# Research Papers — 2026-09 · bundle page 255 of 266 > Full-text markdown of papers #12701–12750 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/255 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/254.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/256.md) ### ToolGate: An Executable Acceptance Pipeline for Tool-Dependent Scientific Benchmark Construction Authors: Ke Zhang, Yankang Liu, Roya Zandi, Maziar Raissi Published: 2026-09-02 Categories: cs.AI, cs.MS, cs.SE arXiv: https://arxiv.org/abs/2609.02067v1 Scientific benchmarks are commonly built by domain experts who write tasks and cross-check one another's work, or who adapt existing material from textbooks, published papers, and online resources. These routes can produce strong evaluations, but they require substantial per-item labor. Language models can reduce this repeated work by proposing candidates quickly. The remaining problem is acceptance. We target scientific questions whose answers require computations with specialist software rather than unaided reasoning alone. A candidate is invalid if its script fails or returns a different answer, or trivial if a model answers it without the software. We present ToolGate, which treats every generated item as a proposal and keeps it only if three gates pass. First, an executable solution script must reproduce the proposed answer when run with the scientific software. Second, randomized no-tool screening rejects candidates that models can already solve from the prompt alone. Third, a tool-using agent must solve each survivor within a fixed time limit. We instantiate ToolGate in FEniCSx with 500 generation attempts. The local-verification gate retains 478 candidates. For final reporting, we rescreen this pool after generation: two randomized no-tool screens exclude 222 from the reported pool, and direct GPT-5.5 API calls at medium reasoning (the API default) exclude another 121. Of the remaining 135, a GPT-5.5 Codex CLI agent with access to FEniCSx solves 130; exact deduplication leaves 128 unique protocol survivors. ToolGate turns repeated answer checking and difficulty screening into an auditable process while leaving domain design and final review to experts. --- ### LaST-SR: Laplace-Inspired Steady-Transient Complex-Frequency Decomposition for Single Image Super-Resolution Authors: Linhao Li, Zhaojie Pan, Langkun Chen Published: 2026-09-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.02063v1 Single-image super-resolution (SISR) requires global context modeling for structurally consistent reconstruction. Fourier operators are increasingly adopted for global feature modeling. However, their periodic spectral bases constrain the representation of localized aperiodic variations, limiting the recovery of irregular structures and fine details. In dynamical systems, the Laplace neural operator extends Fourier modes to complex frequencies and decomposes the output signal into complementary steady-state and transient responses to jointly model periodic and aperiodic information. We derive, for the first time, an approximate steady-transient decomposition for two-dimensional feature maps, providing an analytical basis for the proposed complex-frequency decomposition. Accordingly, we propose LaST-SR, centered on a Complex-Frequency Decomposition module that couples a global full-spectrum Fourier branch for image-wide dependencies and long-range structural consistency with a window-conditioned local complex-frequency branch for localized, content-dependent aperiodic variations. To fuse the resulting features, we further design a Steady-Transient Collaborative Aggregation module for cross-branch interaction and joint aggregation. Experiments on five benchmarks show that LaST-SR achieves the best PSNR/SSIM among the compared methods for $\times2$ and $\times4$ SISR. Ablation studies further validate the effectiveness of the proposed architecture and its key modeling mechanisms. --- ### MineTRACE: An Evidence-Grounded Interactive Reasoning System for Mineral Prospectivity Authors: Yiran Zhang, Jinwen Liu, Daniel Su, Yisu Chen, Qiang Sun, Chris Gonzalez, Eun-Jung Holden, Marco Fiorentini, Wei Liu, Yihao Ding Published: 2026-09-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.02060v1 Mineral exploration requires integrating heterogeneous geochemical, geophysical, and geological evidence, yet existing prospectivity systems often provide only opaque scores or heatmaps. We present MineTRACE, a web-based system for evidence-grounded exploration of eight commodities: Cu, Au, Ni, W, Sn, Co, Ta, and Mn. Users can explore prospectivity maps, query locations or regions, inspect supporting evidence, and interact through natural language. A transparent expert tree, informed by geological knowledge and known deposits, combines multi-source evidence into interpretable prospectivity scores. For a new location, the conversational assistant retrieves the score and supporting evidence from the analysis pipeline and presents them in natural language. The scorer achieves spatial AUC values of up to 0.917 across different test scenarios, while end-to-end evaluation assesses query accuracy and response grounding. MineTRACE makes public geoscience data easier to access, interpret, and verify, supporting more efficient and transparent mineral exploration. --- ### DocHop: Benchmarking Out-of-domain Multi-hop Reasoning in Information-Dense Documents Authors: Zhuoran Yu, Le Thien Phuc Nguyen, Jaden Park, Xinyi Gu, Zexue He, Soochahn Lee, Rogerio Feris, Yong Jae Lee Published: 2026-09-02 Categories: cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.02059v1 Multimodal Large Language Models (MLLMs) have achieved strong performance on structured visual understanding tasks such as chart and document question answering. However, existing benchmarks typically evaluate these domains in isolation, leaving underexplored a key capability: whether models can use textual context to determine how chart evidence should be selected, interpreted, and aggregated. We introduce DocHop, a benchmark for integrated chart--context reasoning in document-style images. In DocHop, the document narrative specifies multi-step compositional constraints, while charts provide the corresponding data values. Questions are grounded on a semantic reference label defined in the narrative, requiring models to resolve target entities from context before aggregating evidence across multiple charts. To enable systematic evaluation, we construct DocHop via a stochastic logic-first generation pipeline with controllable reasoning depth and visual density, covering 2,074 examples across six task categories. Experiments on a wide range of proprietary and open-source MLLMs show a substantial gap to human performance: annotators achieve over 90% accuracy, while the best model reaches only 62.83%. Reasoning-enhanced models consistently show improved results, but performance degrades as reasoning complexity increases. Overall, DocHop provides a controlled testbed for challenging multi-hop document reasoning. --- ### Monitoring Web Agents Without Internal Signals: Observable Trajectories and Key-Step Supervision Authors: Sitong Pan, Yipeng Shen, Yilin Lu, Caiwen Ding, Lu Cheng, Qianwen Wang Published: 2026-09-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.02057v1 Reliable web-agent monitoring is difficult when model-internal uncertainty signals such as token logits are unavailable. In this work, we study prefix-level risk prediction for web agents using observable trajectory signals: given an evolving prefix, estimate whether the current execution remains on track or is tending toward failure. We derive two observable trajectory representations: Macro features summarize cross-step agent--environment behavior and feedback, while Micro features measure the consistency of intention, action, and anticipated state change through repeated black-box queries. Instead of inheriting the final result label, we label the first critical error that remains uncorrected in the observed continuation and is associated with final failure as a key-step boundary, preserving valid early prefixes of failed trajectories as on track. Across WebArena-Lite and Online Mind2Web web agent benchmarks with five open- and closed-source backbones, observable trajectory signals are competitive with internal-signal baselines. The resulting predictors also support early intervention under fixed false-cut budgets and transfer across held-out website categories. These findings show that observable trajectory signals support valuable risk prediction abilities. --- ### HyGRAIL: Cost-Aware and Evidence-Grounded Scientific Hypothesis Discovery over Knowledge Graphs Authors: Yihang Sun, Zhihan Zhu, Zhiyuan Jiang, Jingyi Ge, Zixuan Li, Jiaxuan You Published: 2026-09-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.02056v1 Scientific knowledge graphs organize entities and relations extracted from scientific literature, but they remain inherently incomplete. Missing typed links in such graphs can therefore represent plausible scientific hypotheses, such as unexplored associations between materials and applications. However, scientific hypothesis discovery is challenging because true discoveries are extremely sparse among typed candidate pairs: graph neural networks (GNNs) are efficient but unreliable for ambiguous cases, while large language models (LLMs) are knowledgeable but too costly to apply exhaustively and are not naturally grounded in graph structures. We propose HyGRAIL, a cost-aware and evidence-grounded framework that combines heterogeneous GNN triage with LLM-based hypothesis review. HyGRAIL first uses a GNN to score candidate hypotheses and identify a validation-calibrated ambiguous region, routing only graph-uncertain cases to LLM review. For each routed hypothesis, HyGRAIL retrieves node-level associations and multi-hop relational paths from the knowledge graph (KG), then converts this structured evidence into natural language through template-based or LLM-based naturalization. An LLM review agent finally judges each hard hypothesis using the naturalized evidence and validation-selected decision criteria. On MatKG, HyGRAIL achieves the best F1 score of 0.429, improving over the strongest prior baseline by 0.242 F1 points and over the GNN-only baseline by 0.322. Meanwhile, GNN triage reduces the LLM call rate by 54.36% on average. Ablation studies further show that retrieved graph evidence is crucial for reliable hypothesis verification and that compact, two-sided evidence is more effective than simply increasing retrieval quantity. --- ### Privacy Washing: Detecting Internal Contradictions in Privacy Policies Authors: Thomas Brackin Published: 2026-09-02 Categories: cs.CY, cs.CL arXiv: https://arxiv.org/abs/2609.02055v1 Privacy policies may contain internal contradictions in which commitments are undermined by practices documented elsewhere in the same policy. We operationalize this phenomenon, privacy washing, through a four-stage pipeline: statement extraction, compatibility filtering and natural language inference screening, multi-model judge verification, and thematic analysis, with contradictions confirmed by majority vote of a three-model LLM panel. Applied to two corpora of website privacy policies, 123 collected in 2026 (OPPT) and 115 collected in 2015 (OPP-115), the pipeline finds the same category patterns recurring across the 11-year gap, with third-party sharing contradictions the majority of confirmed cases in each primary run, consistent with structural factors in policy composition rather than necessarily intentional deception. At least one panel-confirmed contradiction appears in 12.2% of OPPT companies (15/123; 9.8% excluding legacy pairs) and 36.5% of OPP-115 companies (42/115). A stability re-run seven months later, with a fully separated configuration (new extraction models, judges from three Chinese providers absent from both corpora, matched filters, no judge-submission similarity threshold), reproduces the OPPT prevalence under the original protocol (13.0% vs. 12.2%), finds sub-threshold pairs confirm at rates of the same order as those above (raising prevalence to 20.3% and 40.9%), and shows the third-party majority is panel-sensitive while the recurrence of the same category pairs is not. Two caveats govern all figures: panel verdicts are not validated against human expert judgment, so precision is unknown and prevalence figures are lower bounds; and the two primary runs used different filter configurations, so their prevalence difference is not interpretable as a corpus or era effect (the matched re-run reduces the gap to roughly twofold but does not eliminate it). --- ### A Tri-Agent Framework for Evaluating and Aligning Question Clarification Capabilities of Large Language Models Authors: Yikai Zhao, Saurabh Pandey, Pradeep Kumar Misra Published: 2026-09-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.02054v1 Large Language Models (LLMs) are increasingly deployed in interactive systems where understanding user intent precisely is paramount. A key capability for such systems is effective question clarification, especially when user queries are ambiguous or underspecified. This paper introduces a novel tri-agent framework for the robust evaluation of an LLM's ability to engage in clarifying dialogue. Our framework comprises three distinct LLM-based agents: (1) a Question Clarifying Agent (QCA), the system under evaluation, tasked with identifying ambiguities and posing clarifying questions; (2) a Respondent Agent (RA), designed to simulate human user responses, potentially including irrelevant or challenging replies; and (3) an Evaluator Agent (EA), an LLM-as-a-judge, which assesses the quality of the dialogue based on a comprehensive set of metrics. We detail a methodology for synthetic data generation in the supply chain domain as an example. We propose metrics evaluating ambiguity handling, question quality, dialogue efficiency, language appropriateness, and final intent alignment. We also briefly discuss the validation of the EA against human judgments. This work provides a structured approach to benchmark, validate, and improve the clarification capabilities of conversational LLM applications. --- ### The Dynamics of Continuous Mixture Collapse in Language Models Authors: Ali Backour Published: 2026-09-02 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.02049v1 LLMs latent-state reasoning methods replace discrete intermediate tokens with continuous states, such as weighted mixtures of token embeddings, to retain multiple possible reasoning directions rather than committing to one. Yet pretrained language models often fail to preserve these mixtures. We study why through a combination of theoretical analysis and controlled empirical investigations on a variety of models. We identify three independent, distinct sources of failure. First, transformer architectures already distort mixture geometry, and training substantially amplifies this effect. Moreover, the failure can occur even if the model transports mixtures perfectly linearly: the softmax readout and autoregressive feedback form a dynamical system that either amplifies small differences until one component of the mixture dominates or contracts different mixtures until they become indistinguishable. We verify this theoretical prediction empirically: the observed transition between contraction and amplification occurs near the theoretical threshold derived by our analysis, and pretrained-model rollouts lie predominantly on the amplifying side. Finally, we generalize to mixtures of many components and show that exact preservation generally requires context-dependent correction, whose required dimensionality can grow with the number of components. --- ### Modeling What Changes: Sparse, Residual World Models for Object-Centric Manipulation Authors: Param Thakkar, Parsika Paresh Shah, Manisha Sushant Gote Published: 2026-09-02 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.02046v1 Monolithic world models predict the entire next state at every step, spending capacity re-predicting the static majority of a scene and injecting error into it. We ask whether explicitly modeling change (a per-object change gate plus a residual delta head that perturbs only the objects the gate flags) is a more effective and interpretable bias for physical prediction and control. On a MuJoCo tabletop pushing benchmark scaling from 3 to 8 objects, the sparse/residual model predicts next-state poses 2.5 to 4.6 times more accurately than a dense multilayer perceptron at 8.6 to 11.1 times fewer parameters, sustains change-detection F1 of 0.80 to 0.87 where the dense baseline is degenerate, transfers across object counts with zero retraining (99.4 percent F1 retention), and reaches about 90 percent of its full-data accuracy with a quarter of the data. In autoregressive rollout it compounds far less error, hugging the no-motion floor while the dense model drifts. Finally, inside a sampling-based planner, prediction-only models fail (though a true-simulator oracle solves the task with the identical planner, confirming the planner is sound), but once featurized and trained for the states a planner visits, the sparse model begins to plan (0.23 plus or minus 0.06 success over three seeds) while the dense monolith stays at zero at every seed. Modeling what changes, rather than re-predicting the whole world, is a simple, effective bias for object-centric physical AI; code, data generators, and all checkpoints will be released upon publication. --- ### Act More, Decide Less: Skill-Guided Adaptive Action Chunking for Long-Horizon LLM Agents Authors: Yanting Yang, Can Jin, Jinman Zhao, Jiahao Wu, Yang Zhou, Zhepeng Wang, Zhendong Wang, Mu Zhou, Dimitris N. Metaxas Published: 2026-09-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.02042v1 Large language model (LLM) agents for long-horizon interactive tasks typically follow a ReAct-style protocol, issuing one primitive action per LLM round. While this enables frequent replanning, it is inefficient for long-horizon tasks where many rounds are spent on routine action sequences. A natural alternative is to let the agent emit variable-length action chunks. However, naively training such policies with standard reinforcement learning fails: the agent either collapses to single-action behavior or over-commits to excessively long sequences. Both failures share a common root cause: the inability to learn chunk boundaries. We propose SPACE, which addresses this challenge by distilling chunk-boundary supervision from trajectory-induced programmatic skills. We induce two-level programmatic skills from successful trajectories, where subskill boundaries serve as direct chunk-boundary supervision. This temporal structure is then distilled into a primitive-chunk policy via hybrid on-/off-policy optimization with chunk-aware credit assignment. Experiments on ALFWorld and ScienceWorld show that SPACE improves success rates by 7.0%-31.3% over the strongest baseline in each setting while reducing average LLM decision rounds by up to 78.9%. --- ### Test-Time Logit Prompting for Source-Free Missing Modality Adaptation Authors: Taixi Chen, Nancy Guo Published: 2026-09-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.02039v1 Vision-language models (VLMs) have achieved remarkable performance by leveraging complementary information from large-scale image-text pairs. However, missing-modality inputs are commonly encountered during real-world deployment, often leading to significant performance degradation. Existing methods primarily enhance model robustness by learning modality compensation strategies from source training data. However, their reliance on source training data makes them difficult to apply when original data are unavailable due to privacy, storage, or accessibility constraints, such as clinical applications and personalized AI services. This raises an important yet underexplored question: can VLMs be efficiently adapted at test time for visual recognition with missing modalities without accessing source training data? To this end, we propose Test-Time Logit Prompting (TLP), a lightweight source-free test-time adaptation framework for visual recognition with missing modalities. To address missing-induced prediction shifts, TLP optimizes logit prompts with uncertainty-aware adjustment and modality-complete consistency regularization, adaptively adjusting prediction confidence while preserving semantic consistency. Extensive experiments across diverse vision-language benchmarks demonstrate that TLP consistently enhances recognition performance under missing-modality scenarios, achieving up to 8\% improvements while requiring only hundreds of tunable parameters and a few test-time optimization steps. --- ### SelfLift: Accelerating Few-Step Diffusion via Self-Recovering Resolution Transition Authors: Tingyan Wen, Chenqian Yan, Xurui Peng, Xiazhang Fang, Shuai Wang, Xueqian Wang, Songwei Liu Published: 2026-09-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.02036v2 Few-step diffusion models substantially compress temporal computation, making the spatial cost of each model evaluation an increasingly dominant source of inference latency. Progressive-resolution inference reduces this cost by performing early denoising at low resolution and reserving high-resolution computation for refinement. However, existing methods typically lift intermediate latents directly and rely on subsequent steps to absorb the induced distribution mismatch. In the few-step regime, the limited recovery budget leaves these errors as visible artifacts, constraining how late the transition can occur and, consequently, how efficiently it can be performed. We introduce SelfLift, a self-recovering progressive-resolution framework that derives both transition-repair signals and trajectory-aligned supervision from the generative model itself. SelfLift-zero proposes a training-free Artifact-Aware Consistency Lift, using disagreement between direct latent lifting and pixel-VAE re-encoding as both a localized artifact-risk signal and a model-native correction direction. It enables reliable late transitions without external super-resolution, extra denoiser evaluations, or sampling-schedule modifications. Building on this robust transition, SelfLift-rich performs On-Policy Self Recovery on student-visited states, transferring dense high-resolution guidance from an internal self-teacher while remaining aligned with the altered progressive-resolution dynamics. Across FLUX.2-Klein and Z-Image-Turbo, SelfLift reduces end-to-end latency by 41.5% and 44.1%, respectively. Combined with timestep distillation, it delivers overall speedups of 29.61x and 19.21x over the corresponding 50-step models while preserving competitive generation quality, establishing a stronger speed-quality frontier for few-step diffusion. --- ### HeadWiseKV: Budgeted Per-Head Cache Residency for Hybrid Long-Context Language Models Authors: Renjie Xie, Juncheng Yang, Aoting Hu, Mingxi Zhang, Liyao Wu, Zheheng Hong, Wei Xu Published: 2026-09-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.02029v1 Long-context inference retains a growing key--value (KV) cache during decoding, which consumes substantial GPU memory and can reduce generation throughput. This bottleneck remains in hybrid language models because their residual global-attention layers can dominate context-dependent cache demand. We study how to allocate this state under an aggregate KV-residency budget. We introduce HeadWiseKV, a training-free framework that compresses the residual global KV caches of hybrid language models while preserving their native local, recurrent, and linear paths. It assigns each physical KV head a static, multilevel history window, making cache demand predictable before serving. We formulate this allocation as a restricted operational rate--distortion problem and propose SeqCalib as the core policy-generation algorithm in HeadWiseKV. SeqCalib processes layers in execution order and conditions each decision on the lower-layer policy used at deployment, thereby accounting for interactions across depth. A grouped-cache runtime materializes the selected policy as actual per-head KV residency rather than a mask over a full cache. We evaluate downstream quality across four hybrid long-context models and study physical residency and serving behavior on Qwen3.6-27B. HeadWiseKV retains near-Full-KV RULER and LoCoMo quality across the evaluated models. In the fixed-model systems study, it reduces sampled peak device memory by 8.59\% at a 112K context length and extends the largest verified successful context from 114K to 161K. --- ### Detecting Object Hallucinations in Large Vision-Language Models via Cross-Modal Attention Drifts and Mask-Based Verification Authors: Xuanbing Wen, Boxu Chen, Le Yang, Jiakai Wang, Zhengyu Zhao, Chenhao Lin, Chao Shen Published: 2026-09-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.02028v1 Despite recent advances in large vision-language models (LVLMs), object hallucination remains a major barrier to their reliable deployment. Existing detection methods often characterize visual grounding using attention from individual layers, leaving its evolution across layers underexplored. We propose CADMP, a lightweight object hallucination detection framework that combines adjacent-layer cross-modal attention drift with prediction sensitivity to targeted visual masking. During decoding, CADMP quantifies distributional changes between consecutive cross-modal attention maps to capture abrupt transitions in visual grounding. It then selects the transition with the largest drift, locates the corresponding visually relevant regions, and measures the change in prediction probability after masking these regions. These two signals provide complementary evidence: attention drift characterizes the stability of internal visual grounding, while probability variation verifies whether a prediction truly depends on the identified visual evidence. A lightweight detector integrates both signals to identify hallucinated predictions. Experiments on multiple benchmarks and representative open-source LVLMs demonstrate that CADMP achieves consistently competitive detection performance. Ablation studies further confirm the complementary contributions of adjacent-layer drift modeling and mask-based grounding verification. --- ### Source-Free Class Relearning: Diagnosing Forgetting in Class Unlearning Authors: Zahra Dehghani, Pablo Piantanida, Mohammadhadi Shateri Published: 2026-09-02 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2609.02018v1 Class unlearning aims to remove a model's ability to recognize designated forget classes while preserving performance on retain classes. However, low forget accuracy after unlearning does not necessarily mean the class structure has been erased. Approximate unlearning methods can alter classifier decision boundaries while leaving recoverable structure in the representation. Prior work has shown that forget classes can be recovered, but existing approaches require real forget or retain samples, auxiliary data, or reference checkpoints. We study class relearning in a strictly source-free setting, asking whether a forget class can be recovered through a classifier-head update using only the unlearned model. Our approach rests on a theoretical analysis establishing a sufficient alignment condition under which a single gradient step on a synthetic probe set increases the expected logit margin of the forget class. Building on this, we propose a white-box Source-Free Relearning Audit (SFRA), which generates candidate embeddings in representation space and uses model-guided confidence filtering to construct high-confidence retain probes and low-confidence boundary-adjacent probes that are relabelled as the forget class. Gaussian sampling and Softmax confidence are used by default, while ablations with alternative proposal distributions and uncertainty criteria show that recoverability is not specific to these choices. To quantify recoverability, we introduce the Relearning Score (RS), which jointly measures forget-class recovery and retain-accuracy preservation, and report class-matched $Δ$RS relative to a retrained reference. Experiments on CIFAR-10, CIFAR-100, and TinyImageNet with ResNet-18, ViT-B/16, and Swin-T show that several unlearning methods exhibit substantial source-free recoverability, and that for a subset of methods this recoverability exceeds the matched retrained reference. --- ### Perceptually Regularized Diffusion Model for Image Super-Resolution Authors: Chuxiangbo Wang, Pavithra Venkatachalapathy, Ying Liang, Min Wang, Jing Qin, Yifei Lou, Weihong Guo Published: 2026-09-02 Categories: eess.IV, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.02016v1 Image super-resolution, which aims to reconstruct high-resolution images from their low-resolution observations, is fundamental to medical imaging, remote sensing, surveillance, microscopy, and scientific visualization. Traditional model-based methods formulate super-resolution as an inverse problem with hand-crafted regularization priors. While interpretable and theoretically grounded, they rely on fixed assumptions and require computationally intensive iterative solvers. Deep learning methods offer data-driven flexibility by learning nonlinear mappings from low- to high-resolution images, among which diffusion models have achieved particularly impressive perceptual quality. However, the standard diffusion training objective is a pixel-domain noise-prediction loss that does not explicitly enforce perceptual fidelity, which can lead to oversmoothing and loss of fine image structure. To address these limitations, we propose a perceptually regularized diffusion framework that incorporates prior knowledge through perceptual-loss-based regularization, improving training convergence and encouraging the recovery of meaningful image features. Experiments on benchmark datasets demonstrate improved perceptual quality and competitive distortion metrics, highlighting the effectiveness of regularization for diffusion-based super resolution. --- ### How Output Format Confounds Data Quality and Capability in Instruction Tuning Authors: Chengguang Gan, Hanjun Wei, Yunhao Liang, Qinghao Zhang, Shiwen Ni, Zhixi Cai Published: 2026-09-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.02015v1 Instruction-tuning data are judged by quality metrics, and tuned models are judged by benchmarks, but both judgments pass through an output interface: the surface format in which an answer is written. Using gradient signatures across 12 tasks, four semantically equivalent interfaces, three model families, and controlled corruptions, we show that this interface confounds both measurements. Spectral statistics such as effective rank are provably invariant to interface rotation and empirically blind to semantic corruption, while the direction of the update carries the quality signal. The interface-varying residual is not noise: it identifies each unit's own target task perfectly across all three families. Capability itself is stored relative to the training interface: a skill that raises accuracy by more than 40 points under the training format can be nearly invisible under every other, and correcting a single generation budget flips the measured effect of fine-tuning on GSM8K from a gain into a large loss. Pre-registered interventions delimit where this geometry stops short of control. Data quality and model capability are interface-conditioned quantities, and current practice often reports the interface instead of the content. --- ### What Would it Cost to End Extreme Poverty? Authors: Roshni Sahoo, Joshua Blumenstock, Paul Niehaus, Leo Selker, Stefan Wager Published: 2026-09-02 Categories: econ.GN, stat.ML arXiv: https://arxiv.org/abs/2609.02013v1 We study poverty minimization via direct transfers, framing this as a statistical learning problem while retaining the information constraints faced by real-world programs. Using nationally representative household consumption surveys from 34 countries that together account for 76% of the world's poor, we estimate that reducing the poverty rate to 1% (from a baseline of 13%) would cost $211 B nominal per year. This is 4.0 times the corresponding reduction in the aggregate poverty gap, but only 19% of the cost of universal basic income. Extrapolated globally, the results imply a cost of 0.28% of global GDP to (approximately) end extreme poverty. --- ### POI-Loc: A Fine-Grained POI Localization Benchmark and an Asymmetric Global-to-Local Matching Method Authors: Lu Han, Xiting Sun, Hao Wang, Zhiqiang Cao, Ruihuan Du, Ziquan Zeng, Chunlong Lv Published: 2026-09-02 Categories: cs.CV, cs.IR arXiv: https://arxiv.org/abs/2609.02012v2 Point-of-interest (POI) localization matches user-provided storefront close-ups to the same shops in wide, geo-tagged vehicle-mounted street views. POIs may change while the surrounding scene stays similar, so scene-level recognition alone cannot establish POI identity. Differences in target scale and capture domains further challenge matching. We introduce POI-Loc, to our knowledge the first benchmark dedicated to this asymmetric, fine-grained POI localization task. Many visual place recognition methods represent each image with a single global vector, which tends to dilute fine-grained features of small storefronts amid background clutter. We propose GLAM (Global-to-Local Asymmetric Matching) to combine global and local evidence. In stage one, a single attention-pooled query probe is matched against compact reference region tokens via learnable soft top-k interaction, with the resulting local similarity fused with global similarity for retrieval. Stage two reuses query region tokens before attention pooling and stored reference tokens for mutual-nearest-neighbor re-ranking. GLAM surpasses both global and two-stage baselines on Recall@1/5/10 and mAP, with about $5\times$ smaller re-ranking features and $280\times$ lower per-pair matching cost than FoL. The benchmark and code will be released at https://github.com/roadhan/glam. --- ### Seed-Anchored Budget-Bounded Graph Rendering for Question Answering on Industry-Standard Power-Grid Information and Exchange Models Authors: Jayakumar Manoharan, Yamini Sehgal Published: 2026-09-02 Categories: eess.SY, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2609.02011v1 Large language model question answering over power-grid models must respect a fixed context budget. We introduce seed-anchored graph rendering, a deterministic method that prioritizes query-local graph evidence without adding method-specific tuned or learned parameters beyond the shared hop bound and context budget. The method provides a checkable condition under which predefined seed-local answer-bearing render units are preserved in a greedy bounded-context prefix. We evaluate the approach on Common Information Model (CIM) network models exchanged through the Common Grid Model Exchange Standard (CGMES). On two budget-binding CGMES encodings, naive descriptions-first rendering retains local evidence for every single-hop item but only 0.12 and 0.00 of multi-hop items, whereas seed-anchored rendering retains all such evidence. On a preregistered fresh 100-item bank from the SmallGrid topology family, accuracy rises from 0.450 to 0.970 under a fixed 8,000-character context budget. Under a common retrieval and rendering pipeline, the standards-native seed-anchored graph matches or exceeds extracted graph representations produced by LightRAG, Microsoft GraphRAG, and HippoRAG, while avoiding LLM graph-construction tokens. The results are specific to the evaluated CIM/CGMES models, reader, and context budget; they concern budget-bounded retrieval rather than general question answering. --- ### Train What You Deploy: Closing the MLP Reachability Gap in Low-Rank Clone Distillation Authors: Wenhui Chen, Zhifeng Li, Jie Zhou, Navan Preet Singh, Madalina Ciobanu, Chenghua Wang, Qingqing Mao, Ritankar Das Published: 2026-09-02 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.02006v1 A compressed student has two shapes that need not agree: the weight it deploys at inference and the weight family its training can reach. We show that a state-of-the-art weight-inheritance distiller, Low-Rank Clone (LRC), deploys a full-width student MLP but ties training to a teacher-induced slice, leaving 62.5-81.4% of each deployed matrix's independent linear degrees of freedom unreachable-paid for at inference, never trainable. Our principle is one line: train what you deploy. From the identical LRC warm start, we make the training object the entire deployed matrix, with no change in deployed shape, deployed parameter count, or inference FLOPs, via two mergeable realizations (Dense-LRC and CORE-LRC) that both collapse to one deployed weight. This recovers stranded capacity: taking the stronger realization per teacher, +2.36/+2.71/+10.45 Avg9 over matched-budget plain-LRC baselines across three teachers (Llama3.2-3B, Llama3.1-8B, Qwen2.5-3B), with the largest gain on the widest teacher (Qwen), where it reaches the original recipe's approx. 20B-token accuracy at 10B tokens (2x token efficiency); there the strictly same-lineage arm still recovers +6.39, the fully controlled figure. Controls strongly support attributing the gain to the enlarged reachable set, rather than to added parameters or the recipe. From approx. 10B distillation tokens plus a short SFT, a half-parameter 1.5B student matches its approx. 9T-token teacher's 9-task macro-average, within evaluation noise and with a residual MMLU deficit, and a 2.7B student beats Meta's own official compression of Llama3.1-8B at ~900x fewer compression tokens (a token count under unmatched recipes, not a compute claim). All results are from single-seed runs on the LRC backbone. --- ### InstEditSeg: Instruction-Driven Image Editing for Polyp and Skin Lesion Segmentation Authors: Ziquan Liu, Zhewei Zhu, Xuyang Shi Published: 2026-09-02 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.02004v1 Accurate segmentation of polyps and skin lesions is pivotal for clinical diagnosis, yet existing methods struggle with low contrast, ambiguous boundaries, and cross-domain distribution discrepancies. Discriminative networks and most diffusion-based segmentation approaches predict standalone binary masks, leaving the visual priors of large-scale pretrained generative models largely unexploited. We propose InstEditSeg, a unified generative framework that reformulates medical segmentation as an instruction-driven image editing problem. Instead of emitting a mask, the model renders a color-coded overlay on the original image, conditioned on a textual instruction, so that the edited output aligns with the natural image distribution learned by latent diffusion models and mitigates the domain gap between natural and medical imagery. To recover fine anatomical structures, we introduce DINOv3 as an auxiliary visual encoder and a DINO Feature Guidance Block that builds a multi-scale feature pyramid. The pyramid is fused into the diffusion U-Net by channel concatenation and zero-initialized convolution so that hierarchical discriminative priors can be injected without perturbing the pretrained weights. A dual-branch classifier-free guidance strategy requiring only two forward passes per denoising step reduces inference cost. On polyp and skin lesion benchmarks the framework achieves accuracy competitive with strong discriminative baselines, and it further demonstrates concrete advantages of the generative formulation: notably better cross-domain generalization on unseen data, more complete multi-lesion segmentation, instruction-conditioned task control, and sampling flexibility. We also analyze the strengths and limitations of the paradigm, including its color sensitivity and unsupported attribute-conditioned selection. Code is available at: https://github.com/wincharm001/InstEditSeg. --- ### InsightSeg: Reusing Correction Insights for Guideline-Consistent Segmentation Authors: Vanshika Vats, Ashwani Rathee, James Davis Published: 2026-09-02 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.02002v1 Guideline-consistent semantic segmentation requires more than category recognition, as real-world labeling policies demand fine-grained, task-specific decisions. Recent multi-agent refinement systems improve compliance with such textual guidelines by detecting and correcting errors. However, they are stateless: feedback from the critiquing agent is discarded, causing the same guideline-specific mistakes to be repeatedly rediscovered and corrected across the dataset at the cost of additional refinement. We introduce InsightSeg, an episodic memory mechanism that converts successful correction episodes into reusable, visually grounded insights. A meta-analyzer distills each qualifying episode into directive natural-language insights and anchors them to the local image regions that caused the error using patch-level visual concept vectors. On subsequent images, these concepts are matched against dense patch embeddings to retrieve relevant insights, which condition the segmenting agent before making its first prediction. This shifts the system from correcting recurring errors to preventing them, improving segmentation quality before any refinement occurs. Across Waymo and Cityscapes, InsightSeg improves both first-pass and final guideline-consistent segmentation performance while requiring fewer refinement steps, demonstrating that multi-agent refinement can become more accurate and efficient by drawing on past correction experience. --- ### Who Drives the Probability Game of VLMs? A Temporal Causal Drive Evaluation Framework Authors: Shuyao Xiao, Shengling Wang, Haoyu Niu, Ke Chao, Changwei Xu, Xinran Duan, Chaoyong Jiang Published: 2026-09-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.02000v1 Vision-language models (VLMs) are increasingly evaluated on complex image and video understanding tasks, yet conventional metrics primarily assess final-answer quality and reveal little about how different information sources shape the generation process. We propose a causal and temporal evaluation framework that traces the evolving roles of visual input, question text, and generated prefixes during autoregressive decoding. Grounded in a Structural Causal Model, we use interventions and backdoor adjustment to derive three step-indexed causal-drive metrics---Visual Causal Drive (VCD), Question Causal Drive (QCD), and Prefix Causal Drive (PCD)---for characterizing source-specific generation patterns without requiring reference answers. Experiments on Qwen3-VL-8B-Instruct across MAVIS, LLaVA-Video-178K, and MiraData, together with cross-model validation on InternVL2-8B, reveal a consistent transition from stronger early question and visual guidance toward increasing reliance on generated prefixes. Randomized-intervention validation shows that QCD and PCD reduce recovery error over observational PMI baselines by 34.8\% and 47.1\%, respectively. On VLMBias, the prefix--visual imbalance score achieves 0.767 AUROC and 0.873 AUPRC for distinguishing prior-driven from visually grounded generations. These results show that causal-drive trajectories provide complementary source-level diagnostics for multimodal generation. --- ### Posterior Tempering Explains Variance Inflation in Linear and Generalized Linear Thompson Sampling Authors: Prateek Jaiswal, Debdeep Pati, Anirban Bhattacharya, Bani K. Mallick Published: 2026-09-02 Categories: stat.ML, cs.IT, cs.LG, math.ST arXiv: https://arxiv.org/abs/2609.01999v1 We study a variant of the Thompson Sampling (TS) algorithm, called $α$-TS, for solving stochastic generalized linear bandit problems. Existing analyses of TS require inflating the posterior variance to derive near-optimal regret guarantees. We formalize the idea of variance inflation by introducing $α$-TS that uses a fractional or $α$-posterior instead of the standard posterior. Our main contribution is to identify general regularity conditions on the prior and reward distributions that enable a regret analysis of $α$-TS without assuming any tractable approximation of the posterior distribution, unlike previous works. For a specific choice of $α\propto d^{-1}$, our general regret bound yields the best known regret bound of $O(d^{3/2}\sqrt{T}\log T)$ for both the exponential and sub-Gaussian families of reward distributions. We further provide an $α$-dependent lower bound showing that the regret constant depends on the product $αd$, and that when $α\propto d^{-1}$ the regret scales as $Ω(d^{3/2}\sqrt{T})$, explaining the origin of the $d^{3/2}$ factor in the upper bound. Our proof technique adapts and combines recent advancements in the analysis of linear bandit problems with first- and second-order posterior concentration theory from the Bayesian statistics literature. --- ### Linear Fusion MultiDiffusion for Fast Training-Free Spherical Panorama Generation Authors: Akio Hayakawa, Yusuke Mukuta, Tatsuya Harada Published: 2026-09-02 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.01997v1 We propose LF-MultiDiffusion, a training-free panorama generation method that extends MultiDiffusion to support linear projections between target and reference image spaces. Our key idea is to reformulate latent aggregation as a regularized least-squares problem and solve it efficiently with a Krylov-based iterative solver inside the denoising loop. This formulation enables denser and more natural mappings than prior training-free methods, yielding more stable generation with far fewer perspective views. As a result, LF-MultiDiffusion reduces the number of image generator evaluations during denoising and significantly improves inference efficiency. Experiments show that LF-MultiDiffusion achieves better visual quality, text alignment, and panoramic consistency than the strongest training-free baseline, while providing a 15.36$\times$ speedup. Our project page is available at: https://ahykw.github.io/lfmd. --- ### ClaimReceipt: Verifying Evidence Sufficiency and Coverage in Agent Evaluations Authors: Peiying Zhu, Sidi Chang Published: 2026-09-02 Categories: cs.AI, cs.CR, cs.MA arXiv: https://arxiv.org/abs/2609.01992v1 Agent evaluations face two distinct evidentiary questions: whether a reported claim is recomputable from retained evidence (sufficiency), and whether the retained records cover the committed experiment set (coverage). Generic logs and hash-linked transcripts answer neither reliably. We introduce ClaimReceipt, a claim-relative receipt specification and selective verifier that binds typed transaction evidence to a signed experiment manifest and returns PASS, INVALID, or INCONCLUSIVE per claim. We freeze the specification before implementation (SHA-256 18d109...b81). On 1,392 historical buyer--seller records, a CR-2 verifier reproduces all five manually labeled audit verdicts, exactly replays 600 deterministic and 792 post-generation records, makes every one of 13 declared field groups non-redundant under tested ablations, and returns the expected result on 11/11 semantic faults with 0/8 false positives. We then run a separate prospective CR-3 epoch: 30 assignments are committed before inference, terminal receipts are signed and chained, and private evidence is encrypted for an auditor. Complete evidence yields coverage and accounting PASS; withholding one terminal receipt returns INCONCLUSIVE_COVERAGE, while withholding all private openings preserves coverage and protocol verification but makes economic claims inconclusive, exactly matching a preregistered prediction. Receipt instrumentation adds 0.021% of model-inference time and 9.9 KB per transaction. A specification-legibility probe indicates that our own frozen specification is not yet unambiguous to an independent reader. Claim verification therefore requires both claim-sufficient evidence and a committed universe against which omissions become visible. --- ### CAHR-Net: Condition-Adaptive Hysteresis Reconstruction for Compact and Interpretable Magnetic Core Loss Modeling Authors: Chunye Gong, Cong Yao Published: 2026-09-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.01991v1 Magnetic core loss originates in the hysteresis loop: the energy dissipated per excitation cycle equals the loop area, and frequency, temperature, and waveform shape set the loss by reshaping the loop geometry. Most existing models let these conditions act only on a terminal scalar - empirical equations fold them into fitted exponents, and data-driven predictors append them to encoded features - so no intermediate hysteresis representation remains for the conditions to reshape. This paper proposes CAHR-Net, a condition-adaptive hysteresis reconstruction network that injects the operating conditions where they physically act. It preserves the interpretable chain from flux density waveform to magnetic field reconstruction, loop-area integration, and power loss estimation, and uses feature-wise linear modulation to inject frequency, temperature, and waveform statistics into the intermediate reconstruction representation. A matched large-batch training protocol based on AdamW, cosine scheduling, and a staged reconstruction-to-power-loss objective is also reported, because the modulation pathway takes effect only within it. On the MagNet final A-E material protocol, CAHR-Net attains an average p95 relative error of 6.89% with only 1874 parameters, the lowest among all compared methods, together with a lower worst-material p95 than the strongest black-box solution at about 48x fewer parameters; it reduces the average p95 of the physical reconstruction backbone from 7.47% to 6.89% and the p95 of material D, the most difficult material, from 16.40% to 14.87%. Ablation and condition-slice analyses attribute the improvement to the coupling of physical loop reconstruction, structured condition modulation, and the matched optimization trajectory. --- ### Morphology signal in whole slide image foundation models can automatically triage slides Authors: Ayushi Sinha, Shashank Yadav, Benjamin Holmes, Pravat Das, Aaron W. Bogan, James S. Lewis, Santiago Romero-Brufau, Andrew Y. K. Foong, Scott H. Kaufmann, Kathryn M. Van Abel, David M. Routman, Michael R. Lucas Published: 2026-09-02 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.01987v1 Patient exams in the cancer diagnosis and staging process typically generate several whole slide images (WSIs). One of the initial steps in training models on WSI data is identifying one or a few slides containing tumor or other diagnostic biomarkers necessary for downstream prediction tasks such as estimating recurrence risk or progression-free survival. This step requires tedious manual curation by experienced pathologists. Many published datasets make the artificial assumption of 1 slide per patient. Alternatively, all slides per patient may be used for model training, which may dilute the signal from the few slides containing tumor or other relevant information. In this paper, we present a pipeline to overcome these challenges using publicly available WSI foundation models (FMs). Our evaluations show that ranking WSIs based on predictions from zero-shot classification using WSI FMs accurately identifies slides with the most tumor, indicating that WSI FMs contain sufficient morphology signal to automatically triage slides. We also present a formulation for ranked evaluation to benchmark FM performance in slide triage. We show, on multiple datasets, that tumor slides are identified in the top-2 ranked slides for patients with up to 43 slides. --- ### When Agents Implement Systems: A Case Study in Defects, Detection, and Evaluation Rigor Authors: Phanindra Reddy Madduru Published: 2026-09-02 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2609.01985v1 As LLM coding agents increasingly perform end-to-end engineering work, we lack empirical characterization of how they behave on systems-level requirements: schema design, async orchestration, configuration correctness, and retrieval-filtering trade-offs. We present a case study of one such agent implementing a multi-component data system against a detailed pre-existing specification. Storage technologies, schema, entity-resolution algorithm, and retrieval-filtering strategy were fixed in advance; the agent autonomy was in the implementation, in diagnosing and fixing defects it introduced, and in interaction-design choices left open. Over a single session, we catalog five such defects, categorized by constraint violated and detection method. We further evaluate, on the public HotpotQA benchmark, the one retrieval trade-off specified in that architecture: restricting candidates to a graph-identified entity set before ranking versus unfiltered search. We substitute the benchmark gold evidence labels for entity identification, since we lacked LLM access to run that stage, and report standard recall rather than the benchmark own accuracy metrics. Across retrieval budgets from 1 to 10 and 100 questions against a pooled corpus of 2994 paragraphs, filtered recall reaches its ceiling by a budget of 3, expected once candidates are restricted to the gold paragraphs themselves, while unfiltered search recovers all required evidence only 69 percent of the time even at a budget of 10, a gap that holds at every budget tested, with sign test p less than 0.0001. We close with a discussion of where the agent autonomy succeeded versus required correction, including one instance where a claimed performance fix was never re-measured on the regression that motivated it. --- ### Benchmarking Language Models for Statistical Problem Formulation Authors: Chen Wang, Junzhe Zhao, Xin Cong, Wanlu Deng, Ke Deng Published: 2026-09-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.01982v2 Large language models (LLMs) are increasingly used as assistants for statistical and data science work, yet existing evaluations largely assume the analysis target is already specified. In practice, users arrive with informal goals and heterogeneous data, leaving the model to decide what statistical task is implied and which data are relevant. We first formalize this upstream step as Statistical Problem Formulation and decompose it into two subtasks: (1) Statistical Problem Classification and (2) Variable Identification & Role Assignment. We then introduce StatFormBench, a benchmark built from five cross-domain statistics textbooks and a data science case library, covering diverse problem types, data representations, and scenario styles. It contains 1,013 samples spanning 20 coarse-grained and 85 fine-grained statistical problem categories. Across 14 open- and closed-source LLMs, the best zero-shot models reach only 72.0 fine-grained classification accuracy and 63.2 variable set overlap. No model performs consistently best across the two subtasks, while enhanced prompting strategies yield only limited or inconsistent gains. We release the benchmark data on Hugging Face at https://huggingface.co/datasets/THU-CongLab/StatFormBench and the evaluation code on GitHub at https://github.com/THU-CongLab/StatFormBench. --- ### Knowing Is Not Enough: Information Retrievability as a Precondition to Effective LLM Oversight Authors: Xinyu Fu, Narayan Ramasubbu, Dennis Galletta Published: 2026-09-02 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2609.01976v1 Large language models (LLMs) are increasingly embedded in organizational work, yet their errors often pass human review. Prior research locates such failures in users' capability to review LLM output or their engagement in doing so. We develop an alternative, retrieval-based account of human oversight and posit that error detection is more effective when oversight-relevant information is accessible to users at the moment of review. Across two randomized lab-in-the-field experiments with 640 customer-facing employees, we show that self-generated explanations improve error detection and strengthen recall of verification-relevant reasoning, while cues that reactivate such reasoning help sustain detection under repeated LLM use. Theoretically, we identify information retrievability as a distinct precondition for effective oversight and specify generative encoding and cue-supported reactivation as mechanisms that build and sustain it. Practically, lightweight onboarding self-explanations and daily retrieval cues can make human oversight more resilient as LLM use becomes routine. --- ### NS-Copilot: An LLM-Driven Agent System for Autonomous Neuroscience Analysis Authors: Wuche Liu, Yiran Qiao, Linlin Hou, Rui Yang, Shusen Pu, Song Wang, Jing Ma Published: 2026-09-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.01971v2 AI is rapidly advancing neuroscience, yet many laboratories fail to fully unleash its potential due to significant interdisciplinary barriers. While pre-trained neural models for physiological data are progressing quickly, their heterogeneous architectures and modality-specific constraints hinder systematic integration, selection, and evaluation. Despite recent advances in large language model (LLM)-based agent systems for intelligent scientific applications, existing approaches often still lack the domain expertise required to effectively select and coordinate diverse neuroscience pre-trained models and handle unique data types in this domain. We present NS-Copilot, an LLM-driven multi-agent system for neuroscience analysis that autonomously supports end-to-end workflows for diverse professional tasks. It unifies domain-specific pre-trained models and supports key neuroscience modalities, including EEG and extracellular spike data, through a natural-language interface. Given raw data and a task description, NS-Copilot orchestrates agents with specialized roles for planning, adaptive control, code generation, and result synthesis, enabling analysis without dataset-specific heuristics. We evaluate NS-Copilot on neuroscience benchmarks spanning Alzheimer's disease, Parkinson's disease, and working memory spike decoding. Across 8 trials per task, the system consistently outperforms strong baselines on the primary metric, demonstrating the ability of NS-Copilot for effective and scalable neuroscience analysis. Our code is publicly available at https://github.com/FrankLiu1102/ns-copilot. --- ### A Unified Particle Filter LSTM for Data-Driven Process Simulation Authors: Parvin Malekzadeh, Opher Baron, Dmitry Krass Published: 2026-09-02 Categories: cs.LG, eess.SP arXiv: https://arxiv.org/abs/2609.01967v1 Data-driven process simulation aims to generate realistic case trajectories from historical event logs without requiring an explicitly specified model of the underlying dynamics. Deep sequence models can capture complex temporal dependencies through next-activity probabilities and conditional time distributions. However, event logs provide only a partial view of the underlying process state, often recording activity completions without the corresponding service-start times. Consequently, the same observed process history may be consistent with multiple plausible latent process conditions, whereas standard recurrent models compress each process prefix into a single deterministic recurrent state. We propose a Unified Particle Filter LSTM (Unified PF-LSTM) that maintains and sequentially updates a weighted set of recurrent-state hypotheses. We summarize this particle belief using its weighted mean and learned features based on the moment-generating function. The resulting representation is used to predict a categorical distribution over the next activity and conditional quantiles of the current activity's sojourn time. The framework is trained end-to-end from event-log data and evaluated on three real-world emergency department datasets. The results show that the proposed framework consistently outperforms the considered data-driven baselines in reproducing routing, duration, and system-level behavior across all datasets, with particularly strong gains in settings where complex process dynamics are only partially reflected in the available event logs. --- ### Aggregating Neighbor Embedding Projection and Rank-Based Manifold Learning for Image Retrieval Authors: Vinicius Atsushi Sato Kawai, Gustavo Rosseto Leticio, Lucas Pascotti Valem, Daniel Carlos Guimarães Pedronette Published: 2026-09-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.01963v1 Content-based image retrieval (CBIR) has advanced significantly with deep learning, yet effectively ranking similar images remains challenging, particularly in high-dimensional feature spaces, where pairwise distances often fail to capture contextual relationships and the semantic gap between visual features and high-level concepts persists. Manifold learning and rank-based refinement methods have emerged as complementary strategies, respectively improving feature representations and exploiting contextual information embedded in ranked lists, such as neighborhood relationships among images. However, combining these projection-based and rank-based strategies to exploit their complementary properties remains a challenging research problem. To address this, we propose a framework that combines neighbor embedding projections with rank-based manifold learning through rank aggregation. Uniform Manifold Approximation and Projection (UMAP) generates alternative low-dimensional feature representations, and ranked lists obtained from UMAP projections and rank-based re-ranking methods are combined using the Borda Count aggregation strategy. Experiments were conducted on several public datasets using deep learning features extracted from ResNet152, Swin Transformer, and DINOv2 models. Results show that the proposed approach improves retrieval effectiveness in several scenarios, particularly when the baseline representation struggles to achieve high precision. The aggregation strategy also often improves the quality of top-ranked positions, leading to competitive Mean Average Precision (MAP) and Precision values across different datasets and feature extractors. These findings suggest that combining projection-based and rank-based manifold learning strategies through rank aggregation can provide complementary contextual information for image retrieval tasks. --- ### Post-Training Ternarization of Qwen3-4B Capability, Effective Bit Budget, Storage Compression, and Deployment Authors: Anirudh Malik, M Sparsh Mehra, Poojith Devan Published: 2026-09-02 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.01962v1 Ultra-low-bit language models can reduce storage and memory bandwidth, but a nominal "1.58-bit" label does not fully describe the stored representation, retained capability, or runtime behavior. We study an end-to-end post-training conversion of Qwen, an instruction-tuned 4B-parameter model, using KOTMS rotation, E2M-ATQ ternarization, and GPTQ-style error compensation from TWLA. The experiment is weight-only: activations remain at 16-bit precision, so ILA-AMP is omitted. We evaluate effective bit accounting, task capability retention, perplexity, calibration sensitivity, checkpoint composition, and deployment behavior. The final conversion uses 1.641 effective bits per weight for quantized linear weights, with 81.62% of model parameters targeted. Across ten scored capability comparisons, accuracy falls from 64.5% to 54.7%. Degradation is uneven: BoolQ retains 84.6% chance-corrected teacher performance, while ARC-Challenge retains 43.8%. Perplexity rises from 13.639 to 18.748 on WikiText-2, 24.700 to 31.992 on PTB, and 19.831 to 28.966 on C4. A subsequent packing run preserves the ternary planes and scales, reducing reported model size from 8.29 GiB to 3.96 GiB with essentially unchanged perplexity. A separate third-party packing attempt was lossy and is excluded from the primary artifact claim. The packed artifact has not been benchmarked end-to-end for task accuracy or generation throughput. A preliminary Triton GEMV microbenchmark is 4.6x slower than FP16 cuBLAS on one tested shape. We therefore do not claim that compression alone yields faster inference. --- ### Data-Efficient Networks for Multi-Contrast MRI Reconstruction based on a Generalized Content/Style Prior Authors: Chinmay Rao, Efe Ilıcak, Matthias J. P. van Osch, Mariya Doneva, Laurens Beljaards, Navid Jabarimani, Nicola Pezzotti, Marius Staring Published: 2026-09-02 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2609.01959v1 Multi-contrast MR scans contain redundant structural information that can be leveraged during reconstruction and potentially accelerate acquisition times. This idea has inspired end-to-end guided reconstruction models, leveraging one or more contrasts to guide the reconstruction of a different contrast. However, these models require large paired multi-contrast raw datasets for training, limiting their application in low-data regimes. In this work, we propose a modular framework, namely CoSMo-RecNet, for learning guided reconstruction models in the low-data regime. At its core is a reusable multi-contrast representation based on a content/style model, which can be learned from large-scale, publicly accessible, unpaired multi-contrast image datasets, without available k-space data. Using this frozen model as a multi-contrast prior and using a set of reference contrasts, the reconstruction problem reduces to a much simpler refinement problem that can be solved by a lightweight unrolled network and thus learned from small, task-specific reconstruction datasets. We demonstrate the efficacy of CoSMo-RecNet by evaluating it on the low-field 0.3 T M4Raw dataset, showing stable reconstruction quality on decreasing the raw training data budget. CoSMo-RecNet achieved higher reconstruction quality with 5 training subjects or lower compared to a parameter-count-matched MoDL trained on 100 subjects. On a data-limited and severely out-of-distribution ultra-low-field 47 mT Halbach scanner dataset, CoSMo-RecNet was superior to other viable strategies, including classical reconstruction, transfer learning, and zero-shot reconstruction. --- ### Network-Aware Forecasting on Wireless Access Points Authors: Niloo Bahadori, Swadhin Pradhan, Peiman Amini Published: 2026-09-02 Categories: cs.NI, cs.LG arXiv: https://arxiv.org/abs/2609.01957v1 Enterprise wireless access points (APs) are promising platforms for predictive machine learning (ML), but their primary responsibility remains providing wireless connectivity and network services. Predictive inference must therefore share an AP's CPU and memory with packet processing, Wi-Fi and IoT radio operations, and client management. This resource contention creates two risks: a model that performs well on proxy hardware may be too slow on the target AP, while a model that fits in isolation may still degrade network services under load. We define \textit{network-aware deployability} using two gates: qualification of the model and its execution path on the target AP, followed by validation of its execution profile under packet-service and forecasting constraints. Our benchmarks show that edge testbeds do not reliably capture target behavior. Across matched artifacts and serving settings, five model implementations run 6.1--19.1$\times$ slower on an AP than on a Raspberry Pi~5, while peak memory usage differs by up to 22\%. Moreover, two forecasting foundation models of similar size differ in AP latency by 19$\times$. When serving a smaller model across 13 parallel streams at a 30~s cadence under network saturation, default execution increases p99 round-trip time (RTT) by 76\% and reduces throughput by 7.06\%. Understanding these trade-offs is essential for live deployment if we aim to use APs for both networking and ML workloads. --- ### InKAN: B-Spline KANs via Truncated Power Form Authors: Naveen Mysore Published: 2026-09-02 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2609.01956v3 Kolmogorov-Arnold Networks (KANs) place learnable B-spline activations on network edges rather than fixed activations on nodes. The standard Cox-de Boor recursion evaluates these activations through $k$ sequential passes for degree-$k$ splines, consuming over 90% of forward-pass time. InKAN replaces this recursion with the truncated power form, a classical result from approximation theory that expresses each uniform cubic B-spline as five $(x)_+^3$ terms at shifted knot positions. The resulting expression computes exact B-spline basis values: the same mathematical function as the Cox-de Boor recursion, evaluated without sequential passes. This paper documents three contributions: (1) an implementation structured for torch . compile fusion, eliminating recursion, span lookup, and scatter-gather operations; (2) a bounded-coordinate evaluation that clamps the normalized input to $(0, k{+}1)$, preventing the growth of cancellation error at large off-support coordinates; and (3) an open-source package (pip install inkan). In the tested configurations, InKAN has 2.8--3.5$\times$ lower forward-pass latency than the Cox-de Boor recursion. Partition-of-unity errors remain below $10^{-5}$ for grid sizes up to 200. --- ### QINA: Quantum-Inspired Nonlinear Adapters for Pretrained Vision Models Authors: Mostafa Mehdipour Ghazi Published: 2026-09-01 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.29592v1 Adapting large pretrained vision models under limited data and frozen-backbone constraints remains a central challenge in transfer learning. While lightweight adapters and parameter-efficient fine-tuning methods are widely adopted, most rely on generic multilayer perceptrons or low-rank linear updates, offering limited control over the spectral and geometric structure of feature transformations. We investigate whether structured nonlinear feature lifting can improve representational alignment in frozen regimes. We introduce Quantum-Inspired Nonlinear Adapters (QINA), compact modules that perform learnable trigonometric feature lifting followed by bounded nonlinear aggregation. The design induces structured oscillatory basis functions with an explicit norm-dependent Lipschitz bound, enabling spectral reshaping of pretrained representations without increasing the receptive field or significantly expanding parameter count. Importantly, the method operates entirely within standard deep learning frameworks and does not require quantum hardware. Through systematic experiments across natural and medical imaging datasets, classification and segmentation tasks, multiple adapters and placements, and varying training budgets, we show that performance in frozen regimes is primarily representation-limited. Nonlinear lifting improves adaptation, and the proposed structured trigonometric formulation consistently outperforms identity baselines, fixed Fourier feature mappings, and parameter-matched baseline adapters. Within the evaluated frozen-backbone settings, structured spectral parameterization provides a more effective inductive bias than generic nonlinear adapters. This work highlights the importance of geometry- and spectrum-aware adaptation mechanisms for large pretrained vision models. --- ### CATCH: Counterfactual Anatomical Tissue Inpainting with Conditional Haar Diffusion Authors: Simon Winther Albertsen, Hjalte Bjoernstrup, Said Djafar Said, Mostafa Mehdipour Ghazi Published: 2026-09-01 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.29591v1 BraTS local synthesis replaces masked regions in T1-weighted brain MRI with plausible tumor-free tissue while preserving observed anatomy. We present CATCH, conditional 3D diffusion in an invertible Haar-wavelet domain. Its denoiser receives noisy target coefficients, voided-image coefficients, and a signed mask; tumor-excluded wavelet reconstruction and a hole-focused loss guide training, and hard compositing preserves observed voxels. We compare fixed masks, tumor-component augmentation, and a weighted mixture of tumor-derived, irregular-blob, and ellipsoidal masks. Of 25 development cases, five prespecified cases select each arm's checkpoint and all 25 of their trajectory aggregations; a separate 75-case internal set compares the frozen pipelines and selects a weighted mixture for organizer evaluation. Five-trajectory averaging yielded internal SSIM/PSNR/MSE (mean$\pm$SD) of $0.80\pm0.13$, $19.18\pm1.80$dB, and $0.010\pm0.005$. As the sole officially evaluated pipeline, weighted mixture yielded $0.772\pm0.119$, $20.89\pm3.27$dB, and $0.0098\pm0.0054$ on the 219-case BraTS 2026 validation set. Against compute-matched random augmentation internally, it improved SSIM by 0.019 (95% bootstrap CI: 0.013-0.025), PSNR by 0.95dB, and MSE by 0.003; all three paired comparisons remained significant after Holm correction. Results favor the complete weighted-mixture policy within CATCH; absent official fixed- and random-pipeline scores and a directly comparable external baseline limit broader conclusions. --- ### ToCo-Mesh: Topology-Consistent Dynamic Mesh Reconstruction via Adaptive Tessellation and Surface-Aligned 2DGS Authors: Chuanjin Fan, Wenjie Chang, Aibing Li, Bingzhou Wang, Wenfei Yang, Tianzhu Zhang Published: 2026-09-01 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2609.29529v2 Reconstructing dynamic meshes with consistent topology from multi-view temporal images remains a challenge. Existing approaches typically face a dilemma between fine-scale shape recovery and topological stability. Frame-by-frame extraction methods capture fine details but break vertex correspondence, leading to flickering meshes. Conversely, template-based deformation ensures consistency but struggles to adapt its surface resolution during optimization, missing local surface details. To address these limitations, we propose ToCo-Mesh, a dynamic reconstruction framework that maintains topology consistency over time while achieving high-fidelity geometry. Specifically, we introduce a dual-mesh representation, where a canonical template mesh is tightly bound to time-varying coarse guide meshes via barycentric parameterization. While keeping guide meshes fixed to condition the deformation, we perform error-driven split-and-merge on the template mesh to progressively increase reconstruction fidelity. Furthermore, to suppress surface irregularities and achieve photorealistic rendering, we incorporate a Surface-Aligned 2DGS module. By anchoring flattened Gaussians to mesh faces, we utilize their rendered normals to guide inverse geometric fine-tuning. To our knowledge, ToCo-Mesh is the first framework to enable adaptive mesh refinement while maintaining strict topological consistency. Extensive experiments demonstrate that our method achieves SOTA geometric accuracy while maintaining competitive rendering quality. --- ### SALSA: Semi-Autonomous Literature Summarization Assistant Authors: William Schertzer, Sonakshi Gupta, Rampi Ramprasad Published: 2026-09-01 Categories: cs.CL, cond-mat.mtrl-sci arXiv: https://arxiv.org/abs/2609.22210v1 SALSA (Semi-Autonomous Literature Summarization Assistant) is an open- source, human-in-the-loop platform for extracting structured scientific datasets from multimodal literature sources. The software combines document parsing, large language models, optical character recognition, computer vision, figure digitization, and user-guided correction tools to recover structured information from text, tables, figures, and captions. Users can configure extraction stages, define dataset schemas, perform interventions on digitized figures, and export verified data for downstream analysis and machine learning. SALSA is designed to automate repetitive literature curation tasks while preserving oversight where expert judgment is required. By supporting customizable extraction workflows across diverse input types, the software provides a flexible framework for scalable, reliable data curation for materials research, and potentially across several disciplines. Users are responsible for ensuring that all inputs, extraction workflows, and downstream uses comply with applicable publisher agreements, copyright and licensing terms, institutional policies, and data-use requirements. --- ### Schematize: An Agentic System for Generating and Refining Information-Extraction Schemas for Legal Research Authors: Albert Sawczyn, Jakub Binkowski, Kamil Tagowski, Łukasz Augustyniak, Berenika Kaczmarek-Templin, Tomasz Kajdanowicz Published: 2026-09-01 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.22209v1 Empirical legal research often relies on turning research questions into structured data extracted from large collections of rulings and judgments. Designing the extraction schema and then extracting the data remain a manual, expertise-heavy bottleneck. We present schematize, an open-source multi-agent system that interactively turns a researcher's problem statement into a validated extraction schema that can later be used for autonomous extraction. Schematize couples (i) a clarification dialogue that elicits implicit expert intent, (ii) iterative schema generation, (iii) data-grounded refinement that tests the schema against documents, and (iv) chat-based post-editing. We evaluated the system with human legal professional, introducing our novel methodology, and schematize achieves top performance in most of tested configurations. While the system is designed to be domain-agnostic and applicable to any document collection, we tailor and evaluate it on legal research problems. We release schematize as a pip-installable Python package with full documentation. --- ### Replicating the Geometry of Emotion Representations in a Base Open-Weights Model Authors: Adam Hollowell Published: 2026-09-01 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.22208v1 Sofroniew et al. (2026) report that emotion concepts in Claude Sonnet 4.5 are represented as vectors whose geometry mirrors human affect psychology. We replicate the representational core of that study on the base pretrained model google/gemma-2-27b, inheriting every disclosed parameter, resolving unspecified steps by disclosed rules, and changing only the subject model. From 205,200 newly generated Claude Sonnet 4.5 stories matching the original corpus design, we extract 171 emotion vectors and recover the core results. The leading principal components form an affective circumplex (PC1 carries 26.7% of variance against the original study's ~27%, PC2 13.4% against ~14%), emotions cluster into similar intuitive families, and the geometry holds across a broad late-middle band. The valence axis aligns with human norms (r = 0.72, against 0.81) and is stable across scales and depth. Arousal aligns at r = 0.67 (against 0.66) but only at the full 171-emotion scale and late depth, so we do not classify it as replicated. Extending the original analysis, a 46-layer sweep locates a sharp seam at L22-26, where the geometry consolidates and the vocabulary readout becomes legible. An embedding-layer baseline finds much of the geometry already present in the static token embeddings, with arousal as the exception. On top-activating held-out text, the geometry predicts token-level co-activation at r = 0.907. At least 52% of vectors peak on structurally non-conceptual tokens, a measured floor for max-activation confounds. Even when a document contains the vector's emotion word, the peak lands on that word only 6.1% of the time. Because the subject is a base model and the stimuli are Claude-generated fiction, the recovered structure is a property of the pretrained representation of Claude-rendered emotion. The original's causal and assistant-facing analyses are out of scope. Code and data are released. --- ### An Implant-to-Wearable IR-UWB Transmitter-Receiver Architecture and Layered Protocol for High-Density Brain-Computer Interfaces Authors: G. D. Su, Y. Mo Published: 2026-09-01 Categories: eess.SP, cs.AI arXiv: https://arxiv.org/abs/2609.22207v1 High-rate neural telemetry requires an implant-towearable link whose circuit partition, waveform mapping, packet processing, and failure semantics are mutually consistent. This paper specifies a chip-oriented, one-way impulse-radio ultrawideband (IR-UWB) uplink comprising an implanted packet engine and free-running transmitter, a tissue-proxy channel, and a wearable mixed-signal receiver and digital baseband. --- ### Dissecting Training-Free Uncertainty Estimation in Multimodal Large Language Models Authors: Soroush Seifi, Vaggelis Dorovatas, Lin Li, Yarin Gal, Rahaf Aljundi Published: 2026-09-01 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.22206v1 Multimodal Large Language Models (MLLMs) have achieved remarkable performance across a wide range of multimodal tasks, yet understanding and quantifying their predictive uncertainty remains underexplored despite being central for safety critical applications. In this work, we present a systematic study of training-free uncertainty quantification strategies for MLLMs, categorizing existing approaches into three conceptual families: token-level methods, which operate directly in the text output space; verbalized methods, which elicit uncertainty estimates or abstention signals via natural language prompts; and semantic methods, which measure uncertainty in a semantic meaning space. We benchmark these strategies across multiple datasets, model families, generations, and scales, and find that no single family dominates: token-level entropy (at sampling temperature 1.0) wins on short answers, verbalized abstention on sentence-length responses, and semantic methods on long-form generation. --- ### Prediction of Nonlinear Oscillations in a Jumping Quarter-Car Model Using Reservoir Computing Authors: Masahisa Watanabe, Shiva Dixit, Nirmal Punetha, Swati Chauhan, Manish Dev Shirimali Published: 2026-09-01 Categories: cs.LG, nlin.CD arXiv: https://arxiv.org/abs/2609.22205v1 Reliable prediction of vehicle dynamics is essential for smart driving applications such as autonomous control and advanced driver-assistance systems. Off-road vehicles used in agricultural and construction settings are particularly prone to nonlinear behavior, including bifurcations and chaotic motion arising from intermittent loss of tire--road contact. Predicting such dynamics is challenging because it requires resolving both smooth nonlinearities and the discontinuous switching associated with contact loss. In this work, we investigate the feasibility of reservoir computing (RC) -- specifically an echo state network (ESN) -- for data-driven prediction of a jumping quarter-car model. The reservoir is trained on time-series data from a small number of points and evaluated on its ability to reconstruct bifurcation diagrams, phase-space attractors, and time trajectories across periodic and chaotic regimes. The trained reservoir qualitatively reproduces the period-doubling route to chaos, captures the geometric structure of periodic and chaotic attractors. These results demonstrate that reservoir computing is a feasible data-driven predictor of nonlinear dynamics in a practical, non-smooth vehicle system. --- ### Evaluating Personal Information Output from Conversational Interactions in Generative AI Systems Authors: Yosuke Seki, Hirotaka Tahara Published: 2026-09-01 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2609.22204v1 This exploratory pilot study evaluates the scope and perceived accuracy of personal information output from ongoing conversational interactions in generative AI systems using GPT-5.2 Instant and GPT-5.2 Thinking, categorized into three output types: Fact, Inference, and Confidence. Based on the evaluation results obtained from 15 Japanese participants, differences in model design have limited impact on personal information output tendencies. Compared with the Inference type, the Fact type shows a more conservative output pattern. Regarding attribute categories, the findings indicate that Core Personal attributes associated with identification are treated relatively conservatively, whereas Behavioral and Linguistic attributes show higher accuracy across both Fact and Inference outputs. Furthermore, Holistic Profile, Psychological and Cognitive, and Residual attributes are more readily inferred, even when not supported by explicit factual outputs. Notably, the lack of null outputs for these attributes in the Inference type suggests that such inferred profiles may be constructed from indirectly available contextual information. The findings may contribute to future discussions regarding privacy awareness and personal information inference in generative AI systems. ---