# Research Papers — 2026-07 · bundle page 96 of 222 > Full-text markdown of papers #4751–4800 of 11075 published in 2026-07, newest first. AI-readable mirrors of the full 11075-paper 2026-07 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-07/page/96 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/95.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/97.md) ### AI_LectureNote: A Retrospective Pilot Study of a Post-ASR Workflow for English-Script Rendering and Semantic Drift in Korean-English Medical Lectures Authors: Kyeongeon Lee, Donghoon Chang, Seungryeol Baek, Taehong Kim, Wonjun Yang Published: 2026-07-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.17237v1 AI_LectureNote is a historical, readability-oriented post-ASR workflow for Korean-English medical lectures. It rewrites speech-to-text output into study transcripts while restoring Latin-script medical terms rather than Korean phonetic transliterations. We retrospectively evaluate the workflow on four author-recorded lectures across five conditions. In this pilot, post-processing raised the macro English-script rendering rate from 0.39 to 0.71 on the whisper-1 path and from 0.26 to 0.65 when applied to 3-minute chunked gpt-4o-transcribe output. However, English-script rendering did not imply semantic faithfulness: the two post-processed conditions showed semantic drift in 34 and 36 of 282 reference sentences and polarity failures in 11 and 13 of 101 polarity-cue rows. A descriptive cross-input comparison suggested different candidate failure patterns: polarity-failure sets overlapped more strongly across front-ends (Jaccard 0.60; 9 shared of 15 unioned failures) than general semantic-drift sets (Jaccard 0.23; 13 shared of 57 unioned drifts). This single-annotator pilot documents concrete failure modes rather than population rates and supports evaluating surface accuracy, term-script rendering, chunk-level script consistency, and medical-meaning preservation separately. --- ### A RFID Based Campus Wide Payment System Authors: Miraj Uddin Chowdhury, MD Khairul Islam Prime Published: 2026-07-19 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2607.17233v1 This work titled "RFID Based Campuswide Payment System" introduces an innovative cashless payment solution for educational institutions. It uses RFID cards and a Raspberry Pi to enable hassle free payments for various campus services, such as cafeteria purchases, tuition fees, and library fines. A centralized database ensures real-time updates on transactions and account balances, accessible through a simple and user-friendly web interface. This work is involved in designing a secure system with object-oriented principles, setting up databases, and integrating hardware like RFID readers with a Raspberry Pi. The systems are proved to be a cost-effective and efficient alternative to traditional payment methods, enhancing convenience and security for students and administrators. The study also explored similar RFID applications, like smart parking and attendance systems, to identify challenges and improvements. Looking ahead, it envisions features like wearable RFID devices, voice-activated payments, and blockchain integration to boost security and usability. Results show that this system simplifies campus payments and has the potential for broader adoption in similar environments. --- ### Rate-Distortion-Perception Theory: Redefining the Fundamental Limits of Information Representation Authors: Photios A. Stavrou, Giuseppe Serra, Marios Kountouris Published: 2026-07-19 Categories: cs.IT, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2607.17232v1 Classical rate-distortion (RD) theory has long established the fundamental limits of lossy compression by quantifying the minimum number of bits required to represent a source under a prescribed distortion constraint. However, widely used distortion measures such as mean-squared error often fail to capture perceptual quality or semantic validity, which are increasingly central in modern learning-driven applications. Rate-distortion-perception (RDP) theory extends the RD framework by introducing perception as a third fundamental axis, quantified via distributional similarity between the source and reconstructed signals, leading to the rate-distortion-perception function (RDPF). This tutorial provides a structured overview of the coding principles underlying perception-aware lossy compression and surveys recent achievability results under different randomness assumptions. It then presents a unifying optimization viewpoint for computing the RDPF as defined by Blau and Michaeli, for both discrete and continuous sources under broad families of perceptual constraints, including f-divergences, alpha-divergences, and Wasserstein-based metrics. Special attention is given to computational tools such as alternating minimization schemes, Newton-based methods, and convex optimization formulations, as well as to analytically tractable cases such as Gaussian sources and the perfect-realism regime. Unlike recent broad surveys that emphasize generative architectures and AI-empowered communication systems, this tutorial focuses on the coding-theoretic and computational machinery needed to characterize, compute, and interpret the RDP limits. Finally, the tutorial outlines promising research directions at the intersection of information theory, neural compression, robust source coding, and perception-aware networked control systems. --- ### Robust Summarization of Doctor-Patient Conversations: TalTech Systems for the Beyond Transcription Challenge Authors: Aivo Olev, Tanel Alumäe Published: 2026-07-19 Categories: cs.CL, eess.AS arXiv: https://arxiv.org/abs/2607.17230v1 This paper describes TalTech's submissions to the Beyond Transcription Challenge (BeTraC), which requires generating SOAP notes directly from long doctor-patient conversation recordings, without intermediate transcription. After screening open-weight speech LLMs for long-audio robustness, we adapted Voxtral Mini (lightweight track) and Voxtral Small (heavyweight track) with LoRA supervised fine-tuning followed by DAPO reinforcement learning that uses the challenge metric, Open Medical Concept F1, as its reward. Our systems ranked first in both tracks, and an independent LLM-as-a-judge evaluation showed the lowest hallucination rate among all submissions, indicating that reinforcement learning against a concept-matching metric need not compromise factual reliability. We also find that fine-tuning on text transcripts transfers well to speech input and appears to improve robustness on out-of-domain real recordings. --- ### Literary Non-Style in LLM-Generated Text Authors: Cory Massaro Published: 2026-07-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.17228v1 Prior work on LLM-generated text has demonstrated quantitative and qualitative departures from text produced by humans. LLM-generated texts differ from human writing in style, resulting in a characteristic textual "feel," while the semantic range of LLMs is much restricted compared to that of humans. In this contribution, I note simple but consistent patterns in the statistical distribution of n-grams within LLM-generated text. Via qualitative analysis of these n-grams, I reveal deficiencies in LLM style. Because higher-order n-grams correlate to semantic content, I conclude that questions of style and semantics are not cleanly separable. --- ### Specifying the Delegated-Autonomy Boundary: Requirements Engineering for Agentic AI Authors: Chetan Arora, Andreas Vogelsang, Abbi Sharma Published: 2026-07-19 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2607.17225v1 Agentic AI systems do not just predict or recommend; they plan, maintain state, and act in external environments with varying degrees of autonomy. This changes the requirements engineering problem in a specific and under-addressed way: it introduces what we call the delegated-autonomy boundary -- the set of decisions about what may be delegated to the system, under what graduated authority, with what oversight, and how control is returned. Current practices bury these decisions inside prompts, tool schemas, and runtime policies, even though they are requirements-level commitments. This paper proposes two complementary artifacts. First, an Agency Justification Record (AJR) helps teams decide when an agent is warranted over simpler alternatives. Second, an Agentic Delegation Policy (ADP) captures what must be specified for safe and effective development: purpose, authority, information, coordination, assurance, and evolution. Crucially, authority in the ADP is modelled as graduated, i.e., a tiered structure. We illustrate the framework with two contrasting examples: a safety-critical hospital discharge coordination agent and an automated code review agent. --- ### Semantic Context Matters: Analysis of Color Names Across Domains Authors: Adilet Yerkin, Elnara Kadyrgali, Malika Ziyada, Nuray Toganas, Muragul Muratbekova, Ayan Igali, Aruzhan Sabitkyzy, Pakizar Shamoi Published: 2026-07-19 Categories: cs.CV, cs.HC, cs.MM arXiv: https://arxiv.org/abs/2607.17221v1 Color naming is influenced not only by physical color values but also by the semantic context in which colors are used. This paper investigates context-dependent color naming by mapping color-name datasets from Cosmetics, Crayola, and Car-color vocabularies onto the 86 fuzzy color categories of the COLIBRI color model. Contextual variation is analyzed using category coverage, Shannon entropy, and maximum lift. The results show that the three contexts occupy the COLIBRI color space differently: Cosmetics covers 48 of 86 fuzzy categories, Crayola covers 50, and Car colors cover 40. The results demonstrated that Crayola provides the broadest and most balanced use of the fuzzy color space, Cosmetics is mainly concentrated around warm-tone regions, and Car colors are more specialized around blue and achromatic regions. These findings show that color naming cannot be fully explained by numerical color similarity alone and that semantic context plays an important role in human color interpretation. The proposed framework supports the development of context-aware color models for design analytics, product search, recommendation systems, and human-centered artificial intelligence. --- ### Auditing Question-Order Effects in Large Language Models with the QQ Equality: Mechanism Characterization and a Saturation Caveat Authors: Pilsung Kang Published: 2026-07-19 Categories: cs.CL, cs.AI, quant-ph, stat.ME arXiv: https://arxiv.org/abs/2607.17219v2 Question-order effects in human survey data have been reported to approximately satisfy the QQ (quantum question) equality, a parameter-free prediction of the standard projective quantum question-order model. We develop this equality into an audit framework for sequential binary judgments of autoregressive large language models (LLMs). Theoretically, we characterize mechanism families that satisfy QQ robustly, show that classical repetition can reproduce the equality exactly, and combine QQ with the rank-2 Contextuality-by-Default criterion through $|q_{QQ}| \le \mathrm{OSS}$. This separates order sensitivity, QQ imbalance, and residual contextuality rather than treating them as interchangeable signatures. Methodologically, we introduce a committed multi-turn forced-branch protocol that reconstructs order-conditioned joint distributions from next-token log-probabilities under counterbalanced label mappings and pre-specified health gates. A first-signal pilot on an open-weight instruction-tuned model reveals the central measurement problem. Although all pre-specified health gates passed, the binary-conditioned distributions were near-deterministic for 17 of 18 item pairs under the direct-evaluation framing and 7 of 8 under the persona framing. Label assignment materially changed several mapping-specific QQ verdicts, and no item was certified as residually contextual. Thus, under the tested conditions, the observed QQ outcomes did not uniquely identify a response mechanism in the presence of a saturated and label-sensitive measurement interface. The main implication is methodological: next-token probabilities should not be interpreted as survey-response distributions without first establishing adequate dispersion. We therefore argue that saturation screening and label counterbalancing should precede structural interpretation in distribution-level audits of LLM judgments. --- ### Induce to Empower: Improving Lightweight Baselines via Foundation Model Induction for Generalized Polyp Segmentation Authors: Shivanshu Agnihotri, Snehashis Majhi, Deepak Ranjan Nayak, Dwarikanath Mahapatra, Debesh Jha Published: 2026-07-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.17208v1 Automated polyp segmentation in colonoscopy continues to pose challenges due to substantial appearance variations and indistinct polyp boundaries. Although emerging foundation models (FMs) such as DINOv2, SAM, and OneFormer, demonstrate remarkable generalization capabilities, their direct transfer to the polyp segmentation task and deployment in real-time clinical settings are difficult due to lack of large-scale labeled data and high computational demands. In addition, adopting multiple FMs together raises concerns, even though they encode complementary semantic and structural information. While lightweight models, including U-Net, PraNet and U-Net++, are computationally efficient, they often struggle to generalize across datasets due to limited representational capacity. To address this gap, we propose Lite-Polyp Inductor (Lite-Pi), a novel foundation model induction framework that significantly enhances lightweight polyp segmentation baselines. Our proposed framework generates FM-specific prototype representations and aligns them semantically with the corresponding foundation model priors through reconstruction-based supervision. Subsequently, transformer-based fusion is introduced to highlight the polyp relevant representations, including salient boundary information, while preserving complementary semantic cues. Extensive experiments across five polyp segmentation benchmark datasets demonstrate that Lite-π significantly improves lightweight baselines, achieving superior generalization performance with minimal computational overhead and thereby, offering a practical solution for generalized polyp segmentation. Our code is available at GitHub. https://github.com/lostinrepo/Lite-Pi --- ### A Systematic Evaluation of Trajectory Data Curation for LoRA Fine-Tuning of Code Agents Authors: Yunze Han Published: 2026-07-19 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2607.17205v1 Supervised fine-tuning (SFT) of open-weight LLMs on expert agent trajectories has emerged as a prominent approach to building capable code agents without reliance on proprietary models. A central yet underexplored question is how trajectory quality and quantity jointly shape model performance. We present a systematic empirical study of trajectory data filtering for LoRA fine-tuning of Qwen2.5-Coder-7B-Instruct on the SWE-trajectory dataset (67,074 trajectories, of which 32,161 are resolved). We propose a two-axis quality scoring framework -- Efficiency and Style -- and evaluate it through 16 controlled experiments spanning strategy, scale, and ablation analyses. Since 7B-scale models attain near-zero SWE-bench resolve rates, we adopt cross-entropy (CE) loss on held-out trajectories as the primary metric, validated via first-action generation: CE loss and ROUGE-L are perfectly rank-correlated (Spearman $ρ$ = -1.00), with limited-sample evidence supporting but not conclusively establishing this proxy. Our results reveal a scale-dependent quality-quantity trade-off: at small scales, doubling the dataset (500 to 1,000) yields ~12.7% CE-loss reduction whereas the TopQ-Random gap stays <1% (Mann-Whitney p > 0.10); at 2,000 trajectories this same gap widens to 3.6% (p = 0.016). Ablation further identifies error-retry rate as the dominant sub-dimension, performing comparably to the full composite ($Δ$ < 0.2%). Together, these findings establish trajectory-level quality scoring as a viable but scale-sensitive lever for code-agent SFT and offer a proxy-validated evaluation protocol for the regime where end-to-end resolve rate is statistically infeasible. --- ### Non-Asymptotic Best Policy Identification Guarantees in Online Reinforcement Learning Authors: Joseph Lazzaro, Alessio Russo, Aldo Pacchiano Published: 2026-07-19 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2607.17201v1 In this work we study the Best Policy Identification (BPI) problem in online, tabular Reinforcement Learning. This is an active sequential hypothesis testing problem in which the learner's objective is to identify an optimal policy in a Markov Decision Process (MDP) with high confidence, while minimizing the expected sample complexity to do so. We consider an online setting with deterministic rewards, where the agent must strategically navigate through the MDP in order to effectively explore. Previous works in the literature have provided asymptotically optimal methods for BPI, such as the Navigate and Stop (NaS) algorithm and its variants, however existing analysis remains asymptotic. In this work, we fill that gap by providing the first non-asymptotic sample complexity guarantees for NaS, showing that its sample complexity depends not only on the characteristic time, but also on the connectivity of the underlying MDP, the curvature of the optimal characteristic time, and other instance-dependent quantities. We identify these additional attributes and make explicit their contributions to the overall sample complexity. --- ### Cross-Coordinate Correspondence Pruning for Image-to-Point Cloud Registration Authors: Xin Liu, Rong Qin, Huipeng Lin, Leizhi Shu, Jin Wu, Chi-Man Vong, Liang Lin, Jufeng Yang Published: 2026-07-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.17200v1 Recent detection-free approaches have shown significant efficacy in image-to-point cloud (I2P) registration by employing a coarse-to-fine matching pipeline. In the coarse stage, down-sampled image features and voxelized point cloud features are typically fused to establish initial coarse correspondences for subsequent refinement. However, existing methods largely overlook the critical role of point cloud density, which fundamentally dictates the quality of coarse correspondences and the final registration results. Specifically, excessively sparse point clouds lead to an insufficient number of inliers, while overly dense ones often introduce a high outlier ratio. Consequently, this creates an inherent density trade-off, thereby significantly limiting the registration accuracy of current approaches. For mitigating this trade-off, we propose a novel Cross-Coordinate Correspondences Pruning (CCP) strategy to acquire sufficient inliers while ensuring a low outlier ratio. To minimize interference from inter-modal coordinate discrepancies, we first project cross-coordinate coarse correspondences to the 2D image coordinate system for spatial unification. Subsequently, a lightweight pruning network is responsible for predicting the inlier confidences, which are used to filter coarse outliers, from coordinate geometric and modal feature dimensions. To maximize inlier recall, we further design a Multi-Density Point Ensemble (MDPE) strategy that consolidates and deduplicates pruned coarse correspondences across varying point cloud densities. Our method achieves a significant performance improvement, surpassing existing state-of-the-art methods by at least 8.6% in Registration Recall across various benchmarks. --- ### Toward Anthropomorphic Dialogue: A Closed-Loop Framework for Human-Like Chat Generation, Evaluation, and Preference Alignment Authors: Wentao Liu, Siyu Song, Xi Chen, Youjia Li, Xiaokun Wang, Min Ji, Ji Wang Published: 2026-07-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.17191v2 Human-like private chat requires more than fluent response generation: a system must preserve persona, relationship, memory, bounded knowledge, medium-specific timing, and a coherent multi-turn arc. We present AnthroDial, a closed-loop framework that formulates anthropomorphic dialogue as a joint problem of system architecture, executable evaluation, and diagnostic alignment. It combines (1) a role-conditioned scheduled dialogue runtime with persona and scenario cards, long-term memory, virtual time, and single-draft message decisions; (2) an executable benchmark with an L0 validity gate, five per-turn dimensions, and five dialogue-level dimensions; and (3) a post-training pipeline that filters 16,436 scheduled-decision examples for SFT and applies GRPO with a cognitive-diagnostic, ZPD-aware reward. The reward maintains Kalman-filtered capability estimates for each behavioral dimension, upweights dimensions with larger capability deficits, and uses rollout scores as task-level ZPD matches to focus optimization on learnable weak skills. On a benchmark with 55 personas, 50 scenarios, 50 persona-scenario bindings, and 100 role-conditioned cases per model, we evaluate 16 systems spanning frontier baselines, open models, thinking/no-think variants, and SFT/RL ablations. The strongest non-trained baseline reaches 32.00% strict ACC, while Qwen3.6-27B-SFT+RL reaches 39.00% strict ACC and a 98.5 overall score. In the 9B no-think setting, SFT and RL improve strict ACC from 0.00% to 13.00% and 18.37%. These results show that anthropomorphic dialogue benefits when generation, evaluation, and reward shaping share the same behavioral dimensions. --- ### UPAIR: Diagnosing Reasoning States via Uncertainty-Progress Alignment for Selective Intervention Authors: Cheng Yan, Zhijun Fan, Guangyang Ye, Fan Xu, Xiang Xia, Yawei Wang, Wuyang Zhang Published: 2026-07-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.17188v2 While test-time scaling improves the problem-solving ability of large reasoning models (LRMs) through additional inference-time computation, it can also exacerbate overthinking and underthinking, which we formulate as reasoning state--action mismatch. Resolving this mismatch requires reliable reasoning state diagnosis, yet single-signal monitors provide ambiguous evidence, while steering-based controllers often rely on outcome-labeled supervision or model-specific calibration. We introduce the Uncertainty--Progress Alignment Hypothesis, which posits that the relative transition timing of proxy answer uncertainty and latent reasoning progress distinguishes healthy, stagnant, and ready states that warrant different subsequent actions. Building on this insight, we propose UPAIR, a training-free framework that couples lightweight uncertainty monitoring with event-triggered joint diagnosis and maps the resulting state to native continuation, selective strategy switching, or verification-guided stopping. Across three LRMs and five cross-domain benchmarks, the stagnation diagnosis detects 64.3% of natural errors while flagging only 5.4% of correct samples, revealing a dynamic reasoning regularity shared across models and tasks. End to end, UPAIR improves accuracy by up to 16.67 percentage points and reduces generated tokens by up to 29.64%, demonstrating the effectiveness of its integrated diagnosis and intervention, while online diagnosis costs less than 1% of natural-generation time. --- ### Is Your Model Thinking or Just Stagnating? PUMA: Diagnosing Reasoning Pathology via Phase-Momentum Alignment Authors: Cheng Yan, Guangyang Ye, Wuyang Zhang, Fan Xu, Zhijun Fan, Xiang Xia, Yanyong Zhang Published: 2026-07-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.17188v1 Test-time scaling empowers Large Reasoning Models (LRMs) to tackle complex tasks via extensive Chain-of-Thought (CoT). However, this often induces the "overthinking" paradox, where redundant reasoning increases computational overhead without guaranteeing accuracy. Existing test-time efficiency optimization methods primarily fall into two categories: information-theoretic approaches, which are prone to "deceptive convergence" where low uncertainty masks hallucinations, and latent representation analyses, which are often post-hoc, lacking the real-time sensitivity for dynamic reasoning. To bridge this gap, we first posit the Phase-Momentum Alignment Hypothesis, asserting that reasoning correctness hinges on the temporal synchronization between geometric momentum and uncertainty resolution. We then theoretically formulate the Cognitive-Energy Model to characterize these dynamics through two orthogonal dimensions: Geometric Cognitive Effort, quantified by latent velocity and tortuosity, and Entropic Cognitive Uncertainty. To operationalize this, we introduce PUMA (Phase-Uncertainty Momentum Alignment), a training-free framework employing a tiered diagnostic architecture. By coupling lightweight phase monitoring with event-triggered geometric analysis, PUMA effectively distinguishes active exploration from passive stagnation, enabling precise interventions through adaptive truncation or corrective measures. Extensive experiments on LRMs spanning 1.5B to 32B demonstrate that PUMA consistently outperforms state-of-the-art baselines across diverse benchmarks, achieving a superior accuracy-efficiency trade-off and robust cross-domain generalization. --- ### BanClickThumb: A Multimodal Dataset and Transformer Fusion Benchmarks for Clickbait Detection in Bengali YouTube Videos Authors: Md. Ariful Islam, Md Tanvirul Islam, Md. Maruf Hossain Miru, Md Khalid Syfullah Published: 2026-07-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.17182v1 Clickbait, where video titles and thumbnails exaggerate or misrepresent content, reduces user trust, wastes attention, and promotes misinformation on video-sharing platforms. Detecting Bengali clickbait remains challenging because publicly available multimodal datasets are limited. To address this gap, we introduce BanClickThumb, a curated dataset of 7,147 Bengali YouTube thumbnail-title pairs from five content domains, annotated by ten annotators with high agreement (Cohen's Kappa: 0.83-0.93). Using this dataset, we benchmark text-only, image-only, and multimodal approaches. Among unimodal models, BanClickTextFormer (XLM-RoBERTa) achieves 0.82 accuracy, while BanClickImageFormer (SwiftFormer) reaches 0.68. Our proposed multimodal model, BanClickFusionFormer, combines ViT and XLM-RoBERTa through intermediate fusion and achieves the best accuracy of 0.84. Error analysis shows that dense thumbnail text, figurative language, and culturally specific slang remain challenging. Our findings demonstrate the effectiveness of multimodal fusion for Bengali clickbait detection and provide a publicly available benchmark to support future research on low-resource multimodal content analysis. --- ### Talaria: Session-Aware Serverless Serving of Hundred-Billion-Parameter LLMs Authors: Utopia Meng, Unicornt Zhao, Derek Li, Goalen Gao, Frank Du Published: 2026-07-19 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2607.17181v1 Serverless multi-model LLM systems multiplex popularity-skewed model catalogs over shared GPU pools, yet typically schedule each request independently. Tool-using agents break this abstraction: a session repeatedly calls an LLM across short tool gaps, carries a long reusable KV prefix, and is judged by session completion time (SCT). Load-only routing can separate a continuation from both its model and KV state, while round-based model multiplexing can delay even a correctly placed continuation until the target model's next slot. Both failures are especially costly for hundred-billion-parameter models: their weights constrain residency, while long-context KV is expensive to reconstruct or move. We present Talaria, a session-aware serverless multi-model serving system that makes session continuity a joint placement-and-admission decision. Its router ranks placements by model residency, KV locality, and instance pressure, while soft reservations account for likely returns in the last serving instance's admission budget. Session-prefill (SP) admits budget-eligible continuations before the active model slot closes. An instance-local substrate keeps HBM addresses stable, preserves host-restorable KV, and stages weights across model switches. On a single TP=8 server, we replay 30 SWE-Bench model-sessions (960 calls) over three models, each with more than 100B total parameters. Against an otherwise identical round scheduler with SP, host-KV restoration, and D2D staging disabled, Talaria cuts p50 SCT from 1000 s to 189 s and p95 from 2296 s to 867 s, speedups of 5.3x and 2.6x. --- ### DADIR: Density-Aware Data-level Imbalanced Regression Framework Authors: Shermin Shahbazi, Hossein Mohammadi, Mohsen Afsharchi Published: 2026-07-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.17178v1 Imbalanced learning addresses predictive modeling problems with underrepresented regions of the data distribution. Although widely studied in classification, imbalanced regression remains challenging because of continuous target variables and heterogeneous density distributions. Existing data-level methods often rely on fixed target partitioning or synthetic sample generation without jointly considering density variations and local feature-space structure. We propose DADIR, a Density-Aware Data-level Imbalanced Regression framework that exploits density information throughout the balancing process. DADIR comprises three components: (1) Density-Aware Adaptive Partitioning (DAAP), which recursively partitions the target space according to density variations; (2) a Density-Regularized Conditional Variational Autoencoder (DR-CVAE), which preserves sparse-region representations while learning latent features; and (3) latent-space data balancing, which combines feature-level clustering with oversampling to generate structurally consistent synthetic samples. Together, these components identify minority regions more effectively, preserve sparse-region information, and generate realistic synthetic data. The resulting balanced dataset can be used directly with existing regression models without modifying their architecture or learning objective. Experiments on diverse imbalanced regression datasets demonstrate consistent improvements in predictive performance, particularly in underrepresented regions, while also improving overall accuracy. --- ### KyrgyzLLM-Bench: Benchmarking Kyrgyz Language Understanding Authors: Timur Turatali, Aida Turdubaeva, Rustem Izmailov, Anton M. Alekseev, Sergey I. Nikolenko Published: 2026-07-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.17173v1 Evaluating large language models (LLMs) across languages remains challenging, as most multilingual benchmarks rely on translated English datasets, often obscuring linguistic and cultural specificity in the target language. This issue is particularly pronounced for less-resourced languages such as Kyrgyz, where reliable natively authored evaluation data are scarce. Building on previously introduced Kyrgyz-language evaluation datasets, this work reports the first systematic and large-scale evaluation of LLMs in Kyrgyz using the KyrgyzLLM-Bench benchmark suite. KyrgyzLLM-Bench comprises two natively authored datasets$-$KyrgyzMMLU and KyrgyzRC$-$together with carefully translated and manually post-edited versions of WinoGrande, HellaSwag, BoolQ, and TruthfulQA. We evaluate 26 open- and closed-source LLMs under zero-shot and few-shot settings, analyzing model performance, cross-lingual transfer, and the impact of translation artifacts on evaluation reliability. Across families and tasks, model rankings transfer broadly from English to Kyrgyz on WinoGrande and BoolQ, and to a lesser extent on MMLU, while HellaSwag exhibits a substantial English-Kyrgyz performance gap consistent with translation-induced plausibility shifts. Few-shot prompting improves several open-source models on reading comprehension but behaves inconsistently for proprietary models on translated tasks. We publicly release all datasets, evaluation code, and per-model results, and integrate the Kyrgyz tasks into a widely used multilingual evaluation framework to support future research on Kyrgyz NLP. --- ### Explaining and Tuning Transformer-based LLMs in Arithmetic Tasks with Human Strategies Authors: Luyu Qiu, Jianing Li, Hwanhee Kim, Xiaoyong Wei, Yueyuan Zheng, Janet Hsiao, Lei Chen Published: 2026-07-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.17166v1 Transformer-based large language models (LLMs) continue to achieve state-of-the-art performance across various natural language processing tasks. However, their subpar performance on seemingly elementary problems, such as basic arithmetic, raises concerns about model reliability, safety, and ethical deployment. In this study, we demonstrate that the performance of a vanilla Transformer model trained on integer arithmetic tasks can be improved using methods effective for human learners. We begin by decomposing the arithmetic task into well-defined subtasks and conducting loss convergence order analysis together with ablation studies for each subtask. Our findings reveal that LLMs exhibit learning patterns similar to those of human learners, with a faster learning speed for simpler subtasks compared to more complex ones. In addition, we successfully improved the accuracy of LLMs by applying problem-solving strategies and cognitive empowerment methods shown to enhance the performance of human learners. This suggests that transformer-based LLMs may share cognitive processes with human learners in arithmetic. Lastly, we provide a comprehensive demonstration of our method's effectiveness, including significant accuracy improvement experiments, visualization verification, and explanation-based analysis to illuminate the intricacies of LLMs in arithmetic learning. In general, this work explores the potential similarities between transformer-based LLMs and human learners, supported by explainable AI (XAI) verifications, ultimately fostering trust in LLMs for critical and high-stakes applications. --- ### Robust Assamese Speech Recognition through Controlled Fine-Tuning of Whisper Models Authors: Ganapati Das, Dwipen Laskar, Hasin Afzal Ahmed, Sanjib Kr Kalita, Kshirod Sarmah, Hem Chandra Das, Manjula Kalita Published: 2026-07-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.17164v1 Developing Automatic Speech Recognition (ASR) for morphologically rich, low-resource languages such as Assamese is challenging due to insufficient annotated speech data. The pretrained Whisper model performs poorly on Assamese speech recognition tasks. This paper presents a controlled, fine-tuned Whisper-based Assamese ASR system trained on the Mozilla Common Voice 24.0-Assamese corpus. A hardware-aware optimized training pipeline is implemented for resource-constrained environments, employing mixed-precision training and gradient accumulation on Tesla 4 Graphics Processing Units (T4 GPUs). The proposed fine-tuned model significantly outperformed the Zero-shot baseline, yielding Word Error Rate (WER), Character Error Rate (CER), Match Error Rate (MER), and Word Infomation Loss (WIL) of 43.17\%, 13.18\%, 43\%, and 64.81\%, respectively, achieving significant relative improvements of 78.26\%, 93.10\%, 57.0\%, and 35.19\% over the baseline. Semantic evaluation of the fine-tuned model also demonstrates notable improvement over a zero baseline, attaining Bilingual Evaluation Understudy (BLEU) and Metric for Evaluation of Translation with Explicit ORdering (METEOR) scores of 30.81 and 0.5262, respectively. Additionally, the predicted hallucination rate and Real-Time Factor (RTF) are substantially improved by 96.70\% and 32.38\%, compared to the zero-shot baseline. --- ### VLA-ReID: Video-Level Association for Re-Identification in Multi-Object Tracking with Highly Similar Objects Authors: Yanrong Qin, Xiaoyan Cao, Yao Yao Published: 2026-07-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.17157v1 Multi-object tracking (MOT) aims to localize multiple objects in videos while preserving their identities over time. Long-term identity preservation remains difficult when objects are small, densely distributed, and highly similar in appearance, as in bee swarm scenes. Existing trackers rely on re-identification (re-ID) models trained through single-instance assignment (instance-level querying). At inference, however, MOT requires global assignment between multiple trajectories and detections, corresponding to video-level querying. This training-inference mismatch can cause identity switches among visually similar objects. Existing approaches also often require substantial additional annotations to enhance appearance discrimination. We propose Video-Level Association re-ID (VLA-ReID), which reformulates re-ID as video-level association modeling. It uses aggregated historical trajectory features as queries and all current-frame detections as candidates, enabling direct optimization of their global association at each frame. In addition, Frame-Common Appearance Estimation (FCAE) estimates a common appearance direction from current-frame detections, while Common-Appearance Suppression (CAS) removes the corresponding component along this direction from trajectory and detection features. This amplifies discriminative differences among highly similar objects without additional annotations. Experiments on BEE24 show that VLA-ReID improves HOTA by 1.1, MOTA by 0.3, AssR by 2.6, AssA by 0.7, and IDF1 by 0.8 over state-of-the-art trackers, while reducing identity switches by 28%. These results demonstrate the effectiveness of video-level re-ID modeling for appearance-based association in MOT. --- ### OrderMoE: An expert similarity driven distributed edge MoE inference Authors: Xin Yuan, Ning Li, Quan Chen, Wenchao Xu, Song Guo Published: 2026-07-19 Categories: cs.NI, cs.DC, cs.LG arXiv: https://arxiv.org/abs/2607.17154v2 Although mixture-of-experts, MoE, models have been increasingly adopted to scale large language models with moderate computation cost, it remains challenging to deploy MoE inference over resource-constrained and bandwidth-limited edge infrastructures. Existing distributed MoE serving methods mainly rely on exact expert placement, caching, replication, or communication scheduling, while overlooking the functional similarity among experts, which provides an opportunity to reduce cross-server token transmission. Therefore, this paper introduces a similarity-aware expert allocation and distributed deployment framework, dubbed OrderMoE, which aims to accelerate edge MoE inference while balancing inference latency, communication overhead, server workload, and inference quality. OrderMoE first constructs an expert similarity model based on router-induced logits representations and partitions experts in each MoE layer into multiple similarity groups. Then, it develops a similarity-aware expert grouping and deployment strategy to improve local similarity coverage across edge servers. Since reducing remote expert invocation and preserving exact inference quality are conflicting objectives, OrderMoE further designs a quality-aware and trajectory-aware runtime server-expert selection algorithm to decide whether a token should invoke its remote target expert or use a feasible local substitute expert. Experimental results on a real distributed edge testbed show that OrderMoE significantly reduces average latency, tail latency, cross-server traffic, and remote expert invocation ratio, while introducing only small and controllable inference quality degradation. --- ### OrderMoE: An expert similarity driven distributed edge MoE inference Authors: Xin Yuan, Ning Li, Quan Chen, Wenchao Xu, Athanasios V. Vasilakos, Song Guo, Haijun Zhang Published: 2026-07-19 Categories: cs.NI, cs.DC, cs.LG arXiv: https://arxiv.org/abs/2607.17154v1 Although mixture-of-experts, MoE, models have been increasingly adopted to scale large language models with moderate computation cost, it remains challenging to deploy MoE inference over resource-constrained and bandwidth-limited edge infrastructures. Existing distributed MoE serving methods mainly rely on exact expert placement, caching, replication, or communication scheduling, while overlooking the functional similarity among experts, which provides an opportunity to reduce cross-server token transmission. Therefore, this paper introduces a similarity-aware expert allocation and distributed deployment framework, dubbed OrderMoE, which aims to accelerate edge MoE inference while balancing inference latency, communication overhead, server workload, and inference quality. OrderMoE first constructs an expert similarity model based on router-induced logits representations and partitions experts in each MoE layer into multiple similarity groups. Then, it develops a similarity-aware expert grouping and deployment strategy to improve local similarity coverage across edge servers. Since reducing remote expert invocation and preserving exact inference quality are conflicting objectives, OrderMoE further designs a quality-aware and trajectory-aware runtime server-expert selection algorithm to decide whether a token should invoke its remote target expert or use a feasible local substitute expert. Experimental results on a real distributed edge testbed show that OrderMoE significantly reduces average latency, tail latency, cross-server traffic, and remote expert invocation ratio, while introducing only small and controllable inference quality degradation. --- ### How Jailbreak Attacks Inform Safety Alignment: A Defender-Centric, Shapley-Based Evaluation of Jailbreak Contributions Authors: Yukai Zhou, Feiyang Lu, Xiaokai Mao, Jinfei Liu, Wenjie Wang Published: 2026-07-19 Categories: cs.CR, cs.CL arXiv: https://arxiv.org/abs/2607.17152v1 Jailbreak attacks on large language models are usually evaluated by attacker-centric metrics such as attack success rate (ASR), yet an attack that breaks a model is not necessarily useful for improving its safety. We propose a defender-centric view of jailbreak evaluation, where attacks are evaluated by the downstream safety improvements they enable when used as red-teaming data for safety training. Building on this view, we introduce A-MESS (Minimal Effective Attack-Subset Selection), a setting-agnostic framework for attributing and selecting jailbreak attacks from black-box subset utility observations. A-MESS estimates AttackSHAP, a Shapley-based score that attributes marginal utility to individual attacks and selects compact attack subsets under user-specified budgets via greedy or surrogate-based optimization. Across controlled utility landscapes and real LLM safety settings, we find that ASR rankings are weakly aligned with defender-centric utility, that AttackSHAP can be estimated accurately with limited utility queries, and that directly optimizing subsets yields stronger safety utility than attacker-centric or attribution-only selection. These results suggest evaluating jailbreak attacks as resources for improving safety, not only as tools for breaking models. --- ### A Diagnostic Framework for AI Agent Behavior Authors: Xichen Zhang, Yingjie Zhang, Tianshu Sun Published: 2026-07-19 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2607.17149v1 AI agents increasingly act within the same clinical, political, scientific, and social systems that behavioral scientists study. Evaluating these systems requires source-level diagnosis: the same behavioral pattern may arise from an agent representational substrate or from the roles, objectives, interaction structures, and governance rules that shape its expression. This Perspective proposes a diagnostic framework for AI agent behavior: layer attribution. The foundational computational layer defines what behaviors are possible through architecture, memory, perception, attention, and representation. The behavioral modulation layer shapes how those capacities are expressed through identity, resources, objectives, social interaction, institutional constraints, and governance. The framework clarifies three consequences: surrogate validity is a model-task-layer relation, human-AI divergence provides diagnostic evidence, and governance requires source attribution before intervention. Treating AI agents as behavioral actors therefore requires evaluation methods that determine where behavior originates before deciding how to explain, validate, or govern it. --- ### Noise-Robust Box-Supervised Infrared Small Target Detection via Physics-Inspired Soft Label Optimization Authors: Xizhe Zhang, Fan Shi, Mianzhao Wang, Jiangpeng Zheng, Xu Cheng, Shengyong Chen Published: 2026-07-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.17148v1 Infrared small target detection (IRSTD) commonly relies on pixel-level mask supervision. Such annotations, however, are costly and inherently uncertain because infrared targets have blurred boundaries and weak textures. We formulate box-supervised IRSTD as a problem distinct from generic box-to-mask segmentation and point-supervised IRSTD. Its central challenge is to construct stable pixel-level soft supervision from highly contaminated boxes. To this end, we propose Hotspot-Anchored Label Optimization (HALO). HALO localizes a radiometric anchor inside each box under local background-statistics constraints, then synthesizes a Physically Anchored Gaussian (PAG) soft label around the anchor. This turns noisy box supervision into continuous, pixel-level soft labels. The entire process is performed offline before training, remains decoupled from the detector backbone, and requires no online label updates. Experiments on public datasets show that HALO is competitive with representative box-supervised methods under standard tight boxes. Under looser or shifted box annotations that better approximate real scenarios, HALO is substantially more robust while remaining consistent across backbones. We further introduce a contamination-aware operating-regime analysis to characterize the effective boundary of this class of methods and reveal how intrinsic signal-to-clutter ratio relates to performance. --- ### SlotGuard: Stop Oversharing Private Local Context in LLM Agent Transcri Authors: Haocheng Xia, Yongjoo Park Published: 2026-07-19 Categories: cs.CR, cs.CL arXiv: https://arxiv.org/abs/2607.17147v1 LLM agents can leak privacy (e.g., paths, emails) and credentials (e.g., API keys) as agent observations (e.g., tool outputs, shell logs, and file reads) are appended to provider-bound transcripts. Existing placeholder redaction is brittle: it can miss embedded or cross-turn references, over-redact benign lookalikes, and destroy the structure useful for reasoning. We present SlotGuard, a local transcript boundary that can hide sensitive data while retaining agents' performance. SlotGuard rewrites structural bindings as typed, suffix-aware slots, replaces secrets with format-preserving synthetic values, links cross-turn references with a lightweight session graph, and restores raw values only inside the trusted runtime. On controlled repository-oriented agent transcripts, SlotGuard removes all 20,814 annotated structurally sensitive characters across 9,229 paths and reduces credential leakage to 0.0\% across 852 planted values. It remains close to raw-transcript task success across four upstream models, while generic redaction drops to 2.5\%. Transcript rewriting takes a median of 14.424~$μ$s per agent turn. The code is publicly accessible at https://github.com/illinoisdata/SlotGuard. --- ### The Geometry of Semantic Space: A Continuous Geometric Framework for the Transformer Architecture Authors: Zhihua Liang Published: 2026-07-19 Categories: cond-mat.dis-nn, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.17146v1 We present a continuous geometric framework that models the discrete algebraic operations of the Transformer architecture as an integro-differential equation (IDE) on a semantic fiber bundle $\calE = \calM \times \R^d$. Beginning from a single geometric axiom -- that the token sequence forms a discrete $1$-manifold equipped with a canonical measure lattice -- we translate every core component of the modern Transformer (RMSNorm, RoPE, Softmax Attention, FFN, Residual Stream, SGD, Weight Decay) into a cohesive vocabulary of differential geometry, measure theory, and stochastic calculus. The resulting framework yields quantitative predictions spanning entropic optimal transport (Attention as a Schrödinger bridge) and non-equilibrium thermodynamics (SGD as Itô diffusion violating detailed balance). We conduct a six-part experimental campaign across five architectures (Qwen3, LLaMA\nobreakdash-3.1, Gemma\nobreakdash-3, GPT-2, Mistral) spanning $124$M to $8$B parameters. The empirical observables are quantitatively consistent with the geometric predictions: the $ε^{-1/2}$ Lipschitz scaling calibration at machine precision ($R^2 = 1.000$), the Lie--Trotter operator-splitting torsion, the symmetric ablation instability confirming the Dual-Law of Topological Stability, the $\calO(1/\sqrt{k})$ thermodynamic suppression of Poincaré recurrence on the RoPE torus, the thermodynamic context-limit phase transition, and the Non-Equilibrium Steady State parameter vortex -- verified across two optimizers (AdamW and Pure SGD) to exclude momentum artifacts. The results demonstrate that analyzing Transformers through the lens of continuous stochastic differential geometry provides a predictive descriptive vocabulary for the stability limits, context bounds, and optimization dynamics of Large Language Models. --- ### Fenced Citation-Context Retrieval for Case Law: Temporal Leakage and Degree Control Across Two Jurisdictions Authors: Yao Liu, Tien-Ping Tan, Zhilan Liu Published: 2026-07-19 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2607.17142v3 Prior case retrieval (PCR) aims to identify the precedent cases relevant to the facts of a query case. Incoming citation context, the text with which later cases characterize a case when citing it, is a powerful relevance signal, yet it is typically evaluated without a temporal constraint, so the retriever is credited with citations made after the query. We introduce a temporally fenced retriever with no learned parameters that augments BM25 with incoming citation context restricted to citations predating the query, together with a temporal-admission decomposition that quantifies the phantom fraction: the share of a citation-context gain attributable to citations not known to predate the query. Experiments span two jurisdictions, U.S. federal (CLERC) and European (ECtHR-PCR) case law. On ECtHR-PCR, without any training, the fenced retriever outperforms a strong degree-controlled baseline across the full recall ladder, and a temporal-admission decomposition attributes 14.9% (validation) of an unfenced citation-context gain over BM25 to citations not known to predate the query. Citation-context retrieval must therefore be temporally fenced and degree-controlled before its reported gains can be interpreted. --- ### STBridge: Shared-Target Alignment for Bridging Understanding and Generation in UMMs Authors: Ye Wang, Hongjun Wang, Hao Fang, Tongyuan Bai, Zuwei Long, Peixian Chen, Wei Liu, Weibo Gu, Xing Sun, Rui Ma Published: 2026-07-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.17140v1 Unified multimodal models (UMMs) aim to integrate visual understanding and generation within a single architecture, but architectural unification alone does not ensure semantic consistency. A model may describe the intended target correctly while generating an inconsistent edit. This exposes an understanding-generation alignment gap: linguistic and visual outputs live in different spaces, yet should be governed by the same target semantics. We study this gap in image editing, where an instruction defines a target state that can be both described and visually realized. Given a source image and an edit instruction, we compare a UMM's target caption with its edited image to test whether the two outputs converge on the same result. Our analysis shows that existing UMMs remain weakly aligned, especially for fine-grained entities, attributes, spatial relations, and local details, indicating that semantic unification is not achieved by architecture alone. To bridge this gap, we propose STBridge, a shared-target alignment framework that connects understanding and generation through a common target state. Here the target caption expresses the desired visual result, while the edited image realizes it visually, replacing separate task-specific paths with a shared information flow from target expression to target realization. STBridge follows an align-then-optimize strategy: supervised fine-tuning first establishes the shared-target channel, and sequential reinforcement learning further refines target-centered coordination. Across visual understanding, image generation, and image editing benchmarks, STBridge consistently improves over the initialization model. Alignment analysis confirms that STBridge narrows the gap between what the model describes and what it generates, demonstrating shared-target alignment as an effective post-training strategy for bridging understanding and generation in UMMs. --- ### SynH-Rank: Quality-Aware Code Search via Diverse Data Synthesis and Hierarchical Ranking Training Authors: Keyu Liang, Haoye Wang, Yanfu Yan, Zhiyuan Wan, Zhongxin Liu Published: 2026-07-19 Categories: cs.SE, cs.CL arXiv: https://arxiv.org/abs/2607.17139v2 Code search enhances developer productivity by enabling efficient code reuse. Current code search systems often use a retrieve-then-rerank pipeline, where rerankers focus on modeling semantic relevance between queries and code. However, these rerankers overlook critical non-functional qualities like execution speed, memory usage, and maintainability, which are essential for practical software development. Studies reveal developers expect results to maintain high coding standards and satisfy specific needs, such as resource optimization, highlighting the importance of quality-aware code search. Achieving quality-aware code search faces two major challenges: the scarcity of quality-annotated datasets for effective training and the limitations of standard contrastive learning objectives, which fail to capture the ordinal relationships among high-quality, low-quality, and irrelevant code. Although contrastive learning excels in distinguishing relevant from irrelevant code, its binary objective does not support nuanced quality distinctions. To address these challenges, we propose SynH-Rank, a quality-aware code reranking framework that combines LLM-driven diverse data synthesis with hierarchical ranking training. SynH-Rank employs a three-level labeling scheme to explicitly model the hierarchy: high-quality relevant > low-quality relevant > irrelevant. Additionally, we introduce a new benchmark with 4,209 pairs and two novel metrics: Quality Preference Accuracy (QPA) for assessing prioritization of high-quality code and Multi-Condition Accuracy (MCA) for evaluating performance under complex constraints. Experimental results show SynH-Rank improves QPA by 20.15\% over backbone models and outperforms standard relevance-only contrastive training by 15.80\%, while simultaneously enhancing traditional relevance metrics and multi-condition generalizability. --- ### SynH-Rank: Quality-Aware Code Search via Diverse Data Synthesis and Hierarchical Ranking Training Authors: Keyu Liang, Haoye Wang, Yanfu Yan, Zhiyuan Wan, Zhongxin Liu Published: 2026-07-19 Categories: cs.SE, cs.CL arXiv: https://arxiv.org/abs/2607.17139v1 Code search enhances developer productivity by enabling efficient code reuse. Current code search systems often use a retrieve-then-rerank pipeline, where rerankers focus on modeling semantic relevance between queries and code. However, these rerankers overlook critical non-functional qualities like execution speed, memory usage, and maintainability, which are essential for practical software development. Studies reveal developers expect results to maintain high coding standards and satisfy specific needs, such as resource optimization, highlighting the importance of quality-aware code search. Achieving quality-aware code search faces two major challenges: the scarcity of quality-annotated datasets for effective training and the limitations of standard contrastive learning objectives, which fail to capture the ordinal relationships among high-quality, low-quality, and irrelevant code. Although contrastive learning excels in distinguishing relevant from irrelevant code, its binary objective does not support nuanced quality distinctions.To address these challenges, we propose SynH-Rank, a quality-aware code reranking framework that combines LLM-driven diverse data synthesis with hierarchical ranking training. SynH-Rank employs a three-level labeling scheme to explicitly model the hierarchy: high-quality relevant > low-quality relevant > irrelevant. Additionally, we introduce a new benchmark with 4,209 pairs and two novel metrics: Quality Preference Accuracy (QPA) for assessing prioritization of high-quality code and Multi-Condition Accuracy (MCA) for evaluating performance under complex constraints.Experimental results show SynH-Rank improves QPA by 20.15\% over backbone models and outperforms standard relevance-only contrastive training by 15.80\%, while simultaneously enhancing traditional relevance metrics and multi-condition generalizability. --- ### Denoising Models Develop Human-Like Perceptual Illusion Representations Across Architectures Authors: Gautam Ranka, Paras Chopra Published: 2026-07-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.17138v2 Deep neural networks trained on natural images are shown to produce outputs consistent with human observers for brightness illusions. While this phenomenon has been documented across architectures, all evidence, to date, is measured at the output level: restored pixels, decoded trajectories, or classification decisions. Whether these models actually represent illusions internally, and if so where and how, remains unknown. We show that denoising models develop illusion-sensitive representations at specific internal layers, across varied architectures. Specifically, we identify the layers and channels that discriminate illusory from physically matched control regions. We show that the denoising objective is a more important driver of the effect than the architecture. On domain-appropriate stimuli, these activations track a validated psychophysical model of human brightness perception (FLODOG; Spearman $ρ\geq 0.70$) and scale monotonically with parametric illusion strength. Leveraging these findings, we provide causal evidence via channel ablation showing that illusion-sensitive channels specifically and substantially affect the internal signal. Yet injecting these representations into the generation pipeline produces no measurable pixel shift across all tested architectures; we term such representations perceptual phantoms: active in internal processing yet invisible to any output-based evaluation. While related internal-output dissociations have been characterized in language models, this is the first such characterization for perceptual representations in denoising vision models. --- ### Denoising Models Develop Human-Like Perceptual Illusion Representations Across Architectures Authors: Gautam Ranka, Paras Chopra Published: 2026-07-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.17138v1 Deep neural networks trained on natural images are shown to produce outputs consistent with human observers for brightness illusions. While this phenomenon has been documented across architectures, all evidence, to date, is measured at the output level: restored pixels, decoded trajectories, or classification decisions. Whether these models actually represent illusions internally, and if so where and how, remains unknown. We show that denoising models develop illusion-sensitive representations at specific internal layers, across varied architectures. Specifically, we identify the layers and channels that discriminate illusory from physically matched control regions. We show that the denoising objective is a more important driver of the effect than the architecture. On domain-appropriate stimuli, these activations track a validated psychophysical model of human brightness perception (FLODOG; Spearman $ρ\geq 0.70$) and scale monotonically with parametric illusion strength. Leveraging these findings, we provide causal evidence via channel ablation showing that illusion-sensitive channels specifically and substantially affect the internal signal. Yet injecting these representations into the generation pipeline produces no measurable pixel shift across all tested architectures; we term such representations perceptual phantoms: active in internal processing yet invisible to any output-based evaluation. While related internal-output dissociations have been characterized in language models, this is the first such characterization for perceptual representations in denoising vision models. --- ### Teach it to stop, not just to click Authors: Barada Sahu, Shivesh Pandey Published: 2026-07-19 Categories: cs.SE, cs.AI, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2607.17136v1 Agentic computer-use RL is reported in single runs, and those numbers mislead. Using verifier-guided repair of a 35B computer-use agent (CUA) across five oracle-graded environments, we show a repaired policy's success rate is dominated by upstream variance: a variance-components decomposition across three cells (crossed data-draw $\times$ seed grid, bootstrap CIs) finds evaluation variance negligible ($σ_{\mathrm{eval}} \approx 0$) and the training-seed effect small everywhere ($\leq 10\%$); instead it splits between the data draw and run-to-run nondeterminism, the data draw's share rising to dominant ($48\%$) on the hardest cell. There the run-to-run distribution is bimodal (Hartigan dip $p=0.07$, $k=10$), so a single run has roughly a 30% chance of the failure mode and mean$\pm$std is the wrong summary. On that footing, two findings hold. First, repairability is two-tier in how constrained the corrective action is: a single fixed token installs reliably (done-detection $0.97\pm0.06$), while open-ended corrections are only partial -- spatial-coordinate clicks (grounding $0.53\pm0.35$) and a generative field-fill ($0.14\pm0.04$). Second, the frame-level repair transfers to task success only when the corrective action is the task's sole remaining blocker (LinkedIn 8/20 vs. base 0/15, Fisher $p=0.006$). We caught two of our own over-claims -- a sample-efficiency curve and a 'grounding cannot be bought' boundary -- only by replicating across seeds; a stress test makes the stakes external: a single-run improvement of the size this field publishes would have the wrong sign roughly one-third of the time in a comparable regime. We release a library (cua_reliability) for routine k-seed reporting. The apparatus is, to our knowledge, the first multimodal segment-aggregated on-policy self-distillation (SA-OPSD) update on a real 35B CUA policy. --- ### Scope3Trace: Evidence-Based Identification and Extraction of Scope 3 GHG Emissions from Sustainability Reports Authors: Siyuan Zheng, Yifan Duan, Chao Xue, Flora D. Salim Published: 2026-07-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.17122v2 Scope 3 greenhouse gas (GHG) emissions account for the majority of corporate carbon footprints, yet remain difficult to analyze at scale due to sparse disclosures, heterogeneous report document formats, and limited evidence traceability. Existing approaches typically rely on large language models to extract emissions information from ESG reports, but often lack explicit evidence grounding or depend on costly manual annotation and verification to ensure extraction reliability. To address these challenges, we propose Scope3Trace, an evidence-grounded information extraction framework designed to extract interpretable and traceable Scope 3 emissions information from real-world ESG and sustainability reports. The framework integrates a document information extraction pipeline that performs PDF collection and OCR parsing, LLM-assisted page localization and table reconstruction, and hybrid rule-LLM extraction of organization- and building-level emissions disclosures with evidence-grounded verification. Building upon this framework, we further contribute a dual-level, evidence-grounded, multimodal dataset comprising organization-level Scope 3 disclosures extracted from heterogeneous sustainability reports. Scope3Trace enables reliable extraction and transparent integration of heterogeneous sustainability disclosures, achieving high accuracy in extracting Scope 1-3 totals and category-level disclosures from sustainability reports. --- ### Scope3Trace: Evidence-Based Identification and Extraction of Scope 3 GHG Emissions from Sustainability Reports Authors: Siyuan Zheng, Yifan Duan, Chao Xue, Flora D. Salim Published: 2026-07-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.17122v1 Scope 3 greenhouse gas (GHG) emissions account for the majority of corporate carbon footprints, yet remain difficult to analyze at scale due to sparse disclosures, heterogeneous report document formats, and limited evidence traceability. Existing approaches typically rely on large language models to extract emissions information from ESG reports, but often lack explicit evidence grounding or depend on costly manual annotation and verification to ensure extraction reliability. To address these challenges, we propose Scope3Trace, an evidence-grounded information extraction framework designed to extract interpretable and traceable Scope 3 emissions information from real-world ESG and sustainability reports. The framework integrates a document information extraction pipeline that performs PDF collection and OCR parsing, LLM-assisted page localization and table reconstruction, and hybrid rule-LLM extraction of organization- and building-level emissions disclosures with evidence-grounded verification. Building upon this framework, we further contribute a dual-level, evidence-grounded, multimodal dataset comprising organization-level Scope 3 disclosures extracted from heterogeneous sustainability reports. Scope3Trace enables reliable extraction and transparent integration of heterogeneous sustainability disclosures, achieving high accuracy in extracting Scope 1-3 totals and category-level disclosures from sustainability reports. --- ### Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions Authors: Sosuke Suzuki, Yijin Wei, Koichiro Kamide, Ran Dong, Haoran Xie, Chao Zhang Published: 2026-07-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.17121v1 Skeleton-based emotion recognition from body motion remains challenging because emotional expressions are often characterized by subtle dynamic and relational motion cues, and hard labels may not fully capture ambiguity among related emotion categories. For the DIEM-A task in the MMAC ACII 2026 Challenge, we propose a multi-branch skeleton-based emotion recognition framework that combines a 6D rotation-based branch, a part-aware kinetic multi-stream branch, and a metadata-conditioned weak label distribution learning (LDL) branch. The branches are trained independently and fused by a probability-level ensemble at inference time. In 10-fold leave-performer-out cross-validation, the proposed framework improves Accuracy from 0.271 to 0.366 and Macro-F1 from 0.252 to 0.353 over the rotation-based baseline. Explainability ablations show that velocity and bone streams, as well as arm and leg regions, provide important cues for recognizing emotional body motion. --- ### The generator is the tracker: Multi-object tracking by painting persistent identity colours Authors: Haiyu Yang, Miel Hostens Published: 2026-07-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.17120v1 Multi-object tracking (MOT) is conventionally decomposed into detection followed by association, with object identity maintained as external state: track buffers, motion models, and appearance embeddings. We ask whether a video generator can maintain that state in pixels. We fine-tune a 22B text-to-video diffusion model (LTX-2.3) with a lightweight in-context LoRA to translate an RGB clip into an ID-map clip, a video in which every person is painted a flat, distinct color that persists over time: same color, same identity. Long videos are generated as chained windows, where each window is conditioned on the cleaned tail of the previous one. A brief continuation fine-tune teaches the model to extend a given coloring, after which identity flows through the chain with no tracker, no motion model, and no re-identification module. On the DanceTrack test server, our system, to our knowledge the first generative tracker evaluated there and the only entry with no detector and no tracking stack, reaches 40.3 HOTA. This is well below today's specialist state of the art (>=70 HOTA), but with a unique, inverted error profile: its association score (AssA 44.1) exceeds every tracker of the original benchmark suite while detection remains the sole deficit. Controlled comparisons show the mechanism matters: the same generated windows linked by classical post-hoc association score 2x worse (18.2 HOTA), and frame-to-frame IoU association fragments tracks that the generator's colors keep whole. On 383 mined occlusion events, the generator re-acquires identities after gaps at a 42% conditional rate where appearance-embedding baselines score zero, including gaps longer than its temporal context, evidence that the generator's color assignment functions as an emergent re-identification signal. We release code, checkpoints, and the full pre-registered experimental log. --- ### Persistent Sparse Autoencoders: Learning Feature-Specific Timescales in Language Model Representations Authors: Haoyan Luo, Mateo Espinosa Zarlenga, Mateja Jamnik Published: 2026-07-19 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2607.17117v2 Sparse autoencoders (SAEs) decompose language model activations into sparse features, yet these models traditionally encode each token independently, failing to expose information that persists across a sequence. We first show that temporal persistence can naturally emerge in standard SAE features: after a feature activates, the hidden state remains aligned with its direction, and past activations help reconstruct later hidden states. How long this lasts varies widely across features. We therefore introduce Persistent Sparse Autoencoders (Persistent SAEs), an extension of standard SAEs that learns a persistence coefficient for each feature, allowing the model to learn feature-specific timescales from reconstruction alone. Our experiments show that Persistent SAEs retain competitive reconstruction quality while learning a spectrum of timescales: short-timescale (fast) features stay locally interpretable, whereas long-timescale (slow) features accumulate information that identifies the current context. Moreover, we show in a prompt-injection monitoring case study that slow features preserve injection-related signals and remain causally effective over long contexts. These results suggest that Persistent SAEs offer new opportunities for interpreting and monitoring language models via persistent sparse features. --- ### Persistent Sparse Autoencoders: Learning Feature Timescales in Language Models Authors: Haoyan Luo, Mateo Espinosa Zarlenga, Mateja Jamnik Published: 2026-07-19 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2607.17117v1 Sparse autoencoders (SAEs) decompose language model activations into sparse features, but standard SAEs encode each token independently and do not expose information that persists across a sequence. We introduce Persistent Sparse Autoencoders (Persistent SAEs), which extend standard SAEs by learning a persistence coefficient for each feature, allowing the model to learn which features should persist and for how long. Our experiments show that they retain competitive reconstruction quality while learning a spectrum of feature timescales: fast features behave as locally interpretable detectors, whereas slow features concentrate topic-level information in a persistent state. Moreover, as shown in a prompt-injection monitoring case study, slow features preserve detection signals and remain causally effective over long contexts. These results suggest that Persistent SAEs open up new opportunities for interpreting and monitoring language models through persistent semantic representations. --- ### BLAD: A Historically Contextualized, Multilingual Dataset of Bangladeshi Legal Acts (1799 to 2025) Authors: Adib Sakhawat Published: 2026-07-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.17111v1 We present the Bangladesh Legal Acts Dataset (BLAD), a curated collection of 1{,}484 legislative acts enacted between 1799 and 2025. Each act is represented with its full text, structured sections and footnotes, repeal status, and metadata linking it to the governing regime, head of state, and prevailing legal framework at the time of enactment. The corpus spans English, Bengali, and mixed-language documents, supporting temporal and multilingual analysis of statutory law. BLAD addresses a persistent gap in legal natural language processing (NLP) resources for low-resource, civil-law jurisdictions in South Asia. We describe the acquisition and enrichment pipeline, report descriptive statistics over more than two centuries of legislation, and outline the research directions the corpus enables. The dataset is publicly available under the CC~BY-SA~4.0 license at https://www.kaggle.com/datasets/sakhadib/bangladesh-legal-acts-dataset. --- ### Evidence Interfaces Shape How Retrieval-Augmented Readers Use Support Authors: Junchi Liao, Jiawen Deng, Fuji Ren Published: 2026-07-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.17108v1 In multi-hop RAG evaluation, a top-k answer score can hide two different failures: the retrieval window may drop part of the support chain, or it may contain support in a form the adapted reader does not use well. We call this reader-facing form of retrieved evidence an evidence interface. Using three support-annotated multi-hop QA benchmarks, we compare matched adapted readers trained with raw context, retrieval windows, and gold-support diagnostic renderings. These comparisons distinguish support-availability failures from remaining reader-interface effects. Top-k windows become interpretable only after checking whether the complete annotated support chain survives: when it does, short ranked windows can match or improve over raw context; when it does not, missing support explains much of the loss. Gold support-first improves matched readers; on 2Wiki and MuSiQue, a support-supervised ranker raises coverage and recovers raw-context quality at lower prompt cost, while retaining gold headroom. Support-removal checks further show that the gains rely on exposed evidence, not only answer priors. On support-annotated evaluations, top-k answer scores should therefore be reported together with complete-support coverage. --- ### A Multi-Model Hybrid Defense Approach Against White-box Adversarial Attacks in Computer Network Traffic Authors: Khushnaseeb Roshan Published: 2026-07-19 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2607.17105v1 It is crucial to safeguard computer networks from evolving network security threats and unknown cyberattacks. An essential tool for protecting computer networks against unknown cyber threats is Network Intrusion Detection System (NIDS). However, NIDS faces a major security concern due to its susceptibility to adversarial attacks. Adversarial attacks aim to deceive NIDS by crafting and injecting adversarial examples into the system. These adversarial inputs can deceive the NIDS into misclassifying benign network traffic as malicious. We developed a resilient hybrid defense mechanism aimed to mitigate the impact of two potent adversarial attacks: Fast Gradient Sign Method (FGSM) and Carlini & Wagner (C&W) attack. Our hybrid defense approach leverages the combined strength of two heuristic defense methods: Adversarial Training (AT) and Gaussian Data Augmentation (GDA). GDA provides multi-directional defense, while AT enhances NIDS robustness against specific adversarial vectors. Under pre-attack scenarios, NIDS demonstrated good accuracy and f1-score. However, in the post-attack scenario, its accuracy significantly dropped under FGSM and C&W attacks (0.2649 and 0.4961, respectively). Our proposed hybrid defense method effectively mitigated these adversarial threats, with post-defense accuracy of 96.57% and 89.20% for FGSM and C&W attacks. We evaluated the defense strategy across a range of epsilon and confidence noise factor values (ranging from 0.0001 to 0.0009). This research provides a good direction for future researchers in the emerging area of adversarial machine learning from a security perspective. --- ### Auto Research for Materials: Auditable AI-Scientist Workflows with Held-Out Transfer Authors: Jingjie Ning, Xiaochuan Li, Shanshan Zhong, Ji Zeng, Guolin Ke Published: 2026-07-19 Categories: cs.MA, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2607.17100v2 Auto Research uses language-model agents to propose, implement, and evaluate machine-learning changes in a closed loop, but is usually judged by its terminal pipeline. A terminal score cannot reveal which technical decision produced a gain or distinguish a reusable discovery from a change adapted to development feedback. We introduce intervention-centered Auto Research, which validates research decisions rather than only final artifacts and makes their reliability measurable. Feature, Model, Representation, and Data axes are searched independently with inner five-fold feedback. Each axis winner is frozen before an outer-holdout matrix compares all alternatives on evidence the loop never sees. Across 701 agent-executed attempts spanning ten Matbench endpoints, outer evidence confirms the selected intervention on nine of ten endpoints and preserves 89.3\% of non-tied intervention orderings. It also rejects an aggregate Representation gain that inner feedback endorsed. The resulting matrix reveals an information-dependent hierarchy. Composition-only tasks support several routes to improvement, whereas structure-informed tasks favor local geometry features and complementary tree ensembles. A subsequent compatibility test combines already frozen Feature and Model code without further search or tuning and raises mean outer-holdout improvement from 19.0\% to 26.3\%. By validating decisions rather than only artifacts, this design turns adaptive search into reusable evidence wherever agents propose executable alternatives against a fixed evaluator. --- ### DepthART: Scaling Foundation Monocular Depth to Tiny Models Authors: Feng Xue, Wu Chen, Mingshuai Zhao, Guofeng Zhong, Anlong Ming, Haozhe Wang, Dianqiao Lei, Zhaowen Lin, Haiyang Zhang, Nicu Sebe Published: 2026-07-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.17099v1 Recent geometric foundation models (e.g., Metric3D, Depth Anything and UniDepth) have substantially improved monocular depth estimation (MDE) in both cross-scene generalization and metric-scale prediction, yet these gains have not translated to tiny models. We bridge this gap with DepthART (Depth Anything Rethought for Tiny Models), which is a compact MDE model for on-device deployment across diverse scenes. We first identify two capacity-driven bottlenecks in tiny models: (i) overfitting to dataset-specific distribution bias and (ii) unstable metric adaptation under camera shift, where full fine-tuning easily damages transferable geometry. Accordingly, DepthART combines two simple but effective strategies: a bias-resistant data sampling scheme to reduce distribution bias under the same training budget, and a camera-conditioned fine-tuning protocol that freezes the distilled encoder and adjusts metric scale conditioned on intrinsics while better preserving cross-dataset generalization. Across datasets, DepthART consistently surpasses previous tiny baselines in both zero-shot generalization and metric accuracy (e.g., zero-shot $δ_1$=0.964 for DepthART-S on NYUD v2), and in some cases approaches heavy models. We further provide a scalable model family, with DepthART-S reaching 347/245 FPS (strict FP32) on an RTX A6000 at $224^2/448^2$, 102 FPS (TF32) on a Orin NX 8GB, and over 15 FPS (FP32) on a Jetson Nano 4GB. --- ### HarmoHOI: Harmonizing Appearance and 3D Motion for Multi-view Hand-Object Interaction Synthesis Authors: Lingwei Dang, Juntong Li, Zonghan Li, Hongwen Zhang, Liang An, Wei Min, Yebin Liu, Qingyao Wu Published: 2026-07-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.17097v2 Hand-Object Interaction (HOI) synthesis is a cornerstone for animation production and embodied AI. Despite the strong priors of video foundation models, multi-view consistent HOI synthesis remains challenging due to complex hand motions and occlusions. We present HarmoHOI, a unified diffusion framework that jointly and harmoniously generates synchronized multi-view HOI videos and globally aligned 3D point tracks. Our core insight is that robust multi-view consistency fundamentally requires globally aligned 3D geometry and motion. To this end, we propose a Mixture of Multi-view Diffusion Transformer that co-models RGB videos and 3D point tracks. By representing point tracks as pseudo-videos, we align 3D geometric signals with the 2D latent space of foundation models, thereby minimizing the domain gap and easing adaptation of priors. To further ensure geometry consistency, we introduce Global Motion Aligning Diffusion, which refines coarse point tracks into metric-scale, globally aligned 3D trajectories. HarmoHOI enables on-the-fly co-evolution of 2D appearance and 3D motion during denoising. To overcome the scarcity of multi-view HOI data, we employ a hybrid data curriculum learning strategy that successfully transfers generic priors from single-view data to synchronized multi-view generation. Experimental results show that HarmoHOI achieves state-of-the-art performance in visual quality, motion plausibility, and multi-view geometric consistency. Project page available at https://droliven.github.io/HarmoHOI_project. --- ### HarmoHOI: Harmonizing Appearance and 3D Motion for Multi-view Hand-Object Interaction Synthesis Authors: Lingwei Dang, Juntong Li, Zonghan Li, Hongwen Zhang, Liang An, Wei Min, Yebin Liu, Qingyao Wu Published: 2026-07-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.17097v1 Hand-Object Interaction (HOI) synthesis is a cornerstone for animation production and embodied AI. Despite the strong priors of video foundation models, multi-view consistent HOI synthesis remains challenging due to complex hand motions and occlusions. We present HarmoHOI, a unified diffusion framework that jointly and harmoniously generates synchronized multi-view HOI videos and globally aligned 3D point tracks. Our core insight is that robust multi-view consistency fundamentally requires globally aligned 3D geometry and motion. To this end, we propose a Mixture of Multi-view Diffusion Transformer that co-models RGB videos and 3D point tracks. By representing point tracks as pseudo-videos, we align 3D geometric signals with the 2D latent space of foundation models, thereby minimizing the domain gap and easing adaptation of priors. To further ensure geometry consistency, we introduce Global Motion Aligning Diffusion, which refines coarse point tracks into metric-scale, globally aligned 3D trajectories. HarmoHOI enables on-the-fly co-evolution of 2D appearance and 3D motion during denoising. To overcome the scarcity of multi-view HOI data, we employ a hybrid data curriculum learning strategy that successfully transfers generic priors from single-view data to synchronized multi-view generation. Experimental results show that HarmoHOI achieves state-of-the-art performance in visual quality, motion plausibility, and multi-view geometric consistency. Project page available at https://droliven.github.io/HarmoHOI_project. --- ### Fourier Geometric Wind Power Forecasting with Numerical Weather Prediction Authors: Shiyuan Piao, Fan Zehui, Yang Liu, Hong Cheng, Juepeng Zheng, Jie Zhou, Fugee Tsung Published: 2026-07-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.17095v1 Accurate short-term wind power forecasting is essential for grid stability and operational planning, yet remains challenging due to the complex interactions between atmospheric conditions and turbine dynamics. However, existing methods fail to effectively incorporate weather forecasting with wind turbine data (i.e., SCADA), leading to suboptimal solutions. To address this, we introduce a multimodal framework that integrates historical point-based SCADA data with grid-based Numerical Weather Prediction (NWP) forecasts, which is challenging due to heterogeneous input and the complex physical wind-turbine interactions. Our approach first explicitly decomposes inputs into scalar and vector features to better capture both site-specific and geometric dependencies and then incorporates a geometric encoder to extract rotation-invariant features from wind vectors. We further leverages a Fourier Neural Operator (FNO) architecture, which performs global convolutions in the frequency domain to efficiently model long-range spatiotemporal relationships. Extensive experiments on three real-world wind farms, with weather forecasting data, demonstrate that our model consistently outperforms state-of-the-art baselines, highlighting the effectiveness of its physically-informed design. The core implementation of our method is publicly available at: https://github.com/shawn-sypiao/GWPF. ---