# Research Papers — 2026-10 · bundle page 22 of 156 > Full-text markdown of papers #1051–1100 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/22 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/21.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/23.md) ### Computational compressive imaging reconstruction with a simulated-annealing-based Ising solver Authors: Ze Zheng, Xiaoyan Wu, Hang Xu, Jingzheng Huang, Tailong Xiao, Guihua Zeng Published: 2026-10-14 Categories: physics.optics, cs.CV, cs.DC, math-ph, physics.app-ph arXiv: https://arxiv.org/abs/2610.19778v1 Computational compressive imaging, such as single-pixel imaging and lensless imaging, is a promising imaging technique, enabling the reconstruction of objects from under-sampled measurements through compressed sensing algorithms or deep learning methods. However, the demand for electronic computational resources grows rapidly when recovering high-resolution and multi-dimensional images and training neural networks with numerous parameters, which has become a bottleneck for the widespread adoption of this technique. Here, we propose a physics-driven reconstruction framework that formulates imaging inverse problems as Ising models and directly recovers target objects through the self-evolution of non-von Neumann Ising machines toward the ground state of the Hamiltonian. We employ a simulated-annealing-based Ising solver to demonstrate this proof-of-concept by reconstructing objects in both single-pixel imaging and a lensless diffuser camera at sampling rates ranging from 1% to 25%. By further incorporating a foreground-sparsity constraint and a smoothness constraint, the reconstruction quality of our method is comparable to or even better than that of mainstream algorithms. This approach has the potential to substantially reduce the electronic computational burden of inverse reconstruction, paving the way for real-time, low-power computational imaging. --- ### Q-MAGIC: Quad-only Mesh Autoregressive Generation via Singularity-Aware Circular Relative Offset Tokenization Authors: Yuming Zhao, Zezeng Li, Weimin Wang, Xiang Wu, Na Lei Published: 2026-10-14 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2610.19777v1 Autoregressive models have proven effective for triangular mesh generation by transforming it into predicting the next face, converting the non-differentiable connectivity prediction into a sequence of token predictions. However, generating quad-only meshes remains challenging because quad faces impose stricter topological constraints than triangles. The model must not only serialize quad faces into a valid token sequence, but also support unambiguous connectivity reconstruction during de-serialization. To address this, we propose Q-MAGIC, a novel autoregressive model for quad mesh generation. We first introduce a tailored serialization scheme for quad meshes, which requires at least two new vertices for the next face and is less flexible than triangles due to strict wiring constraints. To meet these requirements and reduce serialization length, we propose a singularity-aware serialization that prioritizes wiring from singular points, leading to more coherent traversals. Additionally, we propose a circular relative offset tokenization that encodes geometry mainly via local relative offsets. Built upon this representation, an autoregressive Transformer learns the underlying distribution of quad meshes via next-token prediction, enabling effective quad mesh generation. Extensive experiments demonstrate that Q-MAGIC produces more compact sequences while consistently improving geometric fidelity and mesh quality compared to state-of-the-art methods. --- ### From Global to Tail Convergence: Dynamics of $α$-Stable Score-Based Generative Models Authors: Ianis Hammani, Claire Boyer Published: 2026-10-14 Categories: cs.LG, math.PR, stat.ML arXiv: https://arxiv.org/abs/2610.19773v1 Score-based generative models driven by $α$-stable L{é}vy processes have been proposed as an alternative to Brownian diffusion models, with empirical evidence suggesting improved sampling and better modeling of heavy-tailed data. Yet theoretical guarantees for these models remain limited. We develop a non-asymptotic convergence analysis for scale-preserving $α$-stable generative dynamics, covering both compactly supported and power-law targets. In p-Wasserstein distance, we quantify the effects of early stopping, initialization, score approximation, and time discretization, and show exponential decay of the initialization error. A comparison with Brownian dynamics reveals that global Wasserstein convergence alone does not fundamentally distinguish the two models: both initialization errors decay exponentially with the forward horizon on the common class of heavy-tailed targets. A sharp separation emerges instead in the tails. At any positive generation time, stable dynamics produces power-law tails with index $α$, whereas Brownian dynamics remains light-tailed. For a target with tail index $ν$, asymptotically correct extreme-quantile scaling is possible precisely when $α$=$ν$. These results identify tail-index matching as a principled mechanism behind the ability of stable generative models to capture extreme events. --- ### When Does the Dependency Graph Help Code-to-Architecture Mapping? Authors: Rakhshanda Jabeen, Morgan Ericsson, Jonas Nordqvist, Anna Wingkvist Published: 2026-10-14 Categories: cs.SE, cs.LG arXiv: https://arxiv.org/abs/2610.19769v1 Architectural technical debt arises when a system's implementation drifts from its inten ded modular decomposition, while the mapping between source files and architectural modu les is missing, incomplete, or costly to maintain manually. We formulate code-to-archite cture mapping as semi-supervised node classification over a directed multi-relational de pendency graph, with files as nodes, typed dependencies as edges, and lexical features d erived from code identifiers and directory layout. Starting from a small labeled sample, an iterative self-training procedure expands the mapping to the remaining files. We com pare a graph convolutional network (GCN), a graph attention network (GAT), and a graph-f ree multi-layer perceptron (MLP), using identical features and training procedures for t he learned models, against a Naive Bayes reference. Across 100 runs on ten open-source J ava and C/C++ systems, all three neural models outperform the reference on both F1 metri cs. GAT achieves the highest averages of system-level median macro and micro F1, at 83.5 and 92.2, respectively, whereas MLP remains competitive or superior on several systems. On Chrome, the largest system with 18,343 files, GAT and GCN exceed MLP by 22 and 19 ma cro-F1 points, respectively, and have substantially fewer persistently misclassified fil es. Connectivity and homophily are associated with where neural message passing helps, w hile multi-relational aggregation outperforms a single merged edge type on every system for both GCN and GAT. A follow-up study finds that several model rankings depend on the training seed, qualifying smaller advantages without removing the large graph benefit ob served on Chrome. --- ### Learning to Compute Is Not Learning to Retain or Reuse in Looped Transformers Authors: Peilong Zhou, Hongtao Zhang, Yulong Huang, Cangyuan Li, Mingyu Chen, Ying Wang Published: 2026-10-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.19768v1 Looped transformers compute by applying one block repeatedly, so they can run for more loops than they were trained with. Recurrent reasoners are known to overthink: iterating past the trained depth can turn a correct answer into a wrong one. Such a late error can reflect failed computation, loss of retention, or a state that later computation cannot reuse. We separate these cases in in-context Mealy-machine execution, where a simulator supplies intermediate targets and exact counterfactuals for hidden-state interventions. Models trained to answer at loop 32 are fully correct there but keep only 22% of these answers at loop 64. Retention depends on what training asks for: supervising one randomly chosen position per example, instead of always the last, keeps 99.8%, and randomizing the number of training loops also helps; truncating gradients, as in progressive training against overthinking, does not. The computation itself is exact: position $k$ is computed at loop $k$, and swapping its loop-$k$ hidden vector for the one from another input redirects every later position to that input's exact continuation (237/237 pairs in each of ten models). Retention, however, is not reuse. Even in models that keep nearly all answers, holding each position $k$ fixed from loop $k$ drops accuracy to 4--6%, whereas holding it from loop $k+4$ is harmless. A released recurrent maze network trained to avoid overthinking behaves the same way. Learning to compute is thus not learning to retain, and avoiding overthinking does not make a state reusable when its answer first appears. --- ### Likelihood Is Not Authorship: Can We Reliably Measure Human Contribution in AI-Assisted Writing? Authors: Hasan Amin, Zhuoran Lu, Ming Yin Published: 2026-10-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.19767v1 AI-text detection generally asks whether a machine wrote a text. As AI becomes an increasingly integral and accepted part of writing, the more relevant question is no longer whether AI was used, but how much of the text reflects human contribution. A prominent line of work estimates this by measuring how predictive a person's prompt is of the final text. We show that this measure can be easily manipulated. We introduce SPECIFICITY PADDING that simply asks the model to copy a few random IDs from the prompt, and that alone makes a title-only request look more human than one that supplies the article's key ideas. A context-swap audit then holds each document fixed, and only shows or hides the IDs to the evaluator. The score of the unchanged text swings by a third to half of its scale, and it rises for every document we test, on news and scientific abstracts, across varied LLMs from 3.8B to 753B parameters. The same articles can average 85\% human or 15\% human depending only on which prompt is on record, and even with no prompt at all, the output-only variant rewards the random strings themselves. An exact identity, the credit ledger, explains why. The score is a surprisal-weighted average over the text, so rare strings that the context makes copyable collect the credit, whatever they mean. A two-point bound marks a deeper limit. If the prompt could have been machine-written, every transcript-only method must, in the worst case, miss by half the contribution at stake. Likelihood-based scores alone cannot reliably establish human contribution without evidence of what the person added and how the text was produced. --- ### Analyzing and Mitigating Poisoning Attacks on Flow-Based Intrusion Detection Authors: Florian Spelter, Johannes F. Loevenich, Tobias Hürten, Erik Adler, Maxime Schwarzer, Laurin Holz, Roberto Rigolin F. Lopes Published: 2026-10-14 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2610.19766v1 Although Artificial Intelligence (AI)-based Intrusion Detection Systems (IDSs) are increasingly deployed in operational networks, their dependence on large-scale training data introduces a critical vulnerability to stealthy poisoning attacks. We demonstrate that latent backdoors can be successfully implanted in flow-based IDS models by poisoning as little as 0.001% of the training data, maintaining near-nominal performance on clean inputs while ensuring high attack success rates. To address this threat, we propose a diagnostic-first methodology that localizes trigger-relevant features through constrained perturbation analysis and detects poisoning-induced behavioral drift by comparison with a distilled baseline model. The proposed methodology further enables targeted mitigation via automated data sanitization or neuron pruning. Our findings expose the operational risks of near-undetectable backdoors and provide a scalable approach to analyzing, quantifying, and mitigating backdoor exposure in AI-based IDS. --- ### Physics-Shaped, Not Physical: Auditing Physics-Guided Underwater Image Restoration Authors: Mochamad Rizal Fauzan, Irgi Surya Published: 2026-10-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.19763v1 Physics-guided networks for underwater image restoration predict transmission and backscatter and invert the image-formation model, yet rarely test whether this physics does any work. We audit one representative design, PhysGuide-Net, with four controlled experiments: five-seed ablations on UIEB with zero-shot evaluation on the complete LSUI (4279 pairs) and AUIED3K (3000 pairs) sets; a data-efficiency study with a capacity-matched control that removes the formation model; and a validation of the predicted maps against measured range on Sea-thru. With all 800 training images the physics module gives no zero-shot gain (mean PSNR differences of at most 0.16 dB; all 95% intervals include zero) at 3.4x the FLOPs. With 80 images it helps more (+0.65 dB on UIEB, +1.48 dB on AUIED3K; seed-to-seed s.d. on AUIED3K from 1.3 to 0.5 dB), although not individually significant after correction, and the control does not reproduce this (0.8-1.0 dB lower). Yet the predicted transmission does not behave like a physical quantity: its correlation with range is no stronger than for the range map of a different image (pooled difference +0.02, versus -0.06 for the dark-channel prior), and a Beer-Lambert fit explains 0.4% of its variance. The effect of the module also changes sign with degradation severity between datasets. The benefit thus comes from a physics-shaped inductive bias, not from physics. We further show that single-run ablations can reverse sign and document implementation defects that invalidate loss ablations. --- ### PRISMATIC : Prescription Risk Inspection System for Multi-Agent Treatment Interaction in Clinical Decision-Making Authors: Ziyang Ling, Shuyu Lu, Ziyi Chen Published: 2026-10-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.19762v1 Medical prescribing errors for multimorbid patients, who require complex drug regimens, are a major patient safety concern. These errors often stem from fragmented decision-making across medical specialties, a critical coordination failure that leads to adverse drug events and rehospitalizations. To address this coordination challenge, we introduce PRISMATIC, a multi-agent architecture where specialized agents, each representing a workflow role, collaboratively generate and refine treatment plans. Operating on a blackboard architecture, the system first structures patient information from clinical notes, then iteratively develops safe, rational, and interpretable drug regimens. The agents' collaboration is governed by two novel adaptive coordination mechanisms: (1) Dynamic Self-Updating Weight Adjustment (DSWA), a long-term mechanism that adjusts the influence weights of agents based on historical case outcomes, enabling the system to adapt and trust more reliable specialists over time. (2) Discrepancy Feedback Precise Calibration (DFPC), a short-term mechanism where agents provide iterative feedback to resolve disagreements and eliminate prescription conflicts for the current patient. Experiments on patient records from the MIMIC-IV database show that PRISMATIC significantly reduces drug conflicts, improves prescription coverage, and enhances treatment consistency compared to strong LLM baselines. Our work demonstrates that structuring clinical co-treatment as a multi-agent coordination problem offers a promising path toward safer and more coherent multidisease management. --- ### CAST: History-Adaptive Spectral Clipping for LLM Pretraining Authors: Jiacheng Li, Jianchao Tan, Kefeng Zhang, Yuchen Xie, Xunliang Cai Published: 2026-10-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.19761v1 Soft spectral clipping (SSC) reduces gradient singular values, but its effect depends on the gradient scale and clipping threshold. We introduce CAST (Clipping with Adaptive Scales and Thresholds), a history-adaptive extension of SSC. AdamW's previous second moment sets row and column scales. An exponential moving average of the clipped output's estimated spectral norm sets each matrix's threshold. CAST restores the original coordinates before the AdamW update. We train a mixture-of-experts (MoE) model with 19.08B total parameters for 83.89B tokens. CAST achieves lower training and mean validation losses than nine gradient-processing baselines, with the fewest relative gradient spikes. It reaches the best baseline's final smoothed training loss in 7.2\% fewer steps. --- ### Qwen-MT-Lumen at WMT2026: Instruction-Specialized Translation via Quality-Aware Training and On-Policy Distillation Authors: Hao Wang, Yangyang Liu, Xiaohu Zhao, Heng Liu, Zifu Shang, Tianhao Li, Ruize Gao, Jialong Tang, Liangying Shao, Haoran Wei, Baosong Yang, Linlong Xu et al. Published: 2026-10-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.19758v1 We present Lumen, The open-source model is available at, our submission to the WMT 2026 General Machine Translation Shared Task. We focus on instruction-specialized translation, where systems must produce accurate translations while satisfying fine-grained requirements on style, terminology, and structured output. Lumen follows a four-stage pipeline. First, continued pre-training and supervised fine-tuning jointly strengthen multilingual translation competence and the ability to follow translation-specific instructions, such as terminology, style, and format constraints. Second, we extend the originally offline M^{2}PO preference-optimization framework into an online preference-optimization stage: the current policy samples candidate translations, an LLM judge assigns continuous direct-assessment scores, and the resulting multi-pair preferences are used to update the model. Third, on-policy distillation transfers stronger translation-instruction-following behavior from a larger teacher model to the Qwen3-14B student, improving translation-instruction adherence while retaining a 14B primary translation backbone. Finally, structure-aware inference and postprocessing preserve required formats, while selective repair addresses clear structural or decoding failures before submission. We participate in 23 translation directions. Under an absolute 1--5 LLM-judge rubric that evaluates translation-instruction following and translation quality separately, Lumen reaches an overall mean score of 4.60. Despite using a 14B translation backbone, it achieves performance comparable to leading proprietary systems in both translation quality and translation-instruction following. --- ### Beyond Reachability: A Relation-Semantic Reasoning Framework for Biomedical Multi-hop QA Authors: Ziyang Ling, Ziyi Chen, Ronald X. Xu, Mingzhai Sun Published: 2026-10-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.19754v1 Biomedical multi-hop reasoning over knowledge graphs requires identifying a semantically valid relation sequence that supports the answer. Existing methods can retrieve correct answers, yet often rank them poorly within a large pool of seemingly relevant candidates. Even when a correct answer is retrieved, its associated evidence and reasoning path may fail to support the relation composition required by the question. We term this disconnect between answer reachability and evidential validity the reachable-but-invalid problem. We present ReSemReason, which shares a question-induced distribution over typed, directed relation schemas between candidate discovery and evidence selection. Schema compatibility guides graph search; ReSemAttn then uses relation-conditioned key/value projections and an uncertainty-weighted path prior to attend to candidate-specific evidence. A separate absolute-support score complements normalized attention when all retrieved paths are weak. The reported experiments on BioHopR, PrimeKGQA, and MedReason show improvements in answer ranking and answer-set quality. Path-discrimination analyses examine the distinction between endpoint correctness and evidential support. We also specify matched controls for search, attention, and schema uncertainty. --- ### Discriminative Score Function: Turning Pretrained Models into Functional Generative Priors Authors: Junhoo Lee, Hyeonjin Kim, Sangbum Han, Nojun Kwak Published: 2026-10-14 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2610.19743v1 Discriminative models are trained with task-specific objectives such as classification, detection, or representation learning, yet their practical utility depends on generalizing beyond the training task to unseen samples from the same domain. This suggests that a discriminative model may retain an implicit trace of the data manifold beyond its task labels. We ask whether this trace can be exposed as a generative signal without task-specific guidance. We introduce the Discriminative Score Function (DSF), which extracts an image-space generative field from the loss-gradient geometry of a pretrained discriminative model. DSF provides a training-free update rule that moves images toward model-consistent visual regions without retraining or task-specific targets. We apply DSF to diverse pretrained discriminative models, including ResNet classifiers, DETR detectors, and DINOv2 ViT encoders. DSF generates unconditional images from noise and supports conditional guidance, editing, inpainting, and explanation through the same field. DSF-generated samples also provide effective zero-shot quantization calibration when real images or labels are unavailable, preserving feature geometry better than data-free calibration baselines. These results show that discriminative training leaves a generative functional signal for synthesis and calibration. Project page: https://junhoo.me/dsf. --- ### HyperLoop: Hyperspectral-Assisted Loop Closure Detection in 3D-SLAM for Planetary Exploration Authors: Annie Bhalla, Dennis Rotondi, Riccardo Giubilato, Kai O. Arras, Wolfgang Stuerzl Published: 2026-10-14 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2610.19742v1 Autonomous navigation of planetary rovers is challenged by visually repetitive, featureless terrain. SLAM systems based on 3D Gaussian Splatting (3DGS) offer dense mapping but rely on RGB appearance descriptors that degrade under perceptual aliasing - a common failure mode in extraterrestrial environments where physically distinct locations appear visually identical. This paper presents HyperLoop, the first framework integrating hyperspectral imaging (HSI) into the loop closure module of a 3DGS-based SLAM system. Hyperspectral descriptors encode material-level spectral signatures complementing RGB features, providing robustness to illumination changes and visual repetitiveness. Two HSI descriptor families are introduced: Bag-of-Spectral-Words (BoSW), encoding spectral material distributions via TF-IDF weighted histograms, and PCA-K VLAD (PCAK-VLAD), capturing first-order residual statistics of PCA-compressed spectral signatures. Both are evaluated with SIFT-VLAD and NetVLAD RGB descriptors under Strict-AND and Weighted fusion strategies on a custom dataset from the Moon-Mars Outdoor Test Site (MMOTS) at DLR, comprising synchronized RGB-D and hyperspectral sequences across four planetary analog traverses (65.5 m total). A key finding is that the sensor's Red-NIR range (600-860 nm) provides limited discriminability for rock terrain: the best HSI fusion (SIFT-VLAD + BoSW, Strict-AND) achieves 5.04 cm ATE RMSE, within 1.8% of SIFT-VLAD alone (4.95 cm). The gain over NetVLAD (8.81 cm) is attributable to SIFT-VLAD, not HSI fusion. This motivates future adoption of SWIR sensors capturing diagnostic mineral absorption features absent from the 600-860 nm range for planetary SLAM missions. --- ### Does the Linguistic Register of Thinking Matter? Wenyan as a Compact Reasoning Register for Chinese LLMs Authors: Minghan Li, Guodong Zhou Published: 2026-10-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.19741v1 Visible reasoning traces of Chinese reasoning-oriented LLMs are typically written in modern vernacular Chinese, which may be verbose under limited decoding budgets. We ask whether the linguistic register of reasoning can be used to improve efficiency. We propose Wenyan Thinking, which emits intermediate reasoning in Classical Chinese (wenyanwen) while retaining a short direct-answer output. Starting from modern-Chinese reasoning traces, we rewrite only the reasoning field into wenyan and fine-tune Qwen3-4B-Thinking-2507 on the rewritten supervision. To distinguish register shift from generic compression, we construct a compact modern-Chinese control using the same source data, teacher family, base model, and SFT recipe. Across budget-sensitive evaluations on MMLU-ProX-Lite-ZH, CEVAL, and AGIEval-CN, Wenyan Thinking substantially reduces reasoning length and missing-answer rates under constrained decoding. Compact rewriting explains much of the efficiency gain, while wenyan consistently outperforms the compact modern-Chinese control on the primary benchmark and remains competitive across the additional benchmarks. These results identify linguistic register as a practical design axis for efficient visible reasoning in Chinese LLMs. --- ### ProtModernBERT: Compute-Efficient Protein Language Modeling Authors: Alberto Martínez, Natalia Flechas Manrique, Llorenç Espinosa-Portalés, Luc Andrea Published: 2026-10-14 Categories: cs.LG, cs.AI, q-bio.QM arXiv: https://arxiv.org/abs/2610.19738v1 Large protein language models provide a powerful framework for learning sequence-function relationships and guiding experimental design. However, architectural improvements are underexplored, especially in low-compute regimes of relevance for resource-constrained research laboratories. We show that the training cost for encoder-only transformer architectures can be reduced by leveraging modern architectural refinements, offering an encouraging performance / compute-efficiency trade-off. We introduce ProtModernBERT, a modernized BERT-style model pre-trained on amino acid sequences, and compare it with ProtBert, Amplify, and ESM2 across a set of supervised structural tasks -encompassing secondary structure prediction, disorder prediction, and subcellular localization- and ProteinGym's zero-shot functional benchmark. We find that ProtModernBERT matches or closely tracks the performance of Amplify-120M and ProtBert with up to 80-90\% reduction in pre-training FLOPs, and narrows the gap to ESM2 when controlling for pre-training. Our analysis using a cluster-based validation protocol for hyperparameter selection and randomly initialized models disentangles the contributions of architecture and data, showing that modern components provide stronger inductive biases that are more consequential than parameter count in low-compute regimes. --- ### MakSafe: A Spatiotemporal Semantic Framework for Formal Specification and Compliance Checking of Road Vehicle Safety Rules Authors: Maksym Labzhaniia, Julien Deantoni, Marie-Agn{è}s Peraldi-Frati, Fr{é}d{é}ric Mallet Published: 2026-10-14 Categories: cs.CL, cs.SC arXiv: https://arxiv.org/abs/2610.19735v1 Scenario-based validation is essential for automated road vehicles but cannot cover the full variability of openworld traffic. We present MakSafe, a formal spatiotemporal framework for specifying and checking road vehicle safety rules through semantic zones, action-based forecasting, and trace-tree reasoning, avoiding uniform time discretization. We formalize the road network, vehicle states, and occupancy zones, then build executable rules for front-vehicle identification and timeto-collision (TTC) verification. The evaluation combines a tracedependent case study with a scalability benchmark over traffic density (N ), horizon (H), and branch factor (B). MakSafe yields branch-specific verdicts, deriving safe and unsafe outcomes from the same initial scene, and re-evaluates a scenario after a control update. A single rule check stays well below a millisecond across the reported sweep, and longer horizons slow the TTC check. --- ### Object Pose from 2-D to 3-D Point and Line Correspondences Authors: Thai Quynh Phong, Radu Horaud, Adnan Yassine, Pham Dinh Tao Published: 2026-10-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.19734v1 In this paper we present a method for optimally estimating the rotation and translation between a camera and a 3-D object from point and/or line correspondences. First we devise an error function and second we show how to minimize this error function. The quadratic nature of this function is made possible by representing rotation and translation with a dual number quaternion. We provide a detailed account of the computational aspects of a trust-region optimization method. This method compares favourably with Newton's method which has extensively been used to solve the problem at hand, with Faugeras-Toscani linear method (6) for calibrating a camera, and with the Levenberg-Marquardt non-linear optimization method. Finally we present some experimental results which demonstrate the robustness of our method with respect to image noise and matching errors. --- ### Exact Cut Complexity of Equal-Length Proportional Cake Cutting Authors: Yasushi Kawase, Bodhayan Roy, Mohammad Azharuddin Sanpui Published: 2026-10-14 Categories: cs.MA, cs.AI, cs.DS, cs.GT arXiv: https://arxiv.org/abs/2610.19733v1 We study proportional cake cutting under an equal-length constraint, where each of $n$ agents must receive a bundle of length exactly $1/n$ that is worth at least $1/n$ to that agent. Our main result determines the exact worst-case number of cuts needed to guarantee such an allocation, namely $2n-2$ for every $n$. This improves on the previously known quadratic upper bound. The proof combines the constrained necklace-splitting theorem with a recursive assignment argument based on Hall's theorem. The same bound extends to the stronger requirement of envy-freeness when $n$ is a prime power, and an $O(n^{1.525})$ upper bound holds for arbitrary $n$. We then ask whether such allocations can be computed. We first show that no deterministic protocol in the Robertson--Webb model terminates after finitely many queries on every instance and always returns an exact equal-length proportional allocation, even for two agents with identical valuations. For every $\varepsilon>0$, however, $O(n^2/\varepsilon)$ queries suffice to produce an allocation in which every agent receives a bundle of length exactly $1/n$ and value at least $1/n-\varepsilon$, again using at most $2n-2$ cuts. Finally, we augment the Robertson--Webb model with two-knife queries. We show that recursive balanced halving attains the optimal bound of $2n-2$ cuts when $n$ is a power of two. For arbitrary $n$, we give a procedure using $O(n\log n)$ cuts. --- ### Controlling the latency in temporal coded spiking models for neuromorphic datasets Authors: Alban Gattepaille, Alexandre Muzy Published: 2026-10-14 Categories: cs.NE arXiv: https://arxiv.org/abs/2610.19732v1 Exploiting temporal information in datasets with high temporal dependencies (such as spoken keyword recognition) by spiking models is still an open problem. Promising frameworks include Time-To-First coding (TTFS) and the inclusion of synaptic delays into learning. In TTFS, neurons are forced to spike at most once, forcing the network to found its learning on the spiking times of neurons rather than their spiking rate. Some models use the TTFS framework to directly compute the spiking time of Integrate-and-Fire (IF) or Leaky Integrate-and-Fire (LIF) neurons. However, most models built in the TTFS framework have not been tested against datasets containing temporal information. Little is known about the latency of these models on temporal datasets, where the latency is the time taken by the network to correctly classify a sample. In this work, we study the behaviour of Delay Neural Networks (DeNN) models, i.e. models that directly compute the spiking time of neurons by bypassing the membrane potential and thresholding mechanisms of spiking neurons. We show how to analytically control their latency, and empirically study the latency-accuracy tradeoff in a dynamic temporal dataset. --- ### What Happens to the Goal? Distinct Failures of Policy Alignment in Goal Misgeneralization Authors: Julia Barth, Armin Sommer, Kunvar Thaman, Jannik Schilling Published: 2026-10-14 Categories: cs.LG, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2610.19731v1 Goal misgeneralization is a common failure mode in which an agent behaves competently out of distribution but does not pursue the intended goal. However, we still have a weak understanding of what happens to the intended goal in misgeneralizing agents. Across three Procgen environments and five robot tasks, we find three distinct forms of policy-goal misalignment: (1) functional target substitution, where behavior follows an alternative goal, (2) a policy shortcut, where behavior follows a learned action strategy, and (3) cue competition between intended and proxy goal cues. We distinguish these regimes by tracing where goal information remains available internally, how strongly it influences the policy, and what role it plays in action selection, and find that the goal is lost at different depths. Where the goal reaches the decision, as in cue competition, steering redirects the policy to the goal's location, raising intended-goal reach from 16.0% to 95.3%. Where it reaches the policy but not the decision, only new downstream wiring recovers goal reach, from 31.6% to 84.3% in the environment with the action shortcut. Where it is inert, neither works. Our results show that goal misgeneralization is not a single failure of goal representation, but distinct failures of policy alignment at different depths, tightly connected to which recovery works. --- ### Design and Analysis of Temporal Representations in Neural Networks Authors: Alban Colas-Gattepaille, Alexandre Muzy Published: 2026-10-14 Categories: cs.NE arXiv: https://arxiv.org/abs/2610.19730v1 The ability to represent temporal information is often hypothesized to underlie the efficiency and learning capabilities of biological neural networks. This motivates the development of spiking neural networks. However, it remains unclear how temporal information is actually represented in neural networks and how different forms of temporal representation affect performance and computational efficiency. We introduce the notion of the degree of temporal representation of a neural network, defined by whether its constituent functions (activation, learning, encoding, and decoding) explicitly manipulate time as a computational variable. This perspective yields a continuum ranging from non-temporal representations, where time does not explicitly appear as a computational variable in the network functions, to fully temporal representations, where computations explicitly operate on temporal variables. Using a fixed deep architecture, we compare different encoding, activation mechanisms and decoding with increasing temporal expressiveness: non-temporal weighted-sum activations used in usual artificial neural networks, non-temporal binary spiking activations used in spiking neural networks, and spike-time-based activations used in delay neural networks. Experiments on event-based datasets show that increasing the degree of temporal representation improves both performance and computational efficiency, allowing state-of-the-art performances on the Google Speech Commands dataset. We further analyze how temporal representations induce distinct forward and backward computational trajectories, leading to gradients that depend explicitly on the history of event times. --- ### A Diagnostic Study of World-Space Human Recovery Under High Camera Dynamics Authors: Hao-Jen Chien, Wei-Lun Chao, Yu-Lun Liu Published: 2026-10-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.19729v2 Monocular world-space human recovery methods excel on current benchmarks, but these rarely include fast camera motion. We introduce the K-Pop stress test, broadcast dance videos that combine fast, large camera motion with dense multi-person choreography. Leading methods produce plausible per-frame meshes on these videos, yet their world-space trajectories drift far from the performers' stage positions. Through a systematic diagnosis, we show that the camera and human estimates each remain self-consistent, and that the drift appears when they are combined at mismatched scales. Each is recovered at its own scale, so a mismatch between the two can turn camera motion into human drift that grows with camera displacement and becomes severe in broadcast dance videos. We derive a closed-form correction that estimates this mismatch and applies one scale to all performers, removing the drift while keeping their relative positions in one shared world frame. It requires no retraining and works with existing backends. Combined with physical constraints, the correction yields stable world-space reconstruction for choreography modeling, scene editing, data generation, and virtual reshooting. Project page: https://chien90190.github.io/worldhmr-fastcam-website/ --- ### Mitigating Video Hallucinations via Attention-Guided Representation Perturbation Authors: Zhixin Cai, Ruoqi Yuan, Xinchen Yang, Zhuofan Chen, Jun Bai, Chuantao Yin, Wenge Rong Published: 2026-10-14 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.19728v1 Video large language models (Video LLMs) often generate responses unsupported by the input video. Contrastive decoding (CD) can mitigate these hallucinations, but its effectiveness depends on how the negative branch weakens visual evidence. Existing methods rely on predefined perturbations or masking guided by question reconstruction, offering limited control over the model's visual reliance during answer generation. We introduce Attention-guided Representation Perturbation for Contrastive Decoding (ARP-CD), a training-free framework for constructing contrastive negatives directly in representation space. ARP-CD uses the attention mass assigned to visual tokens at the answer-prediction position to guide bounded gradient updates of the language model's input visual hidden states. These updates reduce visual attention and produce a negative input, whose predictions are contrasted with those of the original branch throughout generation. Experiments across four Video LLMs and four benchmarks show that ARP-CD outperforms representative training-free baselines in most model--benchmark settings, reducing hallucinations while improving general video understanding. Further analyses show that attention-guided perturbation directions improve negative quality and that the resulting negatives provide effective contrastive references for correcting the original predictions. --- ### Generative World Simulation with DAO and JING Authors: XGEN Team, Guohao Cai, Haoxuan Che, Frank Fan, Chenran Huang, Junjia Huang, Jiayi Jiang, Yanheng Li, Leon Liu, Shaoteng Liu, Xi Liu, Feng Nie et al. Published: 2026-10-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.19726v1 We present a Generative World Simulation framework that couples persistent shared world state with continuous first-person audiovisual generation. The framework integrates DAO, a computable world engine, and JING, an Egocentric Interactive Experience Model, to support sustained interaction for humans and agents. DAO maintains the states of characters, objects, and spaces and their relationships, advancing the world according to interaction rules and world time while preserving the consequences of past actions. From this evolving state, DAO derives observer-specific conditions for JING, which combines these conditions with character, object, and scene references, observation history, and current actions to generate each observer's audiovisual experience. Users can explore environments, manipulate objects, and communicate with characters through viewpoint control and text instructions, with their actions shaping both the shared state and subsequent experiences. By connecting world-state evolution with experience generation in a continuous interaction loop, the framework offers an approach to building interactive worlds that retain their history, evolve through action, and persist beyond any individual observer. --- ### TimeRSI: Towards Self-Improved Agentic Deployment for Time-Series Foundation Models Authors: Haoxin Liu, Deqing Fu, Lucheng Fu, Yiqiao Jin, Rushi Qiang, Harshavardhan Kamarthi, B. Aditya Prakash Published: 2026-10-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.19725v2 Time-series foundation models provide strong zero-shot forecast, but deployment for real-world applications still requires task-specific designs for model inputs and outputs. Direct inference can leave domain knowledge and recurring forecast errors unaddressed, while tailored pipelines require substantial human expertise and effort. We introduce TimeRSI, a self-improving agentic deployment system around frozen forecasting models. A coding agent translates task descriptions into executable pipeline changes. It tests each revision on historical forecasting windows and uses observed errors to guide subsequent revisions. During deployment, an adaptive selector chooses among the resulting pipelines using completed forecasts under similar conditions. Across 198 tasks on TIME and fev-bench, TimeRSI outperforms all submissions on six point and probabilistic forecasting metrics. Controlled comparisons support the value of feedback-guided revision over non-iterative pipeline search. Further experiments verify the generalization with different coding agents and forecasting models. Code is available at https://github.com/haoxin1998/TimeRSI. --- ### Recognizing Dialogue Ambiguity via Candidate Set Visual Grounding Authors: Shun Inadumi, Lee Sangmyeong, Koichiro Yoshino Published: 2026-10-14 Categories: cs.CL, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2610.19723v1 Interpreting an ambiguous utterance in real-world interactions often requires context beyond a single utterance. When the utterance refers to objects in a visual scene, it is necessary to maintain and update the set of plausible referents as context accumulates, without assuming that the available information identifies a unique object. However, prior work on interactive visual grounding, which localizes objects referred to by linguistic expressions, has focused on identifying a unique object once sufficient dialogue context becomes available. To address this gap, we propose Candidate Set Visual Grounding (CSVG), a task for estimating the set of objects consistent with the given dialogue context. We further introduce CandVG, a benchmark that evaluates how the candidate set changes across dialogue turns. Our evaluation of vision-language models shows that stronger visual grounding capability does not necessarily yield better CSVG performance. In particular, models have difficulty predicting the complete candidate set, owing to challenges in candidate generation and premature commitment to a small set of candidates in early turns. Nevertheless, we find that this limitation can be partially mitigated in the evaluated large-scale models using instructions designed for CSVG. --- ### ONCship: A Large-Scale Underwater Acoustic Corpus for Ship Recognition Authors: Zhe Cao, Jichao Zhang, Xiao-Lei Zhang Published: 2026-10-14 Categories: cs.SD, cs.AI, eess.SP arXiv: https://arxiv.org/abs/2610.19722v1 Recent advances in deep learning have significantly improved underwater acoustic vessel recognition. However, existing publicly available datasets are typically limited in scale, hindering large-scale representation learning and downstream task evaluation. To address this limitation, we introduce ONCship, a large-scale underwater acoustic dataset comprising 4521 hours of curated recordings from Ocean Networks Canada (ONC) hydrophones and Automatic Identification System (AIS) data. We evaluate the proposed dataset across three tasks: self-supervised representation learning, vessel-type classification, and MMSI-Level Vessel Classification. Experiments on DeepShip and ShipsEar demonstrate the effectiveness of ONCship for acoustic representation learning, with joint pre-training on ONCship and AudioSet achieving a classification accuracy of 62.45% on DeepShip through linear probing. Furthermore, incorporating ONCship as auxiliary training data improves downstream vessel-type classification performance. Beyond conventional vessel-type classification, we further investigate MMSI-Level Vessel Classification, treating each vessel as a distinct identity. Experimental results show that models fine-tuned with different loss functions achieve Top-1 accuracies exceeding 53% and Top-5 accuracies approaching 69%, demonstrating the feasibility of distinguishing individual vessels through MMSI-Level Vessel Classification. Overall, ONCship provides a valuable resource for underwater acoustic representation learning and vessel recognition, while its rich vessel-level metadata enables further exploration of MMSI-Level Vessel Classification. --- ### Articulation Upper Bounds for Language Models Authors: Alexander Spangher, Daniel E. Ho, Diyi Yang, Noah Goodman, Sanmi Koyejo Published: 2026-10-14 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.19721v1 Language captures only a subset of the perceptions, intuitions and intents that form meaning between speakers. What, then, are the limits of language? We take steps towards measuring this in LLMs as follows: for a set of concepts, we measure how well each concept can be transmitted between two LLMs as their capabilities scale. This requires novel measurement tools: (1) optimal messages: we introduce a prompt optimization algorithm that beats existing algorithms by up to 14% on benchmarks and accurately estimates prompt upper bounds. (2) A transmission measure: the sender is asked to label text; the receiver then tries to recover the sender's prompt, and recovery is measured; we find this correlates strongly with human label error. With these measures, we use observational scaling laws to study how transmissibility of a concept, conveyed with optimal messages, increases as transmitter and receiver capacity grows: does it asymptote below or above a threshold? Measuring 1.2k concepts in eight domains, we find concepts that (a) can be fully articulated; these concepts usually depend on local patterns, e.g. "joke ends with surprise"; (b) might be articulated by future, stronger models; these rely on whole-text structural patterns, e.g. "story's worldbuilding coherence"; (c) concepts that face articulability limits; these concepts' meaning, we find, is tied to identity and social-group awareness, e.g. "comic voice". Interesting, these same concepts are not all challenging for humans: humans have moderate-to-high levels of agreement in 76% of concepts that LLMs struggle with; articulation limits, we find, are executor relative. Finally, we characterize the nature of improvement in each case: while recoverable concepts can be articulated through definitions and explanations, irrecoverable concepts cannot be transmitted, even with examples, and might require novel learning mechanisms. --- ### Learning Individual Scientific Taste with Privileged Hindsight Distillation Authors: Hanwei Fan, Yanqiao Wang, Yiqi Zhu, Xuanyu Lei, Peng Li, Yang Liu Published: 2026-10-14 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.19719v1 Scientific taste shapes which research directions researchers pursue, and it varies across individuals. Existing work evaluates research directions along multiple evaluation criteria or models scientific taste using community feedback signals such as citations and reviews, but neither directly captures how individuals translate assessments under the same criteria into different preferences. We model scientific taste as a researcher-specific mapping from criterion-level assessments in a shared, evidence-grounded evaluation space with proposal-visible evidence, to relative preferences. A population-level mapping learned from retrospective supervision provides a cold start when individual feedback is scarce. We introduce Privileged Hindsight Distillation (PHD), which uses later-emerging scientific evidence during training to improve proposal-time criterion assessment and the population mapping, while exposing only proposal-visible information at inference. We evaluate our approach primarily in quantum research, where structured public reviews are largely unavailable, and use pairwise proposal comparison as a direct interface for observing individual taste. With only 15 comparisons per researcher, our method captures sharply different tastes, including opposing preferences over the same research-direction pairs when they trade off across evaluation criteria. In an interactive study, personalized rankings also surface proposals associated with greater subsequent user engagement, connecting learned taste to downstream research exploration. --- ### No Way To Steal My Face: Proactive Defense Against Identity-Preserving Personalized Generation Authors: Lizhi Xiong, Jun Li, Ziqiang Li, Weiwei Jiang, Zhangjie Fu Published: 2026-10-14 Categories: cs.CV, cs.CR arXiv: https://arxiv.org/abs/2610.19717v1 Recent advances in diffusion models have enabled high-fidelity, identity-preserving image generation for personalized applications such as digital avatars and virtual try-on systems. However, their reliance on sensitive facial reference images raises growing privacy concerns. Existing defense mechanisms are primarily designed for training-based personalization and struggle to generalize to emerging training-free approaches, due to fundamental differences in their identity integration paradigms. To bridge this gap, we propose IDGuardian-the first generalizable and model-agnostic identity protection framework capable of defending against both training-based and training-free personalization methods. IDGuardian abstracts the personalization process into two critical stages: identity extraction and identity injection. It then introduces crafted adversarial perturbations to simultaneously disrupt both stages. Specifically, it degrades the identity features extracted by external encoders and establishes an adversarial conceptual bridge that misdirects the generative trajectory away from the target identity. Extensive experiments show that IDGuardian effectively protects identity across various personalization pipelines and model architectures, while remaining robust to post-processing, adaptive attacks, and cross-dataset generalization. Our code is available at https://github.com/OpenAscent-L/IDGuardian.git. --- ### Uncertainty-Driven Self-Play for Robust Multi-Agent Driving Policies Authors: Sajad Marvi, Julian Schmidt, Alessandro Canevaro, Julian Jordan, Abhinav Valada Published: 2026-10-14 Categories: cs.RO, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2610.19714v1 Learning robust driving policies that generalize beyond their training domain remains a central challenge in motion planning. We propose an uncertainty-driven self-play scheme, in which half of the agents are rewarded for increasing their neighbors' epistemic uncertainty, while the other half learn to drive safely as the exploring agents continuously seek out their weaknesses. Epistemic uncertainty indicates where the policy is least confident and serves as an automatic proxy for scenario difficulty. Exploring agents use this signal to seek out hard cases, generating a challenging curriculum without manual scenario design. The resulting policy outperforms standard self-play, achieving best-in-class zero-shot transfer to nuplan Val14 (99.12% vs. 97.97%) and Argoverse 2 (82.39% vs. 78.03%) without fine-tuning, while also improving performance over standard self-play on Waymo. Our diversity-driven approach achieves 85% higher LSTM hidden-state coverage than the baseline, indicating a much richer set of behaviors. Further analysis shows that epistemic uncertainty serves as a calibrated difficulty detector, with highest-uncertain agents exhibiting 14.8 times the combined failure rate across collision, off-road, and DNF, of lowest-uncertain agents, enabling automatic prioritization of challenging scenarios without ground-truth labels. --- ### New Model, Old Habits: Behavior Transfer under Model Swapping in Multi-Session LLM Agents Authors: Youngbin Choi, Sehyun Hwang, Suhyeon Jun, Seoyeon Lee, Sunghyun Choi, MoonJeong Park, Dongwoo Kim Published: 2026-10-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.19712v1 Multi-session agents can switch between LLMs to balance performance and inference cost. Such switches require transferring a history for continuity, yet their effects on the recipient remain underexplored. Through controlled experiments with multi-session tasks, we uncover behavior transfer: recipients tend to adopt reasoning and action patterns from the models that generated their histories. This effect is most evident with raw-history transfer but is substantially reduced by summarization. Based on these findings, we propose Direction- and Authorship-aware Summarization of History (DASH) that preserves stronger-model behavior while minimizing weak-to-strong transfer via summarization. Experiments with repeated swaps show that DASH outperforms raw-history transfer and naive summarization baselines. These results suggest that effective multi-model orchestration requires considering not only which model to use, but also which behavioral patterns to carry forward. --- ### Beyond State Capacity: Why Retrieval Breaks in Mamba Authors: Nir Yarden, Amit Ben-Artzy, Roy Schwartz Published: 2026-10-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.19709v1 Mamba models underperform Transformers on in-context retrieval. This gap is usually attributed to Mamba's fixed-size recurrent state, which loses information as the context grows. We challenge this assumption by focusing on query-first retrieval, a setup in which the query precedes the context and state capacity should not be the binding constraint. We show that even in this setting Mamba lags substantially behind Transformers, despite its selection mechanism, which was designed to distinguish relevant content from distractors. We then demonstrate that the Mamba selection gates have sufficient control over the state updates to influence the model output: intervening on specific gates alone can swing accuracy between extremes. However, as gates are input-dependent, they require the incoming token's representation to encode its relevance to the query. We therefore probe token representations across layers, and find that the relevance signal emerges only gradually with model depth, and that the gates begin to reflect it only several layers deeper. Crucially, we find that gates in retrieval-critical layers are not yet aligned with relevance. The selection mechanism is thus expressive enough to solve the task, but it commonly operates on a relevance signal that has not yet arrived. Mamba's retrieval bottleneck therefore extends beyond state capacity: even when capacity is sufficient, the delayed emergence of relevance information across depth often prevents successful retrieval. --- ### SceneAE: Scene Generation and Reconstruction in Queryable 3D-Anchored Latent Space Authors: Shuofeng Sun, Wenzhao Zheng, Yunpeng Zhang, Yi Wu, Linqing Zhao, Haibin Yan Published: 2026-10-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.19708v1 Recent video world models have increasingly adopted 3D memory mechanisms to integrate historical observations into a lightweight and persistent scene representation. This naturally raises a complementary question: if 3D representations can serve as an effective mechanism for memorizing observed scenes, can they also be directly used as the latent space for reconstructing and generating scenes? Motivated by this idea, we represent a scene as a compact and unstructured 3D-anchored latent space (\textbf{SceneAE}). Each latent combines an explicit 3D position with an implicit content feature and is spatially grounded to describe its local scene region, forming a sparse latent point cloud. Unlike conventional video-VAE latents that describe how a scene appears from particular viewpoints, our representation directly describes the scene itself, making it naturally applicable to both reconstruction and generation. For reconstruction, once the scene has been generated, our persistent 3D representation can be projected and decoded into RGB-D observations by different target cameras, without the need to regenerate a video for each new camera trajectory. For generation, we leverage the geometry-content separation to first generate camera-controlled 3D geometry and then synthesize content conditioned on it, reducing camera-appearance entanglement and improving camera controllability. Experiments show that this 3D latent achieves superior generation quality, computational cost, and camera controllability. --- ### RouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing Authors: Xiaohan Wang, Haozhen Zhang, Qingyuan Liu, Tao Feng, Wenya Wang Published: 2026-10-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.19705v2 LLM routing dynamically selects and coordinates heterogeneous language models across diverse tasks. However, existing approaches are largely built around a predefined execution paradigm, such as single-round, multi-round, or agentic routing, which fixes how model calls are organized and limits adaptation to different query needs. We propose RouteWeaver, a unified routing framework that integrates these routing modes within a single LLM policy, jointly learning which mode to use and how to select models within that mode. To jointly optimize mode selection and within-mode execution, we develop COMET-GRPO (COordinated Mode-Execution Training), which decouples the trajectory-level advantage into separate signals for mode selection and within-mode execution, enabling more targeted credit assignment to each decision level. We further introduce progressive exploration, which gradually shifts training from externally assigned modes to autonomous selection, so that the router first learns how to execute each mode before deciding when to use it. We evaluate RouteWeaver across mathematics, coding, knowledge, logical reasoning, and factual recall. RouteWeaver achieves an average accuracy of 61.4%, an 11.03% relative improvement over the strongest baseline, and outperforms all compared baselines in each of the five domains. Ablations show that both COMET-GRPO and progressive exploration are important for adaptive routing; without progressive exploration, the routing policy collapses entirely to single-round execution. --- ### BANGLAPLAN: A Benchmark for Constraint-Based Planning and Decision-Making in Bangla Authors: Md Rayhanul Masud, S M Maksudul Alam, Mohammad Jaminur Islam Published: 2026-10-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.19704v1 Large language models (LLMs) increasingly help users arrange appointments, plan journeys, and allocate limited resources. These tasks require models to satisfy constraints on time, cost, capacity, and order, or determine that no feasible solution exists. Bangla is the world's seventh most widely spoken language, and existing benchmarks cover many language and reasoning tasks. However, benchmarks for evaluating planning and decision-making in Bangla under explicit constraints remain lacking. We introduce BANGLAPLAN, a benchmark of 1,000 problems across ten task families grounded in everyday life and institutions in Bangladesh. It includes feasible and infeasible problems in four language registers: everyday, formal, colloquial, and Bangla--English mixed. Answers cover eight structured types, including schedules, routes, allocations, and ordered steps, in a common JSON format. We construct the benchmark through language-model-assisted drafting and independent human validation. We evaluate 11 open-weight and proprietary model configurations using exact match, separately reporting feasible-case accuracy, infeasibility detection, and format errors. We find a large performance gap: GPT-6.1 Sol achieves 98.7% accuracy and Qwen3.5-27B with thinking reaches 80.3%, while direct-answer configurations score at most 30.9%. Seven of eleven configurations perform below the always-``infeasible'' baseline. Our findings also suggest that harder problems primarily reduce plan-construction accuracy, while infeasibility detection remains more robust. BANGLAPLAN provides a reproducible basis for evaluating planning and decision-making in Bangla. BANGLAPLAN is available at: https://github.com/mrayhanulmasud/banglaplan. --- ### Runtime Monitoring of Supermartingale Certificates Authors: Mirco Giacobbe, Thomas A. Henzinger, Konstantin Kueffner, Emily Yu, Đorđe Žikelić Published: 2026-10-14 Categories: cs.AI, eess.SY arXiv: https://arxiv.org/abs/2610.19701v1 Supermartingale certificates formally guarantee temporal properties of discrete and continuous-time stochastic dynamical systems. However, these guarantees rely on a mathematical model of the world, leaving a sim-to-real gap that can invalidate them for the deployed system. We formulate the runtime monitoring problem for supermartingale certificates, in which a monitor observes a single system trajectory and raises an alarm when there is sufficient statistical evidence that the supermartingale certificate has been violated during execution. We present an algorithm to automatically construct a monitor using betting-based sequential tests that bound the probability of ever raising a false alarm at a user-specified level. Within this betting framework, we formulate strategies that allow the monitor to exploit spatial regularity to improve detection power while preserving this statistical guarantee. We demonstrate the efficacy of our approach on supermartingale certificate benchmarks from the literature. --- ### ReGRA: Residual-Gradient Adaptation for Complementary Low-Rank Fine-Tuning Authors: Fanyao Li, Yuxi Liu, Xiaohao Liu, He Chang, Zhaoxin Wang, Zhulin Tao Published: 2026-10-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.19700v1 Low-rank adaptation (LoRA) enables parameter-efficient fine-tuning by learning low-rank weight updates. Increasing rank expands adaptation capacity, but does not guarantee that all learned directions improve downstream performance. In a diagnostic experiment with rank-16 LoRA, we show that retaining only the top singular components achieves the best performance, whereas adding further components degrades it. Motivated by this, we propose Residual-Gradient Adaptation (ReGRA), a two-stage method for making more effective use of a fixed rank budget. After the first stage, ReGRA estimates task gradients on a calibration set and removes their projections onto the two-sided subspace induced by the first-stage update. It then aggregates the residual-gradient directions to initialize a second-stage adapter without changing the first-stage update. An orthogonality regularizer encourages the two updates to capture complementary directions. Both updates can be merged into the pretrained weights, incurring no additional inference overhead. Across diverse benchmark sets, ReGRA achieves stronger performance than alternatives with the same total rank and even matches LoRA adapters with twice the rank. Ablation studies and further analysis support the contribution of its core design choices. Code is available at https://github.com/Fanyao-Li/ReGRA. --- ### RuleTrek: Benchmarking Agentic Rule Reasoning in Complex Scenarios Authors: Chenhao Yuan, Bohan Yu, Yinhao Xu, Chao Yin, Chenxi Zhou, Zhaoxuan Wang, Shuwen Xu, Shaoping Huang, Haolin Ren, Jiaxiang Liu, Yao Xu, Jun Zhao et al. Published: 2026-10-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.19698v1 Large language models (LLMs) increasingly tackle complex real-world tasks in specialized domains. However, identifying and correctly applying domain-specific rules remains challenging when scenario information is distributed across multiple files. Existing rule-reasoning benchmarks typically represent scenarios using only a few factual statements, simplifying the identification and application of relevant rules. To address this gap, this paper introduces \textbf{RuleTrek}, a multi-domain benchmark for agentic rule reasoning in complex scenarios. Its rule-grounded construction pipeline extracts structured rule graphs, generates and incrementally composes rule-specific sub-scenarios while ensuring consistency and solvability. To systematically evaluate agentic rule reasoning in complex scenarios, RuleTrek assesses three capabilities in interactive workspaces: Rule Identification (RI), Rule Deduction (RD), and End-to-End Rule Reasoning (E2E). Experiments on 11 frontier LLMs show that the highest RI and RD scores are only 62.47\% and 60.43\%, respectively, while E2E scores range from 26.97\% to 55.29\%. These results demonstrate that current LLM agents face substantial challenges in rule reasoning over complex scenarios. We make our code and dataset publicly available at \href{https://github.com/yuan247/RuleTrek}{RuleTrek}. --- ### Share the Symbol, Not the Vector: Training-Free Fact Communication Across Language Models Authors: Xin Li, Mengbing Liu, Hao Jiang, Xin Gao, Annan Wang, Xingwei Qu, Yichi Zhang, Chau Yuen Published: 2026-10-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.19696v1 Multi-agent systems allow language models to solve tasks collaboratively by sharing complementary information. These systems typically communicate through text, while recent approaches also explore exchanging internal model states. However, sharing these states across architectures often requires learned translators or assumptions about model compatibility. We introduce SYNC (Symbol-Indexed Neural Communication), a word-indexed interface that connects heterogeneous models without fine-tuning or a learned translator. From descriptions only it can see, the sender selects words from a shared list and sends their indices for each object, without seeing the questions. The receiver writes the described facts into its hidden states using its own word directions, vectors fitted once from its activations. We test selective use by swapping one attribute between two objects and requiring correct answers about both changed and unchanged attributes before and after the swap, four answers in total. We choose an early write layer on four development receivers and then fix it. With three different senders and nine newer receivers from five families, four-answer success on new scenes reaches 72.0-98.3%, up to 96 percentage points above middle-layer writing, and the two largest receivers match plain text. A task-free probe predicted in advance which depths each new receiver can use (45 of 45 cases). Without retuning, messages listing every fact keep 89.6-100% success under new layouts, and sender messages reach 23.9-64.0% on a landmark task with multi-token symbols, below text but from 0% without a message. These results show that shared word indices and receiver-local directions can support selective fact use across model families without additional training. --- ### C3: Rethinking Process Supervision via Confidence-Guided Credit Correction in Multi-Turn Reinforcement Learning Authors: Ai Jian, Haoran Pan, Eryu Guo, Haojin Yang, Jinghan He, Xiaoyun Zhang, Jiangbo Pei, Peiyu Liu Published: 2026-10-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.19695v1 Large language models are increasingly trained as multi-turn agents that interact with external tools. However, outcome-only reinforcement learning can produce a form of misguided reinforcement: even on successful trajectories, undesirable local behaviors may receive positive token-level advantages and be favored by the policy update. To address this issue, we propose Confidence-Guided Credit Correction (C$^3$), a plug-in method for local credit correction. C$^3$ identifies spans corresponding to undesirable behaviors and selectively corrects positive credit after advantage estimation, with the correction strength adaptively controlled by the behavior policy's confidence in the corresponding behavior, while leaving the task reward and original credit estimation unchanged. Across multiple multi-turn benchmarks, C$^3$ improves performance under both {critic-based and critic-free reinforcement learning methods}. Injecting the same behavioral signals as turn-level or outcome rewards does not consistently improve performance. Our results show that local credit correction provides an effective form of process supervision for outcome-driven RL. --- ### ReFormBench: Benchmarking the Stability of Response-Conditioned Format Correction in Large Language Models Authors: Tianxiang Gao, Yahan Li, Chenlu Guo, Diana Inkpen, Yi Chang, Yuan Wu Published: 2026-10-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.19693v1 Reliable use of large language models requires responses to satisfy formatting requirements across changing instructions. Standard compliance scores do not distinguish preserving a model's observed format from correcting it, or reveal whether that correction holds across variants. We introduce ReFormBench, a benchmark that uses each model's unconstrained response to the same question as its formatting baseline. It links targets by feature and require/forbid mode, evaluating their instantiated requirements across variants. ReFormBench comprises 5,000 difficulty-screened three-constraint test instances derived from 910 source questions and covering 66 formatting features. TCPR measures complete instruction compliance, while EMCR measures individual and joint correction of targets opposed to the annotated baseline state. Across ten models, EMCR ranges from 34.04% to 64.72%, and the highest three-target correction estimate is 50.02%. Compliance and correction scores yield different model rankings and task-level profiles. A prompting experiment on Qwen3.5-9B improves both metrics, and the catalog covers over 95% of extracted instances on four additional models. ReFormBench makes response-conditioned correction across instruction variants a measurable dimension of format following. The code and data are available at https://anonymous.4open.science/r/ReFormBench/. --- ### Annealed Lévy Diffusion via Gaussian Surrogate Reverse Dynamics Authors: Yuling Jiao, Lican Kang, Jerry Zhijian Yang, Cheng Yuan, Ruizhe Zhang Published: 2026-10-14 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2610.19692v1 Gaussian diffusion models offer a practical framework for generative modeling. Denoising Lévy Probabilistic Models (DLPM) introduce heavy-tailed perturbations with a fixed tail index throughout denoising. We introduce Annealed Lévy Diffusion (ALD). ALD varies the stability index $α(t)$ to combine heavy-tailed exploration with Gaussian refinement. Our marginal-first formulation represents stable noise as a scalar Gaussian scale mixture. This formulation enables standard Gaussian noise-prediction training with one additional scale input. We study two sampling processes. ALD-renoise estimates the clean sample and injects fresh marginal noise. ALD-posterior preserves dependence between successive states through an accumulated conditional variance and a Gaussian bridge update. Both samplers reuse the same trained predictor with different scalar inputs. We evaluate ALD on four 2D benchmarks and an imbalanced nine-mode mixture. We also examine training efficiency and the effects of prediction perturbations on clipped Holtsmark data. Additional experiments evaluate MNIST and CelebA64 generation and CIFAR-10LT augmentation. ALD preserves local geometry on the evaluated light-tailed and manifold-structured targets. --- ### PPAD-Completeness of Contiguous Envy-Free Cake Cutting with Additive Valuations Authors: Yasushi Kawase, Bodhayan Roy, Mohammad Azharuddin Sanpui Published: 2026-10-14 Categories: cs.GT, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2610.19690v1 We prove that computing a complete contiguous $\varepsilon$-envy-free cake allocation is PPAD-complete for normalized rational piecewise-constant additive valuations. The hardness holds even when $\varepsilon$ is given in unary, and even when every density takes only two values, which are the same for all agents, and is piecewise constant with at most six breakpoints. As a consequence, computing an exact contiguous envy-free allocation is also PPAD-complete, and the hardness holds under the same restrictions on the densities. Our key ingredient is to assign prices to the pieces so that, in every approximately envy-free allocation, all prices are nearly equal, regardless of how the pieces are assigned to the agents. We further show that, for every fixed integer $c\ge1$, computing a contiguous EF$c$ allocation of indivisible goods on a path is PPAD-complete for additive valuations, and the hardness holds even for binary valuations in which each good is valued by exactly one agent and all agents value the same number of goods. --- ### Function-Space Temporal Self-Distillation for Policy Optimization Authors: Aryan Das, Arnab Bhattacharya, Vinay Kumar Verma Published: 2026-10-14 Categories: cs.LG, cs.AI, cs.CL, stat.ML arXiv: https://arxiv.org/abs/2610.19687v1 Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in language models, but scalar outcomes provide coarse supervision over response trajectories. Self-distillation offers denser token-level guidance by comparing an unassisted policy with a feedback-informed self-teacher, yet the teacher evolves with the student, creating unstable targets and motivating additional regularization. We introduce Function-Space Policy Optimization (FSPO), a single-policy framework that combines current privileged adaptation with function-space temporal consolidation. FSPO stores sparse historical next-token distributions as fixed temporal targets, providing temporal separation without maintaining a persistent teacher model. It further introduces privileged disagreement correction to explicitly suppress locally overvalued actions, reliability-adaptive grounding that strengthens reference supervision when self-generated evidence repeatedly fails, and quality and coverage-aware temporal memory that retains verified behaviors and improves privileged demonstrations. Across reasoning and tool-use benchmarks, FSPO achieves the highest average accuracy under a 5-hour training budget, improving over the strongest baseline by approximately 4% points on average while reducing peak memory from about 70 GB to 56 GB on Olmo3-7B-Instruct. --- ### Interlock: From Local Correctness to Task Completion in Long-Horizon Agents Authors: Linji Hao, Yanji He, Zihan Wang, Hansi Yang, Jiayuan Zhang, Hongyan Hao, Qi Gu, Yan Feng, Han Wu Published: 2026-10-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.19686v1 Large language model agents increasingly undertake long-horizon tasks in complex environments characterized by fragmented evidence, partially completed states, and dependencies across resources and artifacts. Existing agents may satisfy individual requirements while failing to maintain these relationships, producing locally correct but incomplete outcomes. These failures arise because task completion depends on relationships among environmental evidence, consequential decisions, and required effects. To address this completion gap, we propose Interlock, a framework for task synthesis that represents each task as a typed completion graph. Grounding edges connect public evidence to decisions, coupling hyperedges impose joint constraints across components, and realization edges connect decisions to all required downstream effects. Interlock compiles this graph into a resettable workspace, a public request, and an evaluation rubric. A source-coverage review checks whether the original requirements survive generation, while a public-input review checks whether the rubric is supported by the materials available to the solver. An agent-as-judge inspects execution artifacts and runs verification scripts, retaining trajectories judged to satisfy all mandatory requirements. To evaluate training utility, we fine-tune two Qwen3.6 backbones on their own accepted trajectories. Across the two backbones, training improves AutomationBench task pass rates by 4.00-4.50 percentage points, JobBench weighted scores by 3.20-6.64 points, and Harvey LAB criterion pass rates by 3.89-4.16 percentage points. These results demonstrate the training utility of the synthesized experience across external task environments. --- ### Beyond Distribution Matching: Selective Margin Preservation for Supervised Fine-Tuning Authors: Yuxuan Wang, Guangxiang Zhao, Xinyu Tan, Yahui Han, Xinxiang Yin, Zhonghai Wu, Xiangzheng Zhang, Lin Sun, Tong Yang Published: 2026-10-14 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2610.19685v1 Supervised fine-tuning (SFT) changes logit margins among non-target tokens at teacher-forced prefixes. Matching a local reference distribution keeps those probabilities and also penalizes margin expansions. We ask whether a soft auxiliary can preserve selected local non-target margin relations without freezing that distribution. We introduce \textbf{Selective Rank-Preserving SFT (SRP-SFT)}, a soft margin target: a hinge on reference-scaled lower bounds for pairs from the reference's top-$K$ non-target tokens, applied at fixed teacher-forced prefixes. The hinge stops once the requested bound is met. We derive the KL cost of violating a margin, characterize the feasible region and its conditional utility, and give a finite-step condition for reducing aggregate violations. In one-epoch experiments on Qwen3-4B-Base and UltraFeedback, this target raises MATH-500 and code-generation scores over CE and LP-SFT at all three training seeds. At seed 1234, MATH-500 pass@1 rises from 49.56\% to 54.56\% and the four-metric code mean rises from 65.91\% to 69.50\% relative to LP-SFT. Ranking controls, held-out cache diagnostics, sensitivity sweeps, and six additional backbones show where these score changes appear. --- ### Enhancing Latent World Models with Associative Memory Authors: Yuwei Sun, Siyu Zhu Published: 2026-10-14 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2610.19683v1 World models trained via latent dynamics offer a scalable path for embodied planning, yet existing methods suffer from representational collapse, computational overhead, and limited long-horizon capability. We introduce a memory-enhanced latent world model that augments JEPA-style prediction with a content-addressable memory bank. Our approach learns high-level representations directly from observations, operating at multiple temporal scales within a shared latent space, and conditions predictions via adaptive layer normalization. To prevent collapse and ensure effective memory usage, we design two complementary losses that encourage slot diversity and balanced temporal utilization. Experiments on PushT, Tworoom, Reacher, and OGBCube demonstrate that our method achieves state-of-the-art performance with a lightweight architecture, outperforming conventional latent world models on long-horizon planning tasks. --- ### MicroSDF: Microfacet-Driven Hybrid Neural SDFs for Mixed-Reflectance Surface Reconstruction Authors: Lejia Ye, Yuhua Xu, Yulan Guo, Lian Xu, Xiaohu Zhang Published: 2026-10-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.19681v1 Accurate 3D reconstruction in real-world environments remains a significant challenge due to the coexistence of reflective and non-reflective surfaces, which pose distinct modeling demands. Existing methods often treat these surface types separately, limiting their generalizability and physical plausibility. To bridge this gap, we propose MicroSDF, a novel neural implicit framework that facilitates geometry and reflectance modeling through microfacet theory. Our approach incorporates three core innovations: (i) a microfacet-guided geometry model that extracts multi-scale surface normals (macroscopic and microfacet) from a signed distance field (SDF), regularized by a proposed microfacet normal consistency loss to enforce physically plausible surface orientations; (ii) an enhanced dual-branch color model, where the specular branch leverages the microfacet normals to model high-frequency reflectance, and the vanilla branch, unlike prior works, uses reflection direction (instead of viewing direction) to better model diffuse and low-frequency specular components; and (iii) a detection-guided color blending strategy that adaptively fuses the color outputs based on reflection priors, providing more physically intuitive blending than implicitly learned blending weights. Combined with a tailored multi-stage optimization scheme, the proposed MicroSDF achieves robust and high-fidelity reconstruction across reflective and non-reflective surfaces. Extensive experiments on DTU, Shiny Blender, Ref-NeRF, and DeepVoxels datasets demonstrate state-of-the-art performance, establishing a new direction for physically grounded neural reconstruction. ---