# Research Papers — 2026-05 · bundle page 91 of 326 > Full-text markdown of papers #4501–4550 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-05/page/91 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/90.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/92.md) ### Streaming Reinforcement Learning under Partial Observability with Real-Time Recurrent Learning Authors: Noah Farr, Aryaman Reddi, Carlo D'Eramo, Jan Peters Published: 2026-05-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.24709v2 Streaming reinforcement learning has emerged as an online learning paradigm that conforms to the restrictions of natural learning agents that process data incrementally, i.e. with a batch size of 1 and no replay buffer. While streaming RL has recently been shown to scale with deep function approximation with full observability, partially observable settings have remained out of reach. Truncated backpropagation through time collapses to a one-step gradient horizon under the streaming setting, and exact real-time recurrent learning is prohibitively expensive. We close this gap using recurrent trace units, a diagonal recurrent architecture that enables exact RTRL with linear time and memory complexity in the parameter count, and show that they integrate cleanly into existing streaming algorithms across both discrete and continuous control. On a MemoryChain diagnostic with chain lengths from 2 to 128, our method sustains performance where streaming TBPTT(1) baselines using feedforward, GRU, and RTU networks collapse. On five POPGym tasks and on partially observable MuJoCo continuous control, the streaming approach is competitive with batched PPO on POPGym and recovers a substantial fraction of batched performance on masked MuJoCo, despite using no replay buffer or batched updates. --- ### TS-Skill: A Benchmark for Evaluating Analytical Skills in Time-Series Question Answering Authors: Liying Han, Kang Yang, Oliver Wang, Jason Wu, Pengrui Quan, Gaofeng Dong, Ozan Baris Mulayim, Sizhe Ma, Yuyang Yuan, Dezhi Hong, Mario Berges, Mani Srivastava Published: 2026-05-23 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.24703v1 Large language models (LLMs) and time-series language models (TSLMs) are increasingly applied to time-series question answering (TSQA). Unlike text-only QA, TSQA requires models to ground answers in temporal signals whose patterns may occur at different scales, specific time locations, or across separated intervals. However, existing benchmarks are typically organized by task types or high-level reasoning categories, making it difficult to diagnose the underlying signal-level capabilities driving model performance. We introduce TS-Skill, a controlled benchmark for evaluating three composable analytical skills in TSQA: temporal scale selection (SK1), temporal localization (SK2), and cross-interval integration (SK3). TS-Skill provides timestamp-aware questions, broad domain coverage, and human-validated QA quality. To construct the benchmark at scale, we develop SKEvol, a skill-guided agentic framework that combines domain-aware time-series seed generation, skill-controlled question generation, metadata- and code-assisted answer construction, multi-phase signal-grounded verification, and human-in-the-loop curation. Experiments on ten state-of-the-art LLMs and TSLMs reveal substantial and uneven capability gaps across SK1-SK3. In particular, SK3 remains consistently challenging for non-agent models, whereas tool-augmented agents show a selective advantage on standalone SK3. These findings demonstrate that skill-level evaluation can uncover temporal reasoning failures that are obscured by aggregate TSQA scores. --- ### Do Image-Text Metrics Respect Semantic Invariances? Authors: Amit Agarwal, Hitesh Laxmichand Patel, Meizhu Liu, Jyotika Singh, Karan Dua, Hansa Meghwani, Matthew Rowe, Michael Avendi, Yassi Abbasi, Tao Sheng, Sujith Ravi, Dan Roth Published: 2026-05-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.24702v1 Reference-free image-to-text evaluators are now standard for scoring image-caption alignment, yet it is unclear whether they respect semantic invariances. We present an invariance probe on five popular evaluators (CLIPScore, PAC-S, UMIC, FLEUR, and a deterministic LLM judge) under semantics-preserving perturbations along three axes -- spatial (flips, context-preserving repositioning, light rotations), object (scale, category), and socio-linguistic framing (cultural/economic adjectives with neutral and length-matched controls). Across curated slices of three detection datasets and three caption evaluation suites, we find consistent non-semantic sensitivities, where benign spatial edits and simple phrasing changes shift scores by $\approx$6--9\% on average, and for systems separated by just 0.7\%, these shifts can cause ranking flips in up to $\sim$37\% of cases, particularly under spatial changes. A small human study also supports this finding and confirms that annotators generally judge perturbed pairs as equally correct, so these shifts reflect metric behavior rather than semantic change. We further propose invariance-calibrated scoring, a post-hoc adjustment that roughly halves median absolute sensitivity while retaining correlation with learned caption evaluators. --- ### SRUG: Shadow-Guided Relightable Urban Scene with Generation Model Authors: Yonghao Zhao, Zexin Yin, Jian Yang, Beibei Wang, Jin Xie Published: 2026-05-23 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2605.24700v3 Creating relightable urban scenes from images or videos is widely useful but highly ill-posed. Urban environments are typically unbounded and extend beyond the visible regions. As a result, many portions of the scene remain unobserved, yet these invisible regions can cast shadows onto visible areas. Reasonably modeling shadows cast by such invisible regions is challenging and poses a significant obstacle to creating relightable urban scenes. At the same time, sparse input views and complex illumination conditions further complicate relighting, as they introduce severe ambiguities in material decomposition. In this paper, we propose Shadow-guided Relightable Urban Scene with Generation model (SRUG), a novel framework designed to address relighting challenges in urban scenes. SRUG leverages shadows to guide a 3D completion model for recovering the geometry of invisible regions, promoting the synthesis of physically reasonable shadows. In addition, SRUG employs an iterative material decomposition scheme that applies the large material model (LMM) to provide material supervision and iteratively decompose the scene's material properties, enabling robust material decomposition. Building upon these components, we introduce a physically-based lighting model that captures the complex illumination of urban scenes and supports reliable relighting. Extensive quantitative evaluations and visual comparisons demonstrate that our method outperforms existing approaches in both novel view synthesis and relighting tasks. --- ### MDIA: A Multi-Agent Diagnostic Intelligence Pipeline on HealthBench Professional Authors: Roberto Cruz, David Rey-Blanco Published: 2026-05-23 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.24699v1 Most reported gains on agentic-LLM clinical benchmarks are often attributed to prompt engineering, yet our results suggest that larger improvements can come from architectural and engine-level design. We present MDIA, a Multi-agent Diagnostic Intelligence Agent implemented as a 7-node specialty-routed clinical reasoning graph, on the full HealthBench Professional benchmark (n = 525), on a non-fine-tuned LLM. MDIA achieves 0.6272 under OpenAI's GPT-5.4-2026-03-05, which is +3.72 pp above the performance of OpenAI's ChatGPT for Clinicians. The experimental work shows that performance lift is attributable to system architecture: specialty routing, multi-turn context preservation, drug-state safety gating, site-filtered search, length-aware synthesis, and engine-level reliability. These findings support the view that agentic clinical benchmark performance is shaped both by the underlying foundation model and the orchestration architecture. Nevertheless, we also noticed notable differences when using other models as a grader; in particular, when using Gemini 2.5 Pro, MDIA scored 0.6585, which suggests that the choice of grader is a source of variability. Robust evaluation of LLMs would therefore require assessment across several independent grader models. --- ### The Path Matters: Learning a Token-Commitment Policy for Diffusion Language Models Authors: Bohang Sun, Max Zhu, Francesco Caso, Jindong Gu, Junchi Yu, Philip Torr, Pietro Liò, Jialin Yu Published: 2026-05-23 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.24697v1 Diffusion large language models promise faster generation by refining many token positions in parallel, but this parallelism introduces a hidden control problem: which proposed tokens should be transferred into the partially decoded sequence at each step? We refer to this decision as token commitment. Existing frozen-generator decoders largely rely on hand-designed confidence rules or block-specific acceptance filters. We argue that token commitment can instead be learned as a reusable trace-state policy. We introduce TraceLock, a lightweight plug-in controller that instantiates this policy for a frozen diffusion language model. Since oracle commitment times are unavailable, TraceLock derives self-supervision from future stability: at decoding step t, a proposed token for position i is labeled stable if it matches the final token at position i after the full decoding trace completes. The controller scores variable-length trace states and decides which active token proposals should be committed to the partially decoded sequence. Once trained for a given frozen backbone, the controller can be deployed across local-window widths, generation lengths, and step budgets without retraining or per-setting calibration. Experiments on question answering, mathematical reasoning, and code generation show that TraceLock improves the quality-step tradeoff over heuristic and learned baselines, with particularly stable behavior under cross-setting deployment. Diagnostic analyses show that its decisions are not reducible to scalar confidence, suggesting that frozen diffusion language models expose a learnable space of commitment trajectories beyond confidence-based decoding. Code is available at https://github.com/BobSun98/TraceLock. --- ### Stream Assembly Is an Uncontrolled Treatment in Streaming Intrusion-Detection Benchmarks Authors: Michel A. Youssef Published: 2026-05-23 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2605.24696v3 Streaming intrusion-detection studies assemble evaluation streams from network captures by interleaving capture days, pooling captures, or replaying records round robin. We show on two benchmarks that this assembly is an uncontrolled experimental treatment changing what the evaluation measures. On CICIDS2017, reordering an identical record multiset under a fixed positional 70/15/15 split yields held-out samples sharing only 32.5% of their records, at prevalences of 68.235% and 25.2396% (42.9954 points apart), and reverses the measured ordering of the two deterministic scorers. Restricting both arms to the 78000 records both held out removes the reversal, so it is attributable to which records the assembly hands to the test set, not to the order in which the detector saw its history. That attribution assumes that history contributes no more on the records the arms do not share than on those they do. On LITNET-2020, pooling three temporally disjoint captures reports one 6.4982% operating point, the equal-weight mean of per-capture held-out prevalences from 0.176% to 15.7747%, an identity presented as an audit check. The evaluated detector's reset posterior P(r_t=0) equals the hazard rate exactly below the run-length cap, though evaluations spend nearly all their length at or beyond it, and its evaluated score is a function of P(r<=5), not of P(r=0). Its deployed max composition ranks worse than its tail term alone (0.103477 AP, 0.302658 AUC-ROC) because the auxiliary branch is inverted (AUC-ROC 0.281890) and the maximum lets it set the score wherever the tail is small. With evaluated records and fitted model fixed, changing only the accompanying batch moves the ECOD reference implementation's AUC-PR by 0.003063, so published ECOD numbers are not comparable across studies scoring different batches. Every measured value traces to an archived, hash-verified run manifest. --- ### CALIBURN: Operationally Calibrated Streaming Intrusion Detection with Regime-Dependent Conformal Risk Control Authors: Michel A. Youssef Published: 2026-05-23 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2605.24696v2 Streaming intrusion detection systems must process flows continuously under bounded memory, yet most leave alerting-threshold selection as a post-hoc tuning problem incompatible with production, where operators commit in advance to alert budgets, misclassification costs, and Service Level Objectives. We present CALIBURN, a streaming alerting pipeline that derives its decision threshold from these operational inputs rather than a label-dependent search. CALIBURN composes five layers on one streaming substrate: truncated Bayesian online change-point detection; isotonic calibration of the posterior to a conditional attack probability; cost-sensitive thresholding from operator costs; a Conformal Risk Control (CRC) wrapper mapping an alert budget alpha to a false-positive-bounded threshold under exchangeability; and multi-window burn-rate alerting from Site Reliability Engineering. Each layer is established; the contribution is the integration and a falsifiable finding about it: the behaviour of calibration and conformal risk control is strongly regime-dependent across attack prevalence. Across three regimes -- LITNET-2020 (5.2%), CICIDS2017 (22%), UNSW-NB15 (64%) -- CALIBURN reaches AUC-PR 0.943 in the rare-attack regime it targets, beating the best streaming baseline by 2.21x and the best batch reference by 4.12x, with isotonic calibration cutting Brier score 30%; it stays strongest among streaming methods at moderate prevalence; and all converge to the prevalence floor under base-rate inversion. A TTL-feature ablation shows this high-prevalence collapse is intrinsic to streaming, not a dataset artifact. We further identify two mechanisms -- a theoretical CRC overshoot 2B/(n0+1) and an empirical-density degeneracy -- collapsing conformal alerting at very small alpha, and propose both as pre-deployment checks. Code and artifacts: Apache 2.0, Zenodo DOI 10.5281/zenodo.20074590. --- ### CP-Agent: A Calibrated Risk-Controlled Agent for Feedback-Driven Competitive Programming Authors: Peisong Wang, Bowen Liu, Zehua Li, Yuyao Wang, Zhiwei Ma, Yuhan Li, Jia Li Published: 2026-05-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.24693v1 Large language models still struggle with contest-level programming, while many agentic remedies rely on massive inference-time sampling or expensive multi-stage post-training. We study when execution feedback reliably helps an LLM CP solver and which mechanisms govern the gains. We model feedback-driven solving as a calibrated stopped process and identify three quantities: false-admission risk, program-level evidence against bad programs, and the active-state success hazard. Under held-out trace calibration and selection from a pre-declared finite controller manifest, the resulting structural certificate lower-bounds the clean success probability before false admission. We instantiate mechanisms targeting these quantities as Dual-Granularity Verification, Test Augmentation, and Experience-Driven Self-Evolving, yielding CP-Agent. Without updating any parameters, CP-Agent raises Pass@1 from 25.8\% to 48.5\% on LiveCodeBench Pro and improves Refine@5 by 11.0\% on ICPC-Eval. Across three LLM backbones, CP-Agent lies on the cost--accuracy efficiency frontier, and ablations show that each component primarily affects its corresponding certificate quantity. --- ### AdaFuse-Det: Adaptive Cross-Modal Fusion of Event Cameras for Robust Object Detection in Low-Light RGB Imagery Authors: Raju Imandi, Chethana B, Bharatesh Chakravarthi, Yong-Guk Kim, Manipriya S, Pavan Kumar B N Published: 2026-05-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.24691v1 Detecting objects reliably under extreme low-light conditions is an open problem in computer vision, with practical urgency in applications ranging from nighttime surveillance to search-and-rescue robotics. Conventional RGB cameras degrade sharply at low photon flux, while event cameras which record asynchronous per-pixel brightness changes at microsecond resolution and high dynamic range provide complementary structural cues that are largely illumination-invariant. We present AdaFuse-Det, a dual-stream framework that fuses CLAHE-enhanced RGB frames with voxelized event tensors through an Adaptive Cross-Modal Fusion (ACMF) module grounded in minimum-variance linear estimation theory. We formally show that the learned attention map asymptotically recovers the Gauss-Markov optimal fusion weights, and establish event conservation and temporal resolution bounds for the voxelization stage. On the LLE-VOS benchmark, AdaFuse-Det achieves a Recall of $65.54\%$, Precision of $53.85\%$, and F1-Score of $59.12\%$ under severe illumination degradation, outperforming single-modality detectors in recall by a margin that reflects the theoretically predicted illumination-adaptation behavior. --- ### Sum of Costs Diffusion with Dynamic Guidance for Motion Planning Authors: Aysu Aylin Kaplan, Özgür Erkent Published: 2026-05-23 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2605.24690v1 The motion planning problem for robotic manipulation can be addressed through classical or deep learning approaches. Existing methods face significant challenges in generalizing to diverse settings. In this study, we present a method with high generalization capability that generates collision-free trajectories using diffusion models where the denoising process is guided by the gradient of the total collision cost. We are also presenting a dynamic approach for choosing start step of the gradient guidance. Experimental results demonstrate that guiding the diffusion model dynamically with the sum of collision costs offers more robust performance by overcoming the generalization issues faced by competing methods. The proposed model demonstrates its effectiveness by achieving the highest performance on diverse test settings in M$π$nets\ dataset among the compared methods. --- ### HoloFair: Unified T2I Fairness Evaluation and Fair-GRPO Debiasing Authors: Ruyi Chen, Lu Zhou, Xiaogang Xu, Chiyu Zhang, Jiafei Wu, Liming Fang Published: 2026-05-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.24687v1 Text-to-Image (T2I) models have made significant strides in visual realism and semantic consistency, yet they often perpetuate and amplify societal biases. Existing evaluation methods typically address only single-dimensional biases, lacking perspectives to uncover model biases at social-related deeper semantic levels. We introduce HoloFair, a comprehensive benchmark framework for multidimensional demographic bias analysis. Built upon our large-scale fairness-oriented dataset and the SpaFreq (Spatial-Frequency) attribute classifier, this framework proposes the Multi-attribute, Group-wise Bias Index (MGBI) metric, designed to assess both intrinsic diversity and conditional biases. Beyond evaluation, we further introduce Fair-GRPO, a reinforcement-learning-based debiasing method that alters the distribution of generative models through a designed multi-objective reward function. E.g., experiments on the SD3.5-Medium model demonstrate that Fair-GRPO significantly improves multidimensional fairness while maintaining high image quality. We also analyze potential reward hacking phenomena and provide corresponding mitigation strategies. Code and dataset are available at https://github.com/1059684669/HoloFair --- ### Emotional intelligence in large language models is fragmented across perception, cognition, and interaction Authors: Minghao Lv, Lu Chen, Enchang Zhang, Anji Zhou, Xiaoran Xue, Hanyi Zhang, Fenghua Tang, Zhuo Rachel Han, Mengyue Wu Published: 2026-05-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.24686v1 As large language models (LLMs) are increasingly integrated into emotionally sensitive domains, the structural integrity of their emotional intelligence (EI) becomes a critical frontier for safety and alignment. Current benchmarks often conflate superficial politeness with deep affective reasoning, failing to distinguish between perceptual accuracy and interactive efficacy. Here, we introduce FACET (Functional Affective Competence and Empathy Test), a psychometrically grounded framework comprising 480 expert-crafted items. Unlike previous metrics, FACET is theoretically anchored in the Mayer-Salovey-Caruso four-branch ability model, operationalizing EI through perception, facilitation, understanding, and management of emotions. Through an evaluation of nine frontier models (including GPT-5, Claude-Sonnet-4), we demonstrate that emotional intelligence is not a monolithic capability but is fragmented across cognitive and interactive dimensions. While frontier models demonstrate robust proficiency in objective emotion recognition and social reasoning, this does not consistently translate to interactive success. We categorize these discrepancies into three distinct performance profiles: cognitive-dominant, interactive-dominant, and context-dependent. These typologies indicate that emotional skills do not scale uniformly with general intelligence or model size; rather, they are shaped by specific alignment paradigms. Notably, we identify hidden emotion recognition as a universal performance bottleneck across all architectures. Our results suggest that current RLHF processes may optimize for "stochastic empathy", a statistical mimicry of emotional syntax, at the expense of integrated affective reasoning. These findings challenge the assumption of linear emotional scaling and provide a rigorous roadmap for developing socially aware agents capable of genuine clinical resonance. --- ### Beyond the Aggregation Dilemma: Prior-Retaining Decoupled Learning for Multimodal Graphs Authors: Hao Yan, Xuanru Wang, Jun Yin, Shirui Pan, Senzhang Wang, Chengqi Zhang Published: 2026-05-23 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.24684v1 Multimodal Attributed Graph Learning (MAGL) integrates intrinsic node attributes with structural topology via graph aggregation. However, as pretrained encoders evolve into Large Foundation Models (LFMs), the landscape of MAGL fundamentally shifts: under high-confidence LFM priors, mandatory aggregation introduces topological noise that overwhelms discriminative signals, triggering a counter-intuitive performance inversion where sophisticated MAGL architectures underperform simple topology-agnostic MLPs. Through systematic empirical and theoretical analysis, we identify that this inversion stems from a fundamental aggregation dilemma characterized by two concurrent pathologies: (1) Representational Pathology (SNR Degradation) - mandatory aggregation dilutes robust intrinsic features with topological noise, causing the noise penalty to outweigh its collaborative benefit; and (2) Optimization Pathology (Gradient Starvation) - topological aggregation attenuates gradient flow, while a shared task loss causes dominant modalities to prematurely suppress weaker ones. To resolve this dilemma, we propose SUPRA (Shared-Unique Prior-Retaining Architecture), a decoupled dual-pathway paradigm. SUPRA processes modality-specific features through topology-agnostic MLPs while capturing structural synergy via a lightweight shared GNN, with auxiliary deep supervision counteracting gradient starvation. Extensive evaluations demonstrate that SUPRA achieves state-of-the-art performance while requiring 3.5x lower peak GPU memory and up to 4.4x faster training time than Multimodal Graph Transformers. --- ### Mix-MoE: Improving Multilingual Machine Translation of Large Language Models through Mixed MoEs Authors: Bo Li, Tianyu Dong, Shaolin Zhu, Deyi Xiong Published: 2026-05-23 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.24681v1 Large Language Models (LLMs) have shown great promise in multilingual machine translation (MT), even with limited bilingual supervision. However, fine-tuning LLMs with parallel corpora presents major challenges, namely parameter interference. To address these issues, we propose Mix-MoE, a mixed Mixture-of-Experts framework designed to train LLMs for multilingual MT. Our framework operates in two distinct stages: (1) post-pretraining with MoE on monolingual corpora, and (2) post-pretraining with MoE on parallel corpora. Crucially, we divide the MoE layers into two specialized groups: Language Model Experts (LM Experts) and Machine Translation Experts (MT Experts). LM Experts are designed to capture and retain the monolingual knowledge learned by the pre-trained LLM. MT Experts, on the other hand, are specifically trained to acquire and store bilingual translation knowledge. Furthermore, to facilitate effective interaction between these specialized experts and leverage potential underlying structural patterns in text, we introduce a routing mechanism enhanced by Fourier Transform features derived from model representations. The experimental results demonstrate that Mix-MoE excels in multilingual MT, significantly outperforming existing baselines and showing notable progress in mitigating parameter interference. --- ### Trajectory-Based Difficulty Scoring for Reliable Learning on Tabular Data Authors: Tomer Lavi, Bracha Shapira, Nadav Rappoport Published: 2026-05-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.24680v1 Gradient-boosted trees achieve strong performance on tabular data, yet often leave a long tail of poorly predicted instances. We introduce a Trajectory-based Difficulty Score (TDS), an instance-level difficulty estimator for boosted ensembles derived from per-tree cumulative prediction trajectories. For each instance, we compute interpretable trajectory descriptors (e.g., variance, oscillation peaks, sign switches, and tail stability) and train a lightweight regression model to predict held-out loss. An empirical CDF calibrates the resulting signal into a score in $(0,1)$ that supports ranking hard cases. Across diverse tabular benchmarks and ensemble sizes, TDS exhibits strong rank correlation with error and outperforms established instance-hardness and uncertainty baselines on classification, while remaining competitive on regression. We then show how a single difficulty signal improves multiple data mining workflows: difficulty-driven active learning for label-efficient training, difficulty-thresholded selective prediction for improved risk-coverage trade-offs, and TDS-stratified (Mondrian) conformal prediction for more uniform conditional coverage. Finally, clustering high-TDS instances using SHAP attributions reveals coherent failure modes characterized by compact feature-value ranges, supporting error analysis and targeted data acquisition. --- ### MindAdapter: Few-Shot Parameter-Efficient Residual Calibration of Cross-Subject Brain-to-Visual Decoding Models Authors: Jiaxiang Liu, Jiawei Du, Xupeng Chen, Guoqi Li, Jiang Cai, Simon Fong, Mingkun Xu Published: 2026-05-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.24679v1 Cross-subject brain-to-visual decoding remains a core challenge in brain-computer interfaces due to severe inter-individual variability that induces systematic subject-specific functional misalignment. To address this issue, we propose MindAdapter, a parameter-efficient few-shot calibration framework for pretrained brain-to-visual decoding models. MindAdapter adopts a decoupled linear-residual cascade alignment paradigm by freezing a pretrained explicit brain functional alignment backbone (coarse) and introducing a lightweight nonlinear residual adapter (fine), thereby disentangling global cross-subject correspondence from subject-specific residual corrections for fine-grained spatial and semantic calibration. To further preserve global representational stability, we design a topology-anchored dual-stream manifold constraint, where a small set of shared stimuli serves as topological pins with voxel-level paired supervision, while a semantic stream enforces consistency through a frozen vision-language decoder on unpaired brain data. Together, MindAdapter efficiently injects subject-specific corrections while maintaining the global representational geometry learned during pretraining. Experiments on the Natural Scenes Dataset (NSD) demonstrate that MindAdapter substantially improves cross-subject visual reconstruction and retrieval accuracy using only a few shared stimuli, offering a practical and data-efficient solution for personalized brain-to-visual decoding. --- ### Exploration of Perceptual Speech Features for Clinical Decision-Support in Mental Health Care Authors: Vassilis Lyberatos, Edmund G. Dervakos, Eleni Adamidi, Athanasios Voulodimos, Giorgos Stamou Published: 2026-05-23 Categories: cs.AI, cs.CL, cs.SD arXiv: https://arxiv.org/abs/2605.24678v2 Speech and language technologies offer valuable opportunities for supporting mental health assessment through objective and interpretable cues. We present a systematic feature-based analysis framework leveraging perceptually grounded acoustic and linguistic characteristics, including prosody, vocal quality, semantic coherence, syntactic structure, and sarcasm. Using statistical analysis and interpretable machine learning (XGBoost with SHAP and LIME), we examine associations between speech features and validated symptom measures of depression, anxiety, and ADHD. Evaluated on both controlled benchmark datasets (StressID, DAIC-WOZ, Androids, EATD) and a real-world clinical dataset, the framework reveals stable and consistent relationships between symptom severity and vocal irregularities (e.g., shimmer, jitter), lexical-syntactic patterns, and affective tone. An ablation study conducted across all datasets further identifies the most informative feature groups. This work explores a transparent and clinically interpretable approach to speech-based mental health analysis. --- ### VaaWIT: Visual-Aware Adaptation of Large Language Models for Multilingual Web Image Translation Authors: Bo Li, Ronghao Chen, Ningyuan Deng, Huacan Wang, Shaolin Zhu, Lijie Wen Published: 2026-05-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.24675v1 Translating text embedded in Web images is crucial for improving content accessibility and cross-lingual information retrieval, particularly within social media and e-commerce domains. Although Large Vision-Language Models (LVLMs) have advanced multimodal understanding, applying them to Web image translation remains challenging due to the visual representation gap: standard encoders often prioritize high-level semantics over the fine-grained visual details required for recognizing diverse character morphologies. To address this challenge, we propose VaaWIT, an end-to-end framework that adapts Large Language Models for multilingual Web image translation. The framework introduces two key technical contributions: (1) a Dual-Stream Attention Module (DSAM), which facilitates bidirectional interaction between multilingual semantic features and detailed visual representations, thereby synthesizing unified features robust to textual variations; and (2) a Visual-Aware Adapter (VAA), a parameter-efficient fine-tuning strategy that dynamically injects these fused visual cues into the frozen LLM backbone. This design enables the model to align the visual context with linguistic reasoning effectively while minimizing computational costs. Extensive experiments on eight tasks on three public benchmarks demonstrate that VaaWIT significantly outperforms state-of-the-art (SOTA) open-source baselines and achieves competitive performance against proprietary models. These results validate the efficacy of integrating fine-grained visual perception into LLMs for complex Web content analysis. --- ### Reasoning to Align: Implicit Reasoning in Diffusion Transformers for Video Editing Authors: Yan Li, Lin Liu, Xiaopeng Zhang, Qi Tian Published: 2026-05-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.24674v1 Instruction-based video editing requires transforming a source video according to a natural-language instruction while preserving irrelevant content and remaining temporally coherent. We argue that existing Diffusion Transformer (DiT) editors struggle with this task for two structural reasons. First, conditioning signals are fed undifferentiated into all transformer blocks, forcing a single token stream to encode both global editing intent and fine-grained visual evidence. Second, the cross-attention patterns that govern the edit are supervised only indirectly through pixel-level reconstruction, leaving the model's internal reasoning process under-constrained. To address both limitations, we propose RVEDiT, an implicit Reasoning Video Editing DiT framework built around two complementary components. The first, Granularity-Routed Token Conditioning, introduces learnable editing tokens distilled from a multimodal LLM and routes them to shallow blocks, while reserving native visual and textual tokens for deeper blocks, thereby inducing a coarse-to-fine editing process inside the backbone. The second, Reference-Anchored Attention Alignment, employs a parameter-sharing reference branch during training and maximizes the mutual information between the attention features of the editing and reference branches, regularizing the model's internal reasoning without incurring any additional inference cost. Experiments on standard instruction-based video editing benchmarks show that RVEDiT consistently outperforms state-of-the-art baselines, with particularly strong gains on localized and compositional edits. --- ### Affinity Graph Connectivity in Convex Clustering Authors: Sam Rosen, Jason Xu Published: 2026-05-23 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2605.24673v1 We generalize finite-sample bounds for convex clustering to the setting where affinity weights appearing in the objective correspond to a general connected graph. These bounds and their analysis lead to a better understanding of clustering behavior under various implied connectivity structures behind the data and to new rates of convergence for centroid recovery. The new theoretical framework is based on random walks, which allow application of concentration inequalities related to random graph models, and formalizes the relationship between the clustering performance and the connectivity of the graph structures. Through the form of the bound and empirical results, we argue proper tuning of hyperparameters to convex clustering problems should also include tuning of input affinity weights. --- ### When Mean CE Fails: Median CE Can Better Track Language Model Quality Authors: Hao Guo, Simon Dennis, Rivaan Patil, Kevin Shabahang Published: 2026-05-23 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.24667v1 Mean cross-entropy is the standard validation metric for language models, but it can fail to track model quality during training. We examine this in two common scenarios. First, in Qwen2.5-1.5B SFT on synthetic fact-learning, we find that mean CE rises substantially after the initial learning phase while held-out fact-recall accuracy remains near its peak. Second, we find that in top-K distillation on TinyStories, decreasing K improves median CE while worsening mean CE; the Top-5 student attains the highest LLM-judge score and crosses below its teacher on median CE, despite having the worst mean CE. In both cases, median CE correlates much more closely with task performance than does mean CE. Analyzing how bulk and tail percentile CE move during training reveals that training reshapes the empirical per-token CE distribution. In top-K distillation, smaller K yields a distribution with more mass at both extremes, decreasing the median and increasing the mean. In Qwen SFT, the bulk saturates quickly while the tail extends in the latter half of training. In both, the task-evaluation metric appears more sensitive to the bulk than to the tail. Practically, we recommend reporting a small set of percentile CE summaries alongside the mean, and using concordance among them as a tool to keep track of distribution reshaping, as well as a low-cost diagnostic for when mean and median CE disagree on model selection. --- ### Finding Koopman Invariant Subspaces via Personalized PageRank Authors: Hyukpyo Hong, Qin Li, Matthew J. Colbrook, Hanbaek Lyu Published: 2026-05-23 Categories: math.DS, math.NA, stat.ML arXiv: https://arxiv.org/abs/2605.24666v3 Selecting a finite dictionary of observables whose span is Koopman-invariant is a central challenge in data-driven Koopman operator approximation. We address this problem by exploiting zero-block structure in Extended Dynamic Mode Decomposition (EDMD) matrices. We show that any sub-dictionary whose span is Koopman-invariant induces an exact zero block in the EDMD matrix, even for finite data. We then show that such blocks can be detected by applying PageRank to a row-normalized EDMD matrix constructed from a large initial dictionary. The theory extends to approximately invariant subspaces and yields stronger guarantees for personalized PageRank (PPR) when the seed observables lie inside the target block and reach all observables in that block. Combining EDMD concentration bounds with PageRank perturbation theory gives end-to-end detection guarantees with $O(1/\sqrt{M})$ finite-sample scaling and explicit constants. More generally, without assuming an invariant subspace exists, high PPR mass on a sub-dictionary controls discounted multi-step leakage from the seed observables. Numerical experiments on the Duffing oscillator, Van der Pol oscillator, Lorenz system, and a three-well Ramachandran potential suggest that the method identifies compact, interpretable dictionaries with accurate predictions. --- ### CyBOKClaw: Human-in-the-Loop CyBOK Mapping for Cybersecurity Curriculum Authors: Yan Lin Aung, Kevin Togbe Published: 2026-05-23 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2605.24663v1 This paper presents CyBOKClaw, an interpretable human-in-the-loop retrieval framework for mapping cybersecurity keywords or phrases (KWoPs) to the Cyber Security Body of Knowledge (CyBOK). Rather than treating the task as strict exact classification, the framework is designed as a top-k candidate generator for expert review. It combines query normalization, curated term expansion, concept-level boosts, topic-description enrichment, and domain-sensitive ranking rules. Because educational KWoPs are often broad, ambiguous, and only approximately aligned with CyBOK terminology, strict exact matching provides only a partial account of practical utility. We therefore evaluate the framework using both structural retrieval metrics and an expert-guided top-5 usefulness metric, ECA-5 (Exact or Closest Acceptable Match at top-5), which records whether the returned candidates contain at least one mapping that an expert would judge exact or accept as the nearest practical CyBOK placement. On the development dataset, CyBOKClaw achieves 64.73% EXA-5 (Exact Match at top-5), 84.18% structural semantic alignment, and 91.88% ECA-5; on the validation dataset, it achieves 81.19% EXA-5, 93.32% structural semantic alignment, and 98.00% ECA-5. These results show that expert-guided top-k usefulness provides a more faithful account of practical CyBOK mapping utility than exact structural matching alone, and that CyBOKClaw is effective as a CyBOK-specific expert-support retrieval system. --- ### Measuring Reasoning Quality in LLMs: A Multi-Dimensional Behavioral Framework Authors: Ali Şenol, Garima Agrawal, Huan Liu Published: 2026-05-23 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.24661v4 Despite remarkable progress on reasoning benchmarks, current LLM evaluation practice remains anchored to final-answer correctness, providing limited insight into how models reason, how reliably they behave under contextual variation, or how efficiently they reach conclusions. This paper proposes a unified multi-dimensional framework for measuring LLM reasoning quality from a behavioral perspective, operationalizing six theoretically grounded dimensions rooted in cognitive science: Correctness (CQ), Consistency (CS), Robustness (RS), Local Logical Coherence (LS), Efficiency (ES), and Stability (SS). The framework introduces deployment-aware aggregation, enabling context-specific model selection beyond accuracy-based leaderboards. Experiments across multiple LLMs and benchmarks reveal behaviors systematically concealed by single-metric evaluation, including the orthogonality of local logical coherence and correctness, deployment-context-dependent ranking inversions, and non-trivial dimensional profiles in small locally-deployed models. Discriminant validity analysis confirms that the proposed dimensions capture largely non-redundant signals. The resulting pipeline provides a foundation for diagnosing LLM reasoning behavior across deployment contexts, with domain-specific validation as a direction for future work. --- ### Measuring Reasoning Quality in LLMs: A Multi-Dimensional Behavioral Framework Authors: Ali Şenol, Garima Agrawal, Huan Liu Published: 2026-05-23 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.24661v3 Despite remarkable progress on reasoning benchmarks, current LLM evaluation practice remains anchored to final-answer correctness, providing limited insight into how models reason, how reliably they behave under contextual variation, or how efficiently they reach conclusions. This paper proposes a unified multi-dimensional framework for measuring LLM reasoning quality from a behavioral perspective, operationalizing six theoretically grounded dimensions rooted in cognitive science: Correctness (CQ), Consistency (CS), Robustness (RS), Local Logical Coherence (LS), Efficiency (ES), and Stability (SS). The framework introduces deployment-aware aggregation, enabling context-specific model selection beyond accuracy-based leaderboards. Experiments across multiple LLMs and benchmarks reveal behaviors systematically concealed by single-metric evaluation, including the orthogonality of local logical coherence and correctness, deployment-context-dependent ranking inversions, and non-trivial dimensional profiles in small locally-deployed models. Discriminant validity analysis confirms that the proposed dimensions capture largely non-redundant signals. The resulting pipeline provides a foundation for diagnosing LLM reasoning behavior across deployment contexts, with domain-specific validation as a direction for future work. --- ### How Many Tools Should an LLM Agent See? A Chance-Corrected Answer Authors: Vyzantinos Repantis, Ameya Gawde, Harshvardhan Singh, Joey Blackwell Published: 2026-05-23 Categories: cs.IR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.24660v2 Before an LLM agent can use a tool, a retrieval system must decide which candidate tools to show to the agent. How long should that shortlist be? Show too many tools and the model struggles to choose. Show too few and the correct tool may not appear. Most systems apply a fixed shortlist size to every query, but no standard metric exists to evaluate whether that size was appropriate. We treat the number of tools shown to an LLM agent as the object of evaluation and we apply Bits-over-Random (BoR), a chance-corrected metric that asks whether success at a given depth is better than what random selection would achieve at that same depth. We evaluate BoR across three tool-selection benchmarks, multiple scorers, and registries ranging from 20 to 3,251 tools. We then turn the same principle into a reinforcement learning (RL) reward for choosing tool shortlist depth per query. The RL agent is deliberately simple, serving as a probe of the metric rather than a proposed system. As the shortlist grows, random chance of including the correct tool rises, so the reward naturally decreases, reducing the need for an engineered depth penalty. On BFCL (370 tools), the learned policy nearly matches the coverage of showing 50 tools ($90.3\%$ vs $90.8\%$) while presenting only 7 on average. On ToolBench (3,251 tools), a fixed shortlist of 5 tools achieves higher aggregate coverage ($64.7\%$ vs $61.9\%$) but finds nothing on hard queries (correct tool ranked 6th-20th). The BoR agent finds $16.7\%$ on those same queries by searching deeper. Downstream validation with Claude Sonnet 4.6 indicates that shorter adaptive lists also improve the LLM's ability to select the right tool: $93.1\%$ versus $87.1\%$ when always shown 5 tools, widening to $76.8\%$ vs $60.9\%$ on medium-difficulty queries where the correct tool is present but not ranked first. --- ### IterInject: Indirect Prompt Injection Against LLM Agents via Feedback-Guided Iterative Optimization Authors: Zixuan Chen, Jiaxiang Chen, Li Luo, Ke Xu, Xiaoxiang Huang, Tanfeng Sun, Xinghao Jiang Published: 2026-05-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.24659v1 LLM-based agents are increasingly deployed for complex tasks requiring planning, tool use, and interaction with external services. Their reliance on untrusted external content exposes them to indirect prompt injection (IPI), in which adversarial instructions embedded in retrieved data hijack agent behavior. Existing attacks rely on static payloads that cannot adapt to agent-specific defenses; even recent adaptive methods lack structured feedback to guide optimization. We introduce \oursys, a feedback-guided iterative framework that closes the loop between injection, diagnosis, and refinement: a rule-based diagnoser produces structured outcome labels with behavioral descriptions, and an LLM-based optimizer refines payloads conditioned on the full optimization history. A synthesis step generates new disguise seeds from failure patterns, enabling the strategy space to self-evolve. On AgentDojo and InjectAgent, \oursys substantially outperforms static baselines and existing adaptive methods across four victim models. Extension experiments on Claude Code, a production-grade coding agent with layered defenses, show that optimized payloads achieve full success on 5 of 9 targets; even those that resist full exploitation exhibit measurable improvement from iterative refinement. We further present a mechanistic analysis of IPI, identifying an attention-mediated threshold mechanism in mid-to-late layers; three causal interventions validate this finding and point to concrete defense directions. --- ### WLNO: Wavelet-Laplace Neural Operator for Solving Partial Differential Equations Authors: Muhammad Abid, Arth Sojitra, Omer San Published: 2026-05-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.24658v1 This work introduces the Wavelet-Laplace Neural Operator (WLNO), a novel neural operator that fuses Haar wavelet multi-scale spatial decomposition with the Laplace-domain pole-residue formulation of the Laplace Neural Operator (LNO). While LNO captures transient and steady-state dynamics through learnable system poles and residues, it lacks an explicit mechanism for extracting spatially localized multi-scale features inherent in complex PDE solutions. WLNO addresses this by augmenting the LNO core with a parallel single-level Haar discrete wavelet transform (DWT) branch that decomposes the lifted feature map into four frequency subbands: approximation (LL), horizontal detail (LH), vertical detail (HL), and diagonal detail (HH) and applies independent learned $1\times1$ convolutions to each subband before reconstruction via the inverse DWT. The two branches are fused through a learnable sigmoid-gated weight $α_\mathrm{wav}$, initialized to give a small initial contribution to the wavelet branch, allowing the model to adaptively balance Laplace-domain dynamics against spatial multi-scale features throughout training. WLNO is evaluated against LNO on five benchmark PDE problems using identical hyperparameters, training data, and evaluation protocols: the diffusion equation, the Burgers equation, the reaction-diffusion system, Darcy flow, and the two-dimensional Navier-Stokes equation. WLNO consistently outperforms LNO on all five problems, with the most pronounced improvement on problems with strong spatial multi-scale structure, such as the Burgers equation with sharp shock fronts and the Navier-Stokes equation with coherent vortical structures, while remaining consistent across smoother and elliptic problems. These results demonstrate that wavelet-based multi-scale spatial decomposition is a principled and effective complement to Laplace-domain operator learning. --- ### Beyond Inference-Only Deployment: Comparing Weight-Based Consolidation Against Cascading Compaction Authors: Simon Dennis, Kevin Shabahang, Hao Guo, Rivaan Patil Published: 2026-05-23 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2605.24657v1 Major LLM platforms deploy models in an inference-only configuration: the model serves requests but never updates per-user weights. Users must repeatedly re-teach preferences, corrections, and project context, and context-based workarounds consume context-window space and degrade under cascading compaction. We evaluate an alternative: nightly consolidation of interaction knowledge into model weights via reflection, synthesis, and Low-Rank Adaptation (LoRA) fine-tuning on a single consumer GPU. Across ten realistic software development conversations (n = 10, 1,146 test questions across three memory types), three cycles of cascading compaction retain 36.8 +/- 3.0% of knowledge (between an 11.8% no-context floor and a 90.1% full-context ceiling), while consolidation retains 80.4 +/- 1.3% -- a 43.6 pp gain (paired t(9) = 14.8, p < 0.001) that more than doubles what compaction preserves, with the largest gains on procedural corrections (36.3% -> 74.6%) and episodic project facts (31.5% -> 78.2%). As a methodological aside, mean per-token validation cross-entropy is negatively correlated with LLM-judged accuracy (r = -0.51) while median per-token validation cross-entropy tracks accuracy almost exactly (r = +0.99): under evaluators that tolerate surface-form variation, the mean is misleading and a heavy-tail-robust statistic is the faithful signal. Persistent personalization requires moving beyond inference-only deployment toward architectures that consolidate knowledge into weights. --- ### AVBench: Human-Aligned and Automated Evaluation Benchmark for Audio-Video Generative Models Authors: Jialiang Yang, Bin Xia, Ruihang Chu, Dingdong Wang, Wanke Xia, Zhun Mou, Tianyang Zhong, Yiting Zhao, Wenming Yang Published: 2026-05-23 Categories: cs.AI, cs.CV, cs.MM, cs.SD arXiv: https://arxiv.org/abs/2605.24652v1 Rapid advances in audio-video (AV) generation have enabled high-fidelity synthesis with synchronized sound, particularly for human-related scenarios involving speech and interactions. Yet evaluation for AV generation remains at an early stage, with only a few coarse-grained benchmarks for human-related scenarios and relying on limited preset evaluations with generic multimodal LLMs, leading to inaccurate assessments of model capabilities. To address these issues, we introduce AVBench, a fully automated benchmark tailored for human-centric AV generation. AVBench is built on two key designs for comprehensive and accurate evaluation: (i) Human-centric and fine-grained metrics. AVBench integrates ten evaluation dimensions designed for human-centered real-world scenarios, covering visual quality, audio quality, and multi-level consistency across modalities. These practical metrics capture human-related details that existing benchmarks often overlook. (ii) Specialized evaluators via preference learning. To address the lack of specialized training data, we construct large-scale supervision by transforming real-world videos into diverse training pairs with controlled perturbations. After fine-tuning on this high-quality dataset, the evaluators learn to reliably detect subtle cross-modal inconsistencies. Crucially, instead of producing discrete textual judgment, AVBench derives continuous evaluation scores from the model's prediction confidence on binary decisions. This probabilistic scoring mechanism enables a more reliable assessment than traditional VQA-style evaluation and aligns closely with human judgment. Taken together, AVBench offers automated evaluation for AV generation, demonstrates strong potential for data filtering, and serves as a differentiable reward signal for Reinforcement Learning from Human Feedback (RLHF). --- ### WINO: A Weak-Form Physics Informed Neural Operator for Hyperelasticity on Variable Domains Authors: Bokai Zhu, Yizheng Wang, Qinghui Zhang, Timon Rabczuk Published: 2026-05-23 Categories: math.NA, cs.LG arXiv: https://arxiv.org/abs/2605.24651v3 We propose a Weak-form Physics-Informed Neural Operator (WINO), a data-free framework that combines the efficiency of neural operators with the geometric flexibility of the $\varphi$-finite element method ($\varphi$-FEM). $\varphi$-FEM is an unfitted method that accommodates geometric variations without body-fitted meshes, where the domain geometry is represented by the level-set function $\varphi$. To impose the boundary conditions, Dirichlet problems adopt the $\varphi$-FEM lifting so only the homogeneous displacement contribution is learned, whereas traction-driven Neumann problems additionally predict the auxiliary fields necessary for the unfitted weak formulation. Parameters are trained by minimizing squared weak-form residuals aligned with $\varphi$-FEM together with squared penalties on the cut-cell auxiliary equations, which removes the need for large paired datasets of converged reference solutions. When labeled reference data are available, an optional data-augmented variant (WINO+data) can further combine this physics-informed loss with a supervised term. After training, WINO outputs can seed the nonlinear $\varphi$-FEM solvers as neural operator warm starts (NOWS), which reduce iteration counts relative to traditional cold-started solvers. Numerical benchmarks show substantial accuracy of WINO together with total training times of about 15%-70% of those of supervised $\varphi$-FEM-FNO across all cases, without requiring reference-solution generation. --- ### WINO: A Weak-Form Physics Informed Neural Operator for Hyperelasticity on Variable Domains Authors: Bokai Zhu, Yizheng Wang, Qinghui Zhang, Timon Rabczuk Published: 2026-05-23 Categories: math.NA, cs.LG arXiv: https://arxiv.org/abs/2605.24651v2 We propose a Weak-form Physics-Informed Neural Operator (WINO), a data-free framework that combines the efficiency of neural operators with the geometric flexibility of the $\varphi$-finite element method ($\varphi$-FEM). $\varphi$-FEM is an unfitted method that accommodates geometric variations without body-fitted meshes, where the domain geometry is represented by the level-set function $\varphi$. To impose the boundary conditions, Dirichlet problems adopt the $\varphi$-FEM lifting so only the homogeneous displacement contribution is learned, whereas traction-driven Neumann problems additionally predict the auxiliary fields necessary for the unfitted weak formulation. Parameters are trained by minimizing squared weak-form residuals aligned with $\varphi$-FEM together with squared penalties on the cut-cell auxiliary equations, which removes the need for large paired datasets of converged reference solutions. When labeled reference data are available, an optional data-augmented variant (WINO+data) can further combine this physics-informed loss with a supervised term. After training, WINO outputs can seed the nonlinear $\varphi$-FEM solvers as neural operator warm starts (NOWS), which reduce iteration counts relative to traditional cold-started solvers. Numerical benchmarks show substantial accuracy of WINO together with total training times of about 15%-70% of those of supervised $\varphi$-FEM-FNO across all cases, without requiring reference-solution generation. --- ### On the Stability and Realizability of Recurrent Polynomial Surrogate Ternary Logic Gate Networks Authors: Sai Sandeep Damera, Ryan Matheu, Aniruddh G. Puranic, John S. Baras, Calin Belta Published: 2026-05-23 Categories: cs.LG, cs.AI, cs.LO, eess.SY arXiv: https://arxiv.org/abs/2605.24649v1 Recurrent Neural Networks (RNNs) can learn to predict Signal Temporal Logic (STL) verdicts online from partial trajectories, but deploying them as runtime monitors in safety-critical systems demands more than predictive accuracy. Standard RNN architectures offer no structural guarantee that outputs degrade gracefully under sensor degradation; a dropped input can silently flip a verdict from safe to unsafe. We introduce the Recurrent Differentiable Ternary Logic Gate Network (R-DTLGN), a recurrent architecture that operates over Kleene's three-valued logic $\{-1, 0, +1\}$, where $0$ explicitly represents unknown. The R-DTLGN trains through continuous polynomial surrogates and hardens to a discrete ternary logic circuit at inference. We analyze the hardened circuit through two gate vocabularies derived from two orderings on the ternary domain: numerically monotone gates ensure stable recurrent dynamics, while information-monotone gates, when present, guarantee principled abstention (unknown inputs never produce wrong outputs) and monotonicity in input certainty (more information can only improve the verdict). We show that the recurrent connections required by bounded STL operators use exclusively AND and OR, which belong to both vocabularies, linking the monitoring task to the architecture's guarantees. A realizability bound derived from the STL formula's temporal operators directly sizes the network's hidden state, replacing hyperparameter search with a formula-driven specification. We evaluate on STL specifications over D4RL PointMaze navigation data, testing prediction accuracy, degradation under predicate dropout, and the accuracy-versus-safety tradeoff between two label construction pipelines. The R-DTLGN is, to our knowledge, the first recurrent architecture that couples learned temporal prediction with formal degradation guarantees rooted in three-valued logic. --- ### Know You Before You Speak: User-State Modeling for LLM Personalization in Multi-Turn Conversation Authors: Jiani Luo, Xiaoyan Zhao, Yang Zhang, Shuyi Miao, Bingbing Xu, Stefan Konigorski, Tat-Seng Chua Published: 2026-05-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.24647v1 Personalized dialogue requires more than recalling explicit user histories: systems also need to infer hidden user states that evolve through interaction and shape appropriate response strategies. Existing memory- and profile-based methods primarily reuse observable user information, offering limited support for modeling user-state dynamics or selecting actions based on how they shape future user states. We propose PUMA (Prospective User-state Modeling for Action selection), a framework grounded in the Free Energy Principle (FEP) that formulates personalization as decision-making under partial observability, centered on an explicit user state model that captures latent user states and their action-conditioned dynamics. At each turn, PUMA maintains a belief over the user's hidden state, refines the user state model for observation generation and action-conditioned state transition, and selects dialogue actions by minimizing expected free energy, balancing epistemic and pragmatic objectives under a unified criterion. This formulation shifts personalization from passive memory retrieval to model-based decision-making over user evolution. We instantiate PUMA on healthcare-oriented counseling and motivational interviewing benchmarks with latent state annotations for rigorous evaluation. Experiments show that PUMA improves long-horizon dialogue outcomes while maintaining strong response quality, and a cross-dataset study demonstrates more reliable user-state estimation and next-state prediction. --- ### Quadratically Regularized Optimal Transport: Localization Bounds and Affine Case Analysis Authors: Long Nguyen-Chi, Nam Nguyen, Binh Nguyen Published: 2026-05-23 Categories: math.OC, stat.ML arXiv: https://arxiv.org/abs/2605.24644v2 Quadratic regularization has emerged as a potential alternative to the popular entropic regularization in computational optimal transport, offering the theoretical advantage of producing sparse couplings through its hinge density structure. Despite recent progress in one-dimensional settings and general upper bounds, fundamental questions about the localization rate of QOT optimizers around the Monge coupling have remained open. In this work, we establish a general lower bound showing that the support of the QOT optimizer cannot concentrate around the Monge graph faster than order $\varepsilon^{\frac{1}{d+2}}$ in the directed Hausdorff distance, matching the conjectured optimal exponent under standard regularity assumptions in \citet{wiesel2025sparsity}. We also show that the QOT value gap controls the mean-squared deviation $\mathbb E_{π_\varepsilon}\|y-T(x)\|^2$ by the scale of $\varepsilon^{\frac{2}{d+2}}$. As a corollary, in the affine Brenier regime, which includes Gaussian-to-Gaussian transport, we derive a sharp pointwise tube bound of order $\varepsilon^{\frac{1}{d+2}}$ by reducing the problem to self-transport and applying recent self-transport sparsity results. Finally, we validate our theoretical bound with a synthetic experiment in high-dimensional settings. --- ### Understanding the Impact of Geometric Foundation Models on Vision-Language-Action Models Authors: Yurou Yang, Muyuan Lin, Roberto Martin-Martin, Martin Labrie, Shreekant Gayaka, Cheng-Hao Kuo, Luca Carlone Published: 2026-05-23 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2605.24642v1 Recent work explores new opportunities at the intersection of vision-language-action models (VLAs) and geometric foundation models (GFMs) for 3D reconstruction, such as VGGT. While the resulting geometric VLAs often show improved performance, it remains unclear (i) if modern VLAs already have sufficient geometric understanding to start with, (ii) what is the best architecture to inject geometric understanding into a VLA, and (iii) what is the effect of other design choices that affect geometric VLAs. In this paper we provide a rigorous experimental analysis to shed light on these questions, for a specific choice of VLA (GR00T-N1.5) and GFM (VGGT). Our first contribution is to formalize prior work's intuition that current VLAs lack geometric understanding, by providing a rigorous analysis based on linear probing. The analysis quantifies, for the first time, the "geometric gap" between VLAs and GFMs. Our second contribution is to identify and compare different strategies to bridge GFMs with VLAs. We implement three different architectures, which differ in the way they inject geometry in the VLA, while keeping low-level implementation details as similar as possible, to ensure a fair comparison. Finally, we analyze the impact of non-architectural choices (e.g., training data, number of cameras, reconstruction quality) on the performance of the geometric VLAs. --- ### DisDop: Distillation with Domain Priors for Open-Vocabulary Aerial Object Detection Authors: Ruihao Xu, Yong Liu, Yansong Tang, Sule Bai, Xubing Ye, Bingyao Yu, Yutao Guo, Jiwen Lu, Jie Zhou Published: 2026-05-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.24639v1 With the widespread application of drones in recent years, object detection of aerial images has attracted increasing attention, especially open-vocabulary aerial detection which is not restricted to predefined categories. Due to the scarcity of drone's viewpoint images and their significant differences from natural images, it is difficult to achieve satisfying results by directly applying vanilla open-vocabulary detection methods designed for natural scenarios. Some studies propose to transfer knowledge from pre-trained models by using lightweight networks or generating pseudo labels, but they tend to rely on models trained on natural images, neglecting the potential of foundation models specifically tailored for remote sensing and aerial imagery. To address this limitation, we propose DisDop, a unified framework that systematically distills multi-level domain priors from remote sensing foundation models (e.g., RemoteCLIP and DINOv3) into a lightweight detector. Specifically, we first distill visual priors through a teacher fusion strategy that combines RemoteCLIP's cross-modal alignment capability with DINOv3's fine-grained local feature extraction ability, transferring their complementary strengths to the detector's backbone. Second, we distill textual priors embedded in RemoteCLIP's text encoder by explicitly modeling inter-category semantic relationships, while incorporating global contextual priors to enhance local feature representation for small objects. Through this multi-level prior distillation framework, our DisDop achieves new state-of-the-art performance on open-vocabulary aerial detection benchmarks. Extensive ablation analysis also demonstrates the rationality and effectiveness of our proposed modules. --- ### GlobalDentBench: A Multinational Benchmark for Evaluating LLM Clinical Reasoning in Dentistry with Expert Calibration Authors: Junjie Zhao, Jingyi Liang, Zhenyang Cai, Jiaming Zhang, Zhenwei Wen, Shuzhi Deng, Wenjing Yi, Chunfeng Luo, Hexian Zhang, Junying Chen, Tianrui Liu, Zhuhui Bai et al. Published: 2026-05-23 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.24636v2 While large language models (LLMs) hold transformative potential for medicine, their reasoning robustness and safety in real-world clinical scenarios remain critically underexplored, particularly in dentistry. Here we introduce GlobalDentBench, the first multinational dental benchmark, featuring a taxonomy that encompasses 14 dental specialties across 88 countries and regions spanning six continents. The benchmark comprises 8,978 expert-validated questions across three formats (multiple-choice, short-answer, and case-based questions) and assesses three progressive reasoning levels: knowledge recall (L1), routine reasoning (L2), and individualized reasoning (L3). To ensure data quality, the automated construction framework was calibrated by six senior dentists, achieving expert agreement rates of 99.98% for multiple-choice and short-answer questions and 96.78% for the more complex case-based questions. Evaluation of 12 frontier LLMs on GlobalDentBench revealed a sharp, stepwise performance degradation with increasing reasoning complexity. Specifically, accuracy plummeted from 81.34% on multiple-choice to 64.53% on short-answer and 22.34% on case-based questions, while declining markedly from 74.01% at L1 to 55.64% at L2 and 35.71% at L3. More critically, risk analysis of real-world dental cases demonstrated an alarming overall unsafe rate of 31.01% in LLM-generated clinical recommendations, with 4.51% posing risks of irreversible patient harm and risks particularly pronounced in specialties such as orthodontics. These findings expose fundamental limitations in the medical reasoning and safety of current LLMs. Consequently, GlobalDentBench provides a scalable foundation for trustworthy clinical AI evaluation, underscoring the urgent need for rigorous validation before the safe deployment of these models in healthcare. --- ### HiMed: Incentivizing Hindi Reasoning in Medical LLMs Authors: Dingfeng Jiang, Han Yan, Chenze Ma, Amit Kumar Jaiswal, Ang Li, Yunxiang Jiang, Xinlei Xiong, Juhao Liang, Hongru Xiao, Xiang Li, Fan Bu, Jiale Han et al. Published: 2026-05-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.24635v2 Medical large language models hold promise for reducing healthcare disparities, yet Hindi remains severely underrepresented. While medical LLMs excel in high-resource languages, their performance degrades sharply in Hindi, particularly on Indian systems of medicine. We argue that robust cross-lingual medical transfer requires Hindi reasoning. To this end, we introduce HiMed, a Hindi reasoning medical corpus and benchmark suite covering both Western and Indian medicine. We further propose HiMed-8B, a Hindi-form medical reasoning LLM, through the design of decaying scaffolding reward. Extensive experiments demonstrate improvement in Hindi medical reasoning performance and a reduction in the English-Hindi accuracy gap. Ablation studies validate the contribution of each training stage and reward component. All code, data, and weights are available --- ### HiMed: Incentivizing Hindi Reasoning in Medical LLMs Authors: Dingfeng Jiang, Han Yan, Chenze Ma, Amit Kumar Jaiswal, Ang Li, Yunxiang Jiang, Xinlei Xiong, Juhao Liang, Hongru Xiao, Xiang Li, Fan Bu, Jiale Han et al. Published: 2026-05-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.24635v1 Medical large language models hold promise for reducing healthcare disparities, yet Hindi remains severely underrepresented. While medical LLMs excel in high-resource languages, their performance degrades sharply in Hindi, particularly on Indian systems of medicine. We argue that robust cross-lingual medical transfer requires Hindi reasoning. To this end, we introduce HiMed, a Hindi reasoning medical corpus and benchmark suite covering both Western and Indian medicine. We further propose HiMed-8B, a Hindi-form medical reasoning LLM, through the design of decaying scaffolding reward. Extensive experiments demonstrate improvement in Hindi medical reasoning performance and reduction in the English--Hindi accuracy gap. Ablation studies validate the contribution of each training stage and reward component. All data and code are available on GitHub: https://github.com/FreedomIntelligence/HiMed. --- ### Resolving Ambiguity in Composed Image Retrieval via Calibrated Interaction Authors: Amsisan Tran, Baogh Le, Tuan Kiet Pham, Sui Yang Guang Published: 2026-05-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.24634v3 Composed image retrieval (CIR) searches a corpus with a reference image and a text describing how to modify it. Despite rapid progress from triplet-trained compositors to zero-shot and generative methods, essentially all systems share one assumption: that a query maps to a single target, scored by Recall@K against one annotation. We argue this is fundamentally at odds with the task. A query such as make it more formal does not name an image but a region of the corpus, and which member the user intends is genuinely underdetermined. This underspecification is the root of the well-known false-negative problem and leaves current models unable to tell a precise query from an ambiguous one. We reframe CIR as calibrated intent resolution under uncertainty: a retriever is wrapped in a conformal prediction layer that returns a candidate set with a coverage guarantee and whose size is a principled measure of ambiguity; when the set is large, an expected-information-gain policy asks the single most useful clarifying question, drawn from interpretable ambiguity axes, and the set contracts. We introduce AmbiCIR, a benchmark and human-validated user simulator that revive the dormant auxiliary and dialogue annotations of CIRR and extend the multiple-positive setting of CIRCO. Across open-domain and fashion benchmarks our method matches single-turn state of the art, confirming calibrated resolution is cost-free on precise queries, while reaching the intended target in a fraction of the interaction budget required by naive conversational baselines, and it is the first to report valid coverage and calibration for the task. --- ### Demystifying the Mythos or Disrupting Bugonomics? From Zero-Day Asymmetry to Defender Remediation Throughput Authors: Alfredo Pesoli, Herman Errico, Lorenzo Cavallaro Published: 2026-05-23 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.24632v1 Recent demonstrations of large language models producing candidate and confirmed vulnerabilities in production software have renewed the narrative that AI will reshape offensive and defensive security. Headlines emphasize capability; they rarely interrogate costs and incentives. This paper examines LLM-driven vulnerability discovery through a bugonomics lens: the operational economics of producing, proving, prioritizing, and fixing security-relevant defects. Historically, the most visible high-end bugonomics was offense-priced because production-grade zero-days and exploit chains were expensive specialist outputs for governments, brokers, and offensive vendors. Defender-side bugonomics already existed in vulnerability research, reward programs, and vendor remediation work; LLM-assisted systems change its scale and distribution. They make candidate generation, code comprehension, harness construction, proof-of-impact drafting, and report preparation cheaper at codebase scale. Exploits and proofs of concept remain important, but in defender workflows they primarily prove impact, guide prioritization, and justify remediation. The resulting bottleneck is not only finding more bugs; it is absorbing, validating, triaging, patching, and shipping a larger stream of reports. Using public data from Anthropic's Mythos Preview and Mozilla Firefox collaborations, along with public exploit-market price anchors and vulnerability reward programs, we argue that the near-term shift is not simply more zero-days. It is a move toward broader defender remediation throughput: low-signal candidates become cheaper, evidence-rich remediation become more important, and scarce capacity shifts toward maintainer review and release work. The effect is acute in open source, where LLM-assisted discovery can increase report volume while maintainer-side validation, triage, funding, and release capacity may not scale. --- ### Beyond Generative Priors: Minority Sampling with JEPA-Guided Diffusion Authors: Sol Park, Soobin Um Published: 2026-05-23 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2605.24631v1 Minority sampling aims to generate low-density instances on a data manifold and is of central importance in applications such as medical diagnosis, anomaly detection, and creative AI. Existing approaches, however, define minority samples relative to generative priors learned from training data, confining rarity to model-specific notions that may poorly reflect real-world semantics. In this work, we propose a world-centric perspective on minority sampling, which defines rarity with respect to real-world priors rather than generator-induced densities. To this end, we introduce JEPA guidance, a diffusion sampling framework guided by a Joint-Embedding Predictive Architecture (JEPA) -- a class of world models that encode broad, semantically rich representations. JEPA guidance steers diffusion trajectories toward low-density regions under the implicit density induced by the JEPA, thereby aligning generated minorities with real-world semantic rarity. To make JEPA guidance computationally practical, we develop principled approximation strategies accompanied by theoretical error bounds, significantly reducing the overhead of guidance computation. Extensive experiments across unconditional, class-conditional, and text-to-image generation demonstrate that JEPA guidance consistently improves the fidelity and semantic validity of minority samples, outperforming generator-centric baselines in capturing real-world notions of rarity. Code is available at https://github.com/soobin-um/jepa-guidance. --- ### DexSIM: Real-time Dexterous Simulation with Unified Causal Video Diffusion Authors: Adam Lee Published: 2026-05-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.24630v1 Recent progress of video diffusion models have enabled extensive simulation of the physical world. While simulation with hand object interaction has been less explored. We propose DexSIM, a dexterous simulation framework for simulating dexterous manipulation in real-time. While previous works utilizing video diffusion and 3D reconstruction focus on navigation, dexterous manipulation has been limited while it has extensive applications for creating interactive experiences with the simulated world and for generating synthetic data for robotics. Existing methods lack real-time interactivity and long-term spatial consistency and memory. We propose a 2-stage training framework for DexSIM. First we train a bi-directional video diffusion model by jointly embedding the hand action trajectory and video in a unified feature space. We utilize gaussian heatmap hand encoding for more accurate hand representation. Then we conduct a roll-out based autoregressive training with updated spatial cache as attention sink for spatial memory, which improves long-term consistency and 3D aware dexterous manipulation simulation. DexSIM outperforms the baseline on pixel and semantic similarity, motion fidelity, and hand projection accuracy. It also allows new applications such as hand motion transfer and runs at 15.24 FPS real-time interactivity. --- ### Memory Uncertainty Relation and Harmonic Memory in Random Recurrent Networks Authors: Taichi Haruna, Kohei Nakajima Published: 2026-05-23 Categories: nlin.AO, cond-mat.dis-nn, cs.NE arXiv: https://arxiv.org/abs/2605.24628v1 We present an inequality that bounds the short-term memory capability of dynamical systems from below. It can be interpreted as an uncertainty relation between a measure of short-term memory and that of the size of state fluctuations induced by input signals. The lower bound can be achieved by a readout weight and thus represents a suboptimal memory called harmonic memory. We examine analytically and numerically the inequality in a number of reservoir systems subject to input noise. We illustrate cases in which equality is achieved exactly, equality holds asymptotically, and the inequality is strict. We also study the effect of a state-space regularization to elucidate the inequality in terms of the fluctuation structure of the state-space. We find that a certain strength of input noise induces extra memory under the regularization, and we refer to this phenomenon as noise-induced memory. We observe that the memory uncertainty relation does not hold in general for the regularized memory and harmonic memory. This fact is explained in terms of the mechanism of noise-induced memory. --- ### ULF-Synth: Physics-Guided Ultra-Low-Field MRI Enhancement for Pediatric Neuroimaging Authors: Toufiq Musah, Salvatore Calcagno, Federica Proietto Salanitri, Xiaomeng Li, Maruf Adewole, Marawan Elbatel Published: 2026-05-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.24625v2 Ultra-low-field (ULF) MRI offers portable and accessible neuroimaging but suffers from reduced signal-to-noise ratio and limited spatial resolution compared to high-field (HF) systems. Acquiring paired ULF-HF data for supervised enhancement is often difficult, particularly in resource-limited settings. We introduce ULF-Synth, a framework that combines: (i) acquisition-based synthesis of realistic ULF images from HF volumes to create large-scale paired training data, (ii) a spatial-frequency domain objective that prioritizes recovery of high-frequency anatomical detail. This formulation is architecture-agnostic, consistently improving structural similarity and perceptual fidelity across encoder-decoder, adversarial, and diffusion-based translation models. When trained exclusively on synthetic data, the resulting models generalize effectively to real 64mT ULF acquisitions, improving downstream multiclass brain segmentation and achieving higher radiologist preference and diagnostic acceptability in a blinded reader study. These findings demonstrate that synthetic paired supervision provides a practical and scalable pathway for enhancing ULF MRI without requiring real paired acquisitions. Code, Models and Dataset: https://github.com/toufiqmusah/ULF-Synth --- ### ULF-Synth: Physics-Guided Ultra-Low-Field MRI Enhancement for Pediatric Neuroimaging Authors: Toufiq Musah, Salvatore Calcagno, Federica Proietto Salanitri, Xiaomeng Li, Maruf Adewole, Marawan Elbatel Published: 2026-05-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.24625v1 Ultra-low-field (ULF) MRI offers portable and accessible neuroimaging but suffers from reduced signal-to-noise ratio and limited spatial resolution compared to high-field (HF) systems. Acquiring paired ULF-HF data for supervised enhancement is often difficult, particularly in resource-limited settings. We introduce ULF-Synth, a framework that combines: (i) acquisition-based synthesis of realistic ULF images from HF volumes to create large-scale paired training data, (ii) a spatial-frequency domain objective that prioritizes recovery of high-frequency anatomical detail. This formulation is architecture-agnostic, consistently improving structural similarity and perceptual fidelity across encoder-decoder, adversarial, and diffusion-based translation models. When trained exclusively on synthetic data, the resulting models generalize effectively to real 64mT ULF acquisitions, improving downstream multiclass brain segmentation and achieving higher radiologist preference and diagnostic acceptability in a blinded reader study. These findings demonstrate that synthetic paired supervision provides a practical and scalable pathway for enhancing ULF MRI without requiring real paired acquisitions. Code, Models and Dataset: https://github.com/toufiqmusah/ULF-Synth --- ### Vision-Language Binding in In-Context Image Generation Authors: Chris Ge, Rohit Gandikota, Antonio Torralba, Tamar Rott Shaham Published: 2026-05-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.24624v1 In-context image generation models such as FLUX.2 take a text prompt and an optional reference image as visual conditioning for the output. Internally, all three inputs -- text, reference image, and the noise tokens -- are concatenated and processed through a single attention stream, where all tokens can attend to one another. This leaves open how reference information flows through the model to produce the output image. We show that an implicit cross-modal binding emerges between the text tokens and the reference image: the text tokens absorb visual reference content during the forward pass, and that absorbed content causally influences the generated output. We surface this binding with three causal interventions on FLUX.2: T2I Lens, which decodes intermediate text-token activations through a text-to-image path; Attention Knockout, which severs specific attention edges; and I2I-to-I2I Patching, which copies text token activations between editing runs. Across 2,875 editing tasks on various images, including SUN397 and DreamBench++ datasets and images collected online, we observe a consistent division of labor: properties of the reference image, like color, style, and scene setting, are first written into the text tokens, which carry them to the generated image; pixel-exact properties like a specific face or instance identity bypass the text tokens and flow directly from reference to image through image-to-image attention. We further localize the reference-text binding to the padding tokens of the text sequence. These results show that text tokens in a multimodal DiT are not just prompt holders, but a structured channel for reference image content. More broadly, they suggest that even in unified-attention multimodal generative models, token modality structures how conditioning information is represented and routed across the network. --- ### PoseRefer: Pathway-Local Parameters for Semantically Grounded Reference Resolution Authors: Anna Deichler Published: 2026-05-23 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2605.24622v1 A robot resolving ``put the cup on that one'' must fuse gesture, language, and scene geometry, yet 3D grounding benchmarks only partially capture this regime: descriptions are written post-hoc, gestures are templated, or pointing is staged for the camera. MM-Conv captures natural co-speech gesture from dyadic VR interaction alongside full-body motion capture and 3D scene graphs. We use it to evaluate pose-language fusion with a decoupled late-fusion architecture in which pose and text pathways share no learned parameters. The two choices together make category, pose, and text contributions easier to isolate through controlled ablations. Fusion with frozen MiniLM category embeddings exceeds pose alone and the best text-only pathway on every reference type, reaching 31.9% top-1. The learned scalar gate flips between opposing policies depending on whether the text pathway has category access. This is a reliability diagnostic: fusion-accuracy claims for semantic grounding systems are indistinguishable from category-representation artifacts unless pathways are architecturally decoupled. ---