# Research Papers — 2026-10 · bundle page 54 of 156 > Full-text markdown of papers #2651–2700 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/54 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/53.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/55.md) ### Hyperbolic Time Series Forecasting with Learnable Decomposition and Manifold Dynamics Authors: Sarang Rajendra Patil, Vishal Fenn, Mengjia Xu Published: 2026-10-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.15760v1 Multiscale structure is central to time series forecasting: temporal signals contain slowly varying trends, intermediate seasonal patterns, and high-frequency residuals. Traditional forecasters model this multiscale structure in Euclidean space, without representing the ordering it induces among components. We identify that cascaded decomposition orders components by their characteristic frequencies, forming a natural frequency hierarchy. This hierarchy aligns with the exponential volume growth of hyperbolic space, which provides increasing representational capacity with radius and naturally accommodates nested hierarchies. We propose HyperForecast, the first long-term time series forecasting (LTSF) framework operating in hyperbolic space. HyperForecast embeds decomposed temporal segments on the Poincaré ball where radial distance captures this nested structure, from low-frequency components near the origin to high-frequency components near the boundary. We model geodesic velocity through two manifold-dynamics variants: (a) autoregressive forecasting via Poincaré residual dynamics, and (b) non-autoregressive forecasting that predicts all future segments in parallel. HyperForecast consistently outperforms existing and state-of-the-art baselines on 9 of 11 long-term forecasting benchmarks, achieving up to 58% lower mean squared error at long horizons. Further analysis reveals that the learned radial embeddings recover the frequency hierarchy and that hyperbolic geometry contributes substantially to forecasting performance. --- ### Enhancing Zero-Shot Domain Transfer in Low-Resource Sentiment Analysis: A Case Study in Marathi Authors: Tanvi Somani, Aryan Babare, Samyak Bora, Raviraj Joshi Published: 2026-10-11 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.15757v1 Sentiment analysis is a key task in Natural Language Processing that determines the polarity of opinions in text. For low-resource languages like Marathi--where limited data prevents the direct use of standard statistical methods--models are often trained on single-domain datasets. While this yields strong in-domain performance, it leads to poor generalization to unseen domains. Recent studies highlight the need for domain-robust systems that can handle diverse real-world content through multi-domain modeling. This study investigates how multi-domain training improves sentiment classification for unseen Marathi domains. Models are trained using single-domain, two-domain, and three-domain dataset combinations. Results show that two-domain training improves accuracy on unseen domains by about 8\% compared to single-domain training. Adding a third domain provides further improvement, though the gain is smaller, averaging around 2\% for some domains. These results suggest that training with data from multiple domains helps build more robust sentiment analysis models for low-resource languages, though the benefits reduce as more domains are added. --- ### Frozen History: When Temporal Losses Stop Accumulation in Learned Real-Time Supersampling Authors: Hao Yu, Guoying Zhao Published: 2026-10-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.15752v1 Learned real-time supersampling accumulates jittered low-resolution samples along motion vectors. Many methods use a temporal consistency loss to reduce flicker. We show that with accurate registration, this loss can suppress accumulation: on static content, the network copies its warped history at almost no temporal cost. Camera jitter in motion vectors raises this cost and can hide the effect. We identify four registration errors that training can conceal: jitter-carrying motion vectors, one motion field for both resolution lattices, jittered depth, and an unregistered skip path. A model-free oracle shows that correct registration makes freezing two orders of magnitude cheaper on static pixels. Controlled training shows that registration reverses the temporal weight's effect on PSNR. Under exact registration, increasing the weight reduces pixel variance at the expense of accuracy and perceived quality, with a 0.7 to 0.9 dB loss on static frames at weight 0.25. This reversal recurs across three network families and two scales; the loss also reduces accuracy on unjittered STSS data. With a small temporal weight and a normalised sample accumulator, a plain registered network improves the best published QRISP PSNR by 0.34 to 0.62 dB at $\times$2, $\times$3 and $\times$4 upscaling to 1080p. At $\times$2, its static pixel standard deviation is one quarter that of DLSS 2. Without retraining, it outperforms classical temporal upsampling by at least 4.4 dB on Arm's jittered Bistro capture. Our most accurate $\times$4 model runs in 2.03 ms per 1080p frame on an H200. Code: https://github.com/CV-AC/Frozen_history --- ### Google Earth AI Geospatial Reasoning Agent: Capabilities and a Systematic Evaluation Authors: Noam Slonim, Aviv Slobodkin, Gil Fidel, Gal Moshitch, Mimi Sun, Lily Mihalkova, Joydeep Paul, Per Bjornsson, Sydney Lin, Jamie McPike, Samapriya Roy, Utkarsh Patel et al. Published: 2026-10-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15750v1 Google Earth AI is a family of geospatial AI models, together with an agent that orchestrates them. We present this agent, Google Earth AI's Geospatial Reasoning agent (GRA), a Gemini-powered research system that combines geospatial data sources, foundation models, and tools to answer questions about our planet. GRA organizes these into modular domain skills and pairs them with upfront geospatial planning to decompose complex queries into multi-stage workflows. Evaluating such systems is hard: real-world problems admit multiple valid workflows, require data discovery across large catalogs, and rely on evolving ground truth. We introduce two benchmarks and release their development splits. GeoExpertQueries poses complex analytical problems grounded in practitioner use cases and refined by geospatial experts; each is paired with a consensus golden workflow from three independent experts and scored by a human-validated, tool-agnostic autorater. GeoKTools consists of templated queries with deterministic reference solvers that systematically vary the number of required tool types. We also use two external benchmarks, CBGB and UnivEARTH; the latter we find to be saturated. To isolate the contribution of GRA's tools and its agentic orchestration, we compare four configurations, each with Gemini 3.1 Pro and 3.8 Flash: a standalone LLM, the LLM with basic tools, the LLM with GRA's skills and tools but without its upfront planning and execution guidance, and GRA itself. With at most basic tools, an advanced model recovers much of the answer on templated queries but satisfies only a small fraction of the expert workflows on open-ended problems; GRA performs well on both. The largest step comes from GRA's skills and tools; on open-ended problems, its planning and execution guidance add a further gain with Gemini 3.8 Flash, letting Flash match or exceed Pro at lower cost. --- ### SpikeOcc: Towards Resilient Multimodal 3D Occupancy Perception via Spiking Experts Authors: Yiding Sun, Zijie Xu, Hongqiang Lin, Jiajun Cao, Dongxu Zhang, Kai Tang, Jihua Zhu, Wenxuan Liu, Zhaofei Yu, Tiejun Huang Published: 2026-10-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.15745v1 Multimodal 3D occupancy prediction underpins safe autonomous driving through comprehensive scene understanding. However, existing methods have largely pursued higher accuracy through sophisticated fusion, leaving resilience to missing sensors underexplored. In this paper, we investigate spiking neural networks (SNNs) as a means of building more resilient multimodal perception. Still, the discrete nature of spiking neurons makes optimization challenging. To overcome this difficulty, SpikeOcc is introduced with two complementary components, a Spiking Mixture-of-Experts (SMoE) and Sensor Availability Learning (SAL). Specifically, SMoE organizes RGB, LiDAR, and joint fusion into specialized pathways, enabling full-width unimodal representations while retaining the original multimodal features via a bounded residual. Beyond sensor dropout, SAL employs a staged curriculum with explicit routing supervision, progressively improving robustness under severe sensing conditions. Remarkably, SAL also yields notable gains for conventional models, highlighting its broader potential for resilient multimodal learning. Extensive experiments demonstrate that SpikeOcc maintains competitive full-sensor accuracy while markedly raising the performance floor under sensor outages. SpikeOcc illustrates the promise of neuromorphic computing, pointing toward more reliable and energy-efficient autonomous driving. --- ### RSAJEV: Training-Free Abstaining Prototype Memory for Eliminating Silent Hallucination in JEV-Based Remote Sensing Classification Authors: Man Chen, Antai Chen, Shuai Xu, Chengjie Gu, Huaping Zhou, Kelei Sun, Tao Wu, Yongjie Huang Published: 2026-10-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.15742v1 Scene classification of remote sensing imagery with multimodal large language models (MLLMs) is formulated as a single-forward-pass decision problem: candidate class names are lettered options in the prompt, a registered answer slot is conditioned on the prompt, and classification is read out by scoring letter tokens with the language-modeling head. We show that although this letter binding is highly effective within its training vocabulary (97.71% OA on UCM), it behaves erratically out of vocabulary: zero-adaptation accuracy across four cross-dataset directions fluctuates between 7.35% and 96.40%, and under out-of-vocabulary weights its confidence fails inversely on open-set evaluation, assigning higher confidence to unseen than to seen classes (AUROC 0.38), a failure we term silent hallucination. We retain the slot representation and replace the readout with RSAJEV, a training-free abstaining prototype memory that performs retrieval-based prototype matching: K reference images per class are cached as prototypes via their slot representations under the same prompt, and classification becomes nearest-neighbor retrieval over the prototypes, refined by a shrinkage-Mahalanobis geometric correction. This readout is mechanistically isomorphic to retrieval-augmented generation (RAG) but operates on discriminative decisions; it is the first retrieval-based readout for MLLM slot representations. The retrieval readout reaches 89.43% on the UCM cross-dataset gate with 16 references per class and zero gradient updates, and 96.90% on AID. Its ID-ness scores attain 0.91-0.99 AUROC on open-set evaluation over two datasets, exceeding symbolic confidence (0.38-0.96) in all four open-set settings, restoring a calibratable abstention channel and supporting class addition/removal at zero extra inference cost via offline rescoring of the cached matrix. --- ### Visible but Not Avoided: State-Dependent Re-Proposal of Rejected Candidates in Catalog-Based LLM Optimization Loops Authors: Jianlin Chen, Wenhui Chen, Chi Man Vong Published: 2026-10-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15738v1 LLM optimization loops often show the proposer the candidates it has already tried and rejected, but leave it to the proposer to avoid them. We ask whether avoidance measured in a static probe predicts avoidance in the states an optimizer's own trajectory produces. In catalog-based loops where three open LLMs improve a GUI agent by naming one of 40 edits, a re-proposal is identified exactly by the edit's name. Clean base-state probes underpredict re-proposal in the proposers' own loops (macro-averaged loop-minus-probe rate 0.32 (0.27, 0.37)), and proposals of already evaluated harness-edit pairs consume 28-63% of valid proposer iterations. The two settings reject different edits: a probe's rejected edits are mostly ones the proposer did not choose, whereas a loop's are its own earlier choices, which remain preferred when the history is removed. Ordinary history lowers re-proposal for two proposers but raises it for the third, and the effects of failure evidence are model-specific. Stating the rejection status in one sentence lowers re-proposal in every model (-0.16 (-0.22, -0.09) relative to a neutral list of the same IDs). For catalog-based loops with exact edit identities, rejection avoidance should be measured on the rejected sets the loop produces. --- ### ScenePlacer: Reformulating Scene-Level Object Pose Estimation as Visibility Field Learning Authors: Ken Deng, Jiarui Liu, Guibiao Liao, Kunming Luo, Mochu Xiang, Hongyu Yan, Yebin Liu, Shenghua Gao, Yizhou Yu, Ping Tan Published: 2026-10-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.15734v1 We present ScenePlacer, a framework for scene-level pose estimation of objects generated by state-of-the-art native shape generation models, placing generated 3D objects into scenes given a partial geometric observation without modifying the underlying generative pipeline. Existing scene generation approaches either generate objects directly in scene coordinates, compromising their canonical-space priors, or regress poses from complete generated shapes in the shape generation process - the latter being a poorly conditioned problem that is sensitive to scale ambiguity and partial observations. ScenePlacer decouples object generation from pose estimation by reformulating alignment as conditional visibility-field learning. Given an observed partial point cloud from reconstruction and a generated mesh, it predicts a visibility field defined in object space, then estimates the rigid transformation by aligning the partial observation to visible parts on the mesh. We propose a pretrained 3D shape VAE as our backbone, preserving its mesh prior while conditioning it on a separately encoded observation. We further introduce visibility-aware, radius-constrained supervision and synthesize training pairs using only object-level meshes and rendered views, eliminating the need for scene-level pose annotations. On 3D-FUTURE, ScenePlacer consistently outperforms existing placement and pose-refinement baselines under both ground-truth and monocular depth estimation. With generated objects, it achieves a Chamfer distance of 0.0077 and an F-score of 92.40 under estimated depth and improves to 0.0023 and 98.27, respectively, under ground-truth geometry. --- ### NepPlural: A Human-Anchored Benchmark for Persona Annotation in Nepali Migration Discourse Authors: Jinu Nyachhyon, Anish Khatiwada, Bimal Timilsina Published: 2026-10-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.15732v1 Pluralistic alignment asks that language models faithfully represent a society's diverse, competing values rather than collapse them into one dominant viewpoint, yet flagship pluralistic-alignment datasets remain heavily skewed toward Western respondents. We introduce NepPlural, a human-anchored benchmark for modelling competing socio-cultural personas in Nepali public discourse on youth migration and brain drain. We curate 2,148 code-mixed (Devanagari, Romanized Nepali, English) YouTube comments, annotate them along a four-axis persona taxonomy (Intent, Primary Driver, Value Orientation, Affect) plus an explicit No-Persona class, and build a 300-comment gold set labelled independently by three native Nepali speakers (mean Fleiss' $κ\approx 0.55$). Using this gold set to audit automatic annotation, we find that LLM annotation reliability is driven by protocol. Labels collected in batches through chat interfaces reach only near-chance inter-model agreement ($κ\approx 0.17$). Annotating one comment at a time raises agreement above the native-speaker level ($κ\approx 0.72$), but consistency is not validity: under a forced-choice schema, models agree on personas for the 39% of comments native speakers judge to express none, keeping macro-F1 against human gold near 0.50. Allowing abstention resolves this: models recover No-Persona comments with F1 of 0.79 to 0.87 and, against leave-one-annotator-out references, match or exceed individual native speakers (macro-F1 0.75 to 0.86 vs. 0.75). Encoders fine-tuned on the batched labels reach only 0.34. Finally, a human-judged steerability probe finds that three frontier models adopt single persona axes with 59 to 77% fidelity but compose full personas only 33% of the time, with no congruence gap detected at this scale between Western-congruent and Nepali-collectivist personas. --- ### A Dependency-Aware Multi-GPU Training Framework for Temporal Graph Neural Networks Authors: Yang Zhao, Yue Dai, Liang Qiao, Buxin Tu, Bo Liu, Sen Zhang, Yi Zhang, Xiaoyu Hao, Jun Shi, Junshi Chen, Hong An Published: 2026-10-11 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2610.15730v1 Temporal graph neural networks (TGNNs) achieve superior performance in many dynamic graph learning tasks. These models use node state vectors (i.e., memories) to capture and record graph changes (i.e., events), and then exploit these memories to assist prediction. However, this memory-centric design makes multi-GPU training challenging because predictions for later events often depend on memory updates from earlier events. To maintain model quality, existing multi-GPU TGNN training schemes strictly preserve all event dependencies, which limits parallelism and causes expensive cross-GPU memory synchronization. In this work, we observe that many of these dependencies can be handled more flexibly without harming training quality. Specifically, (a) dependencies in TGNN training have high locality in both time and graph topology, (b) the short-range dependencies missed within a large batch can often be recovered cheaply, and (c) many memory updates are not immediately needed. Based on these observations, we propose DepBloom to accelerate multi-GPU TGNN training with three techniques: (1) temporally bounded spatial partitioning to reduce unnecessary cross-GPU synchronization and improve parallelism; (2) intra-batch memory refinement to recover missing short-range temporal dependencies inside enlarged batches; and (3) critical-path optimization to prioritize urgent memory updates while deferring non-critical work during multi-GPU pipeline execution. Experimental results across representative models and diverse datasets show that DepBloom achieves an average speedup of 2.84$\times$ and up to 5.16$\times$ over state-of-the-art methods, while maintaining comparable or better model accuracy. --- ### Visually Legible but Adversarial: Watermark-Constrained Attacks on End-to-End VLMs for Document Understanding Authors: Qingzhe Han, Fan Dang, Shengqi Chen, Xinyi Sun, Haoyu Xiong, Lingkun Li, Di Zhang Published: 2026-10-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.15728v1 Visible watermarks convey document ownership, confidentiality, and status, but can also carry adversarial signals. We introduce Auto-Regional Adversarial Watermarking (AR-AWM), a model-aware white-box attack on end-to-end visual language models (VLMs) for document understanding. AR-AWM constructs a small, spatially distributed watermark-text support and optimizes only its pixels to disrupt visual representations. The attack is untargeted and question-agnostic: generation uses no questions, answers, parsing prompts, language-model gradients, or language-model outputs. Each attacked page is reused across downstream queries. On Qwen2.5-VL-7B, a watermark support covering 7.98% of page pixels under the reporting threshold reduces DocVQA exact match from 0.899 to 0.150 and average normalized Levenshtein similarity (ANLS) from 0.939 to 0.212. Selected qualitative cases retain visually legible source fields. The same support without optimization and with matched random perturbations retains ANLS of 0.932 and 0.933, respectively, identifying adversarial optimization as the primary cause of degradation. Layout-matched optimized rectangles yield ANLS of 0.276, showing an incremental benefit from text-shaped geometry. AR-AWM also degrades all reported text, formula, reading-order, and table metrics on OmniDocBench. Separate white-box optimization on InternVL2.5-8B reduces ANLS from 0.922 to 0.046, while weak cross-model transfer reveals strong encoder specificity. These results identify conventional watermark-shaped supports as an adversarial surface for document VLMs in the evaluated white-box setting.luated white-box setting. --- ### SkillMarker: A KGW-Based Watermarking Method for Agent Skill Ownership Verification Authors: Alan Tang, Lifeng Wang, Gang Wu, Tao Zhang, Yantao Jia, Xiaofeng Zhu Published: 2026-10-11 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2610.15725v2 Agent skills encode operational procedures and domain expertise as reusable knowledge assets, yet their distribution in plaintext exposes them to unauthorized copying and leakage. However, practical mechanisms for skill ownership verification and leakage tracing remain underdeveloped. Watermark embedding before distribution offers a potential solution, but structured, compact skill instructions impose stringent requirements for factual and procedural accuracy. To address these challenges, we introduce SkillMarker, a KGW-based watermarking method that jointly targets functionality preservation and strong watermark embedding. SkillMarker unifies quality-constrained rewriting with signal-oriented candidate search. The former separates essential knowledge from flexible expression to preserve instruction fidelity; the latter explores alternative expressions to obtain a stronger watermark signal under preservation constraints. We release an open-source toolkit that integrates watermark embedding, quality auditing, and detection to support the protection of agent skills. SkillMarker targets ownership verification and leakage tracing in distributed skill ecosystems, where content may be copied in whole or in part, or incorporated into other skills. Across four datasets, SkillMarker negligibly affects downstream task performance on average. In our copy-paste tests, window-based detection consistently identifies copied passages containing as few as 1,536 consecutive tokens. Even after merging with one or three background skills, SkillMarker retains watermark detection rates of 72.2--77.8\%. --- ### Uncovering the Generative Landscape of Diffusion Models: A Spectral-Guided Quality-Diversity Diffusion Framework Authors: Hannah Janmohamed, Joao Correia, Penousal Machado, Antoine Cully Published: 2026-10-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.15724v1 Denoising Diffusion Probabilistic Models have emerged as powerful generative priors across domains ranging from molecular design to high-resolution image synthesis. However, standard diffusion sampling is inherently biased toward high-likelihood regions, often limiting the diversity of outputs. In many domains, a single, high-likelihood sample is insufficient. Instead, diverse portfolios of high-performing solutions are required, motivating methods that uncover a model's full expressive range. Here we show that integrating Quality-Diversity (QD) optimisation with diffusion models enables the discovery of diverse, high-performing outputs. We first propose Quality-Diversity Diffusion, a framework that adapts QD to diffusion models by directly optimising the model's latent noise and conditioning embeddings and leveraging embedding models to quantify diversity. Second, we introduce a novel h-space Spectral Mutation operator, which guides search along directions of maximal semantic sensitivity by analysing principal singular vectors of the model's input-to-activation Jacobian. We evaluate our combined approach, Spectral-Guided Quality-Diversity Diffusion, on text-to-image generation. Against 12 baselines, our method consistently achieves the lowest FID score, demonstrating an excellent balance of image quality and diversity. --- ### Adaptive Robust Confidence Sets in High Dimensions Authors: Ilias Diakonikolas, Chao Gao, Daniel M. Kane, Yuetian Luo Published: 2026-10-11 Categories: math.ST, cs.DS, cs.LG, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2610.15723v1 We study adaptive confidence sets for mean vectors of multivariate Gaussians with identity covariance under Huber contamination when the contamination proportion is unknown. We show that an information-theoretically optimal adaptive confidence set can be constructed by simultaneously quantifying uncertainty across all one-dimensional projections. The resulting confidence set achieves the optimal diameter and reveals a substantial adaptation cost compared with the minimax estimation error. Although statistically optimal, this construction is computationally infeasible. We establish a Statistical Query (SQ) lower bound showing that achieving diameter $O(m^{-1/2})$ requires either exponentially many queries or query tolerance $d^{-Ω(m)}$. Thus, in contrast to robust mean estimation, adaptation to the unknown contamination proportion incurs both a statistical cost and a computational barrier within the SQ framework. Finally, we give a low-degree moment-matching algorithm that constructs an adaptive confidence set using $d^{O(m)}$ samples and time. Its diameter bound contains an additional $O(m^{-1/2})$ term beyond the information-theoretic rate, matching the dependence on $m$ in the SQ lower bound. Together, these results characterize the statistical limits of adaptive robust confidence sets under Huber contamination and quantify a computational barrier within the SQ framework. --- ### PhySimCode: A Benchmark and Evaluation Method for Physics Video to Code Generation Authors: Souraja Kundu, Aditya Gupta, Joel Julin, Yizhou Zhao, Liuyue Xie, Laszlo A. Jeni Published: 2026-10-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.15722v1 Multimodal large language models (MLLMs) are good at video understanding and code generation, but it remains unclear whether they can recover the physical laws underlying videos, a capability essential for converting videos into executable simulations and for providing structured physical supervision in robotics. Captioning motion video does not imply that a model has inferred its governing dynamics, estimated quantitative parameters, or can regenerate the observed scene from code. Existing video-physics benchmarks evaluate plausibility, property estimation, or future-state prediction, but offer limited insight into whether models can translate visual dynamics into runnable simulation code. We introduce PhySimCode, a benchmark for physics video-to-code generation: given only a raw video, a model must infer the relevant physics, recover parameter values, and generate runnable Python that reproduces the input video. The dataset contains 160.6K procedurally generated samples spanning 162 physics phenomena across analytic SciPy simulations and PyBullet-rendered rigid-body, articulated, fluid, and contact-rich scenes; each sample bundles the simulation code, physical parameters, rendered video, and a structured chain-of-thought covering observations, laws, ODEs, numerical methods, and validation checks. We evaluate ten state-of-the-art closed- and open-source MLLMs along physical-law correctness, simulation equivalence, code executability, and parameter recovery. Models reliably state physics laws (4.27-4.93/5) yet score only 1.51-2.47/5 on inferring them from video, and the best system (Claude Sonnet 4.6) recovers just 7.7% of ground-truth parameters within $\pm 20\%$, exposing a substantial video-to-simulation gap. The 2,430-video evaluation set is available at https://huggingface.co/datasets/SourajaKundu123/PhySimCode and the evaluation code at https://github.com/SourajaKundu/PhySimCode --- ### To Cache or Not to Cache: Understanding and Mitigating Safety Incompatibility in Cross-Model KV Cache Reuse Authors: Zhiwei Lin, Jiahao Liu, Yan Liu, Chengpeng Wang Published: 2026-10-11 Categories: cs.LG, cs.CR, cs.SE arXiv: https://arxiv.org/abs/2610.15721v1 Cross-model KV cache sharing reduces prefill computation by allowing a receiver model to reuse prefix KV states generated by a related sender model. Existing methods optimize such reuse for latency and generation quality, but its safety implications remain unclear. In this work, we systematically evaluate this issue across diverse sender-receiver pairs and reuse configurations. We refer to deviations from the receiver's native safety behavior as safety incompatibility. Our study shows that both the direction and magnitude of safety incompatibility depend on the model pair and reuse configuration, with value reuse causing substantially larger deviations than key reuse across all evaluated pairs. Furthermore, we propose VReparo, a technique that learns per-layer and per-KV-head affine maps offline to align reused sender value tensors with their receiver-native counterparts before decoding. Across two model pairs under full KV reuse and the state-of-the-art selective reuse setting, VReparo reduces the average HarmBench attack success rate (ASR) from 57.28% to 39.21% and the average StrongREJECT score from 0.4215 to 0.2163 upon our benchmarks, while retaining an average Time to First Token (TTFT) reduction of 85.62%. --- ### History Replays Itself: Unleashing Long-Context Capability in Linear Attention Authors: Li Nanbo, Firas Laakom, Yilan Zhang, Piotr Piękos, Yimeng Chen, Liangyu Wang, Yifan Xu, Mateusz Ostaszewski, Dandan Guo, Wenyi Wang, Yanning Dai, Yuhui Wang et al. Published: 2026-10-11 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.15715v1 Linear attention promises the efficiency needed for long-context language modelling, yet its fixed-size recurrent state must simultaneously support ongoing computation and preserve information from an ever-growing history. This coupling has reinforced a prevailing view that the state's memory capacity defines the model's long-context capability. We challenge this presumed ceiling: \emph{recurrent computation need not bear the full burden of long-term storage}. We introduce NoteBank, a sparse episodic memory that archives selected text before future queries are known, uses the backbone's native features for writing and addressing, and reads retrieved evidence through its native forward computation via replay. This \emph{training-free, plug-and-play} interface requires no external embedding model, separately trained retriever, or separate neural reader. At one million tokens, it raises Gated DeltaNet's mean accuracy across six RULER retrieval tasks from 1.7% to 70.3%, with no observed significant retrieval degradation from 4K to 1M tokens. This recovery adds $\leqslant$0.025% to analytical FLOPs, with persistent context storage approximately 1/2,600 that of a Transformer's full MHA KV cache at matched width, depth, and precision. Experiments extend from three 1.3B recurrent backbones to Mamba-2-8B and post-trained Qwen3.5-9B, demonstrating gains on LongBench v1/v2 and MemoryAgentBench. Together, these results show that sparse evidence storage and native replay can substantially expand the long-context capability of pretrained linear attention models while retaining the efficiency of recurrent computation. --- ### MedHarnessBench: A Unified Benchmark for Healthcare Agent Evaluation Authors: Rui Tang, Hongqiu Wang Published: 2026-10-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15714v1 Healthcare agents must transform longitudinal clinical evidence into reliable actions through heterogeneous tools and stateful workflows, conditions under which model-centric systems may lose context, misuse tools, fail to verify consequential transitions, or cross authorization boundaries. Existing medical-agent benchmarks primarily emphasize terminal task outcomes, making it difficult to determine whether execution failures arise from the agent model, the runtime harness, or their interaction. We present the Medical Harness Protocol, an outcome-preserving framework that independently evaluates seven healthcare-specific process dimensions: Care Action Fulfillment, Clinical Resource Competence, Patient-Evidence Alignment, Clinical Workflow Continuity, Clinical Auditability, Closed-Loop Verification, and Clinical Conduct Boundaries. A normalized intervention trace further tracks whether runtime support is available, activated, delivered, adopted by the agent, and propagated into subsequent behavior. We instantiate the protocol as MedHarnessBench, comprising 342 executable tasks across FHIR/EHR operations, healthcare-administration interfaces, and multimodal clinical tools. Across more than 16,000 controlled task executions, MedHarness yields broad improvements in terminal task success, intermediate subtask completion, and healthcare-specific process quality. We further evaluate MedHarness against multiple general-purpose harnesses and use controlled single-fault perturbations to verify the sensitivity and discrimination of the seven-dimensional evaluation. These results demonstrate that healthcare-specific runtime support can substantially improve both task completion and execution quality, while revealing failures that terminal outcomes alone cannot capture. Code and resources are available at https://github.com/Tomry1114/Awesome-Agent-Harness-for-Healthcare. --- ### TL;QR: Querying Temporal Discursive Patterns in Textual Corpora Authors: François Hublet, Vladimir Krsmanovic, Jesus Solano, Ahmed Bouhoula, Ana Oliveira da Costa Published: 2026-10-11 Categories: cs.CL, cs.CY, cs.DB, cs.LO arXiv: https://arxiv.org/abs/2610.15712v1 Many questions about large textual corpora concern patterns that unfold over time, such as a political group whose stance on a topic drifts from support to criticism over several years of debates. We present TL;QR (Too Long; Query with logical temporal Reasoning), a declarative query language and open-source engine for finding such temporal discursive patterns. In TL;QR, a single query combines natural-language predicates, whose truth is judged by a Large Language Model (LLM), with regular expressions and the operators of a temporal logic. The LLM answers only local questions about individual text passages; a symbolic engine then aggregates these judgments over time and links every match to the recorded passages and predicate decisions behind it. With this division of labor, the temporal and relational reasoning stays exact and auditable even over long time horizons. In addition, when a query includes a regular-expression pre-filter, only a small fraction of the corpus ever reaches the LLM. On a suite of controlled synthetic benchmarks with temporally and semantically complex patterns, TL;QR is substantially more accurate than LLM-only baselines. In a case study on ten years of European Parliament debates (442,593 multilingual speeches), TL;QR identifies candidate shifts in the political groups' stances on the GDPR privacy regulation. --- ### What DNA Foundation Models Learn Beyond Sequence Composition Authors: Vincenzo Yuto Civale, Andrew David Bagdanov, Alberto Magi Published: 2026-10-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.15711v1 Do genomic foundation models (FMs) provide predictive information beyond simple sequence composition? We evaluate frozen representations from five DNA FMs against normalized k-mer frequencies across 57 genomic classification datasets and two exploratory gene-expression regression tasks. Simple k-mer features remain competitive with most models, whereas NTv3 shows a consistent advantage; the ranking is robust to globally fixed and multi-scale k-mer baselines and alternative downstream probes. To test incremental predictive utility directly, we compare global 6-mer features with their concatenation with each FM embedding under a matched Random Forest protocol. NTv3 improves 46 of 57 datasets (mean $Δ$MCC = +0.072), while Caduceus provides smaller gains and the other models do not improve mean MCC. We separately decompose embeddings into a component linearly predictable from 6-mer frequencies and a ridge residual, finding that linear recoverability does not reliably indicate downstream utility. Exact 6-mer-preserving shuffles further reveal task-relevant sequence-order sensitivity, most pronounced for NTv3, although order sensitivity alone does not guarantee predictive improvements. Our results establish compositional features as essential controls and offer complementary diagnostics for evaluating the added value of frozen genomic representations, without making claims about fine-tuning capacity. --- ### Suggested Is Not Superseded: A Pre-Registered Evaluation of a System-One Model as a Memory-Retirement Gate Authors: Xupeng Chen, Chenqian Le Published: 2026-10-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15710v1 Long-term memory for assistants needs a gate that decides when a new utterance retires an old stored claim. Benchmark labels for this step mark a pair as changed or not, so they cannot tell a gate that acts on established change from one that acts on a hint. We write a task contract that separates the two (SUPERSEDED vs. NEEDS-CONFIRMATION vs. COMPATIBLE), label 500 test pairs built from STALE (change pairs plus same-user controls) with three LLM annotators and two human adjudicators (one author and a second annotator; provenance reported), and evaluate Jev, a typed "System One" decision model, under pre-registered hypotheses. Of the 179 test pairs STALE marks as changed, 72 meet the contract's bar for an established change. Jev never retired a claim on 141 same-conversation non-changes. Its failure is premature retirement: the binary gate retires 39.2% of claims whose change is only suggested. A three-way decision cuts this to 15.5% at a 15.3-point detection cost, which misses our pre-registered 10-point budget, and it lands on the binary gate's own threshold frontier; these verdicts hold under three readings of the gold labels. On a held-out vault scored against a second annotator's labels, a cascade that escalated uncertain cases to a reasoning model and looked best on development data was indistinguishable from simply raising the threshold (premature retirement 26.8% vs. 6.5% on dev). Part of the gap comes from the gold labels: relative to that annotator's reading, LLM-majority gold shares most of its errors with a same-family escalation model, and an identity for binary labels says how much such shared errors hide. The rest is small-sample selection on development data. For builders this means a binary score should not be wired to delete: route suggested changes to pending evidence, and do not trust a cascade selected on development data of this size. --- ### Preserving Updates in Low-Bit Recurrent State Quantization Authors: Haotian Li, Liran Dong, Kaicheng Xiao, Guoliang Xing Published: 2026-10-11 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2610.15709v1 Linear attention and recurrent models compress past tokens into a fixed-size state that is updated at every step. However, storing these states in high precision incurs substantial memory and bandwidth costs at large batch sizes, motivating low-bit state quantization. Unlike weights and key--value caches, a recurrent state is requantized after every update, so its quantization errors accumulate across steps. Our analysis shows that these errors are highly coherent across steps, so reducing per-step errors alone is insufficient. This coherence arises mainly from small updates that are lost in rounding. To preserve these updates, we intervene both before and at rounding. Before rounding, we propose Low-Rank Bypass (LRB), which accumulates small updates in a compact low-rank buffer and periodically merges its sufficiently large elements into the state. At rounding, we observe that a state element can even move opposite to its update, and such reversals prove particularly harmful. Therefore, we propose Bounded Directional Rounding (BDR), which rounds reversed elements toward their updates without additional storage. Although BDR enlarges the rounding error, it improves the model, suggesting that the direction of an update matters more than its rounding error at a single step. Across Gated DeltaNet, GLA, Mamba2, and RetNet, our training-free method substantially outperforms INT4, while reducing state memory by up to 5.3$\times$ and speeding up decoding by up to 1.9$\times$ relative to FP32 states. --- ### SpecForge: Recursive Self-Improvement for Coding Agents via Behavioral Specifications Authors: Yutong Cheng, Haifeng Chen, Peng Gao, Wei Cheng Published: 2026-10-11 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2610.15708v1 Coding agents based on frozen language models can improve their performance by refining the external context they rely on, without updating model weights. We study recursive self-improvement through behavioral specifications: natural-language code documentation that describes the behavior of program entities and guides agents in generating correct code. We formulate a self-improvement loop in which an agent generates code from its current specifications, evaluates it with execution-verified tests, and refines the specifications based on observed failures. The improved specifications then guide subsequent generation, progressively improving the agent's understanding of the codebase. However, recursive refinement is challenging because program entities are interdependent. Improving the specification of one entity can inadvertently degrade the correctness of others, a phenomenon we call output coupling. This creates a whack-a-mole effect in which local improvements cause regressions elsewhere, preventing consistent progress. We introduce SpecForge, a multi-frontier tree search framework that addresses this challenge with three mechanisms: (i) Pareto-guided state selection preserves complementary specification states and prevents premature commitment; (ii) dependency-constrained entity selection prioritizes callee-before-caller refinement; and (iii) error-diversified expansion explores multiple refinements using different subsets of test failures. On DevEval+, SpecForge achieves the best performance across five backbone models, including a 94.9% solve rate with Claude-4.5-Sonnet and a 5.7-percentage-point average improvement over the strongest baseline. The improved specifications also make the agent better at tasks outside the loop: they transfer to cross-language translation and to new-feature implementation, where they outperform the benchmark-provided requirement documents. --- ### Generalizable Model Editing Could Be More Than Direct Generalization Authors: Xiaotian Ye, Chunyao Yang, Xiaohan Wang, Junkai Chen, Yongqi Duan, Mengqi Zhang, Shu Wu Published: 2026-10-11 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2610.15707v1 A central desideratum in model editing is generalization to complex tasks, which prior work formalizes under a direct generalization paradigm: treating and evaluating LLM behavior as an input-output mapping and expecting a factual update to alter outputs on reasoning tasks. Yet despite substantial empirical effort, the field consensus remains that such generalization is highly challenging and elusive. However, when we deploy the latest models in an in-the-wild chatbot-user setting, we surprisingly find that even classical editing methods exhibit remarkably fluent generalization behavior. This motivates us to revisit the obstacles to generalization and the limitations of the prevailing paradigm. We find that direct generalization is fundamentally constrained both theoretically and practically: theoretically, it suffers from an identifiability issue; and practically, existing approaches attempting to circumvent this are further hindered by the ambiguity of their constructed biases and by vulnerability to being overridden by other factors such as optimization dynamics. We instead identify compositional generalization, empowered by the increasingly strong reasoning and composition abilities of modern LLMs, as a theoretically grounded and empirically validated alternative. We validate this phenomenon across multiple models and editing methods, showing that such generalization behavior is widespread. Overall, we argue that generalizable model editing could be more than direct generalization, and call for a paradigm shift toward more generalizable and practically deployable knowledge update techniques. --- ### bharatSetu: a 1M x 22 bridge for indic translation Authors: Haq Nawaz Malik, Nahfid Nissar, Faizan Iqbal Published: 2026-10-11 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.15705v1 India's Eighth Schedule recognises 22 languages, yet parallel data is uneven across them, and many language pairs, especially among lower-resource languages such as Bodo, Dogri, Santali and Kashmiri, lack direct bitext. We present BharatSetu 22-Indic 1M, a row-aligned table of 984,764 English sentences, each paired with machine translations into all 22 scheduled languages (21,664,808 Indic cells), generated with the sarvamai/sarvam-translate model family. Because every Indic cell in a row translates the same English sentence, any two columns form a translation pair: 462 directed Indic-to-Indic pairs, or 506 including English, without direct bitext. We call these pivot-derived pairs and propose a confidence layer that lets users choose how strictly each pair is connected. The corpus is machine-generated and not human-verified; quality is expected to vary by language, domain and sentence style, and pivot-derived pairs can inherit errors from both sides. We therefore release BharatSetu as a machine layer and propose a human-correction layer keyed to the same row identifiers, so that each corrected column upgrades every pair that uses it, together with an evaluation protocol. We report no translation-quality results. --- ### RespFocus: Learning Temporal Evidence for Weakly Supervised Respiratory Sound Classification Authors: Yi Tian, Xiaohuan Chen, Yufei tang, Xinyu Lin, Hongliang Li, Chengbin Hou, Degen Huang, Rongshan Yu Published: 2026-10-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.15702v1 Respiratory auscultation provides a low-cost means of assessing pulmonary function, yet transient crackles and sustained wheezes can be difficult to recognize in noisy clinical recordings. Conventional deep learning classifiers often operate as black boxes, offering limited insight into the temporal acoustic evidence supporting their predictions. We present RespFocus, a weakly supervised framework that uses multiple instance learning (MIL) to learn inspectable temporal evidence from cycle-level labels and integrate it into classification. We also introduce PedResp2026, a multicenter pediatric respiratory sound cohort collected in routine clinical environments with adjudicated cycle-level annotations. In classification experiments, RespFocus achieves four-class Scores of 69.55\% on public ICBHI 2017 and 72.91\% on PedResp2026. Evidence diagnostics and matched temporal interventions support the functional contribution of the learned evidence to model predictions. Together, these findings highlight RespFocus's potential as a tool for automated respiratory sound diagnosis. --- ### TabMosaic: Unified In-Context Diffusion for Tabular Generative Tasks Authors: Jayoung Kim, Sanghyun Hong, Noseong Park Published: 2026-10-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.15699v1 Generative modeling for tabular data has advanced to the point where models can synthesize realistic records, recover missing values, and generate samples conditioned on class labels or observed attributes. Despite recent advances, existing approaches either require table-specific training or restrict in-context learning to single-cell prediction. In this work, we formulate these tabular generative tasks as a single problem: modeling the joint conditional distribution of an arbitrary set of target cells given the observed cells of an unseen table. To this end, we turn to diffusion, whose denoising objective is defined jointly over all target cells rather than one cell at a time. Under the pretraining distribution, this objective is minimized by the posterior predictive distribution over the target set. Building on this, we propose TabMosaic, a unified in-context diffusion model for generating mixed-type target cells in unseen, potentially incomplete tables without table-specific training. We further show that its pretraining objective bounds the conditional negative log-likelihood and the divergence from the posterior predictive for arbitrary target sets, extending the Bayesian account of in-context learning from a single-value prediction to joint multi-cell generation. Across 48 real-world tables, TabMosaic ranks first on all evaluated generative tasks against 20 baseline approaches --- ### DRanker: A Transformer-Based Multi-Task Ranking Model for the Disney+ Homepage Authors: Priya Nirmal Singh Khokher, Daniel Nemirovsky, Benjamin P. Whitesell, Ethan Sukrae Lee, Eric Wulf, Tom Chee-Duffy, Nicholas Flores Published: 2026-10-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.15696v1 We present DRanker (Disney+ Ranker), a transformer-based multitask ranking model serving personalized recommendations on the Disney+ homepage. We describe the encoder-only architecture over enriched engagement-history sequences paired with a lightweight causal debiasing mechanism, and the inference stack that enables transformer-based ranking at scale. Through iterative development, we systematically evaluated more complex alternatives and found that simpler designs consistently outperformed them on offline metrics, qualitative behavioral evaluation, and in production. Deployed globally, DRanker drives over 1% lift in our key engagement metric and 0.5% lift in daily active users across all experiences powered by the ranker. We share practical lessons on data engineering, debiasing, and architectural choices that shaped our ranking system at scale. --- ### Do LLM Tutors Actually Teach? A Process-Centered Synthesis of the Tutoring Loop Authors: Sayantan Adak, Rima Hazra, Koyel Mukherjee, Digbalay Bose, Somnath Banerjee Published: 2026-10-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.15692v2 Large language models can produce fluent tu- toring dialogue, but whether they actually help students learn remains unclear. We present a process-centered synthesis of LLM tutoring that follows the path from learner-state infer- ence to pedagogical action, tutor training, eval- uation, and student simulation. This view ex- poses a central gap: implementing a tutoring component does not establish that it works or that its outputs meaningfully affect later stages. A structured study-level audit shows that peda- gogical evaluation is common, while evidence becomes much thinner for learner-conditioned intervention, human learning gains, and espe- cially transfer or delayed retention. Human studies nevertheless provide a conditional posi- tive result: LLM tutors can improve learning, but benefits depend on pedagogical structure, learner engagement, and how learning is mea- sured. We argue that progress requires validat- ing the interfaces between tutoring stages, not only improving individual components. --- ### FARL: A Fully Automated Pipeline of RL Interface and Solver Design Authors: Tianyu Jin, Liuyu Xiang, Chaowen Yang, Xingyang Chang, Pei Pei Li, Zhaofeng He Published: 2026-10-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15691v1 Existing reinforcement learning (RL) largely focuses on optimizing learning algorithms within a pre-defined task formulation, while applying RL to new tasks still relies heavily on human expertise to design the learning pipeline: what an agent observes, how it is rewarded, which algorithm it uses, and how training is configured. Automating these choices is challenging because they are tightly coupled. We introduce FARL (Fully Automated Reinforcement Learning), a framework that automates RL design by jointly searching observation and reward programs, learning algorithms, and training settings. FARL uses training statistics and observed behavior to diagnose failures, propose changes, and test whether they improve learning. Its search preserves diverse candidates and the controls needed for these tests, using a staged budget to screen designs before investing in longer training. Experimental memory records each finding together with its conditions, so an unsuccessful component can be reconsidered in a different combination. Across expert-withheld and expert-available settings, FARL outperforms the evaluated automated baselines on challenging navigation, locomotion, and manipulation tasks. On Adroit Hand Relocate, FARL achieves 97.1% success at 5M training steps per policy, compared with 0% for Eureka and LiMEN and 1.0% for native Proximal Policy Optimization (PPO) under the same policy training budget. --- ### Notes on Uniform Policy Score Bounds and Lipschitz Continuity for Truncated Gaussian, Product Cauchy, Boltzmann, and Softmax Policies Authors: Yanjie Dong Published: 2026-10-11 Categories: stat.ML, cs.LG, math.PR arXiv: https://arxiv.org/abs/2610.15690v1 We establish uniform score bounds and Lipschitz continuity for truncated Gaussian, Cauchy, Boltzmann, and softmax policies under explicitly stated parameterizations. --- ### When do explicit penalties improve flow matching? Authors: Lea Kunkel, Alberto González-Sanz, Sophie Langer Published: 2026-10-11 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2610.15689v1 Flow matching can learn structure directly from data, raising the question of when additional constraints improve generation. We study penalties that encode such constraints, with physics-informed flow matching as a motivating example. Satisfying a constraint more closely need not make the generated distribution more accurate. We therefore compare penalised and unpenalised generative modelling through their expected squared $2$-Wasserstein error. Our analysis covers both vector-valued and functional data in a Hilbert-space setting. We first derive geometric criteria that account for constraint violations and the distribution of samples after projection onto the constraint set. We then solve the statistical comparison explicitly for specific velocity-field classes and constraints via flow matching. In this model, penalisation improves accuracy exactly when the reduction in estimation variance outweighs the increase in squared bias. The resulting formula shows how this trade-off depends on sample size, the model class, the noise schedule, and the penalty weight. --- ### Towards Autopilot Labeling for Short Video Content Governance Authors: Junwen Chen, Hongwei Wang, Zixuan Wang, Jingbing Wang, Gorden Liu, Sheng Siong Ong, Xiaojiao Zang, JuChin Chao, Ze Jin, Kaiwen Men, Yin Li, Jeremy Li et al. Published: 2026-10-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.15687v1 The explosive growth of short videos has presented significant challenges to content governance. Traditional manual labeling is inefficient, slow to iterate, and costly. Therefore, we explore and develop a multi-stage autopilot labeling framework aimed at progressively increasing the level of automation in short video content annotation. To move beyond the heavy reliance on human expert labeling at the initial L0 stage, we first introduce a discriminative MLLM labeler at the L1 stage, which is fine-tuned with supervised data to directly predict labels for short videos. Advancing to the L2 stage, we shift to a domain-adaptive MLLM pretrained on short video data and use it for zero-shot labeling, enabling flexible generalization without task-specific supervision. In the L3 stage, we propose an agentic annotation workflow, and equip the agent with several key tools, which empower the agent to handle complex, unfamiliar, or vaguely defined cases, significantly reducing the need for human intervention. We conduct extensive experiments across various content issues, and results demonstrate that each stage of the autopilot labeling framework progressively improves labeling accuracy, and has significantly reduced manual labor costs in real-world applications by up to 85%. --- ### Radioactive Feedback: Tracing Models Trained by Label-Only LLM Supervision Authors: Yuejia Li, JunHeng Li, Hao Wu, Ke He, Mang Ye Published: 2026-10-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15685v1 Conventional distillation transfers capability through teacher-generated demonstrations. LLM-as-a-Judge knowledge distillation offers a distinct and increasingly practical alternative. In the label-only variant studied here, the student generates every response and improves from scalar scores alone. Prior work shows that this non-demonstrative feedback can improve student capability, but it creates a fundamentally different provenance problem. No teacher-generated answer enters the student's training set, so any evaluator-specific trace must pass through a low-bandwidth reward signal rather than copied text. Existing watermarks and distillation detectors do not cover this score-only channel. We introduce Radioactive Feedback, which encodes a registered pattern of behavioral preferences in the rewards themselves. The evaluator applies bounded pointwise adjustments to quality-qualified responses, allowing repeated optimization to transfer the pattern to a student trained by another party. Experiments on code and mathematics show that the registered preferences transfer through scores alone and across datasets, enabling black-box detection against a fixed reference pool. --- ### Rethinking Human Intent-to-CAD: Parametric CAD Model Generation via Cooperative Multi-Task Alignment and Spatial-Aware Reinforcement Learning Authors: Qingwang Zhang, Jiahao Li, Xiangdong Zhou Published: 2026-10-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.15681v1 Parametric Computer-Aided-Design (CAD) modeling from human intent remains challenging, particularly during the conceptual design stage, where design goals are expressed through incomplete and unstructured modalities (e.g., hand-drawn sketches and textual descriptions). In this work, we rethink the human intent-to-CAD pipeline and propose a unified method that directly maps multi-level human intents to executable codes, without assuming the prior existence of target CAD models. To support our study, we construct HiCAD, the first large-scale dataset aligning hand-drawn sketches, textual descriptions, and parametric CAD codes. Based on this, we introduce HiCAD, a two-stage framework comprising Cooperative Multi-Task Alignment to bridge the representational gap between heterogeneous inputs, and Spatial-Aware Reinforcement Learning to enforce geometric and topological consistency. Extensive experiments demonstrate that our method significantly outperforms existing baselines across multiple tasks, validating its effectiveness and robustness in transforming heterogeneous human intents into high-fidelity parametric CAD models. Our project page: https://zqwlearning.github.io/HiCAD. --- ### The Mathematical Collective Unconscious: Jungian Archetypes within the Latent Space Authors: Andrew Breen Published: 2026-10-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.15678v1 Carl Jung theorised that the human psyche contains an inherited framework, the collective unconscious, populated by universal archetypes. As large language models (LLMs) are trained on vast corpora of textual data, this paper investigates whether they spontaneously construct distinct archetype-like regions within their high-dimensional latent spaces. The paper proposes that these regions function as spatial constraints that naturally organise semantically related narratives. To evaluate this, we applied cosine similarity and angular distance metrics across thirteen experiments utilising OpenAIs text-embedding-3-small model. The paper contains two experimental sections the first section explores these ideas using synthetically constructed narratives, the results of which act as a baselines for experiments conducted in the second section where the synthetic data is replaced by human-authored literature (Shmoop corpus), unedited dream reports (DreamBank corpus), and culturally distilled folklore (Andrew Langs Fairy Books). The results show that archetypal roles occupy distinct, measurable regions in the latent space. Crucially, these regions remain compact and consistent because of narrative structure rather than simple word overlap. Additionally, text category dictates spatial distribution: dream reports concentrate within Trickster and Shadow regions, while traditional folklore distributes evenly across all tested archetypes. We conclude that transformer latent spaces encode stable regions which appear to correspond to recognised Jungian archetypes. --- ### Knowledge Interaction in Hypernetwork-based Continual Learning: Conflict and Composition Authors: Jiaqi Zheng, Yi Hu, Yadong Mu, Muhan Zhang Published: 2026-10-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15677v1 Continual learning aims to adapt pretrained large language models (LLMs) to evolving data while preserving their pretrained capabilities. A central challenge is catastrophic forgetting: adaptation to new data can impair performance on previously learned knowledge. Since continual learning commonly changes model parameters, the model's predictions may draw on knowledge from the base model, the parameter update, and the input context. Understanding how these sources interact is essential: conflicts reveal whether new knowledge can override outdated knowledge, while multi-hop reasoning tests whether new knowledge can be composed with existing knowledge to support generalization. We study these interactions in a hypernetwork-based adaptation framework, where a shared network generates adapters from context, allowing a frozen base model to adapt without task-specific updates. We find that, under knowledge conflict, models preferentially follow the context, and their choices depend more on where knowledge is presented than on its content. We also show that context and adapter knowledge perturb the base model's representations along directions orthogonal to its clean hidden states, enabling us to derive steering vectors that control which source the model follows. In multi-hop reasoning, we find that models fail to reliably compose knowledge across the three sources, with the key breakdown arising from the interaction of the hypernetwork with both the base model and the context. Code and reproduction materials: https://github.com/missswiftie/Knowledge-Interaction-in-CL --- ### Recovering Low-Bit Failures in Vision-Language-Action Policies via Quantization-Conditioned Reinforcement Learning Authors: Seongmin Park, Jaewon Lee, Yujun Heo, Yoonsik Kim, Seheon Choi, Hyoung-rock Kim, Jungwook Choi Published: 2026-10-11 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2610.15675v1 Quantization lowers deployment costs of vision-language-action (VLA) policies but can compromise task completion. Across five VLA models and 4,050 real-world trials, we systematically reveal that quantization-aware training (QAT) generally improves on post-training quantization (PTQ) but leaves substantial gaps to full precision (FP) on long-horizon tasks and under visual and semantic shifts, while its imitation-based objective does not explicitly use rollout success or partial completion. To exploit these outcome signals, we introduce Quantization-Conditioned Reinforcement Learning (QCRL), an offline RL method coupling progress-based advantage estimation with quantization-aware source conditioning. FP rollouts supply reference experience beyond action-level distillation, progress-scaled terminal penalty distinguishes partial completion, and quantization-aware conditioning selects advantageous reference behavior within the quantized policy. We evaluate weight-only INT4 W4A16 on $π_{0.5}$ and GR00T N1.5 and joint weight-activation NVFP4 W4A4 on $π_{0.5}$. Using only in-distribution data, QCRL reaches 99.3% of FP's mean score across three visual-shift conditions for $π_{0.5}$ with INT4 W4A16, alongside 42.9% model-memory savings. With NVFP4 W4A4, it reaches 100.7% of the same FP baseline, alongside a $1.73\times$ speedup using NVFP4/FP8 deployment. Hardware gains are relative to FP16 on Jetson Thor. --- ### ProtoPur: Prototype-Purity Pseudo-Labeling for Weakly Supervised Instance Learning in Pathology Authors: Chen Shu, Chengyang Zhang, Boyu Fu, Ting Yin, Wenchuan Zhang, Jie Chen, Yuhao Yi, Hong Bu Published: 2026-10-11 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2610.15669v2 Weak bag-level labels are widely available in computational pathology, whereas reliable instance-level annotations for whole-slide images remain expensive and ambiguous. Weakly supervised multiple instance learning (MIL) achieves strong bag-level classification, but instance-level supervision from attention scores, model predictions, negative bags, or spatial refinement may fail to identify class-specific local evidence. We propose ProtoPur, a prototype-purity pseudo-labeling method for weakly supervised instance-level learning in pathology whole-slide images. ProtoPur estimates class-balanced local purity over prototype regions constructed from frozen foundation-model features, and assigns pseudo-labels to high-purity regions strongly associated with a target class. This purity-first design separates class-specific evidence from negative or shared morphology, with coverage used only to ensure sufficient pseudo-label assignment. We provide a PAC-style analysis showing that the risk of an instance classifier trained with ProtoPur pseudo-labels can be decomposed into a standard uniform-convergence term and a ProtoPur-specific pseudo-label noise term, comprising selected-region mismatch and a coverage residual. Experiments on three public whole-slide image datasets with two pathology foundation encoders show that ProtoPur consistently improves instance-level performance across multiple MIL backbones while maintaining competitive bag-level performance. Pseudo-label quality comparisons on two public datasets further demonstrate that prototype-purity selection provides stronger instance supervision. These results suggest that the foundation-model features contain exploitable instance-level supervision signals, and ProtoPur is a way to reveal and use these signals from weak bag labels without requiring dense instance annotations. --- ### Rate-Resolved Text Evaluation with Masked Diffusion Language Models Authors: Yiqi Liu, Kun Zhao, Chenghua Lin, Nafise Sadat Moosavi Published: 2026-10-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.15667v1 A single evaluation score can rank generation systems but rarely reveals what failed. We propose rate-resolved text evaluation, which turns the masking rate of masked diffusion language models into a diagnostic axis. By reconstructing text under different fractions of masked tokens, one diffusion score becomes a vector of band-conditioned scores that reflect reconstruction difficulty at varying levels of visible context. On SummEval, preserving this rate structure yields complementary signal: the best masking-rate band improves fusion with autoregressive likelihood over a collapsed diffusion scalar, survives a sample-shuffle control that breaks rate ordering, and adds residual signal to a fixed prompted judge. A second diffusion model reproduces the effect more weakly. On WMT MQM zh-en, roundtrip mask-and-reconstruct probing produces a tunable localization curve in which ranking-oriented AUROC and span-detection F1 peak at different masking rates. Factuality benchmarks bound the interpretation: band semantics are model- and task-dependent, so each application requires empirical validation. --- ### A Persian Vision-Language-Action Dataset and Benchmark for Ambiguity- and Infeasibility-Aware Instruction-to-Plan Grounding Authors: Abdollah Pourasghari, Saeedeh Sadat Sadidpour, Mohammad Roustaei Published: 2026-10-11 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2610.15666v1 Converting natural-language instructions into executable action plans conditioned on a scene image is a core capability for embodied human-robot interaction, but existing benchmarks target English, simulated or video-grounded environments, and largely assume instructions are clear and executable. We introduce the first Persian vision-language-action dataset for this task: 258 instances over 230 real household/office photographs, annotated with reference plans, deliberate ambiguity and infeasibility labels, disambiguating question-answer pairs, and an auto-generated chain-of-thought rationale for training. Using this resource, we ablate retrieval-augmentation, chain-of-thought prompting, and an agentic disambiguation step, evaluated with an LLM-as-judge protocol and a new metric, PGOS-FA, extending prior work (PG2S) with step-order sensitivity, an over-generation penalty, and Persian-adapted embeddings. Paired statistical testing across 36 comparisons shows retrieval-augmentation is a large, robustly significant effect, while finer-grained additions are directionally consistent but not statistically distinguishable from noise at this scale, and the LLM-judge metric has near-zero power where PGOS-FA succeeds. A blind human-correlation study on 79 real outputs shows PGOS-FA tracks human judgment at least as closely as the LLM-judge. Testing generalization beyond the ablation's single backbone, we find that most of the gap between an open-weight and a substantially stronger closed planner is attributable to open-weight model generation rather than to the closed model's capability specifically, and that our best configuration significantly outperforms an independently reproduced external baseline despite a weaker backbone. The dataset, PGOS-FA implementation, and evaluation code will be made available upon reasonable request. --- ### Drift, Then Spread: Learning One-Step Generative Policies for Online Reinforcement Learning Authors: Chunyu Luo, Hongyu Zhao, Guangyi Ni, Yue Song, Lingkai Kong Published: 2026-10-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.15662v1 Generative policies offer expressive action distributions for online reinforcement learning (RL), but many diffusion- and flow-based policies require costly iterative sampling. We propose DriftSpread, a one-step generative policy based on Drifting for online maximum-entropy (MaxEnt) RL. To incorporate entropy without a tractable policy density, we build on an energy-based view of Drifting and derive critic-guided Drift and entropy-induced Spread from the negative MaxEnt objective. Our method learns these updates sequentially in the same actor, using action regression for value improvement and distribution matching to capture the effect of entropy. The actor updates require neither direct samples from the critic-defined Boltzmann target nor policy-density or score estimation. Under exact fitting with a fixed critic, we prove convergence to the Boltzmann target in the small-step limit followed by the long-time limit. On MuJoCo, DriftSpread achieves the highest aggregate normalized return among all evaluated methods, while outperforming the diffusion- and flow-based baselines in both training and inference efficiency. --- ### Feedback as an Interface: Controlling Form and Detail in LLM Translation Refinement Authors: Yiqi Liu, Flavjo Tomori, Nafise Sadat Moosavi, Steffen Eger, Chenghua Lin Published: 2026-10-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.15661v1 Feedback presentation shapes how LLMs use evaluator judgments during translation refinement. We introduce a machine translation protocol that keeps the evaluator score, main issue, and recommendation fixed while varying feedback form and supporting detail. Across seven models and six translation directions, low-load feedback outperforms high-load feedback in all 42 translator-direction settings under xCOMET. On the 29,400-record rewriting subset, mean xCOMET scores multiplied by 100 are 83.30 for low-load feedback and 80.67 for high-load feedback; the full-matrix original-translation reference mean is 83.46. MetricX-24 supports the low-load advantage on a stratified subset. A no-feedback second pass yields a small improvement over the original translations, and direct evaluator prompting reproduces the low-load advantage without a separate rewriting stage. These results show that compact feedback limits the quality loss from evaluator-guided refinement in the evaluated high-resource MT settings. --- ### Sparse All-Layer Connector for Domain Generalised Semantic Segmentation Authors: Ruoyu Guo, Xin Kun Lin, Maurice Pagnucco, Yang Song Published: 2026-10-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.15660v1 Domain generalised semantic segmentation (DGSS) has recently benefited from combining multiple foundation models, such as vision-language and vision foundation models, to leverage their diverse representations for generalisation. Existing multi-model approaches share a common design choice: cross-model fusion is restricted to depth-aligned layers, implicitly assuming that mutually beneficial information resides at the same depth across models. However, foundation models pretrained under different objectives may develop distinct representation hierarchies, making the optimality of depth-aligned fusion questionable. Moreover, we observe that the foundation models exhibit different depth-wise domain sensitivity. Motivated by these observations, we propose a Sparse All-Layer Connector (SALC) that enables each layer to access information from preceding layers of another model. As the number of accessible layers grows with depth, dense aggregation may hurt generalisation. SALC therefore learns to adaptively select a sparse subset of informative layers. We further introduce a candidate dropout regularisation that strengthens sparsity and encourages SALC to explore diverse layers, leading to more robust selection. Across four foundation model combinations and three DGSS evaluation settings, the proposed design demonstrates stronger generalisation than conventional depth-aligned fusion. The code is available at https://github.com/RuoyuGuo/SALC. --- ### Testing Central Structure for Complex Networks Authors: Qilong Wu, Yuxiao Li, Simeng Zhang, Xinying Liu, Yan Liu, Zengyou He Published: 2026-10-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.15659v1 Centrality measures rank nodes even when the observed differences can be explained by ordinary structural variation. We therefore study a preceding question: whether a network contains a statistically identifiable central structure at all. We formulate this question as a network-level hypothesis testing issue using the adjacency spectral radius as the test statistic and estimate an empirical p-value from randomized networks generated under a specified null model. The framework is evaluated using G(N,M), Chung-Lu, and two implementations of the configuration model on simulated benchmarks and 55 real networks. Controlled experiments further vary the number and connection weights of designated central nodes while holding network size and density fixed. The results show a clear negative association between central-structure strength and the empirical p-value. They also demonstrate that rejection decisions depend substantially on the structural properties preserved by the null model: the detected network sets are not simply nested across models. --- ### Dynamic Conflict Clustering with Lightweight Learning and Strategic Repair for Distributed Constraint Satisfaction Authors: Raziyeh Moghaddas, Fabio Caraffini Published: 2026-10-11 Categories: cs.MA, cs.AI, cs.DM arXiv: https://arxiv.org/abs/2610.15658v1 Distributed Constraint Satisfaction Problems (DCSPs) model distributed decision-making in multi-agent systems, where agents assign values to local variables while satisfying shared constraints. However, many DCSP solvers still rely on broad, repeated peer-to-peer communication and are largely reactive, with limited support for strategic coordination or learning. This increases communication overhead, can lead to stagnation, and reduces the success of hard instances. Hence, we propose Dynamic Conflict Clustering-Incomplete (DCC-Incomplete), a repair-based solver that combines conflict-centred decomposition, structured coordination, strategic repair, and lightweight learning for stagnation recovery. DCC-Incomplete groups the unsolved part of the problem into conflict clusters and restricts communication via a coordination layer to agents within the same conflict region. It also introduces memory-guided restart, enabling agents and clusters to pause, revise, and adapt repairs based on neighbouring conflict states. A thorough evaluation of DCC-Incomplete on distributed graph-colouring benchmarks with planted satisfying assignments shows that its memory-guided restart improves the success rate from 37.50% to 61.11%, reduces median runtime from 0.565s to 0.367s, and cuts median communication from 12.493 to 6.503 messages per constraint. These results suggest that dynamic conflict clustering, combined with lightweight strategic and learning-guided repair, improves both communication efficiency and robustness in incomplete DCSP solving. --- ### SurgCast: Action-Conditioned Future Skeletons for Controllable Surgical World Models Authors: Wanhao Liu, Rulin Zhou, Liangjing Shao, Zhaocheng Lin, Dongyue Li, Jinsong Lin, Guoheng Ma, Hangheng Yang, Zhiqing Tang, Jing Chen, Panshuo Li, Hongliang Ren Published: 2026-10-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.15645v1 Surgical world models must turn prospective robot actions into visually faithful, structurally consistent instrument motion. We introduce SurgCast, which predicts future instrument skeletons from current structure, robot state, and future actions, then uses the forecast to control video generation. Dual-path injection combines skeleton geometry with derived, instrument-specific motion descriptors through geometric residuals and conditioning modulation. Both paths complement native action conditioning and are retained in a four-step causal student. On SutureBot and SRTH-Porcine-Cholei, the teacher and student improve all seven reported quality and instrument-consistency metrics over their respective direct-action baselines; teacher FVD decreases by 37.6% and 67.3%. Ablations show that future actions improve skeleton prediction and that combining both injection paths performs best across all six metrics under predicted skeletons. These results support using predicted articulated structure and its motion semantics as a control interface for surgical video prediction. Project videos and examples are available at https://surgcast.netlify.app/. --- ### Recall What Is Missing: Composing Evidence from Long-Term Agent Memory Authors: Qi Feng, Jicong Fan Published: 2026-10-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15642v1 Under a limited context budget, a long-term agent must recall not merely memories that are individually relevant, but evidence that is collectively sufficient for the current query. Conventional memory access retrieves, scores, and truncates memories, often spending multiple context slots on redundant facts while leaving complementary evidence behind. We cast the read phase of long-term memory as query-conditioned evidence composition: each memory is valued by what it adds beyond the evidence already selected. We instantiate this operation with MemPursuit, a training-free mechanism that uses the residual of a sparse convex query reconstruction as a representation-space proxy for what the current memory set is missing. By reusing the query and candidate embeddings already available from retrieval, MemPursuit progressively composes nested evidence contexts without invoking a language model or cross-encoder to score each query--memory pair. The effectiveness of our method is verified on 3 popular benchmarks in comparison to strong baselines. In fixed-budget LoCoMo experiments, MemPursuit improves end-to-end accuracy by 7.2 percentage points at Top-10 and 5.5 percentage points at Top-20, with consistent gains across multiple memory frameworks, while achieving a 32.9$\times$ speedup in median reranking latency over fully batched BGE-v2-m3. Our implementation is available at https://github.com/FengQi-HITSZ/MemPursuit. --- ### Context-Aware Precision Scheduling for Small Language Models Authors: Mukund Athmaram, Manoj Rao, Liang Ma Published: 2026-10-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.15640v1 Small language models (SLMs) used as on-device agents must balance accuracy and latency as their context grows. Mixed precision helps manage this tradeoff by assigning different precisions to weight tensors according to their size and sensitivity. However, these choices depend on the operating conditions, so a configuration selected for a short context may no longer provide the best tradeoff at a longer one. We calibrate a timing model from measurements at different precisions and context lengths, and combine it with tensor sensitivities to choose configurations under a latency or accuracy budget. We argue that fewer bits do not always mean faster execution, so our predictor estimates latency from calibrated execution costs rather than weight bytes alone. Under a latency budget, reading the larger key-value (KV) cache leaves less time for weight operations, leading the allocator to select lower precisions. This gives a schedule of tensor changes that can be prepared before execution. Our runtime follows the schedule while retaining the session's KV cache. We evaluate executed schedules on a laptop GPU, including a longer-context schedule with three weight formats and a tool-use benchmark measuring full response time and correctness. Under an accuracy budget, measured error from a quantized KV cache determines the budget left for weights. The allocator can raise or lower weight precision as this estimate changes. These experiments show where context-aware precision helps and where accuracy recovery remains limited. --- ### MERIT: Scaling KG Foundation Models with Relation Transformers Authors: Cosimo Gregucci, Daniel Hernandez, Antonio Vergari, Steffen Staab Published: 2026-10-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.15638v1 Knowledge graph (KG) foundation models (KGFMs) predict links on unseen graphs zero-shot. KGFMs have been pioneered by ULTRA which builds a relation graph from co-occurrences that match motif templates, and passes messages over it to obtain relation representations. More recent KGFMs such as MOTIF and TRIX increase the size of this relation graph, and FLOCK replaces message-passing with probabilistic random-walk ensembles. However, larger relation graphs mean more messages, and more walks mean more sequences to encode, so they improve performance at higher training and inference cost. This cost hinders their use in more complex reasoning tasks, such as complex query answering. To reverse this trend, we design MERIT, the first KGFM with a transformer relation encoder: every relation name attends to every other, and the motifs enter as a soft prior rather than as edges. Over 56 benchmarks, MERIT matches the zero-shot MRR of SoTA KGFMs while being 6x faster than TRIX and over 100x faster than FLOCK at inference. Fine-tuned for complex query answering like UltraQuery, MERITQuery improves over it at matched cost. ---