# Research Papers — 2026-10 · bundle page 103 of 156 > Full-text markdown of papers #5101–5150 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/103 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/102.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/104.md) ### EM-SNN: Efficiently Modulated Spiking Neural Network for Remote Sensing Image Dehazing Authors: Jie Shao, Jiaqi Ma, Wenwen Min, Beihang Song, Ning Chen, Youfa Liu, Jun Wan Published: 2026-10-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.09275v1 Although spiking neural networks (SNNs) provide an energy-efficient alternative to artificial neural networks (ANNs), their application to remote sensing image dehazing remains limited. A key challenge arises from the coupling between haze-induced high-frequency attenuation and discrete spike thresholding. This interaction suppresses weak responses and fundamentally limits the recovery of edges, textures, and fine details in spiking dehazing models. To address this challenge, we propose the Efficiently Modulated Spiking Neural Network (EM-SNN), a dedicated spiking framework tailored to remote sensing image dehazing. EM-SNN integrates a statistics-driven Threshold-Modulated Leaky Integrate-and-Fire (TM-LIF) neuron to adaptively compensate for haze-induced contrast compression, together with a Spike Sobel Modulation (SSM) module that enhances structural cues and reduces depth-wise attenuation during spiking feature propagation. By jointly modulating activation scales and structural representations, EM-SNN improves dehazing performance while preserving the inherent event-driven sparsity of SNNs. Experiments on HRSD, RICE, RRSHID, and SateHaze1K demonstrate that EM-SNN achieves competitive dehazing performance while consuming only one quarter of the energy of the strong ANN baseline SFRDP-Net. --- ### Hardware-aware Calibrated Clustered Attention for Efficient Visual Geometric Transformers Authors: Weitian Wang, Shubham Rai, Cecilia De La Parra, Akash Kumar Published: 2026-10-07 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2610.09274v1 The Visual Geometry Grounded Transformer (VGGT) marks a significant leap forward in 3D scene reconstruction, as it is the first model that directly infers all key 3D attributes (camera poses, depths, and dense geometry) jointly in one pass. However, this joint inference mechanism requires global attention layers with extremely long sequences that causes a significant latency bottleneck. In this paper, we propose blockwise clustered attention (BC attention) to accelerate the global attention layers in VGGT. By limiting the clustering within HW-friendly neighborhood blocks, BC attention reduces the computation overhead of query clustering as well as the costly data movement between on- and off-chip memory. This enables BC attention to scale to long sequences and deliver practical latency improvements on GPUs. Moreover, we introduce a hashing hyperplane calibration method and a threshold-based error compensation method to reduce clustering errors efficiently, which is a bottleneck in the current clustered attention mechanism. Overall, our experiments on GPU demonstrate that calibrated BC attention accelerates the global attention layers by 2.10-2.63$\times$ and the whole backbone by 1.77-2.35$\times$ with negligible loss (1%) for large scenes. With a small performance loss (< 5%), calibrated BC attention further achieves a 2.26-2.87$\times$ latency improvement on the global attention layers and a 1.90-2.55$\times$ improvement on the backbone. --- ### Evaluating Trajectory Features for Routing Final-Layer Attention Authors: Yupeng Yao Published: 2026-10-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.09272v1 Attention routing requires a signal that predicts the value of attention on the current prefix. We evaluate whether hidden-state extrapolation error, curvature and error change improve this prediction beyond uncertainty, one-step displacement, position and state projections. Paired executions of the final attention layer supply signed next-token loss differences in frozen SmolLM3-3B-Base and Qwen3.5-4B-Base checkpoints. Utility-supervised routers are tested on 100 held-out PG-19 books at an identical causal 20 percent invocation quota. None of six prespecified comparisons shows a positive gain after familywise correction. In Qwen3.5, a parameter-matched fixed-projection control lowers NLL by 0.00356 nats/token relative to the trajectory router (95 percent interval 0.00218 to 0.00487). Secondary results depend on the operation removed, feature location and scoring horizon; frozen thresholds also drift substantially at longer horizons. Actual selected-query execution yields small long-sequence latency reductions with increased NLL, while learned routers remain slower during cached continuation. The study identifies limits on the incremental value of these trajectory summaries and separates allocation quality from measured inference benefit. --- ### Package Hallucination Attacks on Coding Agents through Prompt Injection in Rule Files Authors: Yupu Wang, Zhengyuan Jiang, Reachal Wang, Neil Zhenqiang Gong Published: 2026-10-07 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2610.09264v1 Modern agentic coding frameworks increasingly rely on community-shared rule files (e.g., AGENTS.md or .cursorrules) to guide autonomous code generation, yet the security risks of this pipeline remain underexplored. To bridge this gap, we introduce the package hallucination attack, where an attacker injects malicious prompts into benign rule files to induce coding agents to replace legitimate dependencies with attacker-controlled packages. To obtain effective malicious prompts injected into rule files, we propose PackHallu, an evolutionary optimization framework that iteratively rewrites these injected prompts using trajectory-level feedback and LLM-guided mutations. Evaluations across multiple benchmarks, LLMs, and agent frameworks show that PackHallu achieves high attack success rates and strong transferability across diverse models and agent combinations. Our findings demonstrate that coding agents are vulnerable to package hallucination attacks, highlighting the urgent need for stronger security safeguards in autonomous coding systems. --- ### The Symbol of the Surrogate: Measuring Numerical Provenance in Neural PDE Solvers Authors: Ridham Patel Published: 2026-10-07 Categories: cs.LG, math.AP, stat.ML arXiv: https://arxiv.org/abs/2610.09255v1 Neural PDE surrogates are trained on numerical solver outputs that contain both physical evolution and solver-specific discretization errors. Because surrogates are also evaluated against held-out trajectories from the same solver, standard benchmarks cannot distinguish fidelity to the exact evolution from imitation of the numerical scheme. We introduce an empirical Fourier-symbol diagnostic that probes a trained surrogate's linearized one-step operator with individual Fourier modes and compares it with both exact-evolution and training-scheme references. To address architectural spectral bias, we train identical networks on schemes with orthogonal dissipative and dispersive signatures and compare their learned operators. In linear advection, the learned surrogates reproduce the training schemes' amplitude and phase errors, with the twin-scheme difference reaching more than 99.8\% of the analytically predicted full-imitation ceiling. The same behavior occurs for a non-local Fourier neural operator and at the operator level for nonlinear Burgers dynamics. These results show that agreement with solver-generated test data does not by itself establish fidelity to the exact evolution. Fourier-symbol measurements provide a direct diagnostic of numerical provenance. --- ### PhyDiCT: Plug-and-Play CT Reconstruction from Sparse X-Rays via Differentiable Rendering and Strong Priors Authors: Weicheng Dai, Shantanu Ghosh, Kayhan Batmanghelich Published: 2026-10-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.09253v1 Reconstructing 3D Computed Tomography (CT) images from a few X-ray projections is a highly ill-posed inverse problem due to the loss of volumetric information. We propose PhyDiCT, a training-free framework that integrates a differentiable Physics-based forward model, grounded in the Beer-Lambert law, with a text-conditioned Diffusion as a strong prior to reconstruct 3D lung CT images. We refer to our approach as training-free since the prior model is used without fine-tuning, and our goal is to steer the denoising procedure to generate samples consistent with X-ray observations. We guide the diffusion generation using Split Gibbs sampling to jointly optimize for projection fidelity (reward) and consistency with prior knowledge. Also, we introduce a test-time refinement step that enhances image realism and anatomical coherence. We extensively evaluate our method on publicly available 3D CT datasets using both perceptual and semantic metrics, demonstrating that it surpasses existing plug-and-play diffusion and fully trained reconstruction approaches. Our findings highlight that combining a strong generative prior with the underlying physics of image formation substantially improves reconstruction quality, e.g., 7.5\% improvement on SSIM compared to full training methods. Code will be released at https://github.com/batmanlab/PhyDiCT. --- ### Adaptive Visual Token Reduction for Accelerated Image Understanding Authors: Seyoung Jeong, Jong Pil Yun, Sang Jun Lee Published: 2026-10-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.09252v1 Large Vision-Language Models achieve strong VQA performance, but processing high-resolution, information-rich images requires substantial computation, motivating visual token reduction. However, existing methods often prune individual tokens or rely on fixed-size cropping, limiting their ability to preserve spatially structured information such as horizontally or vertically elongated text. To address this limitation, we propose ReFIT, an instruction-guided visual token reduction framework for efficient LVLM inference. ReFIT consists of Relevance-Guided Window Reshaping (RWR) and Instruction-Guided Token Refinement (ITR), where RWR captures instruction-relevant regions by adapting to their spatial characteristics, while ITR further removes unnecessary visual tokens. Experiments on four VQA benchmarks demonstrate that ReFIT improves answer accuracy while reducing computational cost, and qualitative results demonstrate its effectiveness in localizing relevant regions and removing unnecessary visual information. --- ### Efficient Best-of-N policy evaluation for inference-time alignment Authors: Jonas Schweisthal, Yuxin Wang, Athiya Deviyani, Stefan Feuerriegel, Dennis Frauen Published: 2026-10-07 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2610.09250v1 Best-of-N (BoN) is a common inference-time alignment method that selects the highest-scoring response among N samples from a reference model. Evaluating BoN policies from logged data is challenging under sample-only access because standard off-policy estimators require density ratios that depend on unavailable response likelihoods. In this paper, we propose a sample-only framework for evaluating and selecting BoN policies without access to these likelihoods. We show that the order-statistic structure of BoN allows the required density ratios to be expressed through score-rank probabilities that are estimable from samples alone. We then develop a doubly robust estimator of the BoN policy value (BoN-DR) that efficiently reuses a shared auxiliary sample pool across candidate budgets. We establish valid asymptotic inference even under reward estimator misspecification and prove the efficiency of our BoN-DR estimator. Since larger budgets can amplify errors in the score function and lead to reward overoptimization, we derive two selection rules: (i) maximizing the estimated policy value and (ii) maximizing a lower confidence bound on the improvement over the reference policy, which accounts for estimation uncertainty and provides a no-harm guarantee. Across synthetic experiments and GSM8K with multiple reference and reward models, our framework accurately estimates BoN policy values and selects effective sampling budgets. --- ### An Informational Curse of Horizon in Goal-Conditioned Policy Learning Authors: John L. Zhou, Yuxuan Dong, Jonathan C. Kao Published: 2026-10-07 Categories: cs.LG, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2610.09247v1 The difficulty of learning goal-reaching policies is often attributed to a "curse of horizon" that manifests as bias accumulation in temporal-difference backups and noisy advantage estimates. In this work, we identify an additional informational curse of horizon in goal-conditioned policy learning, where increasing the goal relabeling horizon can significantly reduce policy generalization and performance. Through a series of controlled experiments with oracle planners, we decouple the goal horizons sampled during training from those that the policy is asked to reach at test time. Even when evaluated only on a sequence of nearby subgoals, goal-conditioned behavioral cloning (BC) policies suffer from severe, training horizon-dependent performance degradation that is mitigated by reinforcement learning (RL) objectives. We explain this phenomenon as a horizon-dependent decrease in the conditional mutual information between actions and hindsight-relabeled goals, and find empirically that both BC and RL policies trained on longer-horizon goals exhibit a shift in sensitivity from goal to state information, as measured by the policy's input Jacobians. Motivated by this observation, we find that distilling the input Jacobians of short-horizon policies into long-horizon policies yields significant performance gains, especially in combinatorial manipulation tasks. Taken together, our results highlight goal relabeling horizon as an important consideration when learning generalist policies from offline data. --- ### Beyond Nominal Equilibria: Risk-Averse Multi-Population Mean-Field Games Authors: Bhavini Jeloka, Siddhartha Ganguly, Panagiotis Tsiotras Published: 2026-10-07 Categories: math.OC, cs.GT, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2610.09244v1 Recent advances in mean-field games and its multi-population variants enable large-scale heterogeneous multi-agent systems to be modeled through representative agents and their associated mean-field distributions. However, existing approaches do not explicitly account for uncertainty in the behavior of other populations. To this end, we introduce a new paradigm: risk-averse multi-population mean-field games, where each population optimizes a worst-case expected reward over dynamically feasible ambiguity sets of mean-field flows of a subset of the other populations. Employing an occupation-measure formulation along with tools from set-valued analysis, we establish, under mild assumptions, several theoretical properties of the multi-population game, including the geometric properties of the ambiguity sets and the existence of a novel risk-averse multi-population mean-field equilibrium. Further, we derive contractivity results of the fixed-point operator under entropy regularization and show that it can be utilized to learn the equilibrium. Finally, we propose a risk-averse fictitious-play scheme and show that exploitability decays to zero, despite the additional nonlinearity introduced by the worst-case objective. We report several numerical experiments to illustrate convergence and risk-averse behavior. --- ### We Query, Therefore We Compute: On Oracle Computation beyond the Machine, with an Application to Agents Authors: Kefan Liu, Fengning Ou, Yelin Luo, Jingdi Lei Published: 2026-10-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.09243v1 Agentic systems use large language models (LLMs) to carry out concrete tasks. Prior work often borrows abstractions such as scheduling, caching or isolation piecemeal from operating systems, so the mechanisms it builds share little common ground, and the shared view of the two forms of agentic system, Workflows and Agents, is limited. We construct an abstract machine that provides both. We treat the LLM as an Oracle and extend a two-stack pushdown automaton with one instruction, which hands the Oracle a whole stack as its query and appends the answer to that same stack. The machine thus performs two computations, the Oracle's and a Turing-complete one that we call the Priestess. A stack that the program only appends to grows autoregressively, as an agent's context does. Two symmetry breakings, S in storage and T in transitions, make a Priestess program the operating system of the programs the Oracle runs, and produce the Agent and the Workflow as the two placements of a task's program. For internally autoregressive Oracles, the two computations synchronize at the end of every answer under certain conditions, and through that synchronization we model caching and analyse scheduling. No guarantee that holds for every Oracle can fix which content crosses between the two computations, but such a guarantee does fix the boundary itself. The construction V fits the machine to a von Neumann computer. To show that it is realizable, we propose ArchNights, an extended RISC-V ISA and a Linux-style operating system implementing the machine by design. ArchNights-SE runs on gem5 as a computer system, becomes an agentic system when it runs an LLM as the Oracle, and will be open source. Agentic systems can then be designed as computer systems are. With a foundation built and a unified view, future work can share invariants and bounds, each with its conditions. --- ### Pooling Representation Autoencoders for Efficient Diffusion Authors: Ramón Calvo-González, Youssef Saied, François Fleuret Published: 2026-10-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.09242v1 Representation Autoencoders (RAEs) generate images from pre-trained visual fea- tures, but their dense token grids make generative modeling expensive. Motivated by local feature correlations, we introduce PoolDINO, a learned affine pooling operator that merges neighboring tokens. Training the pooling operator jointly with the RGB decoder preserves the standard two-stage RAE procedure without a separate feature auto-encoder. On ImageNet-256, 4x token compression retains comparable generation quality under internal guidance, while 16x compression trades some quality for greater efficiency. At a fixed budget of 100 sampling steps, latent-sampling throughput increases by 3.7x and 9.0x, respectively, relative to the unpooled baseline. Classification and dense prediction evaluations show that comparable guided generation quality can coexist with weaker performance on other tasks. --- ### Adversarial Images Hijack Web Agents from Visual Grounding to Browser Execution Authors: Wanjing Han, Levi Taiji Li, Mu Zhang, Yue Jiang, Guanhong Tao Published: 2026-10-07 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.09240v1 Modern web agents built on large vision-language models process webpages, select relevant UI elements, and translate model outputs into browser actions. Existing visual red-teaming approaches use adversarial visual content to manipulate this process. However, they primarily target model inference and do not explicitly account for structured input processing or action post-processing. Consequently, model-level success does not establish control over browser execution and cannot reliably characterize end-to-end agent robustness. To address this gap, we formulate red teaming for vision-grounded web agents as an end-to-end grounding-to-execution problem, and introduce WebMirage, a framework that crafts localized visual perturbations that cause agents to select attacker-controlled content and execute the corresponding browser action across varying webpage renderings. It uses a role-slot abstraction and webpage recomposition to capture competition among webpage elements, and dataflow analysis to align optimization with action post-processing. We evaluate WebMirage across four agent configurations and six VLM backbones on 2,250 tasks covering 13 public websites and a sandbox benchmark. WebMirage achieves an average attack success rate of 91.9%, compared with 17.4% for the strongest baseline, and remains effective against three agent-level defenses. --- ### The Winner's Curse in LLM Self-Improvement Loops: Selection Noise, Lock-in, and Acceptance Rules Authors: Litao Hu, Yutong Tang Published: 2026-10-07 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.09239v1 Self-improving LLM systems propose changes to themselves and keep those that score better on a small evaluation set. We treat this keep-if-better step as selection under measurement noise, model the correlated errors of the candidates in a single decision, and study empirically what happens when the evaluation set is reused. In runs where Qwen models rewrite their own instructions and every candidate is also scored on 600 held-out items, most proposals after the first are harmful, and the model gives the size of the winner's curse of a generation's best candidate. With a prior from a separate pilot, it matches the average overstatement of first-generation commits in native loops, though not setting by setting. In a pre-registered study, the final selection-set score of greedy loops exceeded held-out accuracy by 13 to 20 points with 16 selection items and by 1 to 5 points with 256. Held-out gains grew with the selection set on TREC but not on GSM8K, and the tested acceptance rules did not beat greedy acceptance over whole runs. Gains measured on the selection set also exceeded held-out gains when a current model refined a competent instruction, and in the validation scores of GEPA and MIPROv2. Scoring the starting and the current instruction on 64 items never used for selection removes the average bias of a loop's reported gain, but single estimates remain off by about 6 points. Self-improvement studies should report held-out gains with their uncertainty. --- ### Physics-Guided Multi-Fidelity Surrogate Modeling for Natural Supercavity Geometry of an Axisymmetric Conical Cavitator Authors: Vinh Pham, Van Tu Nguyen, Warn-Gyu Park Published: 2026-10-06 Categories: physics.comp-ph, cs.LG arXiv: https://arxiv.org/abs/2610.18886v1 Natural supercavitation behind conical cavitators generates a vapor-filled envelope that, when sustained over the full body of a high-speed underwater vehicles, reduces hydrodynamic skin-friction drag and enables performance levels unattainable in fully wetted flow. Accurate prediction of maximum cavity length and maximum cavity radius and local cavity profile as functions of cavitation number and cone half-angle is essential for both the static design and the real-time shape management of super-cavitating torpedo cavitators. Classical analytical models provide computationally inexpensive predictions but exhibit systematic disagreements in the practically important regime of moderate cavitation number and large angle, where slender-body assumptions begin to break down. Existing data-driven machine learning approaches offer higher accuracy but are constrained by the prohibitive cost of multiphase computational fluid dynamics (CFD) sweeps over the full design space. This study proposes a physics-guided multi-fidelity surrogate framework based on Extended Hierarchical Kriging (PG-EHK) that addresses this challenge by fusing the multiple competing analytical cavity formulas as non-level low-fidelity (LF) trend functions corrected by a sparse set of high-fidelity (HF) CFD data. It simultaneously incorporates the analytical models regardless of their local fidelity ordering, using Bayesian-estimated scaling factors to construct the trend function as physical baseline. The resulting surrogate maps operational condition inputs to cavity geometry responses using fewer than 20 high-fidelity CFD evaluations. Cross-validation on five independent hold-out CFD cases demonstrates that the proposed PG-EHK surrogate achieves 61% reduction in prediction error compared to the best-performing individual analytical approach. --- ### The Future of AI-assisted Physics: Discovering, Verifying and Organizing Results via Formalization Authors: Sven Krippendorf, Leopoldo Sarra, Joseph Tooby-Smith Published: 2026-10-06 Categories: hep-ph, cs.AI, cs.LO, hep-th arXiv: https://arxiv.org/abs/2610.14059v1 Rapid advances in AI have opened a new era for physics, enabling unprecedented capabilities in research and discovery. However, these advances also bring challenges in verifying, trusting, and reusing the results they so rapidly produce. Formalization is a necessary part of the solution to these challenges. In this paper, as well as giving an overview of the role of AI and formalization in physics, we make the case that: (1) formalization is an essential layer for AI-driven discoveries in both computational and theoretical physics; (2) AI is lowering the barrier to, and increasing the efficiency of, formalization in physics, though it remains weaker at choosing definitions and designing libraries than at writing proofs; (3) the speed AI brings to formalization in physics currently comes at the cost of trust, credit, and community; (4) shared, community-reviewed formal libraries such as Physlib should be central in making progress in this field, both as a trusted, reusable foundation for physics results and as the environment in which AI systems can reason about physics; (5) formalizing physics raises challenges beyond those in mathematics, most importantly that a checked proof does not establish that its definitions faithfully capture the intended physics. We also give our perspectives on near-term and long-term directions in these areas. --- ### Energy-Efficient Spiking Neural Networks for Sensing-Aided Beam Prediction Authors: Nhan Thanh Nguyen, Phuong Nam Tran, Mengyuan Ma, Huy T. Nguyen, Ahmed Alkhateeb, Markku Juntti Published: 2026-10-06 Categories: cs.NE, cs.AI arXiv: https://arxiv.org/abs/2610.12507v1 Sensing-aided beam prediction can reduce the beam-training overhead of millimeter-wave (mmWave) systems by leveraging environmental information from complementary modalities such as vision and position. However, the resulting sensing and inference pipeline can be energy-intensive, motivating the use of energy-efficient spiking neural networks (SNNs) as an alternative to conventional artificial neural networks (ANNs). In this work, we develop SNN architectures for beam prediction and systematically compare them with ANNs using position-only, vision-only, and multimodal inputs. Our results show that compact ANNs consistently outperform SNNs for position-only sensing. In contrast, for vision and multimodal sensing, SNNs achieve higher accuracy than ANNs at similar energy costs and require up to an order of magnitude less energy at a comparable accuracy. For example, the multimodal SNN achieves 58.08% top-1 accuracy, outperforming the closest-energy ANN by 18.11 percentage points. We further show that SNN accuracy is limited by the binary communication between layers rather than by model size. These results demonstrate the potential of SNNs for energy-efficient sensing-aided beam prediction while highlighting their accuracy limitation. --- ### The optimal information complexity of VC learning Authors: Steve Hanneke, Juexiao Wang Published: 2026-10-06 Categories: stat.ML, cs.IT, cs.LG, math.ST arXiv: https://arxiv.org/abs/2610.10600v1 Steinke and Zakynthinou(2020) introduces the Conditional Mutual Information (CMI) framework of analyzing the information complexity of learning algorithms based on algorithm-dependent information-theoretic quantities. We study one of these quantities, the evaluated Conditional Mutual Information (eCMI). It has been an interesting question whether the optimal PAC guarantee for VC classes can be recovered from the algorithm-dependent analyses via CMI. And we show that it is possible to recover this guarantee by constructing a learning algorithm whose eCMI is of order O(d) in the realizable case, where d is the VC-dimension of the concept class. Specially, our algorithm is a randomized Majority-of-5 base learners with optimal in-expectation generalization guarantee. --- ### Certified Corruption Budgets: Anytime-Valid Leaderboard Claims under Adaptive Rigging Authors: Hamed Khosravi, Xiaoming Huo Published: 2026-10-06 Categories: cs.CR, cs.AI, stat.ME arXiv: https://arxiv.org/abs/2610.10597v1 Public leaderboards for AI models are read continuously, and attackers can see every published standing. Vote rigging, selective disclosure of private variants, and benchmark contamination can each move a ranking. Existing guarantees assume genuine records or bound the corruption per step, which an attacker who corrupts in bursts evades. We introduce the certified corruption budget, a tolerance $\widehat{B}_t$ computed after $t$ records and published with each pairwise claim. With probability at least $1-α$, simultaneously at all times, the claim is correct or more than $\widehat{B}_t$ records were corrupted. It holds against attackers who watch every certificate, with no bound on their budget. Forged records and records altered once seen require different certificates: the certificate for forgeries fails, with probability approaching one, against an attacker who flips votes it has seen, while one that charges roughly twice as much per record remains valid, with constant bets even against attackers who see the future, and no smaller charge is valid at every level. The certified budget grows nearly as fast as any valid method allows: with a win fraction $\frac{1}{2}+δ$, each new record adds close to $2δ$ to the number of forged records the claim can withstand ($δ$ flipped). Publishing the best of $V$ private variants costs only an amount growing like $\log V$. In replays on 1.8 million Chatbot Arena votes, a few hundred rigged votes make standard confidence intervals certify false orderings, while ours stays valid. On real votes, our certificate shows that clearly separated models withstand about 2,000 forged votes. --- ### Coverage, Not Difficulty, Sets How Much Synthetic Data an Activation Probe Needs Authors: Ankush Checkervarty Published: 2026-10-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.10594v1 Activation probes that monitor deployed language models are trained on synthetic conversations, and how many a probe needs is open. We trace learning curves over 10-590 synthetic samples for three monitoring concepts, high-stakes situations, replies harmful to a person, and replies that do not follow the user's instruction, on fourteen held-out evaluation distributions and four probe models, varying the generator LLM and the prompt's detail. The need is set by what is monitored: probes for high-stakes and harmful are within a few hundredths of their plateau from 80 samples on Gemma-3-27B-IT, instruction probes need several times as many, and the ordering holds on three smaller probe models and on real samples (from dev set). Prior work advises spending a generation budget on breadth, more kinds of data, over depth, more of each kind. We read the depth a concept needs as the half-gain size of a fitted curve, the number of samples at which half the gain is in hand. Concept and distribution account for 42-45% of its variance, the generator, probe model, and prompt detail for under 10%. What sets the value of the half-gain size is coverage, not per-kind difficulty: the number of samples of its own kind a distribution needs to saturate. Every kind, one per evaluation distribution, has a median half-gain size of 7-11 own-kind synthetic samples under all three concepts alike. What differs is how far samples of one kind transfer to the concept's other kinds, almost fully under high-stakes, less under harmful, and least under instruction, which accounts for most of the gap between concepts on generated and real samples. Breadth therefore pays differently by concept: many kinds are necessary under instruction, where no kind covers another, and nearly redundant under high-stakes, where one kind covers the rest. We release the evaluation suites, dev sets, and generated sets. --- ### Wieszcz-XIX: A 3.1-Billion-Word Corpus of Pre-1918 Polish and Temporally Bounded Language Models Trained From Scratch Authors: Szymon Kocur Published: 2026-10-06 Categories: cs.CL, cs.DL arXiv: https://arxiv.org/abs/2610.10592v1 Historical Polish is well documented as a language but annotated in machine-readable form only to about a million words for the period this paper covers; the rest sits behind optical character recognition of variable quality. We present Wieszcz-XIX, a corpus of 6.75 billion tokens (about 3.1 billion words) in 294,369 documents, most of them periodical issues, of Polish published from 1800 to 1918, assembled from Wolne Lektury and the Internet Archive by a pipeline that filters, deduplicates, audits for post-1918 leakage and splits at the document level. It is over three orders of magnitude larger than the annotated corpus of the same period, and we quantify its defects: recognition corruption against a false-positive floor, near-identical duplication, which is removed, and post-1918 leakage, which is excluded from the training corpus itself down to a known residue of 0.04 to 0.38% of its bytes, found in the transcribed source, so the published corpus is the trained one document for document. On a hand-corrected sample the character error rate is 0.68% where the text is legible, and 45% of the sampled passages cannot be corrected. On it we train a ladder of decoder-only models from 47M to 349M parameters from scratch, and measure their temporal boundedness. Against two modern Polish base models, one far larger, the 349M shows a crossover, as does the 107M against the comparator of its size: post-1918 vocabulary costs them about 3.1 bits per byte more than period vocabulary, a gap the comparators do not show, and period vocabulary costs them fewer bits than it costs the comparators. Shown period text, the models keep its spelling and the comparators only partly. Adding parameters gains about twice as much as a second pass over the data. We release the corpus, code and weights. Content warning: the models reproduce period prejudice, including antisemitic statements. --- ### Agent-Controlled Forgetting for Tool-Using Agents: Reversible Context Curation in Practice Authors: Jan-Peter Franke Published: 2026-10-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.10590v1 Tool-using agents repeatedly carry observations whose useful content can be much smaller than their original payload. We study agent-controlled forgetting: the acting model selects previously observed tool results, replaces each with a short note at its original position, and retains the exact original in a recoverable archive. A Python harness exposes batch archival and explicit recovery without task-specific model training, while protecting user instructions and assistant messages from these operations. In an exploratory OpenTelemetry debugging case followed by an unrelated implementation task, the method ended with 231,951 provider-reported prompt tokens versus 912,492 under retained history, used 50% fewer cumulative input tokens, and had an estimated API cost of USD 1.28-1.44 versus approximately USD 4.38. Both arms passed the two-case primary behavioral oracle; neither fully satisfied the follow-up evaluation. The method made more requests and took 17% longer. A contrasting application-development pair produced no context or cost saving, and an earlier continuation exhibited lower manually assessed quality despite reduced context. These observations demonstrate substantial resource savings in noisy tool-use trajectories and identify workload dependence as a central consideration for reversible context management. --- ### A Survey on LLM-Integrated Hardware Design Verification Authors: Hao Zheng, Jaime Rafael Imperial, Bardia Nadimi, Xiangfei Kong Published: 2026-10-06 Categories: cs.AR, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2610.10580v1 Large language models (LLMs) are increasingly being integrated into hardware verification to automate specification interpretation, verification-artifact generation, debugging, formal reasoning, and tool orchestration. This survey provides a systematic review of LLM-assisted hardware functional verification across SystemVerilog assertion generation, stimulus and testbench generation, bug localization and design repair, model checking and equivalence checking, SAT/SMT optimization, and emerging agentic verification workflows. We organize the literature by methodology, verification objective, tool interaction, benchmark, and evaluation criterion, and examine both inference-time techniques--including prompting, retrieval, structured reasoning, and agentic workflows--and training-time adaptation. Across these areas, a common pattern emerges: LLMs are most effective as semantic reasoning, search, and orchestration components embedded within verification-aware workflows, while simulators, formal engines, coverage tools, and solvers provide executable feedback and correctness evidence. However, tool acceptance alone does not establish verification correctness, since assertions, tests, repairs, or proofs may satisfy available checks without faithfully capturing the complete design intent. We therefore identify semantic alignment between specifications and verification evidence, scalable integration with deterministic tools, generalization to unseen designs, and rigorous evaluation of correctness, cost, robustness, and human effort as key challenges. Finally, we discuss emerging directions toward specification-centered, neuro-symbolic, and persistent agentic verification systems that combine LLM flexibility with independently checkable verification evidence. --- ### Trajectory Abstraction for the Science of Language Agent Behavior Authors: Tianqiang Yan Published: 2026-10-06 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.09237v1 Scientific studies of language agents need behavioral variables that support hypotheses across tasks and models. We formulate this research problem as learning and testing a hierarchy of trajectory abstractions. A concrete recursive procedure first measures role- and phase-indexed events, proposes temporally constrained relations, and tests their stability across conditions. It then constructs episode-level motif variables from selected relations and repeats the analysis on those variables. Explicit measurement functions connect every abstraction level to the original trajectories. Observations and randomized protocol experiments assess the resulting hypotheses, while comparisons between intervention realizations determine whether an abstraction should be retained, refined, or restricted. We derive a finite-depth bound for accepted reductions, identify protocol effects on fixed abstractions, and characterize realization disagreement and composition of abstraction error. A finite-sample test makes projected intervention consistency operational, and constructed examples illustrate motif construction and abstraction refinement. The formulation distinguishes this experimental approach from semantic taxonomies, qualitative theory induction, and behavior-model recovery. It specifies a proposed research procedure for discovering generalizable behavioral hypotheses, with literature-relative novelty assessed separately from model-relative surprise. --- ### Symmetry-Informed Causal Partial Identification Authors: Uzair Akbar, Zulfiqar Zaidi, Niki Kilbertus, Krikamol Muandet, Bo Dai Published: 2026-10-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.09230v1 Partial identification (PI) entails estimating bounds on causal effects by encoding different assumptions on data generation as a constrained optimization problem. Such bounds can suffice to inform policy decisions even if the causal effect itself is not identifiable. Often vacuous in practice, practitioners seek to exhaustively encode domain knowledge as additional constraints to make the PI bounds more informative. We introduce known data symmetries -- invariance of the causal effect under certain data transformations -- as a new source of constraints to inform PI. We operationalize this as a shape constraint on the causal function, and via a change of measure against which PI is posed using simple data pre-processing. Both approaches are shown to sharpen bounds under two canonical PI models. This is shown both theoretically for the population case, and via experiments in the finite-sample case. More broadly, our framework establishes data symmetries as a natural, underutilized source of background knowledge for robust causal inference. --- ### Conditional Accuracy Profiles: Diagnosing LLM Judges across Deployment Conditions Authors: Wenqi Li, Bin Liu, Mindi Ruan, Chuanbo Hu, Minglei Yin, Xin Li Published: 2026-10-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.09229v1 LLM-as-judge is now a standard tool for scalable evaluation, but judge performance is still often summarized by a single accuracy number. This aggregate view hides the deployment conditions under which a judge succeeds or fails. We introduce \textbf{Conditional Accuracy Profiling} (CAP), a post-hoc diagnostic framework that decomposes pairwise LLM-judge accuracy into eight conditions organized into content sensitivity, robustness, and rationale quality. CAP is benchmark-agnostic: it can be applied directly when a benchmark provides the required annotations, approximately through task-subset proxies, or through controlled augmentation when perturbation pairs can be generated. We instantiate CAP on seven LLM judges across six pairwise judging benchmarks, including \textsc{judgerEva-Standard}, a controlled testbed we created to support all eight conditions. CAP exposes profile differences hidden by aggregate accuracy: on \textsc{judgerEva}'s judge-independent Hard-Constructed subset, the two judges most sensitive to omitted qualifications rank in the bottom three of seven by overall accuracy, so omission sensitivity is not predicted by aggregate accuracy. Across benchmarks, Position Robustness shows the strongest rank stability (mean Spearman $\barρ{=}0.87$) but is itself fragile under JudgeBench-Pro adversarial stress, showing the largest mean accuracy drop among the shared conditions, though the dominant degradation channel varies by judge. Condition-level profiles provide a more actionable basis than aggregate accuracy for selecting LLM judges. --- ### Quantize by Drift: Label-Free Mixed-Precision Post-Training Quantization for Text Embedders Authors: Hyojung Han, Jongmin Kim, Seung-Hun Jeon Published: 2026-10-06 Categories: cs.IR, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.09227v1 Mixed-precision post-training quantization needs a per-module sensitivity signal; for a text embedder the obvious one -- the retrieval quality a module costs when quantized -- needs relevance labels that deployments rarely have. We measure a label-free substitute: quantization-induced representation drift, obtained by quantizing one module, re-encoding the corpus, and recording how far the output embeddings moved from their full-precision positions. What is specific is the observable: the deployed output representation a dense retriever ranks with. Across five development embedders, configuration-level drift orders sampled mixed-precision plans against held-out retrieval quality at a macro Spearman of 0.911, the sensitivity transports across calibration corpora and retrieval domains in the usable regime, module drifts compose rank-consistently but not numerically, and relevance-derived sensitivity adds no consistent value. The method is one additive allocation under a hard packed-byte budget, with no labels and no search. On three embedders held untouched until method, baselines and hypotheses were frozen and sealed, the pre-registered directional hypothesis against the prior LieQ criterion holds (3/3 at the main budget, no collapse) and drift scores above a two-sided LieQ steelman in 2/3; but at the main budget drift is numerically lower than same-budget uniform precision on all three (-0.99, -0.85, -1.01 points), having reduced module and whole-model drift as designed. Output drift is thus a robust coarse sensitivity signal, not a universally optimal allocation objective: it avoids the catastrophic failures of the transferred signed-geometry adaptation and can remain usable at stressed budgets where uniform collapses, but fine-grained redistribution around a strong uniform operating point remains unresolved. --- ### FLoRa: Flight-Assisted Data Collection from Duty Cycling LoRa Nodes under Energy Constraints Authors: Naresh Babu Kakarla, V. Mahendran Published: 2026-10-06 Categories: cs.NI, cs.LG arXiv: https://arxiv.org/abs/2610.09226v1 Data collection using Unmanned Aerial Vehicles (UAVs) is challenging when LoRa IoT Devices (IoTDs) duty-cycle to conserve battery. Under energy constraints, a UAV must decide which IoTDs to visit, in what order, where to hover, and how many times to probe each node, while time-based data freshness decays. Tractably solving this problem requires a multi-level optimization architecture: discrete combinatorial optimization for routing, continuous global optimization for spatial positioning, and sequential decision-making under uncertainty. We propose FLoRa, a Flight-assisted LoRa data collection architecture using Simulated Annealing (SA) for path planning, Covariance Matrix Adaptation Evolution Strategy (CMA-ES) for hover positioning, and Partially Observable Markov Decision Processes (POMDPs) for probing IoTDs. To quantify collection utility from duty-cycling nodes, we introduce the Value of Information for Pull-based systems (VIP), a metric that rewards fresh data and penalizes failed probes, imposing well-posedness and preventing indefinite probing when an IoTD is off. Tracking hard battery constraints on every POMDP sample path requires state augmentation, worsening the curse of dimensionality. For tractability, SA and CMA-ES work on the hard battery constraints, while at the POMDP layer we relax them into soft average constraints via Lagrangian relaxation. Since solving the network-wide POMDP is computationally complex, we decompose it into node-level POMDPs by approximating inter-node time dependency using a forward-decomposition technique. Evaluation shows FLoRa outperforms metaheuristic, greedy, and deep reinforcement learning baselines by 30.6%, 27.8%, and 15.2% in total expected VIP, while increasing node coverage by 24.5%, 29.2%, and 8.8%, and successful collections by 24.3%, 25.6%, and 15.2%, respectively. --- ### PVSync: A Unified Lip-Sync Expert for Timing and Articulation Authors: Kevin Stephen, Varun Menon, Timo Mertens, Nikita Drobyshev Published: 2026-10-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.09223v1 Lip movements can match the timing of speech without matching the spoken sounds. We introduce PVSync, a unified model for audio-visual offset estimation and phoneme-level articulation scoring. PVSync combines window-level contrastive learning for synchronisation with a phoneme-level articulation objective that aligns audio and video embeddings of the same viseme class across clips. Visemes group phonemes with similar visible articulation. Viseme labels are derived automatically from forced-aligned transcripts, without manual annotations. On offset-corrected videos from 13 talking-head video generation models, PVSync matches human rankings of lip-sync quality more closely than LSE-C, achieving a Spearman correlation of 0.83 versus 0.34. On an automatically constructed benchmark from held-out speech, PVSync distinguishes viseme-matched from mismatched audio-visual pairs with an ROC AUC of 0.91. PVSync also outperforms SyncNet and MTD-VocaLiST in temporal offset recovery on held-out in-the-wild clips. Code and benchmark data will be released upon acceptance. --- ### Consistent Distribution Matching for Data-Free Diffusion Distillation Authors: Yuxiang Fu, Qi Yan, Zike Wu, Yongxing Zhang, Purang Abolmaesumi, Lele Wang, Renjie Liao Published: 2026-10-06 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2610.09221v1 Flow and diffusion models suffer from slow inference due to computationally expensive numerical integration. Distillation provides a promising way for a student model to learn from a teacher's dynamics, enabling one-step or few-step generation. However, existing methods often depend on curated distillation datasets, costly teacher rollouts, or auxiliary proxy networks, which complicate model training and scaling. In this work, we propose Consistent Distribution Matching, a simulation-free and data-free distillation method for accelerating diffusion and flow models while preserving strong generative capacity. Our key insight is to unify sample generation and score estimation with one student network. Thus, our framework uses only two models, a frozen teacher and a trainable student, and optimizes one objective. We prove that minimizing our objective indicates Wasserstein convergence of the student flow-map pushforwards to the teacher marginals. On ImageNet 256$\times$256, our method attains an FID of 2.04 with a single function evaluation (1-NFE) and a 4-NFE FID of 1.37 within 40 epochs of training, surpassing the state-of-the-art distillation baselines without data. Our code code and model are available at https://consistentdmd.github.io/. --- ### CM-DPO: Constraint-Margin Direct Preference Optimization for LLM Planning Authors: Rabimba Karanjai, Qun Gu, Hemanth Hegadehalli Madhavarao, Wenhuan Sun, Xiaojiao Yu, Suryabhan Singh Hada, Libin N. George, Uma Kona, Richard Williamson, Linsey Pang, Prakhar Mehrotra Published: 2026-10-06 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.09219v1 Direct Preference Optimization (DPO) treats all constraint violations equally: a $1 budget overshoot and a $1,000 overshoot induce the same training signal. It is also susceptible to length and style bias when preference pairs come from different model families. We introduce Constraint-Margin DPO (CM-DPO), which replaces DPO's binary preference signal with a continuous margin derived from a deterministic symbolic verifier and scaled by violation severity. Hard and soft constraints are separated through a lexicographic objective, ensuring hard constraints are never traded off against preferences. To supply CM-DPO with bias-reduced training pairs, we generate preference data through procedurally generated constraint profiles (DCCG) and minimal-edit distillation from a reasoning teacher (RT-MED), within a framework we call SynPlan-R. On TravelPlanner, NaturalPlan, and out-of-distribution PlanBench, an 8B model fine-tuned with CM-DPO achieves 89.2% pass rate and 93.4% solve rate, matching multi-agent systems at 13x lower latency while outperforming GPT-4o on unseen Blocksworld by 9.2 points. --- ### RLDISCOVER: LLM-driven co-evolution of reinforcement learning algorithms Authors: Haoran Li, Zengle Ge, Xiaomin Yuan, Yui Lo, Songlin Zhou, Jiahua Ying, Haoxin Li, Qianhui Liu, Yuanhang Liu, Jiaqun Liu, Guokai Chen, Mingju Chen et al. Published: 2026-10-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.09218v1 LLM-guided program evolution has enabled discoveries in mathematics and computational optimization, raising the prospect of reinforcement learning (RL) algorithms that self-evolve to improve how agents learn. However, realizing this prospect faces two obstacles. Joint search over coupled algorithmic components is difficult to scale: simultaneous changes can disrupt learning, while isolated changes overlook their dependencies. Evaluating candidate algorithms also requires costly training, with fitness remaining uncertain across random seeds. We introduce RLDiscover, a framework for the self-evolution of model-free deep RL algorithms. Progressive Co-Evolution advances from targeted component edits to joint evolution, while Progressive Probabilistic Evaluation balances search breadth and evaluation fidelity through staged training and repeated evaluation. Experiments across SAC, PPO, and DQN on four benchmark suites show substantial improvements in mean return, with per-family median gains of 32%-84% and a peak return ratio of approximately 363x over a near-zero baseline. These gains include transitions from failed learning to successful task completion, and improvements persist when evolution starts from stronger open-source implementations. On measured SAC locomotion runs, evaluation uses approximately one-fifteenth the estimated compute required to fully evaluate the same candidate pool. Remarkably, independent searches repeatedly discover interpretable combinations of adaptive robust losses, progress-dependent value targets, and running statistics, with selected programs transferring to unseen tasks. These findings point toward a broader role for self-evolution in AI: discovering interpretable algorithms that improve how agents learn. --- ### A Deterministic Evidence Layer for Vision-Language Autism Screening from Naturalistic Home Video Authors: Wenqi Li, Mindi Ruan, Chuanbo Hu, Shuo Wang, Xin Li Published: 2026-10-06 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.09217v1 Autism spectrum disorder (ASD) is diagnosed through specialist observation of a child's social behavior, and access to that expertise is the bottleneck for early identification. Vision-language models (VLMs) describe a child's behavior from video well; the verdict drawn from the description is unstable: at temperature~0, across eight pipeline configurations on one backbone, 16--37\% of clips change their predicted label between repeated runs, and the cause lies in the serving stack. We keep the VLM frozen and move the decision out of the model. Under our grounded perception constraints the VLM writes an event table of timestamped, glossary-labeled events that names the eliciting press and logs counter-evidence; a text-only stage age-calibrates the confidence of each row; a deterministic weight-of-evidence scorer sums it into an evidence total and stratifies it into a risk category, so every decision decomposes into named per-feature contributions and can be re-scored from the saved table. On 43 caregiver-recorded, protocol-free home free-play clips of preschool children, the pipeline reaches AUC $0.851 \pm 0.012$, 86.0\% accuracy, and F$_1$ 71.8 over three runs. It labels 74.4\% of clips correctly in every run (60.5\% for the zero-shot baseline) and flags no typically developing clip in every run (9 of 31 at zero-shot). An ablation on the same backbone attributes the gain to the grounded perception constraints read through the deterministic scorer. --- ### AGAR: a reinforcement learning substrate for LLM program evolution Authors: Haoran Li, Zengle Ge, Xiaomin Yuan, Yui Lo, Haoxin Li, Songlin Zhou, Qianhui Liu, Jiahua Ying, Yuanhang Liu, Mingju Chen, Annan Li, Jianmin Wu et al. Published: 2026-10-06 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2610.09215v1 Given a task and an evaluator, a language model can rewrite a candidate program while a search loop decides which rewrites survive, offering a practical route to algorithm discovery. But that loop is governed by five constants set by hand: which parent to select, how hard to mutate, how to keep diversity, what to remember, and a scalar score that never says which part of the program earned it. Reinforcement learning already has an estimator for each. The obstacle is that program evolution is not usually written down as a decision process. We formalize it as a Markov decision process whose action is the modular prefix the model is conditioned on, rather than the program it emits. Credit assignment, value estimation, adaptive exploration, and experience memory can then attach to distinct components. AGAR (Algorithm Generation As RL) provides the resulting substrate: any estimator can be replaced or switched off without changing the controller, making the transfer auditable one mechanism at a time, with no gradient training of the backend model. Across 19 tasks, two backends, and three seeds under one harness, AGAR improves on the stronger of two published baselines on most tasks, with gains concentrated in the competitive-programming family. The formalization also yields a checkable reading of prior work: these systems are implicitly zero-discount, not by choice, but because fitness is exogenous to an individual rather than a return over successors, leaving a discount factor nothing to act on. --- ### CurveTQ: Rotation-Free Trellis Quantization of LLM Weights via Curvature-Weighted Search Authors: Guanhua Ding, Zi Wang, Ruichao Li, Jack Liu Published: 2026-10-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.09212v1 The best two-bit weight quantizers for large language models, such as QTIP and Proteus, rotate each weight matrix by a random orthogonal transform, which must be undone at every decoding step, then encode it with a trellis or lattice code under a Euclidean search; the layer Hessian enters only through error feedback between coding blocks. We show that this leaves part of the Hessian unused. Error feedback turns the loss into a weighted sum of per-coordinate rounding errors whose weights, the diagonal of the Hessian's LDL factorization, existing quantizers compute but never read. We put these weights into the Viterbi branch metric, so the search follows the curvature within each coding block. This also explains the rotation: it removes this within-block variation, so weighting in the native basis and rotating are substitutes. On three models the weighted native search matches a full-dimension randomized Hadamard to within about one point of downstream accuracy, and weighting after the rotation gains little. Around this search we build CurveTQ, a trellis codec with no rotation, which handles the weights' amplitude and marginal shape with a factored scale field and a closed-form quantile table, and stores a start state per coding block so the trellis can adapt to the residual that error feedback carries into it. At two bits CurveTQ is 1-3 points higher in mean downstream accuracy than QTIP and Proteus on three 4-8B Instruct models, even after both are given our start state, which alone lifts either baseline by 1-3 points. It also leads on a 35B mixture of experts, to our knowledge the first trellis-coded result on such a model. With no rotation to undo, our decoder is the fastest of the three at all tested batch sizes and bit widths. --- ### Multi-Objective Aligned Small Language Model Framework for SUD Patient Dialogue Generation Authors: Thushara Manjari Naduvilakandy, Hyeju Jang, Mohammad Al Hasan Published: 2026-10-06 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.09209v1 Substance Use Disorder (SUD) counseling requires patient responses that reflect underlying cognitive states such as beliefs, coping strategies, and readiness for change. Although large language models (LLMs) can generate fluent text, they often fail to produce cognitively coherent and clinically realistic patient behavior, especially under ethical and data-scarce clinical settings. Moreover, deploying frontier-scale LLMs in healthcare applications presents practical challenges including high computational cost, latency, privacy concerns, and limited deployability in resource-constrained environments, motivating the need for cognitively aligned small language models (SLMs). We propose a cognitively grounded framework for SUD patient dialogue generation that explicitly models and aligns latent cognitive components with patient histories and counselor questions. Our pipeline consists of two stages: cognitive component detection and cognitive component-aligned dialogue generation. To enable effective learning with smaller models, we combine knowledge distillation from high-capacity teacher models, preference optimization from human-annotations, and attention-guided reward shaping. Extensive evaluations using automatic scores like BERTScore, ROUGE, METEOR and BLEU, and LLM-as-judge hit-metrics against both human and teacher-model references show that cognitively informed fine-tuning substantially improves cognitive realization and alignment over a generic instruction-tuned baselines and mental health domain specific SLMs, with particularly strong gains for open-ended cognitive components. --- ### Sketched Calibration for Conformal Prediction under Covariate Shift Authors: Mehrdad Pournaderi Published: 2026-10-06 Categories: stat.ME, math.ST, stat.ML arXiv: https://arxiv.org/abs/2610.09208v1 Weighted conformal prediction corrects for covariate shift by reweighting calibration scores with the likelihood ratio between target and source covariates. Its cost grows with the chi-square divergence between the two covariate laws, typically exponentially in the size of the shift, and much of it can be paid for shift in directions that do not affect the response. We propose sketched calibration: weighted conformal prediction with the ratio of compressed covariates $Z=T(X)$, used in the weights and optionally in the score. Compression never increases the shift-dependent calibration cost, and target coverage is at least $1-α-Δ_T$, where the leakage $Δ_T$ measures how much of the discarded shift reappears as a change in the law of the response, or of the score, given $Z$. The leakage is a covariance between the discarded shift and the response on the fibres of the sketch; it vanishes when the sketch is sufficient or retains the shift, and a minimax construction shows that no threshold rule for a fixed score can avoid it. In a heteroscedastic simulation where unweighted calibration fails, a one-dimensional sketch cuts the fraction of infinite prediction sets from $37.8\%$ to $8.0\%$ at mean coverage $92.3\%$ for a $90\%$ target; nonlinear and real-data experiments show when learned sketches succeed and when they fail. --- ### An Accuracy-Information Tradeoff for Loss-Difference Conditional Mutual Information Authors: Hazar Yueksel Published: 2026-10-06 Categories: cs.LG, cs.IT, stat.ML arXiv: https://arxiv.org/abs/2610.09206v2 Loss-difference conditional mutual information (ld-CMI) uses the smallest of the standard observations in the supersample hierarchy of generalization bounds: it measures what a learner's loss differences reveal about which candidate of each pair it was trained on. Accuracy is known to force information into the model; data processing does not carry such lower bounds to losses. We show, by bounding three moments of the loss differences, that accuracy also forces ld-CMI. For linear predictors with a smooth convex loss of nonzero slope at zero, such as the logistic loss, plus a regularizer whose curvature and growth are both of power $r\ge2$, on product distributions over a scaled sign cube in dimension at least linear in $n$, every proper learner with expected excess risk at most $\varepsilon$ on these distributions at the optimal sample size $n\asymp\varepsilon^{-2+2/r}$ has worst-case ld-CMI of order $n$ bits, and $Θ(n/(1+(τ/\varepsilon)^2))$ bits under Gaussian noise of standard deviation $τ$ on the loss differences. The same holds without a regularizer, at $n\asymp\varepsilon^{-2}$. Consequently, range-scaled ld-CMI bounds cannot vanish on these distributions, although every proper learner's generalization gap is $O(n^{-1/2})$. We also show that model-level information does not determine noisy loss-difference information, and that the growth, slope and dimension conditions are needed, the last up to a logarithm. --- ### Do Vision Models Learn Physical Constraints or Rendering Shortcuts? A Counterfactual Benchmark for Grounded Physical Consistency Authors: M. Moein Esfahani, Sepehr Salem, Mohammed Alser, Vince Calhoun Published: 2026-10-06 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.09205v1 Modern image editing models can satisfy a text instruction while breaking the physics of the edited scene. A new object may cast no shadow, a mirror may fail to reflect visible geometry, or an object may float above a surface that should support it. We study physical plausibility diagnosis, detecting whether an edited image violates scene physics, naming the violation type, localizing the affected region, and explaining the failure in language. We introduce a counterfactual benchmark whose controlled synthetic component uses Mitsuba~3 to generate 5,500 images from 500 scene families. Each family contains one clean image and ten matched violations involving shadows, reflection, support, surface response, and occlusion. The renderer pipeline provides category labels, affected-region masks and boxes, scene metadata, and explanation targets. We use LLaVA-1.5-7B, Qwen2.5-VL-7B, and InternVL3.5-8B as diagnostic baselines rather than proposed methods. On a 1,650-image synthetic test set, the adapted baselines reach 64.0--67.8\% category macro-F1 on standard held-out scenes. For LLaVA-1.5-7B, category macro-F1 falls from 64.0\% on the standard split to 40.8\% under intervention shift. This gap shows that high in-distribution accuracy partly reflects cues tied to rendering and counterfactual construction. --- ### Few Bits, One Law: Toward W2A4KV2 Authors: Kai Yi, Tarek Elgamal, Sruthikesh Surineni, Vignesh Vivekraja, Soumyadeep Ghosh, Steven Li Published: 2026-10-06 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.09202v1 Extreme low-bit LLM compression is most challenging when weights, activations, and KV caches are quantized together: their distributions differ, and quantization errors interact throughout the network. We introduce CanonQ, a unified quantization-aware training framework that addresses these challenges by separating source canonicalization from task-aware adaptation. Fixed rotations and energy normalization map heterogeneous tensor sources to canonical coordinates, enabling frozen Gaussian-reference codebooks to be reused across layers and models. Joint training then adapts the network to the coupled errors of weight, activation, and cache quantization within a common scalar/vector interface. We bound frozen-codebook transfer error and local task loss, and derive an exact normalization-aware straight-through Jacobian that links quantization distortion to gradient bias. The strongest gains arise under joint W2A4KV2 compression: across LLaMA3-1B/3B/8B, CanonQ-Omni achieves up to 14.28x lower WikiText-2 perplexity and up to 57.9% higher mean zero-shot accuracy than prior state-of-the-art and representative quantization baselines. The benefits extend to Qwen3-1.7B, code generation, and mathematical reasoning: on instruction-tuned MobileLLM-Pro-1B at W2A16KV16, CanonQ achieves relative improvements of 41.7% in HumanEval pass@1 and 39.1% in GSM8K exact match over the strongest evaluated quantization baseline. --- ### StyleFields: Multi-Scale AdaIN-Modulated Implicit SDFs for Coarse-to-Fine 3D Shape Reconstruction and Editing Authors: Ehsan Garaaghaji, Nicolas Talabot, Pascal Fua, Doruk Oner Published: 2026-10-06 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2610.09200v1 We introduce StyleFields, a DeepSDF-based architecture for high-fidelity 3D reconstruction that enables controllable geometric style mixing: the coarse structure of one object can be combined with the fine-scale details of another. The core idea is depth-aware modulation: instead of a single global code, we inject latents via multi-level Adaptive Instance Normalization at several decoder depths, and supervise matching auxiliary heads with a coarse-to-fine schedule while gradually growing network depth. This aligns early layers with global shape and later layers with high-frequency detail, achieving content-style decoupling without part labels or adversarial training. StyleFields delivers faithful reconstructions, convincing cross-instance hybrids, and consistent gains in ablations over injection depth and supervision granularity. We further demonstrate a practical application in automotive aerodynamics: a learned surrogate drag predictor serves as a differentiable objective to optimize reconstructed cars, allowing targeted edits of global form or surface details by freezing the complementary latent stream. StyleFields offers a simple, effective recipe for controllable implicit reconstruction and downstream performance-driven design. --- ### FreeEvolve: Learning to Evolve Beyond Fixed Loops Authors: Lecheng Kong, Like Hui, Nikos Kanakaris, Prithwish Jana, Sahika Genc, Narayanan Sadagopan Published: 2026-10-06 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.09197v1 Agent evolvers automate the design of the prompts, skills and workflows around language model agents, yet the optimization process they follow is still designed by hand: a fixed search loop decides how candidates are evaluated, which are kept and when the search stops. We propose FREEEVOLVE, which automates this process as well. An environment specifies the goal, target agent, evaluator, data and resource limits; within these limits, the evolver itself decides what to test, how much evidence to collect, which candidates to pursue and when to stop. These decisions follow an editable evolution skill, which we improve through meta-evolution by scoring each candidate skill on the fresh target agent it produces. The optimization process thus becomes a capability learned from experience rather than a loop engineered in advance. On tau3-bench, ARC-AGI-2, ARC-AGI-3 and Terminal-Bench 2.1, FREEEVOLVE controls the evolution campaign by itself, yet improves the primary held-out metric by 13.6 points on average and matches or exceeds hand-designed evolvers. The learned process keeps improving with experience: meta-evolved skills add 6.9 points over the seed skill on fresh target agents, demonstrating transferability across environments. --- ### Exact Dynamics and Finite-Sample Trajectory Recovery of Linear Recursive Feature Machines Authors: Andrew Cheng, Bobak T. Kiani, Yue M. Lu, Adityanarayanan Radhakrishnan Published: 2026-10-06 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2610.09196v1 Recursive feature machines (RFMs) learn representations of data by alternating between fitting a predictor to a dataset and updating features of that predictor using the average gradient outer product (AGOP). Connections between AGOPs and feature learning in neural networks motivate linear RFMs as a simple setting for analyzing how representations evolve during training. Here, we study the dynamics and statistics of linear RFM in noisy multi-output regression with isotropic sub-Gaussian input data and targets generated by a low-rank teacher matrix of dimension $d$. We extend the known connection between linear RFM and iteratively reweighted least squares from the interpolating setting to ridge-regularized multi-output regression with noise. We show that the learned feature matrix remains close to its infinite-data ideal counterpart at every iteration. Namely, for $n$ samples, we show the error in the feature matrix decays as $O(\sqrt{d/n})$ with high probability. Experiments on real-world text and single-cell gene-expression data illustrate the features learned by this simple linear model. --- ### StableGrasp: Reconstructing Physically Stable Human Hand Grasps from Single Images Authors: Han Jiang, Etienne Vouga, Qixing Huang, Georgios Pavlakos Published: 2026-10-06 Categories: cs.CV, cs.GR, cs.RO arXiv: https://arxiv.org/abs/2610.09195v1 Reconstructing a physically stable human grasp from a single RGB image is challenging because physically modeling grasps is itself difficult, and the problem requires estimating not only a visually constrained hand pose but also a control target that stabilizes the grasp. Existing methods either model only visual hand geometry without considering physics, or rely on less plausible physical modeling, which limits the physical validity of the resulting grasps. In this paper, we present StableGrasp, a differentiable simulation-based optimization framework that explicitly separates the visual hand pose from the control target that determines the grasping forces. Our method jointly optimizes hand geometry and control by minimizing the kinetic energy of the grasp in a differentiable simulator, while regularizing the hand geometry to preserve visual consistency and geometric plausibility. The reconstructed grasps are substantially more stable under rigorous physical simulation, while remaining visually consistent with the input images and geometrically plausible. Experiments show that our approach produces far more stable grasps than alternative hand-control strategies, benefiting visual-only grasp reconstruction pipelines by turning their outputs into physically stable grasps. --- ### Patient, Place, Prior (P$^3$): What Counts as Personalization in Medical World Models? Authors: Xingrui Gu, Hanxue Gu, Yuxiang Zhang, Yang Yang Published: 2026-10-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.09194v1 Longitudinal models forecast how a patient's imaging state evolves, but accuracy does not show whether the patient's observed trajectory drives the prediction. A population-average forecast may be useful but cannot establish a patient-specific world-model claim. We introduce Patient, Place, Prior (P$^3$), an audit asking whether a forecast benefits from the patient's longitudinal imaging history (Patient), benefits from patient-matched externally supplied spatial support (Place), and gains predictive value beyond a population-average prediction under matched support and context (Prior). We also propose Cancer JEPA, a one-step model that forecasts frozen representations of future breast dynamic contrast-enhanced MRI examinations during neoadjuvant therapy. It adds a lesion-constrained neural correction, trained with an occlusion-based latent objective, to a patient-conditioned low-complexity reduced-rank regression baseline. This factorization permits a post-hoc P$^3$ audit of the frozen model. In a validation cohort previously used in development, forecast error is lower when the neural correction receives the patient's history rather than another patient's and patient-matched lesion occupancy maps rather than substituted maps. However, the descriptive 95% interval comparing the correction computed from patient history with the population-average neural correction includes zero. P$^3$ thus separates input use from evidence of patient-specific predictive value beyond a population-level pattern. --- ### Bookkeeping, Composition, or Unreachable Gold? Reading MemoryAgentBench's Conflict-Resolution Scores Against a Frozen Last-Write Resolver Authors: Egor Pakhomov, Erik Nijkamp Published: 2026-10-06 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.09193v1 MemoryAgentBench's Conflict Resolution split is read as measuring "selective forgetting". We execute the benchmark's own rule - the newest statement about a fact wins - as a zero-learning resolver frozen on one of the four fact lists. Under the official metric the rule answers 80.25% of the questions (74.5% on the three held-out lists). Of the rest, 67 items have a released gold that the last-write graph cannot reach but overwritten statements would ("The capital of India is New Delhi." superseded by "The capital of India is Grosseto."; gold New Delhi); such items are a third of the multi-hop questions at 262K. Two long-context models and our pre-registered approximate re-implementation of the benchmark's BM25 agent, one retained run per item and outcomes only, score 84.7%, 82.6% and 41.6% on the items the rule solves against 10.4%, 11.9% and 6.0% on those 67. The failures are a reachability split plus a small parser-scope residual; the per-item split, not the aggregate, is the unit at which a score here can be read. --- ### R-CNN-Based Chess Position Recognition Authors: Paras Govind, Ognjen Arandjelović Published: 2026-10-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.09191v1 Performing chess game position recognition solely from a single image of a three-dimensional board requires predicting the position and orientation of the board relative to the camera, the occupancy of squares and the piece type, which includes its colour. We propose an R-CNN-based framework with independent components for piece recognition and board geometry estimation, whose predictions are combined to reconstruct the position. For piece recognition, we adapt Faster R-CNN using a class-weighted objective and a deeper classification head. The detector operates directly on the input image, retaining alternative piece hypotheses that are subsequently refined using constraints on piece counts and square occupancy. For board detection, we introduce an octagonal arrangement of eight labelled boundary keypoints, predicted using the keypoint head of Mask R-CNN. These provide redundant correspondences for homography estimation and encode board orientation. The estimated homography maps representative points from the piece boxes to an 8x8 grid. On a synthetic dataset, the modifications to piece detection increase mean average precision from 61.59% to 90.14%. Of the predicted board keypoints, 97.11% are within 1% of the image diagonal of their labelled targets. Using ground-truth piece boxes with the predicted homographies gives correct square assignments for every test position. The complete framework recovers 76.61% of test positions exactly and 96.49% with at most one incorrect square. --- ### From Probabilities to Decisions: Search and Multi-Teacher Distillation with Jev Authors: Mohamad Yazan Sadoun, Sarah Sharif, Yaser Mike Banad Published: 2026-10-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.09188v1 Probability-only models, which TypeSafe calls System One models, return calibrated probabilities for fixed choices in milliseconds and generate no text. We study one such model, Jev, through two tasks that require decisions under tight constraints. In bullet chess, a bot that places Jev's judgment inside Stockfish search alongside an opening book and endgame tablebases climbs above a 2200 Lichess bullet rating against other bots. Live model calls are too slow for search, so we distill pairwise judgments into a compact evaluator that runs at every position. We then ask how best to spend a fixed labeling budget when an LLM, Qwen3-32B, is available as a second teacher. In chess, averaging both judges' labels beats spending the whole budget on Qwen alone by 9.6 Elo (95% interval 4.3 to 14.9), and the gain replicates on fresh openings; a second answer from the same judge is no substitute, and Jev is the strongest partner for Qwen among the models tested. In passage reranking, Jev's labels alone train a reranker that scores as high as Qwen's, from 21 minutes of API calls instead of 5.1 GPU-hours, and adding Qwen gains at most a few thousandths in ranking quality. Search supplies the lookahead, distillation makes the judgment cheap enough to use at every position, and an LLM partner pays off in chess. --- ### The Dichotomy Between Pattern Recognition and Step-by-Step Reasoning Authors: Amrut Nadgir, Pratik Chaudhari, Vijay Balasubramanian Published: 2026-10-06 Categories: cs.LG, cond-mat.dis-nn arXiv: https://arxiv.org/abs/2610.09186v1 We argue that pattern recognition and step-by-step reasoning are two ends of a spectrum. A large language model (LLM) learns to reason step-by-step when data is structured such that the next token depends on a small amount of preceding context. Inference in LLMs resembles pattern recognition when the next token depends on a large amount of preceding context. If the next token depends on only the $c$ most recent tokens, reasoning traces are paths on a De Bruijn graph whose nodes are $c$-length contexts and edges are next-token transitions between contexts. The set of reasoning traces of a task forms a directed acyclic subgraph of the De Bruijn graph. An LLM that has learned all edges of this subgraph can compose them to solve longer, unseen tasks, i.e., it reasons step-by-step. We prove that the number of edges is vanishingly small compared to the number of reasoning traces. Empirically, the number of training samples a transformer needs is a power law in the number of edges, so learning to reason step-by-step is sample efficient. We can induce De Bruijn structure in any task by maintaining a ``state'' that makes future reasoning independent of the past. The frequency of states in the reasoning trace determines $c$. We show, by fine-tuning Qwen2.5-1.5B-Instruct to solve equations and answer questions about stories, that frequent states (small $c$) result in higher accuracy but greater fragility to perturbations at test time. LLMs trained with a large $c$ are only as good as models that perform pattern recognition without reasoning. A moderate density of states balances accuracy and robustness. We show that real-world data has De Bruijn structure: Qwen3-14B and Qwen3-32B retain over 75% of their accuracy on GSM8K, MATH-500 and GPQA-Diamond when attention is restricted to a sliding window less than 15% as long as the full reasoning trace. --- ### One Frame, Full Heartbeat: ECG-Free 4D Cardiac Cine MRI Synthesis via Radial-Decomposed Flow Matching Authors: Shiyi Wang, Ruochen Sun, Xiang Li, Peirong Liu, Fangxu Xing Published: 2026-10-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.09185v1 Cine cardiovascular magnetic resonance (CMR) captures the cardiac cycle as a four-dimensional (4D) sequence, but standard acquisition requires electrocardiogram (ECG) gating and repeated breath holds. Visual realism alone does not establish accurate patient-specific ejection fraction (EF) or ventricular volumes. We present PhaseFlow3D, a generative framework that synthesizes a complete 4D cine sequence from a single end-diastolic (ED) three-dimensional (3D) volume without ECG. To capture asymmetric systolic and diastolic dynamics, it represents the cardiac cycle as a piecewise linear phase anchored at ED and end-systolic (ES) time points. At inference, a population-level canonical template supplies this phase without patient-specific temporal information. A phase-conditioned rectified flow model generates a cardiac motion trajectory in latent space. Radial Contraction Decomposition converts each latent state into a 3D displacement field, combining a physics-informed radial component for centripetal myocardial contraction with an image-conditioned residual for rotation and out-of-plane motion. Each frame is generated by directly warping the ED volume, bypassing variational autoencoder decoding. On the combined ACDC and M&Ms benchmark, PhaseFlow3D achieves the lowest EF mean absolute error, the only positive left-ventricular volume-curve $R^2$, and the best distributional quality among compared methods. Ablations confirm each component's contribution. Downstream evaluations demonstrate the utility of the synthesized sequences and displacement fields for segmentation, pathology classification, label propagation, and myocardial strain analysis. ---