# Research Papers — 2026-07 · bundle page 162 of 222 > Full-text markdown of papers #8051–8100 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/162 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/161.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/163.md) ### Collate: Collaborative Neural Network Learning for Latency-Critical Edge Systems Authors: Shuo Huai, Di Liu, Hao Kong, Xiangzhong Luo, Weichen Liu, Ravi Subramaniam, Christian Makaya, Qian Lin Published: 2026-07-09 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2607.08013v1 Federated Learning (FL) empowers multiple clients to collaboratively learn a model, enlarging the training data of each client for high accuracy while protecting data privacy. However, when deploying FL in real-time edge systems, the heterogeneity of devices among systems has a severe impact on the performance of the inferred model. Existing optimizations on FL focus on improving the training efficiency but fail to speed up inference, especially when there is a latency constraint. In this work, we propose Collate, a novel training framework that collaboratively learns heterogeneous models to meet the latency constraints of multiple edge systems simultaneously. We design a dynamic zeroizing-recovering method to adjust each local model architecture for high accuracy under its latency constraint. A proto-corrected federated aggregation scheme is also introduced to aggregate all heterogeneous local models, satisfying the latency constraint of different systems with only one training process and maintaining high accuracy. Extensive experiments indicate that, compared to state-of-the-art methods and under a latency constraint, our extended models can improve the accuracy by 1.96% on average, and our shrunk models can also obtain a 3.09% accuracy improvement on average, with almost no extra training overhead. The related codes and data will be available at https://github.com/ntuliuteam/Collate --- ### Provably Optimal Learning Algorithms for Assistance Games Authors: Nivasini Ananthakrishnan, Mark Bedaywi, Michael I. Jordan, Stuart Russell, Nika Haghtalab Published: 2026-07-09 Categories: cs.LG, cs.AI, cs.GT arXiv: https://arxiv.org/abs/2607.08012v1 This paper studies an online variant of the assistance games framework, where an informed agent and an uninformed agent repeatedly interact over $T$ timesteps to optimize a common reward function. While the informed agent (the human) observes a latent state of the world, the uninformed agent (the assistant) observes only the human's actions. We provide the first provably efficient learning algorithms for repeated assistance games. We introduce the notion of assistance regret: the gap between the cumulative utility of interactions and that of the optimal joint policies in hindsight, which map latent states to action pairs. We present decentralized algorithms for both the human and the assistant that achieve a $(1-1/e)$-approximate assistance regret rate of $\widetilde{O}(T^{3/4})$, with runtime polynomial in the size of the action and state spaces. These algorithms are general; in particular, they accommodate any no-regret algorithm for the assistant. We prove that achieving a regret approximation factor better than $(1-1/e)$ is computationally intractable. Furthermore, we demonstrate how these generic no-regret algorithms can be tailored to a pseudo-decentralized setting -- using a shared random string -- to achieve a rate of $\widetilde{O}(T^{1/2})$, optimal up to logarithmic factors. --- ### Beware What You Autocomplete: Forensic Attribution of Backdoored Code Completions Authors: Anjun Gao, Yueyang Quan, Zhuqing Liu, Minghong Fang Published: 2026-07-09 Categories: cs.CR, cs.AI, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2607.08011v1 Large language models have enabled powerful code completion systems that assist developers by predicting subsequent lines of code. However, these models remain vulnerable to backdoor attacks, where malicious fine-tuning data covertly implants unsafe behaviors. Despite advances in defensive techniques, adaptive and sophisticated backdoor attacks still evade detection and mitigation. We present CodeTracer, a forensic framework that traces malicious code completions back to the backdoor fine-tuning data responsible for them. Operating under realistic post-deployment constraints, CodeTracer relies solely on the fine-tuning corpus and the reported miscompletion event. It extracts a structured behavioral fingerprint from the compromised output, narrows the search to semantically relevant code samples, and employs LLM-based reasoning to attribute unsafe logic to specific backdoor data. Extensive evaluations across three representative vulnerability cases and ten backdoor attacks, along with sixteen competitive baselines, demonstrate that CodeTracer consistently achieves high forensic accuracy, low false identification rates, and strong robustness against adaptive attacks. --- ### Tool-Making and Self-Evolving LLM Agents in Low-Latency Systems Authors: Kalle Kujanpää, Ning Liu, Shahnawaz Alam, Yeshwanth Reddy Sura, Tianyu Yang, Kristina Klinkner, Shervin Malmasi Published: 2026-07-09 Categories: cs.CL, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2607.08010v2 Production LLM agents often waste latency and reliability by regenerating code for the same procedural steps on every request. We replace this inference-time coding loop with an agentic tool-making pipeline that compiles repeated SOP steps into validated, versioned tools before deployment. The tool-maker grounds synthesis in the live environment as it collects execution traces, observes backend schemas and values, generates candidate tools, and repairs them against labeled cases. At runtime, the production agent calls these tools directly and falls back to code generation only when needed. We deploy the approach in a Fulfillment Center alarm-triage system, where an agent diagnoses alarms against a 44-node SOP over heterogeneous metric backends. In production, tool calls reduce p50 latency by 42%. On 1,500 historical alarms, they reduce end-to-end error rate by up to 53% by suppressing run-to-run variance in repeated steps. Because tools return compact structured verdicts, they also enable a simpler direct-call architecture, reducing p50 latency by a further 62% in a controlled ablation. Versioned tools also improve auditability and expose specification gaps and upstream data drift. Our results show that agents that build and maintain their own tool libraries, a key element of self-evolving agents, can make industrial LLM systems faster, more reliable, and easier to operate. --- ### Tool-Making and Self-Evolving LLM Agents in Low-Latency Systems Authors: Kalle Kujanpää, Ning Liu, Shahnawaz Alam, Yeshwanth Reddy Sura, Tianyu Yang, Kristina Klinkner, Shervin Malmasi Published: 2026-07-09 Categories: cs.CL, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2607.08010v1 Production LLM agents often waste latency and reliability by regenerating code for the same procedural steps on every request. We replace this inference-time coding loop with an agentic tool-making pipeline that compiles repeated SOP steps into validated, versioned tools before deployment. The tool-maker grounds synthesis in the live environment as it collects execution traces, observes backend schemas and values, generates candidate tools, and repairs them against labeled cases. At runtime, the production agent calls these tools directly and falls back to code generation only when needed. We deploy the approach in a Fulfillment Center alarm-triage system, where an agent diagnoses alarms against a 44-node SOP over heterogeneous metric backends. In production, tool calls reduce p50 latency by 42%. On 1,500 historical alarms, they reduce end-to-end error rate by up to 53% by suppressing run-to-run variance in repeated steps. Because tools return compact structured verdicts, they also enable a simpler direct-call architecture, reducing p50 latency by a further 62% in a controlled ablation. Versioned tools also improve auditability and expose specification gaps and upstream data drift. Our results show that self-evolving agents can make industrial LLM systems faster, more reliable, and easier to operate. --- ### From Execution to Education: A Bloom-Aligned Framework for Measuring Educational Control in LLMs Authors: Yi Zhang, Julia Rayz Published: 2026-07-09 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2607.08009v1 We introduce a Bloom-aligned framework for measuring educational control in Large Language Models (LLMs): the ability to preserve a task's instructional intent while shifting its cognitive demand toward specified learning objectives. We apply this framework to programming tasks in computer science education to study the gap between solving tasks and adapting them for learners. Using revised Bloom's Taxonomy as an operational scale of cognitive demand, we evaluate two intervention settings: general difficulty control, where models are asked to make tasks harder or easier, and Bloom's control, where models are asked to target higher or lower Bloom's levels. We evaluate a matched Qwen3-Next model pair, comparing Qwen3-Next-80B-A3B-Instruct with Qwen3-Coder-Next across 2,520 tasks from three benchmarks. The framework reveals a robust directional asymmetry: both models reliably increase cognitive demand, but struggle to lower it. We further characterize these outcomes with semantic-delta clustering and layer-wise Fisher's Discriminant Ratio probing. Within this controlled comparison, the general model shows clearer middle-layer separability for both general difficulty and Bloom-control contrasts, whereas the coder model shows weaker separability for general difficulty and a deeper peak for Bloom-control contrasts. These results show that strong execution performance does not automatically entail Bloom-aligned educational control. --- ### Unit-Independent Low-Rate Wrist GSR Processing for Stress Detection Using Phasic nSCR Features Authors: Zequan Liang, Sally Hang, Geneva M. Jost, Ning Miao, Wei Shao, Mahdi Pirayesh Shirazi Nejad, Hossein Sayadi, Ehsan Kourkchi, Setareh Rafatirad, Camelia E. Hostinar, Houman Homayoun Published: 2026-07-09 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2607.08007v1 Galvanic skin response (GSR) is widely used for stress detection, but wrist-based GSR remains challenging because its absolute amplitude can differ substantially from laboratory-grade palmar measurements. In this paper, we propose a unit-independent low-rate wrist GSR processing pipeline to extract the number of skin conductance responses per minute (nSCR/min) as a stress-related feature. We collect paired wrist and palmar GSR recordings from 31 participants during sitting baseline, standing baseline, neutral speaking, and the Trier Social Stress Test (TSST), a laboratory social stressor task. The proposed pipeline cleans the raw GSR signal, decomposes it into tonic skin conductance level (SCL) and phasic skin conductance response (SCR), applies robust z-score normalization, and detects phasic SCR peaks to compute nSCR/min. Using random forest on 25Hz We-Be GSR, nSCR/min achieved balanced accuracies of 0.823 and 0.871 for binary classification between TSST and the sitting and standing baselines, respectively. Moreover, the 25Hz We-Be GSR features achieved comparable balanced accuracy to the original 100Hz features across the evaluated tasks. These results suggest the feasibility of low-rate, unit-independent wrist GSR processing for wearable stress detection. --- ### LOGOS: Language-guided Oriented Object Detection in Aerial Scenes Authors: Trong-Thuan Nguyen, Minh-Triet Tran Published: 2026-07-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.08004v1 Object detection in geospatial scenes, such as satellite and aerial imagery, poses significant challenges due to the varying orientations and densities of objects, as well as the complex backgrounds inherent to remote sensing imagery. Traditional methods for oriented object detection have struggled to address issues such as angular discontinuity, fixed query sizes, and inefficiencies in handling sparse or cluttered scenes. In this paper, we propose LOGOS, a novel transformer-based approach that leverages textual prompts to guide the detection of oriented objects in aerial scenes. In particular, our proposed approach incorporates prompt-modulated content queries to dynamically adjust the model's focus based on the provided text, thereby improving object detection accuracy in complex environments. Empirically, extensive experiments on the DOTA dataset demonstrate that LOGOS outperforms existing state-of-the-art methods, particularly in densely packed and rotated object scenarios. Our approach offers a significant step forward in improving the robustness and scalability of oriented object detection in remote sensing applications. --- ### Reaction-network reasoning with frontier models for experimentally confirmed catalyst-selectivity hypotheses Authors: Sutanay Choudhury, Anwesha Banerjee, Udishnu Sanyal, Jorin Dawidowicz, Chiezugolum Ijeoma Odilinye, Jesun Firoz, Liney Arnadottir, Simone Raugei, Johannes Lercher, Arnab Dutta Published: 2026-07-09 Categories: physics.chem-ph, cs.AI arXiv: https://arxiv.org/abs/2607.08003v1 Catalysts are essential for sustainable chemical manufacturing, yet discovering novel architectures remains a bottleneck dominated by trial-and-error experimentation and computationally intensive screening. In complex reactions such as electrochemical carbon dioxide reduction, product selectivity is governed by dynamic interfacial, electrolyte, and potential factors as well as kinetic pathway competition. Conventional descriptor-based machine learning and computational potentials struggle to resolve these mechanistic branch points, primarily relying on static ground-state descriptors or bulk structural correlations rather than end-to-end topological pathway analysis. Here, we show that frontier language models, when strictly constrained to reason over explicit reaction networks, can discover novel catalysts by identifying the physical levers that govern pathway competition. We developed a human-AI co-thinking framework that enforces network invariance to extract testable hypotheses from complex chemical graphs. Applied to CO2 electroreduction, the framework identified ketene desorption and hydroxide capture as the acetate-forming pathway, and predicted a distinct adsorbed CO and CH2 coupling route to ketene. By isolating actionable control levers, specifically local alkalinity, controlled iron incorporation, and restricted interfacial proton-donor accessibility, the framework guided the prospective synthesis of a copper-iron oxide catalyst demonstrating a threefold increase in acetate selectivity over matched Cu-rich baselines. This mechanism-guided reasoning architecture shifts the computational paradigm from retrospective statistical prediction to forward-looking hypothesis generation, providing a broadly applicable blueprint for mechanism-guided materials discovery. --- ### SpO$_2$ Predictor-Guided Stage-Wise Time-Frequency Reconstruction of Low-Quality Dual-Wavelength PPG for Oxygen Saturation Estimation Authors: Zequan Liang, Elahe Hosseini, Ning Miao, Mahdi Pirayesh Shirazi Nejad, Wei Shao, Ehsan Kourkchi, Setareh Rafatirad, Houman Homayoun Published: 2026-07-09 Categories: eess.SP, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.07996v1 Continuous oxygen saturation (SpO$_2$) estimation from wearable photoplethysmography (PPG) is important for long-term health monitoring, but low-quality red and infrared PPG segments can distort waveform morphology and degrade SpO$_2$ prediction accuracy. Existing PPG denoising and reconstruction methods usually optimize waveform fidelity or heart rate characteristics, while time-domain waveform loss on PPG signals alone insufficiently preserves frequency structure and SpO$_2$-relevant information. This paper proposes a SpO$_2$ predictor-guided stage-wise time-frequency reconstruction framework for low-quality dual-wavelength PPG signals. The proposed method first selects high-quality PPG segments to pretrain a SpO$_2$ predictor. A masked reconstruction model is then trained to recover randomly masked PPG regions using a joint reconstruction objective that combines time-domain waveform loss with frequency-domain loss computed from the short-time Fourier transform (STFT). To make the reconstruction task physiologically relevant, the pretrained SpO$_2$ predictor is incorporated as an additional constraint, encouraging the reconstructed PPG to preserve SpO$_2$ information rather than only minimizing waveform reconstruction error. The SpO$_2$ predictor and PPG reconstructor model are optimized through four training stages. Experiments on the public OpenOximetry Repository and a private wearable PPG dataset show that the proposed approach achieves the lowest subject-level MAE, with 2.882\% on the public dataset and 2.359\% on the private dataset. --- ### Latent Undertow: How Ordinary Typos Break Probes Authors: Elad David, Max Fomin, Amit LeVi Published: 2026-07-08 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.15994v1 LLMs handle ordinary typing variation fluently: a typo or missing punctuation leaves both user intent and the model's response substantively unchanged. Yet probes that detect malicious prompts by reading the model's hidden states tell a different story: the same edit rotates the readout vector by 43--56 at the perturbed token, decaying below 15% within ~10 downstream tokens. Stacking ~3 common typos per message cuts a single-position prompt-injection probe's TPR@FPR$=1% by 12.0pp, a gap recalibration alone cannot close. Multi-position aggregation cures localized perturbations (<= 0.5 loss) but only attenuates distributed ones, where even attention- and max-based aggregators still drop ~3.8pp. For single-position probes, we introduce a KV-cache fork: a short fixed suffix appended after the user message lets the probe read a few tokens downstream of the perturbation, exploiting its rapid spatial decay. This closes 95% of the gap (-0.6pp residual) -- an order of magnitude better than perturbation-augmented training (-3.7pp). The rotation-and-decay geometry replicates on Llama-3.1-8B, Qwen3-8B, and Gemma-4-E4B; probe evaluation is on Llama-3.1-8B. Code: https://github.com/eladd-ai/latent-undertow --- ### Single Document Extractive Summarization using Domination in Hypergraph Authors: Aamir Miyajiwala, Aabha Pingle, Sheetal Sonawane, Surajit Kr. Nath Published: 2026-07-08 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.15993v1 Automatic Text Summarization (ATS) in Natural Language Processing has been an important task in Information Retrieval. It compresses a document to create a summary that captures all the relevant and important information conveyed in the document. This study explores Hypergraph for extractive text summarization of single documents. Objective: This study explores a novel method of leveraging the property of domination in hypergraphs to generate an extractive summary and compare its performance with state of the art graph based methods. Method: Our work aims to generate an extractive summary by creating a sentence hypergraph where each sentence represents a node and the edge is a keyword or a named entity that contains the sentences in which it occurs. We generate a hypergraph where each edge is a keyword or an important topic and the nodes are sentences containing those keywords. Then we apply a greedy algorithm to find the dominating set of the hypergraph which will contain sentences that will form the extractive summary. --- ### Lexical Prompt Compression for Large Language Models: A Training-Free, Deterministic Pipeline with Empirical Pareto Analysis Across Eleven Task Categories Authors: Shamin Chokshi Published: 2026-07-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.13154v1 Recent advances in large language models (LLMs) have made prompts increasingly large and complex. Techniques such as chain-of-thought reasoning (Wei et al., 2022) and in-context learning (Brown et al., 2020) frequently push real-world prompts past several thousand tokens, increasing inference cost and latency. Learned compression methods such as LLMLingua (Jiang et al., 2023) and Selective Context (Li et al., 2023) achieve high compression ratios but require auxiliary language models and are non-deterministic. We ask a complementary question: how far can a training-free, fully deterministic, CPU-only pipeline based on classical lexical NLP be pushed before output quality degrades significantly? Eleven toggleable lexical transformations - stopword removal, filler-phrase deletion, contraction and abbreviation substitution, part-of-speech-based pruning, lemmatization, WordNet-driven synonym shortening, and named-entity preservation - are assembled into a configurable pipeline. Fifteen configurations are evaluated on 1,242 English-only prompts from six sources (Dolly-15k, LMSYS-Chat-1M, WildChat-1M, MMLU, GSM8K, HellaSwag), spanning eleven automatically derived task categories, yielding 18,630 paired GPT-4o-mini completions. Output preservation is measured using BLEU, ROUGE-1/2/L, BERTScore-F1, and SentenceBERT cosine similarity. The most aggressive configuration achieves a mean token reduction of 40.3% (sigma = 9.2) at a BERTScore-F1 of 0.876 against the original-prompt output; a stopword-only configuration achieves 29.6% reduction at 0.913. The compression-versus-fidelity Pareto frontier is characterized per task category, with commonsense reasoning a systematic failure mode under aggressive compression. All code, prompts, and per-cell results are released for reproducibility. --- ### Neural means and kernel corrections for operator learning Authors: Yitzchak Shmalo Published: 2026-07-08 Categories: cs.LG, math.PR, stat.ML arXiv: https://arxiv.org/abs/2609.00389v1 We combine neural network means with exact Matérn kernel regressions of their residuals and of their learned features, and evaluate the pairing on two public emulation problems with published baselines: the structural-mechanics benchmark of de Hoop et al. and the OCO-2 radiative-transfer emulator of Lamminpää et al. On structural mechanics the combination reaches 4.55% test error, matching the best published architecture, and 5.38% against a published 6.49% in the low-data regime. On OCO-2 it improves on the published Gaussian-process emulator on that problem's own test points, outright on two of the three spectral bands; the same kernel that trails the network tenfold on the raw state overtakes it on the network's features, and we measure why (the target's squared native-space norm drops about fortyfold at fixed effective dimension) and prove the mechanism. Where the two families tie instead, the residuals of every architecture we train correlate above 0.86 and their shared component is flat in diversity and sample size, which reads the published plateau as a property of the data. Supporting results include a second-moment identity that predicts stacking outcomes from measured correlations, an optimal-recovery certificate, and a distribution-free coverage band, the only uncertainty signal that survives our tests. --- ### Parametric Multimodal User Memory: Storing What Captions Cannot Carry Authors: Bojie Li, Noah Shi Published: 2026-07-08 Categories: cs.CL, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2608.28609v1 A personalized agent needs a user memory: a persistent model of who its user is. Today it is almost always text -- transcripts and captions retrieved by similarity. This serves the captionable half of a person ("my cat is named Bibi"), but discards the perceptual half no caption can hold: how a voice sounds, how a face reads across age and lighting, how tired someone sounds. We measure this loss across five modalities: a strong caption-based re-identifier recovers as little as 0.11 of a dedicated encoder's recall, collapsing toward chance on non-nameable signals. We instead ground perceptual memory in the model, decomposing recall into two subproblems: a vision-language model grounds the referent in context (what and where), and a dedicated encoder extracts an identity key (who), stored as one inline token read by attention at generation with no external round-trip. Neither suffices alone -- the VLM identifies cross-age faces at only 0.54 recall where a face encoder reaches 0.81, and an ungrounded encoder recognizes a two-person-scene referent at 0.05 -- yet together they reach correct-region oracle (0.96), generalizing to multi-speaker audio and video. The recognition core is training-free: it reproduces the encoder's recall on any frozen model at O(1) registration cost. On PerceptMem (12 domains, 1,080 tasks) perceptual identity is capacity-limited while exact facts are binding-limited: identity belongs in a parametric bank, facts in a text store. The two memories compose cleanly: an agent with both can remember not only what its user said, but also what they are like. --- ### NLP-Driven Knowledge Extraction and Thematic Classification of Translated Ancient Indian Medical Texts Authors: M. S. Rajeevan, B. Mini Devi, V. S. Anoop, C. Mallikarjuna Published: 2026-07-08 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2608.28608v1 Ancient Indian medical texts like Sushruta Samhita have extensive information on diseases, treatments, and surgical techniques. Yet, their ancient format and use of intricate vocabulary pose difficulties in accessibility and systematic ordering. The research here utilizes Natural Language Processing (NLP) methods like Named Entity Recognition (NER), BERTopic modeling, and Knowledge Graph development in Neo4j to extract, categorize, and visualize important concepts based on translated versions. Thematic classification with BERTopic allows for the identification of the underlying medical topics, whereas NER supports the structured entity recognition of diseases, treatments, researchers, and medicinal plants. Graphbased network analysis with Neo4j also allows for the semantic representation of relationship among extracted entities, supporting knowledge retrieval and digital preservation. The findings illustrate how graph databases, topic modeling, and entity recognition facilitate the computational organization of Ayurveda's historical medical wisdom, closing the gap between the conventional texts and contemporary data-driven inquiry. The suggested method promotes historical text analysis, medical informatics, and digital humanities to make ancient Indian medical wisdom more accessible and understandable. --- ### RegDivergence-101: An LLM Benchmark for Cross-Jurisdiction Regulatory Contradiction Detection in Life Sciences Authors: Chuchu Wu, Zhiyin Zhou, Jingzhuo Hu, Liang You Published: 2026-07-08 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.28607v1 Pharmaceutical sponsors developing a drug for both the United States and the European Union must reconcile guidance issued independently by the FDA and the EMA. Where the two agencies require substantively the same thing, a sponsor can file once; where they diverge, a single trial design risks rejection in one region; where one agency is silent on a point the other regulates, the sponsor must infer obligations. Today this reconciliation is performed manually by regulatory-affairs experts. We introduce cross-jurisdiction regulatory divergence detection: given an FDA requirement and an EMA requirement on the same topic, classify their relationship as AGREE, DIVERGE, or SILENT. SILENT is inherently directional (SILENT_FDA vs. SILENT_EMA); we record direction per pair and report per-direction F1 alongside the collapsed label. We release RegDivergence-101, a 101-pair expert-grounded pilot evaluation benchmark (labels grounded in three peer-reviewed FDA/EMA comparison studies and primary FDA/EMA/ICH guidance text; dual-annotation inter-annotator kappa = 0.85), and systematically characterise a four-method baseline hierarchy: lexical heuristic (0.511 macro-F1, 95% CI (0.411-0.605)), NLI cross-encoder (0.233), obligation-level Graph-RAG (0.663 (0.570-0.747)), and flat LLM judge / Claude Haiku (0.830 (0.747-0.908)). Three directional observations emerge at pilot scale (n = 101): SILENT is semantically detectable but invisible to entailment-only formulations; pair-level obligation graphs improve over lexical methods but trail flat-LLM context (CIs partially overlapping); and corpus-level graph construction is the indicated architectural target for large-scale silent-detection. RegDivergence-101 is a pilot release establishing the task formulation and baseline hierarchy; four unrepresented regulatory domains and an expansion roadmap are described in Section 7. --- ### CityReal: Human-Aligned Urban Behavior and City Dynamics Simulation with Large-Scale LLM Agents Authors: Nicolas Bougie, Xiaotong Ye, Narimasa Watanabe Published: 2026-07-08 Categories: physics.soc-ph, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2608.16897v1 Large-scale urban simulation plays a pivotal role in social science, traffic safety, and transportation policy. Recent work has shown that large language models, when prompted as agents, can generate lifelike daily routines at city scale. Yet these methods typically rely on few-shot prompting, causing agents to reproduce the LLM's behavioral priors rather than the target population. We introduce CityReal, a modular framework for human-aligned urban simulation. CityReal models agents as intention-driven decision makers that pursue coherent mobility and activity plans rather than isolated step-by-step choices. They adapt over time by learning habits and preferences based on experience and constraints. To improve population-level realism, we learn textual adapters for behavior modules that align agent decisions with observed population statistics. Experiments show that CityReal improves alignment with real-world human behavior at both micro and macro levels. Scaling to tens of thousands of agents, it supports analysis of crowd density, place popularity, mobility flows, and well-being under different urban scenarios, offering a scalable testbed for urban simulation and forecasting. --- ### When Do LLMs Apply the Wrong Law? Diagnosing LLM Failures in Temporal Legal Reasoning Authors: Yiqian Huang, Shuyuan Zheng, Qianying Liu, Shaowen Peng, Yuntao Kong, Kotaro Funakoshi, Chuan Xiao, Manabu Okumura, Yang Cao Published: 2026-07-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.14610v1 Legal reasoning tasks such as legal judgment prediction (LJP) require identifying the temporally correct version of the law governing a case -- a capability we term temporal applicable-law determination. However, whether large language models (LLMs) can reliably perform this task remains unexplored. In this paper, we construct a benchmark to evaluate LLMs on temporal applicable-law determination, and systematically investigate why they fail at temporal legal reasoning. Our experiments reveal four key findings. First, LLMs exhibit a strong bias toward applying the most recently enacted law, regardless of when the legally relevant facts occurred. Second, this bias does not stem from an inability to understand that laws have temporal scope, nor from a lack of knowledge about historical statutes. Third, we provide behavioral evidence that reinforcement-learning-shaped explicit reasoning may be a key mechanism: while improving general reasoning ability, it reduces the diversity of reasoning paths, causing models to converge on applying the current law. Fourth, this produces a counterintuitive inverse relationship: models with stronger general reasoning ability tend to perform worse on temporal legal reasoning. Our findings offer concrete guidance for future work on improving LLM performance in temporally grounded legal reasoning. --- ### Decoding Error-Related Potentials under Multisensory Feedback with Varying Congruency Authors: Yixin Liu, Kang Yin, Hye-Bin Shin, Seong-Whan Lee Published: 2026-07-08 Categories: q-bio.NC, cs.AI arXiv: https://arxiv.org/abs/2607.24806v1 Error-related potentials (ErrPs) are widely studied neural signatures associated with error processing in human-machine interaction. In realistic settings, error perception often occurs under heterogeneous multisensory feedback, where variability induced by sensory modality and feedback congruency poses challenges for reliable ErrP decoding. In particular, incongruent feedback is associated with increased decoding difficulty and reduced classification performance. To address this challenge, we investigate learning strategies for robust ErrP decoding under multimodal visual, auditory, and tactile feedback with controlled sensory congruency. We adopt a multi-branch EEGNet-based architecture with auxiliary supervision to improve robustness across heterogeneous conditions, without relying on explicit modality-specific assumptions. Experiments were conducted using a maze-observation task with unimodal, bimodal, and trimodal feedback configurations. Across subjects, the proposed approach achieved consistent classification performance across heterogeneous sensory conditions and showed improved accuracy compared to baseline EEGNet models, particularly under multimodal feedback. These results suggest that appropriate architectural design and training strategies can improve the stability of ErrP decoding under heterogeneous multisensory conditions. --- ### URHead: A Unified UV-Space Representation for Joint Mesh-3DGS Optimization in Head Avatars Authors: Seonghak Lee, Junhee Cho, Jisoo Park, Min-Gyu Park, Jongmin Lee, Ju Hong Yoon, Junseok Kwon Published: 2026-07-08 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2607.22673v2 We present URHead, a unified representation for high-fidelity and animatable head avatars that fundamentally redefines mesh-Gaussian integration. While mesh-based methods offer precise geometric control but lack photorealistic detail, and Gaussian-based approaches achieve photorealism but suffer from poor structural consistency, existing hybrid solutions fail to fully leverage their complementary strengths. Our key contribution is a UV-space unification where both representations share a common UV parameterization. Through joint optimization with adaptive gaussian sampling, our method automatically learns to disentangle and allocate appropriate roles to each component. URHead maintains full parametric controllability while preserving subject-specific details, and outperforms existing state-of-the-art methods in reconstruction quality and animation consistency. --- ### Wavelet Phase Diffusion for Structurally and Semantically Consistent Sim-to-Real Translation Authors: Kaiwen Wang, Frank Bieder, Yinzhe Shen, Carlos Fernandez, Jan-Hendrik Pauls, Omer Sahin Tas Published: 2026-07-08 Categories: cs.AI, eess.IV arXiv: https://arxiv.org/abs/2607.21628v2 Simulation-to-reality translation must bridge the appearance gap between synthetic and real domains while preserving structural and semantic consistency. Conditioning-based methods achieve spatial alignment but introduce computationally expensive control modules. Paired-data methods achieve realism but rely on complex synthesis pipelines, often altering scene geometry and semantics. Training-free editing methods avoid both constraints but lack a learned appearance prior, limiting their perceptual quality. Recently proposed phase-preserving diffusion presents a promising alternative, but Fourier-domain formulations are constrained by global spectral coupling. This coupling induces spatial artifacts such as ringing and boundary leakage, thereby degrading structural and semantic consistency. We introduce Wavelet Phase Diffusion, which addresses this through two components. First, we operate in the Dual-Tree Complex Wavelet Packet Transform domain, whose localized wavelet packets enable spatially adaptive phase injection without global spectral interference. Second, Low-Frequency Randomization (LFR) replaces the low-frequency packet, decoupling the model from the synthetic illumination prior and enabling in-distribution real-world appearance. Both components train on unpaired open-domain data, and introduce negligible inference overhead. The spatial locality further enables instance-level translation, where individual objects or regions are translated to photorealistic appearance independently while the surrounding scene remains untranslated. On vKITTI $\to$ KITTI image translation, ours outperforms prior methods in realism and semantic consistency while maintaining competitive structural alignment. For CARLA video translation, ours approaches the realism of paired-data methods while reducing VLM planner ADE and FDE by $5.4\%$ and $5.1\%$, respectively. --- ### Representation Robustness Under Executable Reasoning Constraints in Large Language Models for Mathematical Problem Solving Authors: Sagnik Nath, Edith Aurora Graf, Liang Zhang, Diego Zapata-Rivera Published: 2026-07-08 Categories: cs.AI, cs.HC, cs.PL arXiv: https://arxiv.org/abs/2607.20520v1 Large language models (LLMs) are increasingly evaluated on mathematical problem solving, yet prior work often treats representationally equivalent formulations as interchangeable and conflates reasoning errors with interface failures. This paper investigates representation robustness in LLM-based mathematical problem solving by systematically varying surface representations of the same underlying problems, including story problems, word-equations, symbolic equations, and isomorphic paraphrases. Using a curated dataset of mathematically equivalent problems, we evaluate five contemporary LLMs under a direct answer generation condition. We find substantial representational sensitivity: models frequently change correctness across equivalent formulations, with nontrivial flip rates across story, symbolic, and word-equation variants. We also observe systematic regressions under isomorphic reformulations, showing that even subtle paraphrase-level changes can degrade performance despite preserved mathematical structure. We then evaluate a code-augmented condition in which models externalize reasoning as executable Python code that is run locally for validation. This interface reveals strong latent reasoning capability in some models that perform poorly under direct prompting, but it does not uniformly improve robustness. Instead, failures shift across interaction layers, from opaque reasoning errors to protocol violations and execution failures. Even when executable reasoning succeeds, representation sensitivity often persists. Overall, our results show that reasoning scaffolds do not eliminate representational brittleness, but expose new tradeoffs among correctness, reliability, latency, and cost. We argue that representation should be treated as a first-class interface design variable in LLM evaluation and deployment, especially for AI-assisted problem-solving systems. --- ### Adaptive Depth in Looped Transformers: Diagnosing Learned Halting Gates and Trajectory Readouts Authors: Andrei Cristian Popescu, Haitz Sáez de Ocáriz Borde, Pietro Liò Published: 2026-07-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.20519v1 Looped Transformers increase test-time computation by repeatedly applying a shared recurrent block. Learned halting objectives in looped Transformers typically use a single exit distribution both as the inference-time stopping rule and as the training-time weighting of per-depth losses. This entangles exit selection with trajectory formation: the gate not only chooses which recurrent state to use, but also determines how strongly each intermediate state is supervised. Consequently, poor adaptive-compute performance can arise from the readout, the induced trajectory, or their interaction. We study adaptive depth in looped Transformers through this trajectory--readout lens, across controlled synthetic tasks (modular arithmetic and binary parity) and large-scale Ouro-1.4B and 2.6B checkpoints. We find that fixed-prior depth supervision, which shapes the trajectory without an input-dependent halting policy, produces difficulty-aware trajectories whose intermediate states expose useful stopping signals, and that simple post-hoc confidence readouts often match or outperform learned linear and MLP gates. Fitting gates on frozen trajectories localizes the failure: it appears to stem mainly from the trajectory induced by joint gate training rather than from limited gate expressivity. The same pattern is present in Ouro evaluations, where pretrained ponder gates are competitive but not uniformly Pareto-optimal, and measured latency confirms that the resulting reductions in average exit depth translate into practical inference-time savings. Our systematic diagnostic evaluation reframes adaptive depth in looped Transformers as a joint problem of trajectory formation and exit readout, rather than gate learning alone, highlighting a distinction that prior learned-halting work has often left implicit. --- ### CANN Bench: Benchmarking Agent Generated Kernels against Real NPU and Algorithmic Limits Authors: Xue-Jian Gao, Deng Pan, Yueming Su, Jiasheng Li, Bin Du, Fengming Zhu, Chengdi Ma, Junyi Fan, Qichen Liao, Chengqiu Hu, Xinxian Chen, Lingchao Zheng et al. Published: 2026-07-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.20518v1 AI agents are now capable of writing, compiling, and iteratively optimizing low-level operator kernels on different hardware platforms. Existing benchmarks, however, focus almost exclusively on CUDA and Triton, leaving hardware ecosystems with less-exposed programming models without a common evaluation baseline. We present CANN Bench, an open benchmark for AI-generated operator code on Huawei's Ascend NPU. The current release covers 53 operators and 1060 test cases organized into four difficulty tiers -- from simple elementwise primitives to MoE dispatch and FlashAttention kernels -- spanning FP16, BF16, FP32, and INT8 precision formats. Evaluation adopts a \textbf{three-dimensional weighted composite score} that treats compilation, functional correctness, and performance as independent axes, providing a principled reward signal for kernel-generation agents. Performance is graded against an out-of-the-box PyTorch-on-Ascend baseline and an analytical per-case Hardware-Anchored Performance (HAP) limit on real NPU hardware, ensuring scores reflect genuine optimization headroom rather than measurement artifacts. The evaluation harness is designed to resist reward hacking from the ground up. CANN Bench is versioned within the official CANN repository and is designed for long-term community co-construction, providing the Ascend ecosystem with a quantitative, reproducible, and sustainably maintained yardstick for AI operator-authoring capability. --- ### Reward-Aware Population Scaling of Evolutionary Strategies in LLM Fine-Tuning Authors: Sung Cho, Gyubin Han Published: 2026-07-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.19408v1 Using Evolutionary Strategies (ES) for fine-tuning large language models is attractive because it is memory-efficient, parallel, and compatible with black-box or discrete rewards. Yet its population-size conclusions conflict sharply: fine-tuning with cross-entropy (CE) reward succeeds with $N=1$, while binary-reward training often needs $N \approx 30$. We show this gap is largely about reward design and normalization, not population size. In the capable-model regime we study, z-score advantage normalization can cause $N=2$ to fail. Disabling normalization lets binary-reward ES with $N=2$ improve on GSM8K and TREC across capable models spanning 0.5B-7B, where the normalized variant collapses or degrades. This small-$N$ risk is set by reward granularity: binary accuracy reward induces a zero-advantage probability $q$ that depends in closed form on base accuracy, batch size, and intra-pair correctness correlation; a zero-training probe on Qwen2.5-Instruct/GSM8K matches the formula with mean absolute error 0.020 across 12 configurations and finds the availability threshold $N_{\mathrm{avail}}$ to be small in this capable-model regime. The implication is not that $N=2$ is universally sufficient, but that small-population failure in capable-model binary ES can be an implementation artifact rather than an intrinsic population limit. --- ### Intelligence-Guided Adaptive Purification for DDoS-Resilient Quantum Networks: A CUDA-Q based Study Authors: Santanu Ganguly Published: 2026-07-08 Categories: quant-ph, cs.AI, cs.ET, cs.NI arXiv: https://arxiv.org/abs/2607.16276v1 Quantum-repeater networks require adaptive control policies that balance entanglement generation rate, end-to-end fidelity, purification overhead, and memory-induced latency. This tradeoff becomes more complex when the classical control plane is degraded by cyber anomalies or denial-of-service traffic. We develop a CUDA-Q/SeQUeNCe co-simulation workflow for studying adaptive entanglement purification in heterogeneous linear repeater chains. CUDA-Q noisy quantum kernels are used to estimate primitive entanglement purification and swapping behavior, while SeQUeNCe provides an event-layer model for stochastic link generation, waiting-time-dependent memory decay, purification failure, and end-to-end swapping. Under stationary conditions, we compare no purification, local threshold purification, mean-field predictive purification, fixed purification, and a resource-penalized risk-aware predictive policy. In an 8-node chain, the resource-penalized risk-aware controller increases above-target delivery probability relative to fixed purification while reducing latency and purification overhead. We then couple the quantum-network controller to anomaly scores derived from the CSE-CIC-IDS2018 benign-to-SSDP intrusion-detection trace. During the attack period, the attack-unaware controller maintains high raw delivery, but its above-target entanglement delivery falls to 0.098+/-0.007; the IDS-aware resource-adaptive controller switches to more purification-heavy masks and increases above-target delivery to 0.344+/-0.011, closely matching the oracle-aware value of approximately 0.335. These results demonstrate that cyber-state awareness can improve useful quantum-network outcomes by trading raw throughput for fidelity-qualified entanglement delivery. --- ### The JEPA Predictor: A Transferable Operator for Occluded Feature Completion Authors: William Nguyen, Christopher Nguyen Published: 2026-07-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.16274v2 Joint-Embedding Predictive Architectures (JEPAs) train a predictor jointly with their encoder, but downstream deployment discards the predictor and reads features from the encoder alone. The predictor is, by construction, a learned operator from visible-context features to features at masked positions, the structure a partial-view classifier needs. We show that this operator is portable across encoder families. We first establish that, at heavy mask, retaining the frozen predictor on a JEPA encoder substantially closes the accuracy gap against the strongest non-JEPA discriminative baselines. We then bolt the frozen predictors of I-JEPA and V-JEPA 2 onto four non-JEPA hosts (CLIP, DINOv3, DINOv2, MAE) through a single linear projection between feature spaces, fit in closed form on 500 ImageNet-1k images. Across both ImageNet-9 and Stanford Dogs and across three mask fractions, the lift over each host's masked-encoder baseline grows monotonically with the mask fraction K in every host-donor pair. CLIP paired with the I-JEPA predictor recovers most of the accuracy that masking removed on ImageNet-9 at heavy occlusion, and lifts fine-grained Stanford Dogs from 15.9% to 52.1% (+36 pp). The mechanism is identifiable: the projection pays a fixed cost on visible patches and the predictor provides a growing benefit on masked patches; the benefit dominates the heavy-occlusion regime. At low K on fine-grained classification the projection cost exceeds the benefit, defining the boundary where the linear bridge breaks down. The frozen JEPA predictor functions as a portable operator for occluded feature completion across encoder families, requiring no retraining of either model while fitting matched linear probes per mask fraction. --- ### ForensicNet: Lightweight Attention-Enhanced MobileNetV2 for Automated Face Identification Authors: Savitha N J, Lata B T Published: 2026-07-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.16273v1 In forensic environments, automated identification of perpetrators is difficult due to pose changes, changes in light, occlusion, and lack of labeled data. This paper presents ForensicNet, a lightweight deep learning framework for forensic face recognition that enhances attention. The suggested model combines the MobileNetV2 backbone with Convolutional Block Attention Modules (CBAM) to improve the learning of discriminative features while maintaining computational speed. A two-phase transfer learning strategy with adaptive layer unfreezing is used to improve domain adaptation and reduce overfitting. This study used publicly available datasets such as LFW and SCFace, with 15,000 facial images spanning 68 identity classes. The proposed model outperforms baseline architectures such as AlexNet, ResNet-50, and MobileNetV2, with an accuracy of 92.4%, a precision of 90.8%, and a recall of 89.5%. Additionally, the framework requires only 2.1 GFLOPs per inference, and hence can be used in real-time forensic surveillance applications. --- ### Near-Optimal Learning of Gaussian Sobolev Operators Authors: Ben Adcock, Michael Griebel, Gregor Maier Published: 2026-07-08 Categories: math.NA, cs.IT, cs.LG arXiv: https://arxiv.org/abs/2607.11921v1 A key question in operator learning is how to design surrogate operators with provable approximation guarantees in reasonable computational time. Whereas smooth operators can be approximated efficiently, i.e., with at least algebraic convergence in the amount of training data, learning finitely regular operators is known to be less efficient. The reason is an intrinsic curse of sample complexity, which allows only subalgebraic sample complexity rates. This fact makes it all the more important to develop algorithms which provably achieve these rates. In this work, we present a fully data-driven algorithm, termed Hermite-PCA approximation, for learning Gaussian Sobolev operators with near-optimal sample complexity. It employs principal component analysis and weighted least-squares methods and is therefore computationally efficient. Moreover, it is spectral, in the sense that it achieves faster (and near-optimal) convergence the higher the Sobolev regularity. We provide a full error analysis of this algorithm, taking into account all sources of error, along with numerical experiments that verify our theoretical results and empirically confirm the efficacy of Hermite-PCA approximation for learning Sobolev operators. --- ### Sensitivity to Subjective Expected Utility Maximization: A Methodological Study, with an Illustrative Application to LLM Decision-Making Authors: Jeff Helzner Published: 2026-07-08 Categories: econ.EM, cs.AI, stat.ME arXiv: https://arxiv.org/abs/2607.11920v1 Evaluating decisions made under uncertainty is hard when labeled outcomes are scarce, costly, or confounded with luck. We treat subjective expected utility (SEU) maximization as a stated standard and define a graded measure -- SEU sensitivity -- of an agent's conformity to it. The vehicle is a softmax choice model with a sensitivity parameter $α$ on SEU-valued alternatives; the contribution is a sequence of identifiability results for $α$ and for belief and utility parameters $(β, δ)$, validated in Stan via prior predictive checks, parameter recovery, and simulation-based calibration (SBC), with finite-sample caveats intact. In the uncertain-choice-only model $m_0$, $α$ is identifiable given the expected-utility vector $η$ and sharply recovered, while $(β, δ)$ are only weakly informed: the posterior barely contracts and concentrates on a $β$-$δ$ trade-off. In the extended model $m_1$, $δ$ becomes identifiable in principle via a $β$-free risky block, but its practical recovery gain at realistic sample sizes is negligible (matched-count CI-width reduction under 1%), and that block yields no detected $α$-precision gain at matched choice count. These are two distinct phenomena: for $δ$, identifiability does not imply precise estimability at realistic $n$; for $α$, identifiability is silent about what governs finite-$n$ precision. Marginal SBC passes for both models even where the joint posterior is weakly informed -- a demarcation we make precise. A two-by-two application (GPT-4o and Claude 3.5 Sonnet, each on insurance-claims triage and Ellsberg-style urns, with sampling temperature as the lever) runs end-to-end on real LLM choice data, detecting a structured comparative $α$ effect in two of four cells. --- ### Semantic Drift and the Stability of Operator Control in Reasoning-Class Decision Support Systems Authors: M. L. Kaluzhsky, V. A. Efirov Published: 2026-07-08 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2607.09790v1 The article investigates the fundamental problem of ensuring the stability of operator control and preserving goal-targeting in hybrid human-machine decision support systems (DSS) of a new generation. Based on a two-month continuous longitudinal experiment on the joint design of a monograph-format textual array, the latent phenomenon of semantic context drift in large language models of deep logical reasoning (Reasoning LLMs) is verified and described. A mathematical model of interaction in the human-machine interface is proposed, and an original metric is introduced - the operator control stability coefficient, which takes into account the non-linear contextual pressure of hidden reasoning chains. Within the paradigm of the cognitome theory, a critical point of control functions inversion is captured. Engineering recommendations are formulated for implementing dynamic relational arbitration loops based on a modified hierarchical similarity model. --- ### PHITSBench: an execution-scored benchmark for AI-assisted PHITS radiation-transport input generation using natural language Authors: Xianglin Ji, Svetlana V. Boriskina Published: 2026-07-08 Categories: cs.AI, cond-mat.mtrl-sci arXiv: https://arxiv.org/abs/2607.09789v1 We introduce PHITSBench, an execution-scored benchmark for the Monte Carlo Particle and Heavy Ion Transport code System (PHITS). PHITSBench comprises 282 transport-scorable tasks spanning three common workflow categories: parameter editing (Edit), syntax repair (Repair ), and complete simulation generation from natural-language descriptions (Reproduce). Each task is evaluated using a Composite Metric Score that combines execution success with agreement between generated and reference transport observables. Using PHITSBench, we evaluate five GPT-5.4-based configurations ranging from zero-shot prompting to knowledge-augmented and agentic workflows. Without domain-specific knowledge, the model performs well on editing and repair tasks (95% and 70% success, respectively) but fails to generate correct simulations from scratch (0% success on the Reproduce track). A structured, machine-readable PHITS knowledge catalog, supplied alongside the user manual, raises single-shot Reproduce-task success to 57%. Agentic execution provides a further improvement to 66-73%, but at increased computational cost. Failure analysis shows that the remaining errors are dominated by incorrect selection and configuration of physical observables rather than syntax generation. These results suggest that future progress in AI-assisted radiation-transport modeling will depend as much on machine-readable knowledge bases, curated domain-training datasets, and execution-grounded evaluation environments as on advances in foundation models themselves. --- ### MVMGNN;Multi-View Masked Graph Neural Network for Alzheimer's Disease Diagnosis using Structural MRI Authors: Ni Yao, Zhenxu Wang, Danyang Sun, Chuang Han, Yanting Li, Jiaofen Nan, Fubao Zhu, Chen Zhao, Weihua Zhou Published: 2026-07-08 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2607.09788v1 Alzheimer's disease (AD) is a common neurodegenerative disorder, and early diagnosis is of great significance for delaying disease progression and enabling timely intervention. Mild cognitive impairment (MCI), which represents an intermediate clinical stage between cognitively normal aging and AD. Structural magnetic resonance imaging (sMRI) provides detailed characterization of anatomical structures and plays an important role in AD-related brain analysis. However, existing sMRI-based brain network methods typically rely on a single graph construction strategy, limiting their ability to jointly capture spatial relationships and morphological similarities between brain regions. To address these issues, this paper proposes an sMRI-based multi-view masked graph neural network model (MVMGNN) for AD diagnosis. A joint node-edge masking mechanism is proposed to simultaneously select radiomics feature dimensions and structural connections, reducing redundancy during graph learning. Furthermore, a patient-level cross-view gated fusion mechanism is proposed to integrate multi-view representations. Experimental results on the ADNI dataset demonstrate that MVMGNN outperforms several competing approaches in AD classification. Interpretability analysis further demonstrates that MVMGNN is able to identify key brain regions associated with AD, providing useful insights into discriminative patterns in sMRI-based brain networks.Our implementation is publicly available at https://github.com/chenzhao2023/MVMGNN_AD --- ### Adversarially Guided Diffusion for LiDAR Range Image Synthesis Authors: Stavros Bouras, Antonios Makris, Alexandros Gkillas, Aris S. Lalos, Konstantinos Tserpes Published: 2026-07-08 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2607.09787v1 LiDAR semantic segmentation is a key perception task in autonomous driving, where false predictions can affect downstream planning and safety-critical decision-making. Although adversarial attacks, and specifically adversarial examples, have been widely studied for image classification and 3D point cloud segmentation, unrestricted adversarial examples remain largely unexplored in the space of 2D range images, which are projections of 3D point clouds. The proposed method is, to the best of our knowledge, the first diffusion-based unrestricted adversarial attack against 2D range-image segmentation, using adversarial guidance from a segmentation loss. By applying guidance directly during sampling, the method produces unrestricted adversarial examples that remain close to the learned LiDAR data manifold while inducing structured segmentation errors. Experiments on the SemanticKITTI dataset using RangeNet++ and CENet segmentation networks demonstrate that the attack provides adjustable degradation across guidance strengths and transfers across segmentation architectures. Compared with norm-bounded FGSM and SegPGD baselines, the proposed attack offers a distinct effectiveness-realism trade-off, achieving controllable white-box and transfer degradation while maintaining competitive distributional and visual realism. --- ### Length Penalties Make Chain-of-Thought Less Monitorable Authors: Bryce Little Published: 2026-07-08 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.09786v4 Recent work trains reasoning models with length penalties to curb overthinking and cut inference cost. We show that these penalties make the chain of thought less monitorable. A length-compressed model still lets misleading hints steer its answers, but it less often verbalizes their influence. We train Qwen3-4B and Qwen3-14B with reinforcement learning under length penalties targeting 60% down to 30% of baseline chain-of-thought length, then evaluate them with nine types of biasing hints on held-out MMLU-Pro-R and four transfer benchmarks. A chain is faithful when an LLM monitor can tell from it that the hint influenced the answer. At the 30% target, accuracy stays near baseline and wrong-answer hints switch answers as often as before. Yet faithfulness drops on every evaluation set for both models, by 39% for Qwen3-14B and 35% for Qwen3-4B on MMLU-Pro-R. A control trained with the same correctness and format rewards but no length penalty leaves faithfulness intact or raises it. Shortening alone does not explain the drop. Compressed chains mention the hint 7 to 35 percentage points less often than the uncompressed model's chains shortened to the same length by random sentence deletion, across both model sizes and all five evaluation sets. Length penalties therefore trade monitorability for inference cost by removing the evidence monitors depend on. --- ### Length Penalties Make Chain-of-Thought Less Monitorable Authors: Bryce Little Published: 2026-07-08 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.09786v3 To curb overthinking and reduce inference costs, researchers now train reasoning models with penalties on chain of thought length. We find that these penalties degrade monitorability. Shorter chains of thought mention misleading hints less often, but the hints still influence the models' answers. We train Qwen3 4B and Qwen3 14B to produce different target chain lengths, then evaluate them using biasing hint interventions on held out MMLU Pro R data and four transfer benchmarks. Compression reduces reasoning tokens and preserves most multiple choice accuracy, while hint influence remains near baseline. At the shortest target chain length, lower bound faithfulness drops to 63.1 percent of baseline for Qwen3 14B and 69.4 percent for Qwen3 4B. The monitor's raw hint detection rate falls from 69 percent to 49 percent and from 60 percent to 48 percent, respectively. To separate length from content, we randomly delete sentences from uncompressed baseline chains until the remaining text matches the compressed length. Across both Qwen3 model sizes and all five evaluation distributions, compressed chains still mention the hint 7 to 35 percentage points less often than these length matched baselines. We therefore identify a compression and monitorability frontier where reducing reasoning costs removes more evidence than shorter traces alone would predict. --- ### Lifelong Representations: A Survey on Continual Self-Supervised Learning for Vision Models Authors: Sergi Masip, Alicja Dobrzeniecka, Jonathan Swinnen, Joachim Collin, Bartłomiej Twardowski, Szymon Łukasik, Tinne Tuytelaars Published: 2026-07-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.09785v1 Traditionally, continual learning has assumed access to labeled data, yet many real-world applications -- such as lifelong robotics -- require models to adapt continuously from unlabeled streams. This has led to the development of continual self-supervised learning (CSSL), a rapidly growing area that lacks a dedicated, systematic review. In this work, we present a comprehensive survey of CSSL for vision, with connections to emerging vision-language settings. First, we analyze existing evaluation protocols and highlight inconsistencies that hinder fair comparison. We then examine why self-supervised objectives exhibit improved robustness to catastrophic forgetting, relating this to task-agnostic representations and smoother loss landscapes. Next, we organize existing methods into a unified taxonomy based on their forgetting-mitigation strategies, including distillation, replay, regularization, architectural approaches, model merging, and objective-level adaptation. Finally, we identify open challenges such as scalability and the need for fast adaptability. We argue that advancing CSSL requires moving beyond small-scale benchmarks towards continual pre-training paradigms for large-scale systems. --- ### Compression Asymmetry and Trajectory Binding in Noise-Anchored Diffusion Inversion Authors: Yongseong Park, Joeun Kim, HoEun Kim, Young-Sik Kim Published: 2026-07-08 Categories: cs.CV, cs.IT arXiv: https://arxiv.org/abs/2607.09784v1 Real-image diffusion inversion is governed by a tight quality-cost trade-off, with costs incurred in computation, storage, or per-image optimization. We study this trade-off through the forward Gaussian noise anchor that defines a diffusion trajectory and isolate two mechanisms behind effective stored-noise inversion. First, diffusion noise exhibits an element-wise compression asymmetry: int8 full-dimensional anchors preserve reconstruction, whereas low-dimensional subspace summaries are much less reliable, often collapsing even at comparable or smaller payloads; the element-wise over subspace ordering persists across five stored-noise inversion methods. Second, inversion is trajectory-bound and score-prior coupled: the matched forward anchor and a trained score network are both necessary, arguing against a purely algebraic-identity explanation. Together, these findings specify what to store and how to use it. They lead to Noise-Anchored Reverse Correction (NARC), a training-free inversion primitive that stores a single int8 latent anchor and reuses it with a fixed, noise-level-dependent anchor-weight schedule: strong anchoring when the reverse trajectory is noise-dominated, then relaxed anchoring as image detail emerges. On PIE-Bench++ with Stable Diffusion 1.5, NARC outperforms five modern non-exact baselines and improves PSNR by +3.24 dB over PnP DirectInv while using about 400x less inversion storage than PnP DirectInv. The compression asymmetry, anchor specificity, and editing plug-in also transfer to SDXL 1024^2. --- ### From Patterns to Maze Structures: SMT-Based Path Synthesis and 2D/3D Construction Authors: Shengyi Wang Published: 2026-07-08 Categories: cs.AI, cs.LO arXiv: https://arxiv.org/abs/2607.09781v1 We present a pipeline for constructing maze structures from input patterns such as text or shapes. The central path-synthesis problem is encoded in Satisfiability Modulo Theories as global constraints on adjacency, continuity, and pattern-constrained coverage, allowing each fixed-bound instance to be solved in one call. The resulting path is either a planar, self-avoiding route or a layered traversal with prescribed over--under crossings, and it serves as a scaffold for constructing planar mazes and three-dimensional realizations of woven mazes. This report extends the published Bridges 2026 conference paper with more representative SMT-LIB examples and a fuller account of how synthesized paths become concrete maze constructions in planar and three-dimensional form. --- ### Towards Real-World Wearable Motion Reconstruction Authors: Andrea Boscolo Camiletto, Rishabh Dabral, Eduardo Alvarado, Thabo Beeler, Marc Habermann, Christian Theobalt Published: 2026-07-08 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2607.09780v1 The modern-day surge in popularity of wearable devices poses a fundamentally unique motion capture problem: reconstructing full-body movement from any set of sensing hardware worn at a given moment. Yet, most research efforts assume fixed sensor configurations (e.g. IMU suits or HMD-centric rigs) and cannot generalize across them. In contrast, we argue that motion capture should prioritize unobtrusive and lightweight devices such as smartphones, smartwatches, smart glasses, and smart insoles, and study the interplay between them. To this end, we make three contributions. First, we present a large-scale multi-modal dataset synchronizing these consumer-grade sensors with ground-truth 3D motion, spanning 50 diverse activities including everyday tasks, sports, and social interactions. Second, we propose WHIP, a baseline generative model that reconstructs motion from arbitrary subsets of available sensors, robustly handling missing modalities and producing physically plausible motions. Third, we conduct a systematic study of sensor complementarity, quantifying how different modalities complement one another. Code and dataset are available at https://vcai.mpi-inf.mpg.de/projects/WHIP/ --- ### A Generalized Deep Non-negative Matrix Factorization Approach for SAR Automatic Target Recognition Authors: Yunhong Zhang, Changjie Cao, Zhongli Zhou, Bingli Liu, Zongjie Cao, Zongyong Cui, Ying Yang Published: 2026-07-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.09779v1 The deep nonnegative matrix factorization (DNMF) technique is proposed to address the low interpretability of deep learning-based methods in extracting multilayer features from synthetic aperture radar (SAR) target samples. However, existing DNMF methods employ a layer-by-layer decomposition strategy, which is prone to causing error accumulation and local optimum, thereby hindering a consistent improvement in recognition accuracy as the number of layer increases. In this paper, a robust multilayer feature extraction method, termed generalized deep non-negative matrix factorization (G-DNMF), is proposed to address the above challenges in SAR automatic target recognition (ATR). The G-DNMF aims global optimality and derives the update rules for each parameter using lagrangian multiplier method. The new update formula indicates that both the DNMF method based on the encoding matrix and the mixing matrix are special cases of the proposed method, theoretically demonstrating the universality of proposed method. In general, the proposed method discards the layer-by-layer decomposition strategy, thereby effectively mitigating the risk of local optima and eliminating error accumulation, leading to a significant improvement in DNMF's multi-layer feature extraction capability. The experimental results, by presenting the feature images extracted from each layer by G-DNMF and the reconstructed original images, verified the proposed method's pure additive understanding of multi-layer features and demonstrated its interpretability. The experimental results based on MSTAR and OpenSARship datasets show that G-DNMF outperforms existing DNMF algorithms and their derivatives in terms of stability and recognition performance. --- ### Time Imprint: Learning Time-Aware Representations in Multi-Modal Knowledge Graphs Authors: Pengyu Zhang, Klim Zaporojets, Congfeng Cao, Jia-Hong Huang, Paul Groth Published: 2026-07-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.09777v1 Multi-Modal Knowledge Graphs (MMKGs) enrich entities with multiple modalities such as text and images, yet entities with highly similar multi-modal features remain difficult to distinguish. Temporal information of an entity can serve as an additional modality to disambiguate such entities, but existing approaches rarely treat time as a separate modality alongside text and images due to two major challenges: (1) sparse temporal semantics, which hinder alignment with richer modalities, and (2) multiple timestamps, which introduce noise or reduce robustness in representation learning. To address these challenges, we propose Time Imprint, a framework that treats time as an entity-level modality and jointly aligns temporal, textual, and visual representations via a three-view contrastive objective. Additionally, to mitigate multi-timestamp ambiguity, Time Imprint studies a compact timestamp subset selection design space and aggregates the selected timestamps into a discriminative temporal embedding with attention pooling, balancing temporal specificity and robustness. Experiments on three MMKG benchmarks demonstrate that Time Imprint achieves state-of-the-art link prediction performance, improving Hits@1 by up to 6.07\% overall and yielding up to 58\% gains on the subset of the top-1\% ambiguity samples. We further examine different fusion strategies and the sensitivity to timestamp availability and quality, clarifying when and why time-as-modality is most beneficial, while adding only modest training overhead. We release our code at https://anonymous.4open.science/r/Time-Imprint. --- ### HELP: Human-Efficient Large-Scale Robot Post-Training with Rollout Segmentation Authors: Shaopeng Zhai, Qi Zhang, Tianyi Zhang, Haoran Zhang, Fuxian Huang, Zhanhui Lin, Zijun Xu, Weinan Zhang Published: 2026-07-08 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2607.09776v2 When adapting Vision Language Action (VLA) models to downstream tasks, multiple rounds of post-training are often required to progressively address policy weaknesses. In this report, we focus on maximizing human efficiency during this iterative process, measured by policy improvement and task throughput per unit of human labor and time. We propose HELP, a Human-Efficient Large-scale robot Post-training pipeline in which two specialized operators supervise twelve robots concurrently. A trained Teleoperator provides high-value remote interventions and recovery demonstrations, while a Floor Operator monitors the robot fleet, triggers takeovers, and performs physical resets. This role specialization improves human efficiency by reducing task switching, lowering operator training costs, and expanding robot interaction coverage. Beyond increasing rollout volume, concurrent supervision also broadens the range of policy behaviors observed by the human team, making recurring failure modes easier to identify and enabling more targeted takeovers, resets, and recovery demonstrations. To efficiently utilize the large and mixed-quality rollout data, HELP incorporates \vlac, an automatic rollout segmentation critic specifically designed for this setting. It separates autonomous trajectories into progress-making, idle, failure-inducing, and recovery segments. Useful rollout segments are retained and combined with Human-in-the-Loop data for the next post-training round. Across four real-world manipulation tasks, HELP achieves 80\%--95\% success rates and improves task throughput by 1.7$\times$--4.2$\times$ over the base model. Under matched HITL recovery budgets, VLAC-CUT further amplifies throughput gains by 1.20$\times$--3.43$\times$ and success-rate gains by 1.50$\times$--3.00$\times$ over HITL-only updates. --- ### GReFEM: Multimodal LLMs as Zero-Shot Semantic Assistants for Physics-Guided 3D Mesh Refinement Authors: Kartik Bali, Mahish K. Guru, Christian J Cyron, Roland Aydin Published: 2026-07-08 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2607.08798v1 Adaptive volumetric finite element meshing is a critical step in computer-aided engineering and analysis that dictates the computational budget of a given problem. It traditionally requires iterative PDE solvers or heavily supervised, data-driven surrogates trained on large-scale simulation data. While Multimodal Large Language Models (MLLMs) excel in 2D visual tasks, their zero-shot capability to semantically ground regions based on geometric understanding and physics remains an open question. Overall, this study explores a significant question: can the high-level semantic understanding of off-the-shelf MLLMs serve as a viable, zero-shot geometric proxy for finite element mesh refinement? To investigate this, we introduce GReFEM (Geometric Reasoning Enhanced Multimodal LLMs for Finite Element Meshing), a framework that utilizes MLLMs to visually localize stress-critical regions based on physics-guided textual prompts. To bridge the gap between 2D MLLM pre-training and 3D geometries, we introduce orthoViews, a view-selection module that maximizes the observability of key geometric features. We conduct an in-depth empirical evaluation across diverse CAD geometries, loading cases, and SOTA MLLMs, comparing them against a tuned geometric heuristic under a strict, matched refinement budget. Our findings reveal that MLLMs demonstrate robust zero-shot capacity to accurately follow complex spatial-physical instructions, isolating stress-relevant features with higher precision than blind heuristics. By mapping both the successes and current limitations of MLLMs in physical grounding, this study defines the frontier of foundation models as semantic assistants in automated simulation workflows. --- ### Multi-Conditioned Diffusion Synthesis of Sand Boils for Low-Resource Earthen-Levee Inspection Authors: Padam Jung Thapa, Abdullah Bin Naeem, Ayon Dey, Anav Katwal, Md Tamjidul Hoque Published: 2026-07-08 Categories: cs.GR, cs.AI arXiv: https://arxiv.org/abs/2607.08794v1 Sand boils on earthen levees are safety-critical defects, but pixel-level detection is limited by scarce annotations. We present a diffusion-based synthesis pipeline for low-resource sand-boil imagery. Using Stable Diffusion XL fine-tuned with DreamBooth and conditioned by a multi-branch ControlNet stack, the pipeline generates synthetic inspection images from a small curated reference set. A soft-mask inpainting protocol preserves the real defect pixels while re-rendering the surrounding scene, avoiding seams and color shifts from prior seamless-cloning compositing. A mask-conditioned ControlNet can also generate a new boil inside a chosen mask, making the mask the segmentation label by construction; however, because large-scale label certification remains unresolved with the available real-trained gate, we release the soft-mask preset as the default. Text conditioning is supplied by a taxonomy-driven Prompt Atlas that expands one domain specification into a stratified, CLIP-validated prompt bank and transfers to new defect classes without code changes. From the real training images, the pipeline produces 1,020 synthetic candidates, of which 815 pass a CLIP admissibility filter. We evaluate image quality using distributional and fidelity-diversity measures against the real reference set and a Poisson baseline, and audit for out-of-distribution drift and memorization. No single preset dominates; each trades off fidelity, diversity, and label reliability. We therefore release the label-reliable preset as the default and treat a curated mixture as the natural augmentation set. Our claims are limited to image quality, label provenance, and diversity; downstream segmentation is left for future work. Code and an artifact manifest are released for reproducibility. --- ### EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Data Authors: Baoyu Li, Xinchen Yin, Mengying Lin, Yixin Zhang, Danfei Xu Published: 2026-07-08 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2607.08436v1 Egocentric human data offers scalable supervision for robot manipulation. However, behavior cloning entangles transferable content like objects, scenes, and task semantics, with non-transferable factors like human morphology, head motion, and behavioral style. We study whether World Action Models (WAMs) provide a better training signal by requiring policies to predict not only actions, but also how the scene evolves. The central question is what world representation best enables human-to-robot transfer. We hypothesize that an effective world target should abstract appearance, capture agent-invariant physical effects, and separate camera motion from environment change. We introduce EgoWAM, a controlled human-robot co-training framework that fixes the policy backbone, action head, and data mixture while varying only the world prediction target, comparing Pixel, DINO, and 3D motion flow. Across three real-world bimanual tasks, WAM co-training scales more effectively with in-the-wild egocentric human data than behavior cloning. Pixel-based prediction transfers weakly, while DINO and 3D flow yield substantial gains: DINO improves out-of-distribution object and scene generalization by up to 4x, and 3D flow improves in-domain performance by 20-30%. More details: https://gatech-rl2.github.io/egowam.github.io --- ### Hallucination Self-Play: Bootstrapping Reinforced Detector via Evolved Generator Authors: Shiping Yang, Shining Liang, Weihao Liu, Wenbiao Ding, Linjun Shou, Lu Cheng, Angel X. Chang Published: 2026-07-08 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.07993v1 Identifying faithfulness hallucinations in LLM-generated outputs remains challenging due to the scarcity of high-quality annotated data. Recent work relies on advanced LLMs to synthesize training data, including rationales, labels, and hallucinated claims. However, these methods treat the generator as a static component, limiting iterative improvement of the detector. To address this limitation, we introduce Hallucination Self-Play (HSP), a novel framework that enables the detector to bootstrap with an evolved generator. HSP involves two roles initialized from the same base model, a detector that assesses the faithfulness of model outputs, and a generator that produces increasingly hard-to-detect hallucinated responses. Specifically, the detector is first fine-tuned on human-labeled data and then employed as a reward model to train the generator via reinforcement learning from AI feedback (RLAIF). In turn, the evolved generator synthesizes hallucination data to further optimize the detector through rule-based reinforcement learning. Experiments on RAGTruth benchmark and two model families demonstrate that the proposed framework can progressively enhance a small LLM to match or even outperform advanced LLMs without external supervision. Our code is available at https://anonymous.4open.science/r/Hallucination-Self-Play-50B5 . --- ### Who Broke the System? Failure Localization in LLM-Based Multi-Agent Systems Authors: Yufei Xia, Anjun Gao, Yueyang Quan, Zhuqing Liu, Minghong Fang Published: 2026-07-08 Categories: cs.CR, cs.AI, cs.IR, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2607.07989v1 Large language model (LLM) based multi-agent systems enable complex problem solving through coordinated reasoning and action, but their distributed structure also introduces new challenges in diagnosing system-level failures. When an execution fails, identifying which agent is responsible and at what point the trajectory first becomes irreversibly misdirected is difficult due to long-horizon interactions and tightly coupled agent behaviors. In this paper, we study the problem of failure localization in LLM-based multi-agent systems and present AgentLocate, a framework that attributes failures to both a specific agent and the earliest decisive step. AgentLocate combines an LLM-based judging mechanism with multi-perspective verification by independent evaluators, whose assessments are aggregated using a confidence-aware strategy. The resulting feedback is further used to adapt the judge through lightweight fine-tuning, improving attribution quality. We evaluate AgentLocate on two complementary benchmarks covering diverse tasks, agent configurations, and trajectory lengths. Experimental results show that AgentLocate consistently outperforms existing failure localization methods in identifying both responsible agents and failure steps, while remaining efficient in terms of token usage and running time. --- ### A Reliability Assessment of LALM Audio Judges for Full-Duplex Voice Agents Authors: A. Sayyad, J. Emmons, S. Jones, T. Lin, H. Krishnan Published: 2026-07-08 Categories: cs.CL, cs.AI, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2607.07985v1 We report the empirical reliability of Gemini models as audio judges that score full-duplex agent conversations directly from the raw stereo waveform, tested across three models in the Gemini family: 2.5 Flash, 3.5 Flash, and 3.1 Pro. Our primary evidence base uses Gemini 2.5 Flash as the ground-truth model, validated against three calibrated human raters on 209 stereo sessions, scored on 8 production dimensions: 152 full-duplex conversations across 13 accent-and-condition strata, together with 57 adversarial defect-injected clips. The evidence for Gemini 2.5 Flash is consistent across three tests. (i) On 5 of 8 dimensions the LALM-human Spearman rho departs from the pairwise human-human rho by at most 0.07, and on 7 of 8 dimensions the two quantities 95 percent bootstrap confidence intervals overlap. (ii) The LALM agrees with the three-rater human mean within 1 point on 60 to 92 percent of sessions on 6 of 8 dimensions. (iii) On 45 of 48 (defect, dimension) cells the LALM is as sensitive as humans or better under Newcombe-Wilson 95 percent confidence intervals, though most of these are underpowered nulls rather than demonstrated parity. Rank-ordering ability transfers across the Gemini family: 3.5 Flash improves simple agreement to 8 of 8 dimensions, while 3.1 Pro rates several dimensions markedly lower than humans despite comparable rank correlation. A model swap should be re-validated on calibration specifically, not assumed from rank-correlation alone. We identify four areas where deployment requires care, and we estimate that human rating alone for our current evaluation cadence costs roughly two orders of magnitude more than the equivalent LALM workload. The data presented here provides a defensible empirical basis for deploying the LALM as a substitute or fourth rater on the dimensions where the evidence supports it. ---