# Research Papers — 2026-09 · bundle page 58 of 266 > Full-text markdown of papers #2851–2900 of 13298 published in 2026-09, newest first. AI-readable mirrors of the full 13298-paper 2026-09 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-09/page/58 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/57.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/59.md) ### Mask-Induced Displacement in Audio XAI via Logit Trajectory Decomposition Authors: Nico García-Peguinho, David Kelly, Fabrizio Smeraldi, Anna Xambó Sedó Published: 2026-09-27 Categories: cs.SD, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2609.33486v1 Perturbation-based XAI methods for audio classifiers often estimate feature importance by masking spectrogram regions and crediting output changes to the retained signal. Yet they typically assume the fill (the mask replacement) is negligible. We propose logit-space trajectory decomposition to examine this assumption. An on-axis component captures output along a line connecting the fully filled (occluded) spectrogram to the fully retained original; an off-axis component captures perpendicular displacement. We evaluate across three fills, three audio classifiers, and 1,100 AudioSet clips. We demonstrate that no fill is acoustically neutral under full occlusion: Zero fill activates silence and Gaussian Noise fill activates broadband noise. Under partial masking, 41-77% of output displacement is off-axis, with the direction of the residual stable across mask retention fraction and specific to each model-fill combination. Attribution methods are unevenly exposed to off-axis displacement through their sampling and weighting strategies, revealing apparatus-dependence. Where the off-axis residual is stable and low-dimensional, its structure affords mitigation. --- ### DISCO: Distributed Long Context Scaling with Grounding-Reasoning Disaggregation Authors: Guanzheng Chen, Viet Dac Lai, Subhojyoti Mukherjee, Branislav Kveton, Seunghyun Yoon, Franck Dernoncourt, Qizhe Xie, Trung Bui Published: 2026-09-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.33485v1 While Large Language Models (LLMs) advertise million-token context windows, reasoning quality often collapses as inputs grow -- a phenomenon termed context rot. This failure stems from a structural entanglement in monolithic architectures, where the massive search burden of contextual grounding exhausts the representational capacity needed for complex reasoning. To resolve this, we propose Grounding-Reasoning Disaggregation via DIStributed long COntext scaling (DISCO). Inspired by distributed computing frameworks like Apache Spark, DISCO partitions long context across a fleet of Worker LLMs dedicated exclusively to parallel, localized grounding. A central Driver LLM, trained via Reinforcement Learning (GRPO) to optimize planning, orchestrates execution by dynamically mapping queries into atomic extraction tasks and reducing the gathered evidence to synthesize a final answer. By isolating reasoning from raw context noise, DISCO effectively eliminates context rot. On RULER-QA (1M tokens), it maintains 78.4% accuracy where standard baselines collapse. Furthermore, it outperforms full-context models by up to 9.8 points on LongBench v2 and matches frontier models like Gemini-3-Pro-Preview while reducing inference costs by over 80%, establishing a highly efficient paradigm for robust long-context inference. --- ### How Synthetic Labels Improve Conformal Prediction: A Perspective on Conditional Coverage Authors: Qianyi Chen, Bo Li Published: 2026-09-27 Categories: cs.LG, stat.ME arXiv: https://arxiv.org/abs/2609.33482v1 Conformal prediction provides distribution-free finite-sample marginal coverage, but post-hoc calibration data may be too scarce to learn how uncertainty varies across inputs. Meanwhile, abundant covariates can often be labeled cheaply by domain models or general-purpose language models. We study whether these synthetic labels can improve conditional coverage when only a small trusted sample is available. Building on score-quantile regression, we introduce prediction-powered quantile learning: a synthetic-labeled pool estimates pinball risk, paired trusted and synthetic outcomes correct its bias, and an independent trusted split performs final conformalization. Profiling pinball risk over scalar corrections reveals that population conditional-coverage error is its functional gradient; the corresponding Hessian removes global shifts and weights remaining shape error by boundary density. Composing this geometry with prediction-powered learning yields a three-resource expansion and a benefit--cost rule for synthetic power. Across eight regression benchmarks, synthetic-powered quantile learning substantially improves downstream conditional coverage while preserving marginal validity and producing more compact prediction sets. A human-rating study finds similar gains from external LLM labels and exposes a quality--quantity--cost tradeoff. --- ### Just Let Linear States Forget the Distant Past: Prefix Caching via Suffix Replay for Hybrid LLMs Authors: Yirui Liu, Ruoling Qi, Xuaner Wu, Yuxin Jin, Jian Chen, Penghang Liu, Yafei Huang, Jiawei Shao, Xuelong Li Published: 2026-09-27 Categories: cs.AI, cs.PF arXiv: https://arxiv.org/abs/2609.33477v1 Hybrid LLMs interleave full-attention layers with linear-attention layers to reduce long-context inference cost, but this structure complicates prefix caching. Full-attention KV caches are token-addressable, whereas linear-attention layers maintain recurrent states that cannot be rolled back to arbitrary prefix boundaries. Existing systems materialize recurrent-state checkpoints, restricting prefix reuse to checkpoint-aligned positions. We present SuffixReplay, the first prefix caching system that lets hybrid LLMs reuse cached prefixes at every cache-supported page boundary without materializing recurrent-state checkpoints. Our key insight is to just let linear states forget the distant past. Modern linear-attention mechanisms use recurrent decay and gating to attenuate the influence of old inputs. Therefore, instead of checkpointing every prefix boundary, SuffixReplay approximates the state at a matched boundary by replaying only a recent suffix of the layer's input hidden states, which we retain as anchors. At the algorithmic level, SuffixReplay combines layer-wise and token-wise anchor sparsity with a bounded replay budget to control storage, computation, and quality. At the system level, it uses an independently managed anchor sidecar and a pipelined replay path to overlap anchor movement and state reconstruction with the native serving pipeline. We evaluate SuffixReplay on three hybrid LLMs: OLMo-Hybrid-7B, Qwen3.5-4B, and Qwen3.6-27B-FP8. Across these models, SuffixReplay retains 91.4-100% of full-prefill quality on average across LongBench and RULER, while using only 0.36-0.51x the amortized per-token storage of SGLang's default 8192-token checkpoint cache. Integrated into SGLang, SuffixReplay reduces median TTFT by 15-70% on branching workloads, sustains 2.3-4.3x SGLang's throughput when the working set exceeds HBM, and matches SGLang on high-hit continuation traffic. --- ### Geometric Identification in Predict-Then-Optimize Learning Authors: Jiaxiao Xu, Changhong Mou, Keji Liu, Dinghua Xu, Yeyu Zhang Published: 2026-09-27 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2609.33472v1 Decision-focused surrogates can recover downstream decisions without identifying the quotient report. We characterize the equality set of the convex Smart Predict-then-Optimize surrogate (SPO+) population risk. Under central symmetry, the centered mean class is the unique Bayes minimizer exactly when every nonzero effective displacement makes the old optimizer leave the shifted optimal face with positive probability. This condition separates face crossing from selected-oracle disagreement and gives quantitative local coercivity. Without symmetry, strict crossing alone need not identify the mean; selection balance with reflected crossing restores quotient-report identification, and conditional versions extend the result to measurable predictors. These are population statements, without finite-sample report-recovery or generic transfer-regret guarantees. Closed-form mechanisms reproduce the analytic identities and rates. Portfolio, complete-matrix KuaiRec, and Energy/Storage studies measure predictive fidelity, shifted regret, and fitted-report geometry. A known data-generating process (DGP) companion retains their application geometries while isolating conditional-mean recovery and crossing, without testing the original observational assumptions. --- ### LiveOption: Evaluating LLM Agents in Structured Option Trading with Nonlinear Payoffs Authors: Haochen Luo, Yifan Li, Binh Minh An, Xiaolong Luo, Zhengzhao Lai, Yuan Zhang, Chen Liu Published: 2026-09-27 Categories: cs.AI, q-fin.CP arXiv: https://arxiv.org/abs/2609.33470v1 Large language models (LLMs) and multi-agent systems (MAS) have shown promise in financial decision-making, yet existing evaluations focus on equity trading and primarily assess directional prediction, overlooking the structural complexity of derivative markets. Option trading introduces fundamentally different challenges, including nonlinear payoffs and multi-leg strategy construction, requiring structured decisions rather than simple directional bets. We introduce LiveOption, an evaluation framework for LLM-based agents in option trading. LiveOption formulates the problem as structured sequential decision-making under realistic execution and capital constraints, and provides a reproducible environment with standardized interaction protocols. The framework includes three task suites covering portfolio overlays, event-driven earnings trading, and 0DTE intraday trading. We further propose a hierarchical metric suite that evaluates action validity, decision quality, risk characteristics, and outcome-level performance. Experiments show that current agents often fail to achieve competitive returns in most scenarios. LiveOption offers a principled testbed for evaluating structured decision-making beyond outcome-based metrics. --- ### A Cheap Verifier is Good Enough: LLM Post-training is Robust to Erroneous Rewards Authors: Andreas Plesner, Curtis Northcutt, Francisco Guzmán, Anish Athalye Published: 2026-09-27 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.33467v1 When post-training large language models on tasks with semi-verifiable rewards, there are many factors (training steps, base model size, training order, data quality, verifier accuracy, etc.) that practitioners must contend with to maximize model performance. Yet, it remains unclear how well verifier agreement predicts post-training performance on such tasks. In this paper, we explore this question with over 11k H100 GPU-hours, across HealthBench and PRBench tasks in medical, legal, and finance domains. Across the tested domains, Qwen3 trainees (1.7B-8B on HealthBench; 8B on PRBench), evaluation splits, and frontier LLM reference judges (which we call golden verifiers), higher verifier agreement does not consistently identify the best training verifier. Expensive verifiers need not outperform inexpensive ones, and open-weight Gemma verifiers produce strong training outcomes. We compare two low-cost choices retrospectively -- a cost-reducing choice and a balanced choice -- with estimated grading cost reductions of 98.8%-99.7% relative to the golden grading protocols and average post-training score gaps of 1-3 points from the best evaluated training verifier. These averages include larger losses in individual settings; they do not establish that verifier choices are interchangeable. --- ### GSM: Efficient Language Modeling with Shared Global State Authors: Yunao Zheng, Bin Wen, Xiaojie Wang, Kaiyu Jiang, Xuanyu Zheng, Changyi Liu, Hongyi Fu, Jianxiong Wang, Tianke Zhang, Haonan Fan, Yingxin Li, Jiankang Chen et al. Published: 2026-09-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.33465v1 Efficient language models must reduce not only the cost of individual accesses to past context but also the overhead of repeatedly selecting and processing historical information across layers. We introduce the Global State Model (GSM), a causal encoder--decoder architecture that concentrates the selection and aggregation of long-range information in the encoding stage. Through multiple stages of history retrieval, the encoder progressively incorporates long-range information into representations at recent positions, forming a shared state with a fixed window size. Each decoder layer accesses this same state using queries updated from the preceding layer, preserving computational depth while avoiding repeated construction of historical key--value (KV) representations and long-range indexing. As a result, neither the decoder's per-step attention cost nor its KV cache size grows with the history length. Experiments show that GSM improves computational efficiency and reduces cache overhead while maintaining model performance and the ability to use long-range information, offering a shared-state architecture for efficient language modeling. --- ### Rethinking Token Reweighting for SFT: Suppress, Reverse, and Extrapolate Learned Features Authors: Cunchun Li, Haonan He, Yifan Gao, Minglei Li, Jingqi Ye, Qingyu Yang, Peng Ye Published: 2026-09-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.33463v1 Supervised fine-tuning (SFT) learns most aggressively from tokens that the model deems least likely. This helps acquire new behaviors, but also amplifies noisy or conflicting supervision and can overwrite useful pretrained knowledge. Through a unified policy-loss view, we revisit existing token-reweighting methods and show that they assign nonnegative coefficients to demonstrated tokens. Consequently, they can suppress or amplify supervised updates, but cannot reverse harmful features once learned. Moreover, larger training weights do not amount to feature extrapolation, since they change the optimization trajectory rather than scale a fixed SFT direction. We argue that reversal and extrapolation require a stable reference frame defined by a fixed SFT delta. Motivated by this, we propose SCALE (Selective Control of Adaptation via Local Entropy), an entropy-guided adaptation-strength-control method that freezes the pretrained model and the SFT delta and learns bounded token- and module-specific gates by minimizing predictive entropy alone. These gates suppress, reverse, or extrapolate frozen SFT features according to their alignment with entropy reduction. Across Qwen2.5-Math-1.5B, Qwen2.5-Math-7B, and Qwen3-4B-Base, SCALE achieves mathematical-reasoning averages of 37.84, 43.60, and 36.57, exceeding the strongest corresponding baselines while remaining competitive on general-retention benchmarks. It also attains the best average code-generation performance across HumanEval, HumanEval+, and MBPP for all three models. These results suggest that effective SFT correction can benefit from controlling how already learned residuals are used, rather than only modifying how they are learned. --- ### SphMind: Towards Robust, Training-Free VLM-based Spatial Reasoning with a 360 Camera Authors: Shriram Damodaran, Soumyaratna Debnath, Cheston Tan, Lin Wang Published: 2026-09-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.33462v2 Omnidirectional or 360 cameras provide embodied AI agents with a holistic, wide field-of-view (FoV) view of their surroundings, motivating the use of Multi-modal Large Language Models (MLLMs) for omnidirectional spatial reasoning. However, most MLLMs are trained on conventional 2D perspective images and struggle with the severe distortions and wrap-around discontinuities induced by spherical geometry. Enabling them to generalize to non-Euclidean 3D spaces without retraining therefore remains challenging. We propose SphMind, a training-free, plug-and-play framework that decouples semantic perception from geometric reasoning. Rather than requiring MLLMs to learn spherical geometry internally, SphMind preserves their semantic capabilities while handling geometry externally. We introduce a Spherical Harmonics-based Spatial Graph (SHSG) that models spatial relationships through equivariant transformations on the sphere, together with Inference-Time Geometric Grounding (IGG), a model-agnostic closed-loop optimization process that aligns MLLM representations with spherical geometric constraints during inference. Experiments on three benchmarks show that SphMind achieves over 21.4% average improvement in directional reasoning on MP3D and Stanford2D-3D, outperforms prompt-engineering baselines by 8.7% on the real-world ODI-Bench, and improves rotational invariance by 5.9% under panorama rotations, without additional training or dataset-specific tuning. In-the-wild evaluations further show that SphMind resolves directional reasoning queries that baseline vision-language models fail to answer correctly. --- ### Protected Cores Are Not Enough: Certifying AI-Proposed Revisions of Temporal Specifications Authors: Ruggero Lanotte Published: 2026-09-27 Categories: cs.LO, cs.AI, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2609.33461v1 Runtime monitoring traditionally evaluates a specification that is fixed before execution or externally modified when requirements change. In learning-enabled and data-intensive systems, however, the temporal relationships represented by a specification may themselves evolve. Allowing an AI component to directly replace a formal specification is unsafe: it may overfit transient behavior, weaken protected requirements, or activate statistically unsupported revisions. We introduce an intersymbolic architecture in which an untrusted AI proposer suggests temporal specification revisions and a symbolic governor controls their activation. Two results organize the framework. First, origin-version semantics makes the outcome of each obligation invariant to later revisions. Second, aggregate certification can conceal systematic failures on protected triggers; simultaneous aggregate and core-conditional post-selection certification controls both targets. A structural invariant preserves designer-protected components, and a proposer-independent lifetime error bound supports repeated activation decisions. The statistical bound concerns the predictable means of completed certification samples; interpreting it as future operational validity requires an additional stability assumption. Controlled synthetic experiments use a frozen supervised AI proposer to illustrate the masked-core failure at one decision and across repeated governed revisions. The proposer is a supervised regressor trained offline on synthetic tasks and frozen before use; it ranks candidates by predicted aggregate margin and never observes the protected-trigger success rate, so the masked-core failure arises from optimising the aggregate rather than from an adversary constructed by hand. --- ### When Does the Concept of "Dog" Emerge in an Audio LLM? Authors: Zhe Wang, Shiqi Liu, Ruiyun Zhong, Tiechong Zhu, Yihua Tan Published: 2026-09-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.33458v1 Multimodal large language models answer audio questions, but how they represent auditory semantics and use them in decisions remains unclear, limiting our understanding of response formation. We study dog barking in Qwen2.5-Omni-7B using Jacobian lens (J-lens) readout and directional interventions. We define the dog direction as a J-lens-derived hidden-state vector associated with dog; adding or removing its component modulates dog-related information. We find this information decodable without dog/bark prompt cues or animal-identification requirements. Directional interventions change response tendencies and some final answers, with effects concentrated in late-layer states immediately before generation across species classification, vocalization classification, and sound description. The dog direction shows no comparable advantage over controls in animal/other classification. These results provide causal-intervention evidence that the dog direction affects output scores in a task-dependent manner, most consistently at L22 and L24 immediately before generation. --- ### A Free Knob: Decoupling Calibration and Predictive Skill in Threshold-Based Evaluation Authors: Md Tanveer Hossain Munim, Bijoy Ahmed Saiem, Al-Amin Sany, Tanzima Hashem Published: 2026-09-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.33457v1 Many dense-prediction benchmarks evaluate rare events by pooling prediction and target over spatial blocks, thresholding each, and scoring the contingency table. At a fixed rare operating point, the max-pooled Critical Success Index (CSI) confounds spatial discrimination with amplitude calibration: sharp observations promote many blocks above threshold, while attenuated predictions from squared-error regression leave the same blocks below it. We repurpose classical monotone calibration as a symmetric audit: a post-hoc transform fitted on held-out data and applied separately to each system. The transform cannot reverse pixel ordering, so any contrast it reproduces cannot establish improved spatial ranking. On SEVIR, two released checkpoints of one architecture differ by -29.5% in extreme-threshold CSI before the control and by +5.3% after it. Across 450 pairwise contrasts among 6 systems, the difference in pooled frequency-bias deviation is associated with how far the CSI contrast moves under the control (r = +0.796), and 51 contrasts reverse sign. At CasCast's published extreme-event operating point, the cascade-over-backbone CSI gap falls from 0.1601 to 0.0339, a 78.8% reduction; the remaining gap stays positive. The effect persists when the transform is fitted on a window before the test period, and calibration also reveals advantages hidden by a better-calibrated baseline. On geostationary infrared imagery the relative gain grows as events become rarer, crowd counting reproduces the bias-gain relationship under patch-sum pooling, and semantic segmentation, where frequency bias is already near one, shows little average change. The confound therefore requires both a fixed operating point and a training regime that leaves the output miscalibrated there. We recommend reporting pooled frequency bias and a symmetric held-out FreeKnob Audit alongside rare-event pool-and-threshold scores. --- ### Sharp training-conditional coverage for conformal prediction under covariate shift Authors: Mehrdad Pournaderi Published: 2026-09-27 Categories: stat.ML, cs.LG, math.ST, stat.ME arXiv: https://arxiv.org/abs/2609.33456v1 Weighted split conformal prediction reweights calibration scores by the likelihood ratio between the test and training covariate distributions and guarantees marginal coverage under covariate shift. We study its coverage conditional on the calibration data. An elementary argument, based on a single concentration inequality at a fixed population quantile, gives explicit training-conditional bounds without unspecified constants, and shows that the relevant scale is not the supremum of the likelihood ratio but a variance proxy built from the chi-squared divergence of the shift and from the average of the ratio over the part of the test population, of probability equal to the miscoverage level, where it is largest. A two-point lower bound shows that the root-m rate and the chi-squared contribution are intrinsic to the shift. Run at an explicitly inflated level, the weighted quantile becomes a deterministic PAC prediction set. We compare it with randomized rejection sampling and with importance-weighted learn-then-test and, through a certified choice of a clipping level for the likelihood ratio, map the regime in which each gives the narrower valid set. The analysis extends to estimated likelihood ratios and to tail functionals estimated from an unlabeled source sample, which yields a fully finite-sample certificate. --- ### What Shared Prefixes Hide: Trajectory Dropout for On-Policy Distillation Authors: Zizhuo Lin, Quanling Liu, Yi Yang, Yawei Luo Published: 2026-09-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.33455v2 On-policy distillation (OPD) trains a student model on its own trajectories using dense token-level feedback from a stronger teacher model. Since each update is conditioned on the reasoning prefix already generated by the student, the prefix also shapes how effectively teacher feedback is converted into learning. We find that shared prefixes can lead to weak token-level updates, a phenomenon we call Prefix-Induced Supervision Attenuation (PISA). This attenuation arises in two common cases. (i) High student confidence can weaken corrective gradients even when the teacher disagrees. (ii) Tokens that rely on earlier reasoning can receive learning signals as weak as those for simple local continuations. To solve this problem, we propose Trajectory Dropout, a simple training-time intervention that exposes these weakened signals. The student first performs a standard full-context rollout to generate a complete trajectory. During training, we randomly drop a certain proportion of the student's reasoning trajectory, while the teacher continues to observe the complete trajectory for token-level supervision. This intervention strengthens corrections for overconfident predictions and introduces additional supervision at prefix-sensitive positions. Trajectory Dropout consistently improves average performance across teacher--student model pairs of different scales and six mathematical reasoning benchmarks, while also yielding gains on two out-of-domain benchmarks. It can also be flexibly integrated into existing OPD variants with negligible computational overhead, further improving their performance. These results demonstrate that Trajectory Dropout provides a simple mechanism for strengthening token-level supervision across model scales and OPD objectives. --- ### Native Association: Confidence-Aware Human Perception in the Wild with a Foundation VLM Authors: Igal Dmitriev, Ofir Liba Published: 2026-09-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.33450v1 Extracting who is where, on which team, wearing which number from a broadcast frame is typically done by stitching a detector, an OCR engine, and classifiers together -- and the stitching step swaps identities under occlusion. We make association native instead: a 0.77B vision-language model (Florence-2) is fine-tuned to emit all per-person attributes as one grammar-constrained sequence, with each attribute generated inside its owner's block. Output is therefore schema-valid on every frame by construction, and no post-hoc binding step exists to attach a correctly read number to the wrong player: residual misassociation is pure perception error, $\approx4\times$ rarer than zero-shot-prompted frontier APIs' (0.057 vs. 0.21-0.24). On a frozen multi-sport test set, this single pass reaches 0.95 detection F1 (APIs: 0.65-0.75). A single extra forward pass yields a per-field confidence that supports a reject option (jersey precision $0.71\rightarrow0.96$ at half coverage) and routes a training-free zoom-and-re-read for small players. Surprisingly, once the grammar is learned, further parameter-efficient tuning yields no measurable gain under the adaptation configurations we test; the identical recipe on WIDER-Attribute reaches 93.1 mAP given-box, yields the first detection-coupled end-to-end results under its standard test protocol (84.5 mAP), and reproduces the same tuning result. In this regime, the gains live in the structure, not in added weights. --- ### A Visual Classification Dataset and Model Evaluation for Historical Manuscript Illustrations Authors: Yoav Evron, Michal Bar-Asher Siegal, Michael Fire Published: 2026-09-27 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.33449v1 Historical manuscript illustrations preserve rich visual evidence of past cultures. They depict people, animals, plants, diagrams, music notations, and decorative forms. Although large digitization projects have made many manuscripts available online, the material itself remains difficult to explore at scale. Extraction systems can find illustrations on manuscript pages, but without meaningful categories, large collections remain hard to search and explore. We address this gap by introducing a manually labeled dataset of 15,000 illustrations from manuscripts dating back hundreds of years across 22 categories, and evaluating modern vision models for image classification on this task. The problem is challenging due to stylistic diversity, degradation, and semantic ambiguity, with many images that fit more than one category. We compare fine-tuned CNN and Transformer-based classifiers, zero-shot CLIP, embedding-based classifiers, and direct vision-language models. Results show that fine-tuned image classifiers perform best overall, with ConvNeXt reaching 88.9% accuracy and 81.3% macro-F1. Using CLIP embeddings with XGBoost provides a strong alternative. In contrast, zero-shot CLIP and direct vision-language classification perform substantially worse, highlighting the limits of general-purpose models in this domain. Beyond overall performance, the analysis reveals which categories are visually separable and where errors reflect genuine semantic overlap, suggesting that some limitations arise from the taxonomy itself. --- ### From PDF to Evidence: Structure-Aware Retrieval for Clinical Practice Guidelines Authors: Xingyu Lin, Dehui Du Published: 2026-09-27 Categories: cs.IR, cs.CV arXiv: https://arxiv.org/abs/2609.33447v1 Guideline documents are published as unstructured PDFs whose evidence is locked in visual structures---tables, flowcharts, and graded recommendations---that standard retrieval pipelines flatten into fixed-size text chunks. We cast evidence access as a document image analysis problem: parse each page image into typed structural elements, then retrieve structure-aware evidence units that follow the document's own layout (sections, table rows, flowchart paths, graded recommendations), each keeping its structural context so a result points to a specific element rather than a page. On 26 clinical practice guidelines from 9 sources (3,619 pages, Chinese and English) with 199 evidence queries, structure-aware units rank the gold element first under BM25, dense, and hybrid retrieval (hybrid Element Hit@1 of 0.382), with a significant element-level ranking gain over per-element OCR text (MRR_e +0.107, p=0.002; the Hit@5 gain is directional, p=0.17), while matching page-level recall (Page Hit@5 0.879 vs. 0.889, p=0.75) at 3.8x less context and clearly outperforming a ColPali visual-RAG baseline (PH@5 0.497). --- ### HESP: Separating What to Probe from When to Stop in Local LLM Alert-Triage Agents Authors: Zhuowen Liu, Zhixuan Wang Published: 2026-09-27 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.33446v1 Security operations centers receive far more alerts than analysts can investigate, and organizations that cannot send their telemetry to hosted models must automate triage with small open-weight LLMs on their own hardware. Current LLM agents leave the investigation procedure to the model, and small local models fail at it: they probe without converging, never commit to a verdict, or dismiss real attacks. In this paper, we present HESP, a controller that holds the investigation procedure outside the model. HESP keeps a ledger of competing explanations, selects read-only probes by expected information gain per cost, accepts only verdicts backed by current evidence, can end an investigation itself, and journals every prediction before its observation. We evaluated HESP in four pre-registered studies with five open-weight models from two families (7B to 72B), totalling 7,272 audited episodes in a controlled triage environment. With likelihood tables counted from LLM-free runs, HESP lifts Qwen2.5-7B from 0.125 to 1.000 verified completion, matching oracle tables. The information-gain ranking adds +0.26 to +0.35 on every model that concludes, and a controller-side stop lifts Llama-3.1-8B, which never concludes on its own, from 0 to 0.917. What to probe and when to stop are therefore separate failures, and different small models exhibit different ones. Because HESP and its planner run entirely on local hardware, it suits environments where telemetry cannot leave the premises. We release all code, protocols, and episode journals at https://github.com/lzwhehe/HESP. --- ### Concept Score Relearning: A Unified Cross-Architecture Attack on Concept Erasure Authors: Hong Xi Tae, Jiaming Zhang, Wenwen He, Xuan Wang, Wei Yang Bryan Lim Published: 2026-09-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.33445v1 Concept erasure aims to suppress undesirable knowledge in text-to-image generative models. However, existing robustness evaluations typically rely on relearning attacks tailored to specific model architectures. We study concept reactivation across two substantially different generative paradigms: noise-prediction U-Nets and flow-matching Transformers. We introduce \textbf{Concept Score Relearning (CSR)}, a unified parameter-level framework that reactivates erased concepts by optimizing each model within its native prediction space. CSR requires no external target-concept image dataset and applies the same concept-directed objective to both U-Net-based Stable Diffusion and Transformer-based FLUX. Experiments across diverse concepts and multiple erasure methods demonstrate consistent concept reactivation across both architectures, highlighting the cross-architecture applicability of CSR and the persistent recoverability of apparently erased concepts. For strict nudity, CSR reaches average ASRs of 50.47\% on FLUX and 40.29\% on Stable Diffusion, consistently ranking first across all evaluated safety settings. --- ### Elucidating the Design Space of Regression-based Diffusion Reinforcement Learning Authors: Toyota Li, David Zhao, Alan Zhao Published: 2026-09-27 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2609.33444v1 A nascent family of methods that forgoes the policy gradient and reweights a supervised regression instead has garnered momentum in reinforcement learning for diffusion and flow models. DiffusionNFT, FlowAWR, and RAM are representative regimes with contrasting motivations. It is yet opaque what, if anything, they share. We substantiate that each is the solution of one divergence-constrained reward-maximization problem, and they are differentiated only by the convex generator that defines the constraint. Under the unified modeling framework, we unravel the relaxations that prior art made during building the advantage-embedded regression target: approximating the KKT condition and posterior normalizer for the linear and exponential tilt shapes DiffusionNFT and FlowAWR respectively, while preserving the exact sparsemax projection onto the probability simplex for linear tilt leads to another superior model type in this work. Beyond the theoretical underpinnings, we further empirically investigate the design space and shed light on the training recipe for regression-style diffusion RL. Retaining the merits discovered during our exploration gives rise to DiffusionRFT, our paradigm that converges faster, trains more stably, and attains the top performance. --- ### Context Spanning: A Communication Framework for Full-Duplex Speech Models and External LLM Backends Authors: Seonghyeon Go, Yongwoo Kim, Hyeonjin Cha, Jaeho Shin Published: 2026-09-27 Categories: cs.CL, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2609.33443v1 Full-duplex spoken dialogue models can listen and speak simultaneously like the real-time dynamics of human conversation. For natural dialogue, the ability to search for external information in real-time is also an important capability. Many models remain trapped in parametric knowledge, leaving them unable to access real-time information and tool execution. Furthermore, even when Large Language Models (LLM) retrieve information, many duplex speech models process it within a compressed latent space rather than in its raw text form, which can lead to information loss from compression. To address this issue, we propose Context Spanning, a framework for information injection between a full-duplex speech model and an external LLM backend via real-time chunked prefill. The injected frame is encoded in a single forward pass inside the real-time frame budget. It feeds the retrieved information to the speech model as-is, enabling it to reason over the information independently and generate responses. With this approach, our model achieves high performance on Full-Duplex benchmarks and strong results on Question Answering tasks, demonstrating its conversation potential. Context Spanning shows that external information can be injected directly into a duplex speech model, introducing a new simple and powerful mechanism for duplex systems. --- ### MIC: Explaining Image-Claim Inconsistencies in AI-Generated Multimodal Misinformation Authors: Ruihong Zeng, Jonathan Tonglet, Preslav Nakov, Iryna Gurevych Published: 2026-09-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.33441v1 Claims paired with AI-generated images are a rapidly growing form of misinformation. Existing automated fact-checking (AFC) methods mainly treat this as a provenance problem, detecting low-level synthesis artifacts to decide whether an image is AI-generated. However, such methods do not verify what human fact-checkers often check: whether an image's content is consistent with the context implied by its accompanying claim. To address this gap, we introduce MIC (Multimodal Inconsistency Checking), an AFC framework that assists human fact-checkers by detecting AI-generated multimodal misinformation and explaining inconsistencies using world knowledge. MIC first uses supervised fine-tuning (SFT) for task adaptation and then applies Group Relative Policy Optimization (GRPO) to directly optimize component-level verifiable rewards for verdict prediction, inconsistency type classification, visual evidence description, and world-knowledge explanation. We further introduce MIC-Bench, a benchmark comprising 8,812 image-claim instances derived from 4,406 claims, where each claim is paired with an authentic image and an AI-generated counterpart that introduces a controlled contextual inconsistency. Compared with SFT alone, GRPO further improves Macro-F1 by 4.67 and 4.11 points in the in-distribution and out-of-distribution settings, respectively, while also improving the semantic similarity of visual evidence descriptions and world-knowledge explanations to reference annotations. Our code and data are available at https://github.com/UKPLab/arxiv2026-mic. --- ### MAC-Net: A Multi-Task Deep Learning Framework for Modeling Cognitive Function From Task-Based fMRI Authors: Md. Tanvir Rahman, Nabil Anan Orka, Asaduzzaman Khan, Mohammad Ali Moni Published: 2026-09-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.33440v1 Objective cognitive assessment from neural signals supports neurorehabilitation, but individual-level prediction from task-based fMRI (tfMRI) remains difficult because neural features coexist with substantial demographic and scanner-related variation. We present the Multi-task Activation and Contrast Network (MAC-Net), a covariate-aware deep learning framework for modeling individual cognitive function from regional tfMRI. By isolating tfMRI features into a dedicated neural pathway and restricting participant variables to a terminal late-fusion pathway, MAC-Net prevents dominant covariates from suppressing high-dimensional clinical representations during feature learning. Evaluating baseline data from 6,500 Adolescent Brain Cognitive Development Study participants under family-aware cross-validation, MAC-Net was benchmarked against linear models, random forests, and alternative deep architectures. The N-back plus Monetary Incentive Delay configuration achieved $R^{2}$ values of 0.174, 0.238, and 0.277 for fluid, crystallized, and total cognition, outperforming covariate-only baselines (0.178) and alternative deep models (0.217). N-back was the most informative paradigm, whereas incorporating the Stop Signal Task marginally degraded performance. Feature attributions via Integrated Gradients, DeepLIFT, and Input Gradient were highly concordant, localizing working-memory-related frontal, parietal, and cingulate regions. These findings demonstrate that covariate-aware multi-task modeling yields reproducible cognitive-function estimations, establishing a robust neural engineering framework for clinical translation. --- ### Raven: The Harness of Harnesses for Composable Agentic Intelligence Authors: EverMind AI Published: 2026-09-27 Categories: cs.AI, cs.CL, cs.GT, cs.MA, cs.NE arXiv: https://arxiv.org/abs/2609.33439v1 As large language models advance, AI agents are moving beyond isolated, domain-specific tasks toward long-horizon, cross-domain workflows. This transition exposes two challenges: increasing harness complexity makes manual design difficult to scale, while tighter coupling to specific domains limits the generality of a single harness. The central question thus shifts from how to engineer a stronger harness for one domain to how to autonomously construct specialized harnesses, improve them through experience, and orchestrate them across domains. We introduce Raven, \emph{The Harness of Harnesses}, an open-source multi-agent ecosystem that automatically constructs and evolves modular harnesses for specific models and domains, treating each executable model--harness pair as a composable unit of intelligence. To support an \emph{All-Domain Collaboration Network}, its Host Agent decomposes goals, matches subtasks to specialized agents, coordinates execution dependencies, and integrates results, while a host archive and EverOS preserve experience across tasks and Skill Forge makes that experience available as reusable procedures. Our theory establishes sufficient conditions for such composition to expand reliable task coverage beyond that of the available individual agents under a shared resource budget. On complex and long-horizon tasks, Raven significantly outperforms the state-of-the-art agent systems, pushing the frontier of composable agentic intelligence. --- ### SMAT: Simple and Efficient Merge-Aware Training Authors: Yanggan Gu, Yuanyi Wang, Zhen Li, Shuo Cai, Yuhang Liu, Junzhuo Li, Zihao Wang, Hongxia Yang Published: 2026-09-27 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.33437v1 Model merging integrates the capabilities of multiple experts without joint retraining, but standard expert training optimizes task loss alone and does not guarantee good performance after merging. Merge-aware training (MAT) aims to improve merged performance, but existing methods do not fully account for common merging operations and add training cost. We observe that, from an expert's perspective, common merging methods can be described by three operations: Scale reweights its own update, Mask removes selected coordinates, and Perturb adds updates from other experts. Based on this view, we introduce SMAT (Simple MAT), which jointly optimizes expert loss and expected loss at simulated merged parameters generated by sampling scaling coefficients, masks, and additive noise. We further introduce periodic scheduling, kernel fusion, and parameter storage switching to make SMAT efficient, with one forward and one backward pass per step. Across four language and vision-language backbones, SMAT improves the mean score across five merging methods by 1.07-2.16 points over the strongest baseline for each backbone, with less than 2% training-time overhead over standard fine-tuning. --- ### SchemaMem: Schema-Indexed Recurrent Memory for Delayed State Retrieval Authors: Sungwoo Goo, Hwi-yeol Yun, Sangkeun Jung Published: 2026-09-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.33436v1 Attention provides direct access to past representations, but retaining an ever-growing history is costly. Recurrent models bound persistent state, yet must preserve selected information while processing subsequent inputs. We introduce SchemaMem, an attention-based recurrent memory architecture combining chunk-local attention with a persistent, schema-indexed phase state. Learned schema embeddings provide a shared representational reference for reading and writing. Reads use the current state, whereas writes use the layer input and static schema embeddings, excluding direct feedback from that layer's own state. Chunk-boundary commits aggregate bounded phase increments through forward computation. The same parameters also support full-history attention training before and during recurrent training. We studied selective updates, preservation, and delayed retrieval in a controlled address--value task, comparing three-layer models with approximately matched parameter counts and persistent-state dimensions. Across nine address/value settings and three training seeds, SchemaMem has higher mean written-value retention at four times the maximum training delay than both baselines, which are trained toward a higher in-range accuracy target. Updated-value recovery favors SchemaMem in all nine settings against Mamba-3 and seven against Gated DeltaNet. Defaults consistently favor Gated DeltaNet over SchemaMem at that delay, and SchemaMem requires substantially more optimization steps. These results identify a promising retention--optimization trade-off in schema-indexed recurrence. --- ### CORA: A Protocol for Diagnosing Boundary Robustness in Text-to-Audio Retrieval under Query Reformulations Authors: Jae Min Woo, Kyongmin Kong, Bogyung Jeong, Minjeong Kim, HaeJun Yoo, Du-Seong Chang Published: 2026-09-27 Categories: cs.SD, cs.CL, eess.AS arXiv: https://arxiv.org/abs/2609.33433v1 Text-to-Audio (T2A) retrievers are typically evaluated with caption style queries, but the same user intent can be expressed in many forms. We introduce CORA (Caption-Offset Retrieval for Audio), a caption anchored diagnostic protocol that rewrites each source caption into five intent preserving forms (Command, Question, Indirect, Key phrase, and Statement) while fixing the target audio. By tracking the same target across query forms, CORA defines RankDrop, a metric revealing failures hidden by Recall@k. Using Pearson's correlation coefficient r, we find that RankDrop is weakly associated with raw text space movement (r=0.084), but strongly associated with Target Alignment Loss and Target Boundary Margin Degradation (r=0.508 and r=0.615). The same pattern appears in OEA retrievers, where RankDrop is better explained by boundary degradation (r=0.472/0.478) than by query movement (r=0.084/0.046). Overall, these results suggest that robust T2A retrieval requires preserving the target's boundary advantage over competing audio under reformulation. --- ### TC-ADA: One-Shot Active Domain Adaptation for Semantic Segmentation Authors: Weihao Yan, Yeqiang Qian, Yueyuan Li, Tao Li, Chunxiang Wang, Ming Yang Published: 2026-09-27 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2609.33432v1 Manual dense annotation remains a major obstacle to deploying semantic segmentation models in new driving environments. Active domain adaptation (ADA) seeks label-efficient transfer by annotating only a selected portion of the target domain. Existing ADA methods commonly implement this process through multiple rounds of acquisition, annotation, and retraining. We study a practical one-shot image-level setting that selects and densely annotates a fixed target subset in a single round, followed by uninterrupted adaptation. Within this setting, we develop Target-Calibrated Active Domain Adaptation (TC-ADA) as a joint design of complete-image acquisition and target-calibrated adaptation. Stage~1 uses visual representations from a vision foundation model (VFM) together with semantic predictions from a fixed unsupervised domain adaptation model to select representative and informative target images without target annotations. Stage~2 jointly uses labeled source data, labeled target data, and the remaining unlabeled target data, while calibrating source and target supervision under limited target labels. Extensive experiments across five synthetic-to-real and real-to-real driving transfers show consistent improvements over representative ADA baselines. With only 23 to 46 labeled target images on four transfers and 140 on Mapillary, TC-ADA stays within 1.9 mean intersection over union (mIoU) points of target-only full supervision. Code will be available at https://github.com/ywher/TC-ADA. --- ### MoGround: Measuring and Mitigating Modality Distraction in Vision-Language Models Authors: Luca Zhou, Bo Zhao, Rose Yu, Emanuele Rodolà, Roberto Dessì Published: 2026-09-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.33431v1 We release MoGround, a vision-language dataset spanning four visual domains in which the answer to every question is guaranteed to be available from exactly one modality. This guarantee enables us to measure modality distraction, the failure in which a model answers a question correctly from one modality alone and then flips to a wrong answer once irrelevant content from the other modality is added. Existing probes rarely establish single-modality answerability this way, making it hard to isolate distraction in the first place. Across seven open-source VLMs, we find that modality distraction is not universal but model-dependent. The weaker-grounded modality is the more distracted one (r = +0.86), and distraction scales inversely with grounding strength (r = -0.90). The single-modality guarantee also enables a mitigation method that needs to distinguish between relevant and irrelevant context. Trained on one split of MoGround alone, a weight-space robustness vector reduces distraction on all seven models by 9% to 51%, at a cost of only 0.1 average points of accuracy on standard multimodal tasks. --- ### APEX: An Extensible Model for Agent-Assisted Production Scheduling Authors: Felix J. Grumbach, Stefan Görlitz Published: 2026-09-27 Categories: cs.AI, cs.NE arXiv: https://arxiv.org/abs/2609.33430v1 Production scheduling requires realistic models that reflect operational constraints and efficient methods that balance competing goals. Putting these methods into use also requires data integration, model adaptation and specialist expertise. We present APEX, an extensible production scheduling framework built around a general model and hybrid multiobjective search. Agent assistance supports both scheduling and model refinement: agents prepare data and explore scenarios in natural language, while coding agents help implement and test new constraints and objectives. Shared construction and checking procedures connect these adaptations to the scheduling core. We benchmark eight APEX configurations against NSGA-II, SPEA2, MOEA/D and SMS-EMOA on 69 public job-shop, flexible job-shop and permutation flow-shop instances, assessing workload completion time (makespan), total job flowtime and computation time. Hybrid configurations achieve the best aggregate solution quality, although the leading method depends on the problem class and objective. A separate synthetic workflow study uses OpenAI's GPT-6-astra as an interaction layer between the human planner and the algorithmic core, testing rule additions, plan and objective changes, and what-if comparisons. All 24 sessions completed the requested changes and passed independent checks of saved models and schedules. A separate coding evaluation produced six native implementations of an additional objective or hard constraint through predefined extension hooks. All passed independent checks without modifying the core. --- ### Graph-Guided Repository Environment Construction Authors: Jianying Pan, John Zhang, Hongyu Zhang Published: 2026-09-27 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2609.33429v1 Coding agents now increasingly rely on execution to validate their solutions, making the construction of reliable execution environments a critical enabling capability. However, repository environment construction is challenging because execution requirements are fragmented across repository artifacts and may only become apparent during execution. Existing agent-based approaches address this problem through iterative interaction, but information about the current construction state, including discovered requirements, satisfied and unresolved prerequisites, and their dependencies, can remain distributed across the interaction history. We present Graph2Env, an agent-based approach centered on DepGraph, a typed dependency graph that explicitly represents the environment requirements needed for repository execution, their dependency relations, and their states. Graph2Env uses DepGraph to guide environment construction and continuously refines it with execution feedback, while persisting successful repairs into a replayable construction procedure. The resulting artifacts are then applied in a fresh environment to verify that the constructed environment can be reproduced. We evaluate Graph2Env on a benchmark of 200 Python repositories drawn from RATBench and EnvBench, against a static dependency-inference baseline (pipreqs), three specialized environment-construction systems (Repo2Run, RAT, and SetupX), and two general-purpose coding agents (SWE-agent and Claude Code). Graph2Env achieves an 81.0% Environment Build Success Rate (EBSR) and a 59.3% Environment Setup Success Rate (ESSR), outperforming the strongest baseline by 9.5 and 9.0 percentage points, respectively. --- ### Temporal Graph Learning of Wearable Actigraphy and Sleep Traces for Modelling Adolescent Crystallized Intelligence Authors: Md. Tanvir Rahman, Nabil Anan Orka, Asaduzzaman Khan, Mohammad Ali Moni Published: 2026-09-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.33428v1 Wearable actigraphy offers a scalable, ecologically valid alternative to episodic clinical assessment. However, predicting continuous adolescent crystallized intelligence ($G_c$) from such traces remains challenging due to irregular device adherence and complex behavioral-environmental interactions. We address this using daily summary data derived from 21-day Fitbit records of 6,091 adolescents in the Adolescent Brain Cognitive Development Study (Release 5.1). We propose SATURN, a Sleep-Activity Temporal Unified Regression Network. It represents participants as 21-node temporal graphs encoding daily behaviors and temporal adjacency. To prevent imputation artifacts, invalid-day edges are dynamically pruned during forward passes. Node embeddings are refined via residual GATv2 layers, aggregated through masked attention pooling, and fused with sociodemographic covariates. Under family-controlled, age-sex-BMI-stratified cross-validation, SATURN achieves $R^2 = 0.2783 \pm 0.0127$, consistently improving upon flattened machine learning (Gradient Boosting, $R^2 = 0.2372$) and sequential deep learning (BiLSTM, $R^2 = 0.2688$) baselines. Explainability analyses identify light activity, metabolic equivalents, and sleep duration as dominant predictors, while Monte Carlo dropout and subgroup analyses confirm equitable performance across sociodemographic strata. Ultimately, SATURN establishes a rigorous computational framework for digital cognitive phenotyping, offering a scalable pathway to complement traditional assessments by highlighting macro-level behavioral anomalies. --- ### TeacherGRPO: Closing the Capacity Gap in Reasoning Distillation via Teacher Alignment Authors: Zhenyu Lei, Zihan Chen, Yaochen Zhu, Shangbin Feng, Zaiyi Zheng, Ruocheng Guo, Yushun Dong, Jundong Li Published: 2026-09-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.33426v1 Reasoning distillation from powerful teacher models to smaller students faces the Gap Curse: as teachers grow more sophisticated, their complex distributions increasingly diverge from what students can approximate, causing performance degradation. Existing mitigation strategies either filter out challenging examples through data selection or introduce weaker intermediate assistant models, inherently compromising supervision coverage or quality. We propose Teacher Alignment, which directly adapts the teacher toward the student's distribution without discarding data or degrading reasoning quality. However, naive alignment through standard knowledge distillation triggers catastrophic collapse of the teacher's reasoning capabilities. To address this, we reformulate teacher alignment as reinforcement learning and introduce TeacherGRPO, built on Group Relative Policy Optimization with two key innovations: (i) Curriculum Selective Alignment applies dual token- and distribution-level curricula to focus rewards on high-signal reasoning gaps while filtering noise from trivial tokens and uncertain tail distributions, and (ii) Importance-Adaptive Length Regularization selectively penalizes verbose redundancy while preserving pedagogically critical reasoning steps. The aligned teacher then distills knowledge to students via standard pipelines. Extensive experiments show TeacherGRPO significantly outperforms baselines across diverse reasoning benchmarks and distillation methods. Our code is available at https://github.com/LzyFischer/TeacherGRPO. --- ### A Light Bilevel Refinement Aligns Self-Supervised Representations for Stronger Task-Specific Learning Authors: Gustav Wagner Zakarias, Zheng-Hua Tan Published: 2026-09-27 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2609.33424v1 Self-supervised pretraining learns representations that are broadly transferable across downstream tasks, yet direct fine-tuning can be suboptimal due to misalignment between self-supervised and downstream task objectives, potentially degrading pretrained features beneficial to the downstream task. The BiSSL framework addressed this by introducing a transitional training stage formulated as a bilevel optimization problem, in which the downstream task objective guides the self-supervised learning process in refining pretrained representations to better facilitate subsequent fine-tuning. However, BiSSL relies on conventional bilevel optimization solving techniques whose costly implicit hypergradient approximations render the method increasingly impractical for contemporary model architectures. To make it efficient and scalable, we introduce BiSSLight, which combines M-FAC-based implicit gradient approximation with parameter-efficient fine-tuning via LoRA, enabling efficient application at larger scales that were previously impractical. Evaluation across multiple downstream tasks and contemporary model architectures shows that BiSSLight consistently improves downstream performance, with gains becoming more pronounced as model size increases despite stronger baselines. The method is highly computationally efficient, reducing computation time by more than a factor of ten compared to its predecessor on a ViT-H backbone. --- ### Explainable Deep Learning of Resting-State Functional Connectomes Reveals Network Biomarkers of Adolescent Intelligence Authors: Md. Tanvir Rahman, Nabil Anan Orka, Asaduzzaman Khan, Mohammad Ali Moni Published: 2026-09-27 Categories: q-bio.NC, cs.AI arXiv: https://arxiv.org/abs/2609.33422v1 Mapping resting-state brain organization to individual differences in cognitive ability remains a major challenge in population neuroinformatics. Although deep learning enables flexible modeling of brain connectivity, limited interpretability restricts its scientific and clinical utility. To address this objective, we developed an explainable deep learning framework based on sparse projected residual networks to predict fluid, crystallized, and total intelligence from resting-state functional magnetic resonance imaging in 5,285 participants from the Adolescent Brain Cognitive Development study. We incorporated three complementary explainability methods (Integrated Gradients, Gradient Shapley Additive Explanations, and Occlusion) to interpret model behavior. The framework outperformed existing approaches, achieving Pearson correlations of 0.44, 0.58, and 0.56 for fluid, crystallized, and total intelligence, respectively, corresponding to predictive improvements of 6 to 9 percent. All three explainability methods produced near-identical feature rankings (pairwise rank correlations greater than 0.99). Consensus maps revealed a dual-layered functional architecture where primary predictive hubs localized within canonical systems, while the strongest global predictive pathways frequently bypassed these hubs through distributed, long-range relay connections. These findings suggest that intelligence emerges from the interaction between localized computational hubs and distributed communication pathways. Ultimately, these normative network architectures provide clinical reference maps to detect individual deviations, supporting earlier diagnosis, cognitive subtype stratification, and treatment monitoring in atypical neurodevelopment. --- ### Recovering Lower-Dimensional Semialgebraic Support of a Measure from its Moments Authors: Ruben Karapetyan, Shenyuan Ma, Ales Wodecki, Jakub Marecek Published: 2026-09-27 Categories: math.ST, cs.LG, math.OC arXiv: https://arxiv.org/abs/2609.33420v1 Recovering probability measures from their moments has numerous applications, esp. in connection with the method of moments in statistics and optimization. In the setting where measure need not be finitely atomic, but its support is known to be compact and semialgebraic with codimension at least one, the problem is still open. We combine moment-matrix kernel information with the Christoffel--Darboux kernel to provide a discrete approximation of the support. To validate the proposed approach, we test our algorithm on analytically computed moments and pseudo-moments arising from polynomial optimization problems without unique global minimizers. This complements well-known recent work on recovery of measures with algebraic support, where the kernel of a moment matrix can reveal polynomials vanishing on the support, and on recovery of sufficiently regular full-dimensional supports, where estimators constructed by thresholding the Christoffel--Darboux kernel are known to converge asymptotically to the support. --- ### TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining Authors: Shih-Ying Yeh, Daniel Z. Kaplan, Xuehai Wang, Fu-En Yang, Min-Hung Chen, Shang-Hong Lai Published: 2026-09-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.33419v2 Comparisons in video self-supervised learning often evaluate complete training recipes rather than isolating the method itself: architecture, objective, data exposure, schedule, scale, and decoder capacity can all vary at once. This makes it hard to identify which choices yield motion-prioritized representations, whose gains concentrate on frame-to-frame change while retaining useful appearance. We address this with a matched $4 \times 6 = 24$ architecture-objective study at roughly 170M ~ 190M encoder scale on $\sim$1.7M OpenVid and Moments-in-Time v2 clips for 8 epochs, and propose TT-VidT. TT-VidT combines a DINOv3-initialized ViT-B/16 per-frame spatial path with a compact Temporal Transfer Layer, trained by Diff Compression to reconstruct target frames from a first-frame appearance anchor and frame-specific motion tokens. The sweep shows that TT3D with Diff Compression, not either component alone, enters the strongest motion-sensitive regime, and decoder ablations favor a compact video-pretrained decoder. In final comparison, TT-VidT leads Jester, Something-Something V2, ARID, and Diving48 fine-tuning simultaneously, improving over the strongest non-TT row by 54% ~ 121%, while using 48% fewer encoder FLOPs than DisMo and 55% fewer than VideoMAE or V-JEPA2. HMDB51, IARD, and EPIC-Kitchens bound the claim. --- ### Grounding Memory Summarization in Utility Intent Authors: Zhenyu Lei, Mingjia Shi, Xingbo Fu, Haoyu He, Qi R. Wang, Jundong Li Published: 2026-09-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.33417v1 Existing summarizers for memory systems are typically optimized for human-facing criteria such as faithfulness, which misaligns with their true objective: preserving the evidence needed to support future queries. We show that conditioning summarization on query-answer pairs substantially improves answer quality, and that this utility-aware behavior is transferable across queries. Motivated by these findings, we propose MemSuit, a self-distillation framework in which a teacher summarizer, conditioned on observed query-answer pairs, produces utility-aware memory entries that a student learns to reproduce from the raw conversation alone. To prevent collateral erasure where conditioning on a single query-answer pair discards evidence relevant to other plausible queries, the teacher decomposes each block into multiple self-contained entries that preserve distinct query-relevant facets as independently retrievable units. To align the retriever with the compact, fact-dense style of teacher entries, we further fine-tune the embedding model with a contrastive objective supervised by teacher entries. Across a diverse suite of conversational query types, MemSuit consistently outperforms state-of-the-art baselines, confirming the value of grounding memory in downstream utility. --- ### Investigating the Effect of k-NN Preprocessing on Developing Graph Neural Networks: A Fairness-Based Perspective Authors: Nikolaos Zafeiropoulos, Emmanouil Mavrikos, George E. Tsekouras Published: 2026-09-27 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.33416v1 In this paper, a methodology to design fair graph convolutional neural networks (GCNs) is developed and tested over several application data sets. The graphs that are used as inputs to the network are constructed by a k-nearest neighbor-based preprocessing procedure, while fairness issues are considered in terms of the equalized odds criterion. To effectively incorporate the above heterogenous information, the equalized odds criterion is directly embedded into the model's optimization objective through an additional fairness-driven loss functional term. The proposed methodology investigates how varying the neighborhood size in the k-NN algorithm during graph construction influences both the classification performance and the fairness of the resulting models. Extensive experimentation is conducted on three real-world tabular datasets with known biases, evaluating the interplay between graph structure and fairness enforcement. The results demonstrate that the choice of the value of the parameter k critically impacts the performance trends, either steadily improving or peaking at intermediate values depending on dataset characteristics, while the application of fairness constraints significantly mitigates disparities in false positive and false negative rates across groups defined by the protected variable at hand, without incurring major sacrifices in overall accuracy. This study highlights the importance of jointly optimizing the graph construction process and fairness objectives in GCN-based learning, providing a systematic approach toward building more equitable and effective graph-based models. --- ### TTRSD: Test-Time Reinforcement Learning with Self-Distillation for Vision-Language Models Authors: Shuning Wang, Zhiheng Wu, Xun Zhou, Chongyang Cui, Chen Jia, Bowen Liu, Chuanjie Li, Xiang Chen, Yi Yang, Yumeng Zhang, Wenjie Huang Published: 2026-09-27 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.33414v1 Test-time reinforcement learning enables vision-language models (VLMs) to adapt using unlabeled inputs. However, repeated sampling under fixed visual conditions can reinforce shared perceptual errors, while sequence-level rewards fail to isolate visual perception the foundational bottleneck that anchors multimodal reasoning risking the degradation of pre-trained reasoning capabilities. We propose TTRSD, a test-time reinforcement learning framework combining multi-view answer-level self-distillation with visual contrastive token selection. A shared policy aggregates teacher predictions across original, cropped, and downsampled views into an answer distribution. Student trajectories generated from the original image receive rewards based on the support for their final answers in this distribution. To allocate this feedback precisely toward perceptual bottlenecks, we compare the log-probabilities of the same sampled tokens under original and visually ablated inputs while holding their textual prefixes fixed, selecting visually sensitive positions for policy-gradient updates. TTRSD separates update direction, determined by group-relative advantages, from update position, determined by visual sensitivity, without requiring ground-truth labels, external verifiers, or a separate teacher. With only 20 unlabeled adaptation samples, TTRSD improves performance across seven benchmarks and three VLMs, raising InternVL3-2B's MMMU accuracy from 35.79% to 49.32%(+13.53%), demonstrating cross-dataset generalization while preserving inherent reasoning integrity. --- ### Resolving State-Representation Mismatch: State-Space Visual Reasoning for Open-Loop VLA Planning Authors: Junhao Xiao, Haoxiang Zhao, Menghao Fang, Jinkui Zhang, Jinghan Yu, Xinyu Huang, Zhiyu Wu, Kaiming Xu, Yi Chen, Youjun Bao, Zhiyuan Ma Published: 2026-09-27 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.33412v1 Despite rapid progress in vision-language-action (VLA) models, existing reasoning paradigms still face a fundamental \emph{state-representation mismatch} in open-loop planning. Given only an initial observation, models must internally simulate action-conditioned state transitions, whereas text-, pixel-, and latent-space reasoning can suffer from lossy spatial compression, error-accumulating visual generation, and bypass of intermediate latent tokens, respectively, undermining reliable long-horizon planning. We propose \textbf{State-Space Visual Reasoning} (SSVR), which decouples static visual context, language constraints, and a recurrent latent state. SSVR encodes the initial image and instruction once, then conditions each action prediction on the latent state and updates it with an action-conditioned GRU. Using Qwen2.5-VL as the backbone, SSVR achieves 99.5/99.6, 96.3/98.0, and 83.9/90.6 EM/PR on FrozenLake, Maze, and MiniBehavior, substantially outperforming prior methods. Extensive experiments support the effectiveness of recurrent state modeling for VLA open-loop planning across input transformations and transfer settings. By reusing static visual-textual context and updating a compact recurrent state, SSVR supports efficient multi-step inference, achieving up to $98.58\times$ faster Maze decoding rollouts than the evaluated baselines with the prefix cache prebuilt. --- ### MetaBench-Harness: Unlocking End-to-End Optimization of Benchmark Harnesses Authors: Xuanjun Chen, Hua-Hsuan Chen, Wei-Chung Lu, Yinghao Ma, Jyh-Shing Roger Jang, Hung-yi Lee Published: 2026-09-27 Categories: cs.AI, cs.CL, cs.SE arXiv: https://arxiv.org/abs/2609.33411v1 Rapid progress in Large Language Models (LLMs) is saturating static benchmarks faster than they can be designed. While existing automated evolution frameworks attempt to generate harder questions by perturbing individual tasks, they remain constrained by rigid, hard-coded generation rules. Moving beyond the evolution of isolated tasks, we propose to optimize the benchmark generation workflow itself end to end with MetaBench-Harness, a dual-loop search framework. Specifically, the inner loop utilizes a benchmark harness to generate a new benchmark in each round, while the outer meta-harness orchestration layer iteratively refines and searches over harness implementations based on historical evolution trajectories. By applying MetaBench-Harness to the competitive programming CodeContests and Olympiad mathematics AIME-2024 datasets, we demonstrate that the evolved benchmarks are challenging and discriminative for frontier models. Trajectory and quality analyses verify that MetaBench-Harness enables multi-dimensional evolution, steadily improving evolution reasonableness, benchmark competency, and evaluator robustness across successive rounds. Furthermore, case studies reveal its effective utilization of diverse difficulty levers to reframe problems and elevate required capabilities. Ultimately, this work provides a solution to the pressing challenge of benchmark saturation. --- ### FoldAttention: Declared-Reference Softmax for Fast Decode and Deterministic Backward Authors: Sriman Achanta Published: 2026-09-27 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2609.33410v1 Autoregressive decode repeatedly streams a growing KV cache, making attention a major cost at long context. Existing high-performance kernels use online softmax, which discovers a row's normalization reference as it scans keys. Earlier contributions therefore remain provisional and may require rescaling. We argue that the reference need not be discovered: softmax is invariant to a common shift, so the reference only has to keep the weights in range. We present FoldAttention, an additive formulation of softmax attention that fixes a finite reference $Z_i$ before scanning the KV cache. Each weight $2^{s_{ij}-Z_i}$ is then final when computed, so contributions add across disjoint key ranges and their quotient equals softmax attention in real arithmetic. We use this property to develop two techniques for Hopper decode: (1) final weights gate key and value reads before the bytes are fetched, and a per-call depth $T$ cuts keys below $2^{-T}$ while keeping their mass, and (2) additive partials compose split KV and shared-prefix cascades without rescaling. On H100 at $T=16$, FoldAttention decodes seven real-model generations 1.36-2.30$\times$ faster than the fastest BF16 baseline, and up to 3.09$\times$ faster across MHA and GQA shapes, at an error within 1.5% of the lowest BF16 error on six of the seven; reading every key, it is 1.14-1.30$\times$ faster at matched error. We validate on Qwen3-8B that a whole decode step is up to 1.46$\times$ faster while likelihood and long-context accuracy match those under BF16 kernels. The same principle makes the backward deterministic: CTAs round bounded partial gradients onto an integer grid declared before the reduction and add them in any order. FoldAttention thereby removes the determinism tax: its deterministic backward is up to 1.84$\times$ faster than deterministic FlashAttention-3/4 and 1.05$\times$ faster than the fastest nondeterministic kernel. --- ### Dense Is Not Enough: Hierarchical Supervision Allocation for Long-Horizon On-Policy Distillation Authors: Yuhao Sun, Binrui Wu, Zhuoer Xu, Ming Wen, Haoxiang Xu, Bin Chen, Yan Lin, Qianzijing Zhang Published: 2026-09-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.33409v1 On-policy distillation (OPD) transfers the capabilities of a large language model to a smaller student by providing teacher supervision on the student's own rollouts. In long-horizon agentic tasks, however, uniform token-level matching can allocate supervision poorly: a large local discrepancy need not improve future behavior, while consequential guidance may be beyond the current student's reach or fail to persist without privileged input. We formulate long-horizon OPD as hierarchical supervision allocation and argue that productive guidance lies at the intersection of future utility and current learnability. Crucially, this intersection evolves as the student learns. Based on this principle, we propose LENS-OPD, a coarse-to-fine framework that organizes supervision through Locate, Validate, and Refine. Locate adapts trajectory exposure to the student's evolving competence and proposes a candidate decision for intervention. Validate tests whether teacher guidance at that decision improves the same student's subsequent behavior. Refine internalizes the beneficial guided behavior into the deployable policy and concentrates token-level supervision on decisive teacher-student conflicts within the validated turn. These stages are nested: each finer allocation is conditioned on the coarser decision, rather than being optimized as an independent importance score. Experiments across multiple long-horizon agent benchmarks and student-teacher configurations show that LENS-OPD consistently improves task performance over vanilla OPD and strong curriculum- and selection-based baselines. Our results suggest that effective long-horizon distillation requires teaching at the right depth, the right decision, and the right token. --- ### StarBOA: Real-Time Mamba State-Space Unrolling for Sparse Radar Micro-Doppler in ISAC Networks Authors: Mustafa Bora Çelik, Ceren Çelik, Orhan Gazi Published: 2026-09-27 Categories: cs.LG, cs.IT, cs.NI arXiv: https://arxiv.org/abs/2609.33408v1 In Integrated Sensing and Communications (ISAC), radar sensing must operate under chirp subsampling with up to 90\% missing data. An attention-based baseline, limited to a 52~ms buffer, collapses toward maximum uniform entropy ($H=2.584$ bits) as sparsity increases, failing to capture long-range gait-cycle context. We propose StarBOA, which replaces attention with a causal Mamba state-space model that updates incrementally on a per-window basis without re-scanning past reconstructions. By maintaining a persistent state, StarBOA integrates over $100\times$ more temporal history at no additional per-step computational cost. StarBOA outperforms the baseline's published results across all sparsity levels, with SSIM gains increasing from $+0.0379$ at 50\% missing data to $+0.2472$ at 90\%. Each window is processed in 1.53~ms with zero lookahead, demonstrating efficient causal reconstruction under extreme chirp subsampling. --- ### Let CSP Be Your ANCHOR: Adaptive Crystal Search over Frozen Structure Priors Authors: Emma Lei Hovmand, Jonas Elsborg, Melih Kandemir, Arghya Bhowmik Published: 2026-09-27 Categories: cond-mat.mtrl-sci, cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2609.33407v1 De novo crystal generation (DNG) models decide where to search in composition space and how to generate structures with one set of weights. We argue that discovery is better served by separating the two. A crystal structure prediction (CSP) model is a physical prior that should be improved by likelihood training, while rewards, including novelty measured against the search's own history, should act on a search over compositions. We introduce ANCHOR, a GRPO composition policy trained with multi-objective rewards around a frozen CSP model, and continuous adaptive novelty (CAN), a graded novelty score against known structures and a growing discovery history. Using the frozen CSP model as a fixed ruler under one evaluator, we test where adaptation should act. Replacing DNG compositions with ANCHOR's policy on the same CSP backbone raises MSUN from 11.4% to 47.6% and SUN from 1.1% to 22.1% at 99.9% formula uniqueness. Fine-tuning DNG models directly on the same rewards instead moves their composition marginal without raising their on-hull fraction. We show that KL-regularized fine-tuning of a DNG model can only reweight chemistry the pretrained model already supports by a bounded factor, while unregularized DNG fine-tunes move toward known or less stable chemistry. Even a stability-only reward routed into ANCHOR's CSP backbone roughly halves SUN relative to the frozen backbone, whereas likelihood training on structures found during search can improve a CSP backbone. Under MatterGen's evaluation pipeline, ANCHOR raises state-of-the-art MSUN from 29.2% to 41.3%, transfers without retraining to two further CSP backbones, and reaches 47.1% after distillation into Crystalite-CSP. As with any model optimised against a potential, its on-hull rate depends on that potential. --- ### Decoupling Token Roles in Autoregressive Pretraining Authors: Suqin Yuan, Runqi Lin, Kevin Qinghong Lin, Junchi Yu, Lei Feng, Chris Russell, Tongliang Liu Published: 2026-09-27 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.33405v1 Autoregressive pretraining increasingly draws on heterogeneous data, making it important to understand how a model learns from an individual token. The next-token prediction objective naturally identifies a token's contribution with its own loss. However, each token is not only a prediction target but also context for what follows. Using controlled corruption, we decouple these two roles and find a reversal: making a noisy token easier to predict reduces its damage as a target but increases it as context. The same decoupling helps explain text generated by language models: generation selects each token by its fit to the prefix, while its role as context is never tested against an independently determined continuation, because that continuation is generated to fit it. At known corrupted positions, acting through the context can reduce damage that removing the token's own loss does not. Understanding and controlling what a model learns from a token therefore requires decoupling its roles. --- ### DataMagic: Authoring Data Videos through Declarative Multi-Agent Orchestration Authors: Yupeng Xie, Zhenyang Wang, Liangwei Wang, Jiayi Zhu, Zhouan Shen, Yuyu Luo Published: 2026-09-27 Categories: cs.HC, cs.AI, cs.DB, cs.MA arXiv: https://arxiv.org/abs/2609.33403v1 Data videos communicate data insights through dynamic charts, voice narration, and synchronized animations, and have become a widely adopted form of data storytelling. However, producing them requires expertise in data analysis, narrative design, and video editing. Static visualization tools lack narrative and animation capabilities; authoring tools rely on pre-prepared charts rather than raw data; and pixel-level models generate videos end-to-end but cannot guarantee data accuracy or provenance. End-to-end automatic generation faces two core challenges: how to uniformly represent charts, narration, and animations together with their temporal relationships, and how to efficiently search a vast design space for narrative-coherent compositions. We present DataMagic, which authors data videos from raw tabular data through declarative multi-agent orchestration. First, the declarative specification DVSpec unifies charts, narration, and animations with data-bound references and declarative synchronization, ensuring data provenance and automatic audio-visual alignment. Second, a "Generate-then-Orchestrate" multi-agent strategy generates candidate scenes in parallel and then optimizes narrative coherence through global orchestration. DVSpec provides a shared state for three complementary interaction modes, bridging full automation with fine-grained human control. Evaluations on 109 real-world samples show that even the most advanced LLM (e.g., GPT-5) achieves only 2.13/5 with execution success rates between 48.62% and 86.24%; DataMagic improves quality to 3.89 (+83%) with success rates above 95%, with the most significant gains in animation and narrative dimensions. A user study shows that, compared to a conversational LLM workflow, DataMagic improves creation efficiency (79.7% reduction in task time) and reduces perceived cognitive load. Project page: https://github.com/HKUSTDial/DataMagic. --- ### VaME: Exploring Variational Latent Reasoning for Multimodal Embeddings Authors: Peixi Wu, Mingzhou Jiang, Feipeng Ma, Biao Yang, Yunhao Zhou, Wei Yuan, Bosong Chai, Huizu Lin, Jie Chen, Zhangchi Hu, Fan Yang, Wenwu Ou et al. Published: 2026-09-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.33402v1 Universal multimodal retrieval requires compact embeddings that preserve task-relevant semantic information across diverse modalities. Prior works have incorporated latent reasoning into multimodal embedding learning to refine this information before embedding extraction. However, most existing approaches remain confined to deterministic latent paths, without exploring alternative trajectories to discover better embeddings. Thus, we propose VaME (Variational Multimodal Embeddings), a framework that models latent reasoning as a learnable distribution over trajectories. Specifically, we first introduce Variational Latent Reasoning (VLR) to enable autoregressive exploration in latent space, guided by answer reconstruction through a lightweight decoder. Meanwhile, we augment the original embedding-token readout with a latent-fused embedding to facilitate exploration during subsequent reinforcement learning. Finally, we optimize latent reasoning over stochastic variational trajectories through reinforcement learning, using Semantic Decoding Reward (SDR) to favor semantically meaningful trajectories with interpretable decoded outcomes. On the 78-task MMEB-V2 benchmark, spanning image, video, and visual-document retrieval, VaME outperforms most explicit CoT-based models and all latent-reasoning baselines. VaME also demonstrates robust performance on reasoning-intensive benchmarks such as MRMR, with substantial gains after reinforcement learning. Importantly, VaME achieves these gains with at least a 4.25x inference speedup over the deterministic latent autoregressive baselines. The code will be made publicly available. ---