2026-10-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.20117v1

KANLab is a browser-based visualization tool designed to interactively teach the core concepts of Kolmogorov-Arnold Networks (KAN), forked from the widely successful TensorFlow Playground. To maximize educational clarity, KANLab omits residual connections and learnable scaling parameters found in modern KAN implementations, ensuring that displayed B-spline activation curves directly correspond to their underlying trainable control points. Users can inspect and modify activation functions, initialization schemes and observe gradient descent correcting manual disruptions. Furthermore, user can explore phenomena such as activation variance, interactive pruning, and re\-/training within a compact 2D machine learning setting. KANLab is open-source and available at https://kanlab.app/

---

### Maximising Transparency in Context Compaction Improves Retention of Facts and Commitments for Lightweight Coding Agents

Authors: Felix Woolford
Published: 2026-10-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.20116v1

Long coding agent sessions outgrow the model's context window, so agents compact: older history is replaced by something shorter, usually a model-written summary. A summary selects and rewords, and the agent cannot see what was lost. Existing work has explored a range of compaction techniques, but comparatively little attention has been paid to their effectiveness with lightweight models, including those deployed locally or used for high-volume workloads. Here, we present transparent-compact, a simple deterministic method for the open-source Pi coding agent, designed specifically for use with such models and with the purpose of maximising the transparency of the agent's view of its own compacted context. It guarantees that user and assistant prose in its context is unchanged by a model or algorithm, and explicitly flags where compaction has stripped information. We compare it with Pi's default model-written summary compaction and with pi-vcc, a popular deterministic method with similar methods but without verbatim retention of prose. Our benchmarks run on four models of varying performance levels, with emphasis on Qwen3.8-27B: a lightweight model at the top end of what consumer hardware can serve locally. On sets probing commitments (rules the user set which exist only in the conversation) and recall of facts, transparent-compact matched or outperformed both alternatives. In particular, it showed an advantage in avoiding confident blunders, i.e. assertion of false information as opposed to recognizing that something was not recalled. Even with a frontier model, its advantage was present but smaller. We argue that transparent-compact spares lightweight models from reasoning or searching their way around what compaction lost, and results in improved recall and application of information as a result, without the need for task or context-specific structuring of the session history.

---

### ACR-Net: Mitigating Semantic Dominance via Contrastive Acoustic-Semantic Decoupling

Authors: Mengke Zhang, Yanda Shao, Tianhe Wu, Kai Feng
Published: 2026-10-14
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2610.20114v1

Speech Emotion Recognition (SER) models and Audio LLMs fail when vocal tone contradicts textual semantics. Extensive training on congruent data engenders a rigid semantic prior, causing "Semantic Dominance", a severe text bias during cross-modal conflicts. We introduce the ASPIRE benchmark of adversarial audio-text pairs across four conflict types, alongside two metrics: Semantic Overconfidence Penalty (SOP) and Latent Decoupling Degree (LDD). Unlike fusion methods that merely re-weight collapsed features, our Acoustic Conflict Resolution Network (ACR-Net) uses Cross-Modal Attention and Contrastive Decoupling Loss to disentangle contradictory representations into orthogonal latent spaces. Experiments show existing models fail under polarity conflicts due to extreme semantic overconfidence. Conversely, ACR-Net preserves acoustic fidelity, maintaining high LDD to drive SOP near zero, achieving superior Acoustic Accuracy (ACC) in both adversarial and standard scenarios.

---

### From Spectral to Frobenius: When Muon Loses Its Spectral Implicit Bias

Authors: Yongtao Wu, Mahdi Mansouri, Zhenyu Zhu
Published: 2026-10-14
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.20112v1

Prior work on implicit bias shows that gradient descent selects the Frobenius max-margin direction on linearly separable problems, whereas Fan et al. (2025) established spectral max-margin behavior for spectral-norm steepest descent methods, including idealized Muon with exact orthogonalization. In practice, however, Muon approximates orthogonalization using finite Newton-Schulz iterations and a positive stabilization constant. We prove that these implementation choices cause Muon to select the Frobenius rather than the spectral max-margin direction in linear classification with separable data. We also establish this behavior for both exponential moving average and Nesterov-style momentum. The key technical ingredient is a summable perturbation argument showing that the resulting parameter trajectories remain at bounded distance from those of gradient descent. We then disentangle the roles of Newton-Schulz iteration count, the stabilization constant, and the Newton-Schulz polynomial, revealing distinct asymptotic behaviors, including directions that achieve neither Frobenius nor spectral max-margin. Finally, we show that Muon can recover its spectral max-margin bias with Newton-Schulz iterations growing logarithmically over training.

---

### RepForcing: Representation-Space Initialization for Autoregressive Video Distillation

Authors: Siming Fu, Zheming Fu, Lianrui Mu, Haoyang Huang, Chaojie Gu, Ruizhe He
Published: 2026-10-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.20111v1

Distilling pretrained video diffusion models into few-step autoregressive (AR) generators typically combines student initialization with distribution matching distillation (DMD). An intermediate AR teacher can provide causally compatible targets for ODE initialization. However, causally compatible targets alone do not ensure high-quality generation under a short sampling schedule. We analyze the posterior-mean predictions favored by direct latent regression and empirically find that causal ODE initialization alleviates blur but still leaves fine detail unresolved. To address this limitation, we propose Representation Forcing, which learns few-step causal initialization through representation-space supervision rather than intermediate-teacher trajectory regression. The student is trained with teacher forcing by comparing clean predictions and training targets through normalized features of a frozen video diffusion transformer. This phase reuses the synthetic videos generated by a bidirectional model for AR teacher training and replaces both teacher training and causal ODE distillation, without generating additional causal ODE trajectories. The subsequent asymmetric DMD procedure remains unchanged. Empirical results show that, at four sampling steps, RepForcing better preserves generation quality than intermediate-teacher-based initialization before DMD. After DMD, our four-step chunk-wise model improves VBench Total from 84.04 to 84.66 (+0.62 points) and VisionReward from 6.326 to 10.074 (+59.25%) over the reported causal-ODE-based baseline.

---

### Exhaustive Canonical Skeletons Generation: A Formal Dataset for Decomposable Symbolic Regression

Authors: Giorgio Morales, Anikó Ekárt
Published: 2026-10-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.20108v2

Neural symbolic regression (SR) models require diverse datasets of mathematical expressions for robust training. However, existing datasets rely predominantly on stochastic sampling methods, which suffer from high structural redundancy and incomplete functional coverage. To address this, we introduce an exhaustive dataset of univariate canonical skeletons generated via a deterministic constrained context-free grammar. A canonical skeleton acts as a generic structural representation that subsumes more specific functional forms, eliminating redundant expressions and avoiding repeated computational efforts. Although our dataset consists of univariate skeletons, it is designed to support the decomposable SR paradigm to solve multivariate SR problems without assuming linear separability. Furthermore, we pair this dataset with a sampling strategy that generates clean numerical data without triggering numerical instabilities or relying on artificial protected operators. Canonicalizing two existing neural SR datasets reveals that our dataset is substantially more compact, eliminates structural repetitions, and achieves a uniform operator distribution free of simplicity bias. Finally, we establish a benchmark of 150 SR problems across three tiers, on which state-of-the-art SR methods are shown to struggle significantly.

---

### Why Generate a Click? Plug-in Decision Heads for Web Agents

Authors: Chengguang Gan, Yunhao Liang, Hanjun Wei, Qinghao Zhang, Zhixi Cai, Shiwen Ni
Published: 2026-10-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.20107v1

Web agents built on vision language models decide every action by generating text such as click(12), although most of that text encodes a choice among a few action types and a few dozen marked elements. We read these choices directly from the hidden states that the generator computes while it reads the goal and the screenshot. Plug-in decision heads on a frozen generator predict the action type, pool the visual tokens inside each numbered box to pick the target, and point at a listed text option or at a WRITE slot that leaves the writing of new text to the generator. A confidence cascade executes the heads' action when they are sure and otherwise lets the generator decode from the KV cache of the same forward pass. With Qwen3-VL 4B and 8B generators trained on 213k web steps, a strict threshold keeps the cascade between 0.3 points below and 1.4 points above the generator on seven offline test sets while the heads decide 12 to 64% of the steps. A looser threshold raises step success on unseen Mind2Web websites by 3.1 and 1.8 points, costs up to 2 points on GUIAct and MiniWoB++, and lifts WebArena task success from 12.5 to 13.8% (4B) and from 13.6 to 14.6% (8B) with less than half of the generated tokens. Training the heads jointly with the generator lowers the generator's own step success by up to 4.9 points; heads on a frozen generator avoid this cost.

---

### What Do Foundation Models for Market Microstructure Learn? A Controlled Study with Synthetic Limit Order Books

Authors: Fernando Acero
Published: 2026-10-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.20104v1

Autoregressive transformers trained on limit order book (LOB) message streams are increasingly proposed as foundation models for market microstructure. Because the generative process of real markets is unknown, these models can be judged only by the realism of their output, leaving open what they actually learn. We make the question answerable by inverting the setup: we train GPT-style models on order flow from simulators whose latent parameters are known, so that the Bayes-optimal predictor, the generating state, and the exact data entropy serve as references. Measured against them, next-token pretraining on order flow implements amortized Bayesian inference over market regimes. The learned predictive matches the exact Bayes optimum to within a millinat per token and approaches the oracle floor even on a nonstationary family whose latent state drifts within an episode, a regime that requires filtering. The latent regime is linearly decodable from frozen activations, well above baselines, so a frozen-model read-out calibrates simulator parameters more accurately than windowed maximum likelihood at a fraction of the cost. In our experiments these capabilities are not produced by scale: capacity and token volume saturate early, and it is the diversity of training regimes, not the token count, that determines generalization to unseen markets. On real NASDAQ data, zero-shot transfer is set by how well the simulator prior covers real flow: an enriched mixture nearly closes the gap to an in-domain baseline, and pretraining beats from-scratch training at every budget across held-out tickers. Known ground truth turns average next-token loss, which is uninformative near the entropy floor, into an exact comparison against the Bayes-optimal and oracle predictors.

---

### Language Exposure Matters: Distribution and Order in Multilingual BabyLM Pre-training

Authors: JiWoo Hwang, Lukas Edman, Alexander Fraser
Published: 2026-10-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.20102v1

We investigate two aspects of multilingual pre-training with limited data, namely how language exposure is distributed across English, Dutch, and Chinese, and how that exposure is ordered during training. In particular, we compare balanced multilingual exposure to language-dominant exposure, where one language is exposed with more training data than the others. We also compare mixed training, where multilingual training data is used throughout training, with curriculum training, where monolingual exposure of the dominant language is followed by balanced multilingual exposure. Our results show that multilingual BabyLM performance varies with both the amount and order of language exposure. Mixed training outperforms curriculum learning across all 15 matched configurations, indicating that simultaneous multilingual exposure is more effective than staged exposure in our setting. Several language-dominant mixed training configurations achieve higher scores than the balanced configuration, suggesting that a balanced distribution is not necessarily the highest-performing configuration in our setting. Interestingly, the Dutch-primary configurations achieve the best overall performance.

---

### Task-State Governance: A Virtual Machine for Verifiable and Recoverable GUI Agent Execution

Authors: Wenkui Yang, Yiming Hao, Kai Zhou, Chengyu Pu, Yuzhe Zhang, Jie Cao, Jin Huang, Shuai Ma, Feng Tian
Published: 2026-10-14
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2610.20100v1

Graphical user interface (GUI) agents now execute workflows across real applications, but when execution drifts, users must determine what changed, what should have remained untouched, and what can still be recovered. Plan-centric interfaces leave users supervising procedure, but users live with changes to application state. We introduce task-state governance, an interaction paradigm that represents a task as an editable contract linking desired outcomes, facts that must be preserved, and observed application state. We instantiate this paradigm in TaskVM, which projects live state into editable task controls, executes user edits as genuine interface actions, verifies outcomes through independent observation, and marks each action as reversible, compensatable, or irreversible. Across an automated contract benchmark, a controlled user study, and an open live-model exploration, the paradigm strengthened contract compliance and users' recovery control and trust, while execution outcomes were held constant. Task contracts open a design space for governable agent interfaces.

---

### EvalBuilder: Can LLMs Build Efficient Benchmarks?

Authors: Huaisheng Zhu, Hangfan Zhang, Teng Xiao, Siyuan Xu, Shijie Zhou, Zhimeng Guo, Zhengyu Chen, Jingang Wang
Published: 2026-10-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.20099v1

Large language model (LLM) agents are increasingly used for long-horizon research and engineering, yet evaluating these capabilities remains expensive, time-consuming, and heavily dependent on human expertise. This motivates a natural question: can LLM agents themselves construct efficient benchmarks that preserve the conclusions of costly reference evaluations? We study this capability by formulating automatic benchmark development as a meta-evaluation problem, where an agent is given a task and an expensive reference benchmark and requested to construct a lower-cost proxy benchmark that faithfully distinguishes among candidate models and solutions. Based on this formulation, we introduce EvalBuilder, a framework for evaluating such benchmark-generation capabilities along three key dimensions: fidelity, efficiency, and robustness. Specifically, we assess whether generated benchmarks preserve model rankings, generalize to held-out models and freshly collected responses, and provide well-calibrated and discriminative scores while substantially reducing evaluation cost. We further provide an iterative environment in which agents can refine their benchmarks under a fixed time budget. Our framework provides a systematic testbed and benchmark for understanding when current LLM agents can develop useful evaluators and how benchmark construction itself can be increasingly automated.

---

### RTAformer: Relation-Transition-Aware Transformer for Video Scene Graph Generation

Authors: Jaeyeon Heo, Geuntaek Lim, Yukyung Choi
Published: 2026-10-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.20091v1

Video scene graph generation (VidSGG) aims to capture objects and their evolving relationships in videos. This requires accounting for both the persistence of object identities and abrupt changes in relationships. Existing methods aggregate information across frames to exploit temporal context, but an emphasis on consistency can obscure these changes. As a result, a model may retain its previous prediction even after the underlying relation has changed. We refer to this failure mode as relational semantic inertia. To address this issue, we propose Relation-Transition-Aware Transformer (RTAformer), a one-stage framework that separately models entity persistence and relation changes. It injects calibrated differences between adjacent-frame relation queries to guide predicate updates, while cross-frame instance alignment during training helps reduce cross-frame representational drift. Experiments on Action Genome show improvements in recall and mean recall over existing methods, with ablation studies supporting the contributions of the proposed components and comparisons using matched backbones showing larger gains on relation-transition frames than on non-transition frames.

---

### When Pairwise Preferences Cycle: A Reliability-Anchored Preference Walk for Video GRPO

Authors: Xinrui Lin, Fan Li, Shumin Wang, Dehong Kong, Yanyong Zhang
Published: 2026-10-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.20089v1

Pairwise preference feedback has become a widely adopted supervision signal for reinforcement learning in video generation models, as pairwise comparisons provide a more reliable alternative than pointwise scalar ratings for evaluating the quality of generated videos. Specifically, we define a preference graph for each GRPO group under a pairwise evaluator, where nodes represent sampled rollouts and edges encode pairwise preferences. Auditing 6,976 on-policy comparison graphs, we find that cyclic preferences are prevalent and persist throughout training. Naive pairwise reward aggregation based on average win rates discards the underlying comparison structures and treats each rollout independently, which may introduce unreliable advantage estimates for certain rollouts and consequently affect reinforcement learning optimization. Therefore, we propose the \emph{Reliability-Anchored Preference Walk} (\ours{}), a graph-aware advantage aggregation method that strengthens the global preference signal from win rates with reliable relational evidence from cyclic preference graphs through a reliability-guided preference walk. Under matched evaluator, comparison protocol, group size, prompt schedule, and query budget, \ours{} requires no additional evaluator queries beyond the observed comparisons within each rollout group and improves over Pairwise-GRPO across controlled comparisons, transfer settings, and blind human evaluations.

---

### AFCS: Atomic-Fact-Conditioned Synthesis for Factual Knowledge Pretraining

Authors: Yunhao Wang, Feng Zhang, Tinghao Yu, Xing Wu, Jiang Zhou
Published: 2026-10-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2610.20086v1

Synthetic data is increasingly used in language-model pretraining. Existing knowledge-corpus synthesis pipelines, including WRAP and Nemotron-CC, usually take a source passage or document segment as input and generate rewritten or QA-style samples from that text. This can improve surface form and prompt diversity, but it does not explicitly require fine-grained source facts -- especially secondary entities, list/table entries, and precise temporal attributes -- to appear in the synthesized corpus. We propose AFCS (Atomic-Fact-Conditioned Synthesis), a pipeline that first extracts source-supported atomic facts and then uses each retained fact to drive generation. AFCS uses structure-aware extraction over the document tree, source-grounded verification, local context expansion, and multi-format generation. In continued-pretraining experiments with OLMo-3-7B and a 32B base on the same FineWiki source corpus, AFCS outperforms WRAP and Nemotron-CC on SimpleQA, SimpleQA Verified, PopQA, and HotpotQA. Granularity ablations show that fact-level synthesis improves over chunk-level, paragraph-level, and entity-level synthesis; and a 100B-token mid-training integration improves factual benchmarks and raises the 12-task general benchmark average by +1.09.

---

### Designing Textual Interfaces To Enhance Llm Reasoning On Audio-Visual Question Answering

Authors: Yi Wang, Tianzi Wang, Tong Lei, Dahan Wang, Peter Bell
Published: 2026-10-14
Categories: cs.AI, cs.CL, eess.AS
arXiv: https://arxiv.org/abs/2610.20085v1

Automatic prompt optimization (APO) has shown strong effectiveness for text-based LLMs and LLM systems, but its application to audio-visual understanding systems requires suitable textual interfaces through which multimodal reasoning can be exposed to text-based optimizers. We investigate how the design of textual interfaces affects prompt optimization for multimodal reasoning, on the audio-visual question answering task. We compare three interface designs, including a direct inference system consisting of a single omni-modal large language model (OmniLLM), a captioner-reasoner system, and an agentic architecture in which a primary agent orchestrates subagent OmniLLMs. Experiments with Qwen3-Omni and Gemini show that direct prompt optimization provides model-dependent gains; the captioner-reasoner system and the agentic system expose more interpretable optimization interfaces but are harder to optimize, where error analysis of cases affected by optimization is conducted. Our study highlights textual interface design as an important factor in making prompt optimization effective for omni-modal reasoning systems. Our implementation details are specified in GitHub repo.

---

### VisualWorldBench: A Fine-Grained Multi-Task Benchmark for Evaluating Visual World Knowledge in MLLMs

Authors: Chen Chen, Zheming Liang, Jiaqi Wang
Published: 2026-10-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.20083v1

Visual world knowledge is a core capability of multimodal large language models (MLLMs), underpinning knowledge-intensive visual question answering and fine-grained visual reasoning. However, existing benchmarks remain limited in two key respects. First, their category coverage is narrow: most benchmarks span only a small number of categories across a few domains, falling far short of the open-ended scale of real-world visual entities. Second, their task construction is often insufficiently rigorous: models can answer correctly using coarse-grained cues, vague associations, or elimination strategies without truly mastering precise concepts, making it difficult to accurately assess their knowledge of fine-grained entities. We introduce VisualWorldBench, a taxonomy-grounded multi-task benchmark built on a hierarchical taxonomy of 21,291 leaf-node classes across 8 visual domains, with 32,541 evaluation instances whose ground-truth labels cover 15,479 categories across four complementary tasks: closed-set recognition, contrastive selection, precise localization, and open-world naming, covering different directions of knowledge retrieval and varying degrees of answer openness to comprehensively evaluate visual world knowledge. Most questions are constructed from taxonomically proximate categories, forcing precise discrimination among fine-grained entities. Experiments reveal that the strongest closed-source model achieves only 80.4% average accuracy, exposing capability gaps hidden under conventional benchmarks. We further construct VisualWorldBench-50K, a training resource covering 50K+ categories. Fine-tuning on VisualWorldBench-50K yields over 21 percentage points improvement on VisualWorldBench, with consistent transfer to public fine-grained recognition and visual knowledge benchmarks.

---

### A Large-Dimensional Analysis of Least-Squares Federated Learning via Generalized Total Variation Minimization

Authors: Ekkehard Schnoor, Malik Tiomoko, Alexander Jung
Published: 2026-10-14
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2610.20075v1

Federated learning over decentralized networks inherently trades off the suppression of local finite-sample noise through collaboration against the bias that collaboration introduces between heterogeneous nodes. We study this tension by performing a large-dimensional analysis of Generalized Total Variation Minimization with least-squares models. Using tools from random matrix theory, we show that Lipschitz observations of the global GTVMin solution concentrate in large dimensions, universally for any underlying network structure. We provide exact analytic expressions for the asymptotically precise performance under both i.i.d. and non-i.i.d. Gaussian mixture distributions on a fixed network. For the latter, these expressions quantify how regularization balances local adaptation against collaboration. Our theoretical results are confirmed by experiments on synthetic and real-world data.

---

### Feasibility of a Patient-Specific Digital Twin for Ventriculoperitoneal Shunt Trajectory Planning

Authors: Kritsanavis Chongsrid, Vich Yindeedej, Supaporn Konmun, Xulei Yang, Si Yong Yeo
Published: 2026-10-14
Categories: cs.CV, q-bio.QM
arXiv: https://arxiv.org/abs/2610.20074v1

Catheter obstruction is the commonest cause of shunt failure; freehand insertion at Keen's point leaves the tip free in cerebrospinal fluid in only one case in ten. We built a digital twin that reconstructs skull, scalp, ear and ventricles from preoperative CT by deterministic geometry, searches every entry around Keen's point for the perpendicular trajectory with the longest intraventricular length under safety constraints, and returns the plan as two ruler measurements from the ear and two depths. Executed freehand in 11 consecutive adults (IDEAL Stage 2a), it achieved Hayhurst Grade 1 placement in 10 of 11 against 22 of 213 historically (p = 9 x 10^-9), median entry and angular deviations 2.5 mm and 5.9 degrees, 1.4 cm more intraventricular catheter than Keen's point, and no intraoperative complication. The technique was unchanged; the gain came from choosing entry and depth per patient. Whether it lowers revision is the next stage's hypothesis.

---

### GDBA-Net: A Gated Dual-Branch Adaptation of SAM2 for Robust Cross-Domain Nuclei Segmentation

Authors: Biplab Poudel, Betserai Albert Magarire, Anish Kumar Shah, Jiacheng Xie, Dong Xu
Published: 2026-10-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.20073v1

Accurate nuclei segmentation underpins quantitative computational pathology, yet remains challenging due to morphological variability, weak boundaries, nuclear crowding, and pronounced domain shifts arising from differences in tissue preparation, staining, and acquisition. While deep learning and recent foundation models have improved segmentation performance under matched distributions with the original training data, their generalization across heterogeneous histopathology domains remains limited. We introduce GDBA-Net, a parameter-efficient nuclei segmentation framework built around the proposed Gated Dual-Branch Adapter (GDBA). GDBA-Net adapts a frozen SAM2 encoder by integrating pretrained semantic representations with explicit frequency-derived structural priors. The complementary representations are independently transformed through Grid MLP branches and dynamically integrated using sample-adaptive channel-wise gating, selectively emphasizing structural cues relevant to nuclear delineation. Despite using only 4.3 million trainable parameters, GDBA-Net achieves state-of-the-art in-dataset performance and consistently superior cross-dataset generalization across six diverse nuclei segmentation benchmarks under fully supervised, cross-dataset, and five-shot adaptation protocols, outperforming competing CNN-, transformer-, and foundation model based methods. Comprehensive ablations confirm that these gains arise from the coordinated design of semantic-frequency complementarity and adaptive gating rather than increased model capacity. By uniting transferable semantic representations with explicit structural priors, GDBA-Net provides a robust, annotation-efficient solution to domain variability in nuclei segmentation. https://github.com/biplabpoudel25/GDBA_Net

---

### Rethinking Prediction Horizons: Decoupling Model Queries from State Updates in Few-Step MeanFlow

Authors: Tinglan Wang, Haixu Liu, Shaobo Chen, Nuo Qian, Qi Gao, Kai Wen, Yu Yao
Published: 2026-10-14
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.20071v1

MeanFlow predicts interval-average velocities, but conventional few-step sampling ties the interval queried from the model to the duration of the state update. We separate these two quantities at inference, fixing the model, update grid, and number of queries while varying the prediction horizon. Our central finding is that the horizon response depends on both query position and the states entering that query. Across seven independently trained CIFAR-10 checkpoints at classifier-free guidance (CFG) scale 2, a longer horizon worsens FID at early steps but improves it at the midpoint. To probe whether query time alone determines this response, we fix the midpoint query and current/subsequent guidance while changing only earlier CFG. In held-out factorial outcomes on five previously studied checkpoints, the mean midpoint horizon benefit increases from 0.109 to 1.308 FID, indicating sensitivity to the incoming-state distribution. A frozen four-query rule reduces mean CIFAR-10 FID by 2.023 without retraining or extra queries, including gains on five checkpoints trained after rule selection. A milder rule also improves mean FID by 1.041 on a stronger frozen grid, with fixed-rule FID gains on the evaluated public ImageNet-256 and AFHQ checkpoints. However, matched-budget calibration favors query-start shifting in historical CIFAR tests, and the tested Horizon allocation adds no FID benefit beyond Grid+Start on two public ImageNet models. Thus, prediction horizon is a distinct, position- and state-sensitive inference control, but not a universally preferred one.

---

### Trainable at Depth, Solvable at Small Size: What the Loss Surface of a Polynomial Activation Dictates for Designing, Initializing and Training Networks

Authors: Xiuyi Yang
Published: 2026-10-14
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.20069v1

What makes a deep network train, and what shape is its loss surface? We answer both with one construction at two scales: a polynomial activation f (z) = z + λz 3 , clamped and projected onto the unit sphere, plus an unnormalized identity path. As a deep stack it trains to one hundred layers on MNIST with no normalization machinery; as a small model its square loss is a polynomial system we solve exactly. The small scale explains the large one: it prescribes how to design, initialize and train the stack.

---

### Which Knowledge Should LLMs Trust? Uncovering a Generalizable Steering Direction Across Knowledge Conflicts

Authors: Yibin Lou, Yi Hu, Jianhui Chen, Chenpeng Wang, Muhan Zhang, Liangming Pan
Published: 2026-10-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2610.20067v1

Large Language Models (LLMs) frequently encounter conflicts between internal parametric knowledge and external contextual knowledge, yet the mechanisms governing this selection remain unclear. We show that the choice between context and parametric knowledge is linearly represented and can be controlled along a single direction in the model's residual stream. We first demonstrate that this direction generalizes across factual-conflict settings, including context formats, knowledge categories, and datasets, while consistently shifting behavior between parametric and contextual answers. We then transfer a direction learned from simple factual conflicts to three more complex task families: RAG, memory, and rule following, where models must acquire information from retrieved documents, interaction histories, or explicit rules. Across four model families and multiple transfer settings, steering consistently improves the use of prompt-provided information over the unsteered model. These results suggest that the direction captures a transferable preference for external knowledge rather than a mechanism specific to factual conflicts.

---

### FoveaVLA: Foveation Actions Replace the Wrist Camera in VLAs

Authors: Bingao Chen, Lihan Zha, C. Karen Liu, Guy Tevet
Published: 2026-10-14
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2610.20064v1

We present FoveaVLA, a Vision-Language-Action (VLA) model that replaces the wrist camera with learned foveation actions. Wrist cameras provide close-up detail but restrict the view to the end-effector's surroundings. External cameras see the whole scene, but the policy receives them at low resolution, so the fine detail needed for manipulation is lost. FoveaVLA recovers this detail by predicting, alongside each action chunk, the interaction region to observe at the next policy query. The policy then receives crops of these regions, taken from the original-resolution images, together with the full views. We build FoveaVLA on $π_{0.5}$ in two configurations, Single and Dual, using one or two external stereo cameras with full and foveal RGB and depth inputs, and post-train both on DROID with RoboInter interaction annotations. Across four real-world task suites, FoveaVLA-Single achieves 70.8% success with one external RGB-D view, and FoveaVLA-Dual achieves 77.1%, versus 52.1% for the wrist-equipped $π_{0.5}$. Both match the baseline on plain pick-and-place and improve success with distractors, cloth manipulation, and far-away objects.

---

### Beyond Correctness: Compute-Responsive Data Selection for Reasoning Model Post-Training

Authors: Liang He, Xiangyu Li, Yuxin Wang, Hanbin Zhang, Mingyu Cao, Zhaomiao Guo, Xilu Wang
Published: 2026-10-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.20057v1

Reasoning language models increasingly rely on test-time compute scaling, yet most existing work studies how to allocate inference computation while treating the model itself as fixed. We ask a complementary question: can reasoning models be post-trained to make better use of a given amount of test-time compute, and which examples are most useful for this goal? Our key observation is that reasoning problems differ substantially in their response to additional computation. Some are already solved under limited compute, others remain unresolved even after further reasoning, while a distinct subset changes from complete initial failure to success when additional reasoning is provided. We call these compute-responsive (CR) examples and introduce Compute-Responsive Data Selection (CRDS), a post-training data-selection principle that prioritizes examples with empirically demonstrated marginal utility from additional reasoning. On Qwen3-8B, SFT on CR examples recovers 45.3\% of held-out low-compute failures, compared with 40.6\% when training on already-solved examples. The advantage extends beyond the selected CR split: SFT-CR reaches 51.8\% overall accuracy on an independently sampled test distribution, with the gain concentrated on compute-responsive problems. CR training also shifts the compute--accuracy frontier across inference budgets from 512 to 4,096 tokens, outperforming matched non-CR training throughout and reaching 48.1\% recovery at the largest budget. The same pattern is supported across multiple data sources, remains visible under on-policy distillation, and extends to Llama-3.1-8B-Instruct when CR sets are reconstructed separately for that model. Better test-time compute utilization can therefore be learned through post-training, with recoverable responses to additional reasoning providing a particularly informative signal for selecting training examples.

---

### GeoCloak: An Agentic Framework for Semantics-Preserving Geolocation Privacy via Peripheral Clue Manipulation

Authors: Yixin Wu, Mingjie Li, Yun Shen, Michael Backes, Yang Zhang
Published: 2026-10-14
Categories: cs.CV, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2610.20055v1

The rapid advancement of large vision language models (LVLMs) has made geolocation inference from images highly accurate and accessible. This poses serious privacy risks: a passive adversary with black-box LVLM access can infer a user's location from a single photo with no metadata. Existing protection methods rely almost exclusively on adversarial perturbation, which introduces perceptible visual artifacts and utility degradation. We identify the visual-geolocation asymmetry: geolocation-decisive clues, such as street signs, tend to be visually peripheral but dominate location inference. Exploiting this asymmetry, we propose GeoCloak, an agentic framework for semantics-preserving geolocation privacy protection. It acts as a clue-aware planner that analyzes each image to identify geolocation-relevant clues, dispatches targeted semantic edits to directly suppress peripheral clues, and autonomously configures adversarial perturbation to further suppress residual geolocation features, all under iterative utility-aware feedback. We evaluate GeoCloak on four diverse datasets spanning 108 countries and 576 cities against five LVLMs and three inference methods. GeoCloak reduces overall city-level accuracy from 41.2% to 9.9%, approximately half of the best-performing baseline, while achieving substantially superior utility preservation both qualitatively and quantitatively. We hope this work takes a meaningful step toward practical, semantics-preserving geolocation privacy protection, giving users greater control over the location information inadvertently embedded in their shared images.

---

### GBTSVR: Twin Support Vector Regression via Granular Ball Computing

Authors: A. Quadir, M. Tanveer
Published: 2026-10-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.20053v1

Regression models used in real-world applications are often challenged by noise, outliers, data heterogeneity, and asymmetric error characteristics, which severely limit the effectiveness of conventional point-wise learning models. While twin support vector regression (TSVR) partially addresses these issues through the use of nonparallel regression bounds, it still relies on individual samples as basic learning units. As a result, TSVR remains highly sensitive to noisy and contaminated observations and fails to leverage the underlying structural and regional information inherent in complex datasets, leading to suboptimal robustness and generalization performance. To address these limitations, we introduce granular ball twin support vector regression (GBTSVR) and its quantile extension, granular ball twin support vector quantile regression (GB-TSVQR). The proposed models integrate granular ball computing with TSVR, replacing individual data points with compact, structure-preserving granular balls as fundamental learning units. This region-level representation effectively suppresses noise and outliers while preserving intrinsic data geometry, thereby enhancing robustness, stability, and generalization. GBTSVR constructs nonparallel lower- and upper-bound regression functions over granular balls, significantly reducing sensitivity to sample-level perturbations. Building upon this framework, GB-TSVQR further incorporates quantile regression principles to simultaneously capture heterogeneous trends and asymmetric error distributions across different quantile levels. Extensive experiments on synthetic datasets, time-series benchmarks, and outlier-contaminated data demonstrate that the proposed GBTSVR and GB-TSVQR consistently outperform state-of-the-art regression models.

---

### What Is a Clarification? Estimating Model-Dependent Input Ambiguity

Authors: Jingqin Tang, Tim Tomov, Sebastian Schmidt, Dominik Fuchsgruber, Stephan Günnemann
Published: 2026-10-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.20052v1

Ambiguous inputs can admit multiple interpretations, each potentially yielding a different answer. Existing work largely treats this ambiguity as a property of the input, yet for a particular language model, only some alternatives may be known and answerable. We therefore distinguish world ambiguity, capturing all alternatives admitted by an input, from model ambiguity, capturing those accessible to the responding model. To characterize these alternatives, we formalize natural-language clarifications through three desiderata: \emph{uniqueness}, \emph{faithfulness}, and \emph{answer equivalence}. We show that these desiderata induce a one-to-one correspondence between valid answers and equivalence classes of clarifications, implying that any interpretation can be represented either by its answer or by the clarifications that uniquely express it. We leverage this correspondence to introduce \circleclar{}, a black-box method that estimates the set of answers available to a model by checking consistency along an answer--clarification--answer cycle. Across open-domain QA and executable Text-to-SQL, \circleclar{} achieves strong recovery of these answer sets. In QA, the recovered support yields the strongest overall performance in model-dependent ambiguity detection and enables effective selection among answering, clarifying, and abstaining. Together, these results demonstrate the practical value of a model-dependent view of ambiguity and its characterization through an answer-clarification correspondence.

---

### FACES: Fine-grained Gated Semantic Alignment for Multimodal Emotional Support Conversation

Authors: Hang Ren, Peidong Wang, Yichen Gao, Wen Zhang, Jiayang Yu, Xiaocui Yang, Shi Feng
Published: 2026-10-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.20051v1

In recent years, with advances in multimodal interaction technologies and the growing demand for intelligent emotional support, Multimodal Emotional Support Conversation (MESC) has emerged as an important task. However, existing systems still suffer from shallow responses and inappropriate support strategies due to weak semantic feedback, cross-dimension reward compensation, and coarse reasoning supervision. To address these challenges, we propose FACES, a fine-grained gated semantic alignment framework for MESC. Specifically, FACES integrates multi-source rewards to construct multidimensional semantic and functional alignment signals, employs a non-compensatory gated fusion mechanism to reduce cross-dimension reward offset, and leverages structured Chain-of-Thought (CoT) anchors to perform token-level credit assignment. Under a controlled response-length protocol, FACES improves the average MLLM-based evaluation score from 3.61 to 4.04 and achieves an 80.22% pairwise win rate over SOTA. Human evaluation under the same protocol yields a 75.3% preference rate. Results on three external datasets further support transferability. The code and dataset are available at https://github.com/OCT-ARR/arr.

---

### CoRedSkill: Stealthy Skill Composition Attacks via AST-Guided Injection

Authors: Qichen Zhao, Shengfang Zhai, Qingni Shen, Zhonghai Wu, Jiaheng Zhang
Published: 2026-10-14
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2610.20049v1

Agents extend their capabilities through reusable skills that package instructions, executable code, and resources. Composing these skills enables complex task workflows, but their dependencies can also connect malicious operations across skills, making their combined intent difficult to identify through individual-package auditing. We introduce CoRedSkill, a compositional red-teaming method that forms stealthy attacks through cooperating skills while preserving their original utility. CoRedSkill decomposes an existing workflow into interdependent skills and embeds attack operations in task functions through abstract syntax tree (AST) rewriting, with skill instructions guiding the agent to autonomously select and invoke the relevant skills, and workflow dependencies and intermediate artifacts connecting the injected operations during task execution. We construct a benchmark of 150 cases covering 50 tasks and three attack objectives to evaluate attack success, task completion, and audit detection. In the main evaluation, CoRedSkill achieves 98.0% attack success and 95.3% task success with a 3.3% detection rate, and a joint success rate of 90.7% (attack success, task completion, and audit evasion in the same case) compared with 6.7--42.7% for the four baselines. Skill compositions can therefore complete legitimate tasks while carrying out unauthorized operations that evade auditing.

---

### Sequential Learning-Based Physics-Informed Neural Network Modeling for Parameter Estimation on a Power Converter

Authors: Samuela Rokocakau, Panagiotis Kakosimos, Giulia Tresca, Pericle Zanchetta
Published: 2026-10-14
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2610.20041v1

A staged physics-informed neural network (PINN) is proposed for identifying the inductance, capacitance and parasitic resistances of a DC buck converter from time-domain data. Gradients are released in the order of L to C to rL to rC, a sequence derived from sensitivity analysis. The five-stage schedule recovers L and C to within 5% and the series ESR to 10%, while a three-stage variant attains the same accuracy 11% faster. An 84 factorial sweep confirms that the trained PINN remains accurate for simultaneous 8% perturbations of all four components, achieving a waveform RMSE of 2.6 x 10-2 over 5 ms-an order-of-magnitude better than a simultaneous-training baseline.

---

### SWE-Nexus: Automated Composition of Software Engineering Tasks from Test Execution

Authors: Songwei Yu, Ziqi Miao, Jingxuan Xu, Junhao Fan, Haoyang Huang, Yuan Xiong, Zihang Xu, Weihao Li, Wenqiang Zhu, Yuechen Luo, Xinshun Feng, Yanan Wu et al.
Published: 2026-10-14
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2610.20038v2

Historical code changes provide convenient task boundaries, but do not identify which production functions selected tests exercise or support composing validated behaviors beyond a single change. We present SWE-Nexus, a fully automated pipeline that constructs repository-level implementation tasks from test execution. Four construction agents select tests, adapt tracing and evaluation protocols to each repository, and generate behavioral specifications. For each selected test file, tracing records an observed execution footprint of production function bodies. A scope is retained only if all expected scoring points pass in the original repository and masking the traced bodies causes at least one failure or error. Compatible scopes are composed deterministically, with shared functions counted once and every constituent test file revalidated under the complete combined mask. The benchmark contains 600 tasks from 105 repositories across six programming languages, including 116 atomic and 484 composite tasks. We evaluate 12 models under three agent scaffolds. The best configuration resolves 37.8% of tasks in one attempt, and scope-weighted scoring measures partial recovery. SWE-Nexus enables task construction from validated behavior beyond individual historical changes.

---

### Weighted Adjoint Matching: Finetuning Flow Matching Models with Time-Dependent Control Cost

Authors: Eliot Beyler, Francis Bach
Published: 2026-10-14
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2610.20035v1

We introduce Weighted Adjoint Matching, a method to finetune a pretrained diffusion or flow matching model given a differentiable reward. We derive it from Adjoint Matching, which reformulates finetuning as a stochastic optimal control problem with a quadratic control cost. Building on the observation that these models generate coarse features before fine details, we place a time-dependent weight on the control cost. A high cost early in the generative process preserves balance and diversity in the coarse features, which carry most of the semantics, while a low cost at the end lets the model increase the reward by refining details. We prove that our method is equivalent to maximizing the reward under time-varying Kullback--Leibler regularization on the generative paths. Experiments on Gaussian mixtures and on MNIST show a better tradeoff between reward and mode balance than Adjoint Matching.

---