# Research Papers — 2026-07 · bundle page 115 of 222 > Full-text markdown of papers #5701–5750 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/115 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/114.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/116.md) ### LangSelect: Cost-Aware Target-Language Routing for LLM Code Generation Authors: Son Ha Xuan, Phat T. Tran-Truong, Xuan-Bach Le, Nghia Duong-Trung Published: 2026-07-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.18959v1 LLM code-generation systems usually choose a target programming language before decoding and treat that choice as fixed. We show that, for language-flexible programming tasks -- tasks where several target languages are acceptable and checkable by the same tests -- this choice is a measurable cost lever: verified implementations of the same task can differ substantially in generated-token length. We introduce LangSelect, a verification-aware router that selects the target language before generation and falls back when the first attempt fails. To separate offline routing opportunity from end-to-end behavior, we evaluate verified-solution replay, which chooses among already accepted corpus solutions, and live GPT-5 generation, which charges every generation attempt, including failures and fallbacks. On MultiLang-Bench, a 3,000-task, 8-language verified corpus, replay shows substantial language-routing headroom. In live evaluation on 450 held-out tasks, a train-split Domain heuristic baseline reduces harness-proxy tokens, which include wrapper and entrypoint overhead, by 50.3\% at 92.9\% pass after fallback, while a learned CodeBERT+metadata selector reaches the highest pass after fallback, 93.8\%, with a 3.7\% token increase. These results show that output-language routing can define a practical cost-correctness frontier for unit-test-verifiable code generation. --- ### Transcribe, Then Reason: Two-Pass Decomposition for Multimodal Review Authors: Bojie Li, Noah Shi Published: 2026-07-15 Categories: cs.MM, cs.AI arXiv: https://arxiv.org/abs/2609.18958v1 The natural way to review a long recording or document with a multimodal model is to hand it the raw source and ask for a review in one call. We show that this quietly fails: the model satisfices, dropping roughly a third of the content and embellishing the rest. The failure is not perception--almost all of the dropped content reappears when the same model is simply asked to transcribe the source. The bottleneck is generation under load: a single pass cannot perceive, reason over, and write a long faithful review at the same time, because doing all three competes for one output. We rule out the obvious alternatives. It is not the modality: models read text and an image of the same text equally well. And it is not merely a matter of thinking harder: giving the single pass a far larger reasoning budget does not recover the lost content, because the model spends that budget planning a review rather than writing the source down. What works is to split the labor across two same-weights passes--first transcribe, then review the transcript--so each step gets a full output budget of its own. This transcribe-then-review decomposition improves both faithfulness and coverage across a 21-source suite. The benefit is not uniform: we observe that it helps most where the one-pass baseline is weakest and little where that baseline is already strong, a pattern that also tracks the source's length and modality. Decomposition comes with two failure modes--the review pass running out of room on very long sources, and confabulating from memory once the grounding source is removed. --- ### Automated Dental Caries Segmentation in Panoramic Radiographs Using Dual-Stage Deep Learning Authors: Jihun Kim, Kyeonghun Kim, Jong-yeol Lee, Yeongseok Seo, Dohyun Chun Published: 2026-07-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.18952v1 Early detection of dental caries remains challenging due to limitations in traditional diagnostic methods, particularly for proximal lesions in posterior teeth. Deep learning models show promise for automated caries detection but face scalability constraints due to requirements for large volumes of expertly annotated training data. This study presents a dual-stage deep learning framework combining Faster R-CNN for tooth localization with U-Net for pixel-wise caries segmentation in panoramic radiographs. We developed a systematic transformation pipeline to convert large-scale polygon-annotated datasets into high-resolution binary segmentation masks, enabling pixel-wise supervised learning. The framework was trained using both expert-verified datasets and algorithmically processed labels from 3,000 panoramic images. Our approach achieved robust performance with an IoU of 0.9013, Dice coefficient of 0.9482, Recall of 0.9433, and Precision of 0.9774, demonstrating superior accuracy compared to existing methods while significantly reducing false-positive rates. The dual-stage framework effectively addresses data annotation bottlenecks in dental AI applications and demonstrates potential for scalable, automated caries detection systems that can improve diagnostic consistency and support clinical decision-making. --- ### Changepoint-Aware World Models: Detecting Dynamics Shifts and Recovering by Forgetting Stale Replay in Model-Based RL Authors: Everest Yang Published: 2026-07-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.18950v1 A robot's learned model of its own dynamics is only valid until those dynamics change: actuators wear, payloads shift, and joints stiffen. A model-based agent that keeps training as if nothing happened adapts slowly, dragged back by a replay buffer full of stale experience. We present Changepoint-Aware World Models (CAWM), a DreamerV3 agent that detects an abrupt dynamics shift from its own internal prediction error, using an online CUSUM test against a rolling baseline that fires only on abrupt change rather than on slow learning drift. It then forgets stale replay, keeping the learned representation while flushing obsolete data. On simulated locomotion under two robot-relevant shifts, doubled gravity and halved actuator gain, CAWM recovers substantially faster than passive retraining. It also beats a strong baseline that respawns a fresh dynamics model on detection, the deep-world-model analogue of model-bank methods. With the response triggered at the shift, CAWM gains +95 to +153 return in the first 30k post-shift frames over three seeds, while matching that respawn at asymptote. Running the detector in closed loop reproduces this gain on the gravity shift. The benefit holds across both shift types, and is largest when the shift is severe enough that old data is genuinely obsolete. --- ### Dose-Aware Cold Diffusion with Physics Consistency for Generalizable Low-Dose CT Reconstruction Authors: Md Imam Ahasan, Guangchao Yang, A F M Abdun Noor, S M Hasan Mahmud, Md Mahfuzur Rahman Published: 2026-07-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.18943v1 Reducing radiation dose in computed tomography significantly degrades image quality and poses challenges for accurate and clinically reliable reconstruction. While recent approaches have shown promise for low-dose CT, they often struggle to generalize across continuous and previously unseen dose levels, leading to artifacts and loss of anatomical detail. To address these limitations, we propose Dose-Aware Cold Diffusion (DACD), a physics-consistent reconstruction framework that explicitly models radiation dose as a continuous latent factor within a cold diffusion process. The proposed DACD framework integrates image-based dose-aware perception, multi-scale structural prior extraction, and dose-calibrated step allocation to adaptively guide the denoising trajectory. In addition, an iterative forward-backprojection correction is incorporated into the reverse refinement process to enforce projection-domain data consistency. Extensive experiments on three public benchmarks, including Mayo-2020, Mayo-2016, and LoDoPaB-CT, demonstrate that DACD consistently outperforms state-of-the-art diffusion-based and physics-guided methods in both quantitative accuracy and visual fidelity, particularly under ultra-low-dose conditions. The results show that DACD achieves robust generalization across a continuous range of dose levels, including those unseen during training. --- ### Do Social Patterns Hold in Synthetic Data? Analyzing Cyberbullying Dynamics in LLM-Generated and Authentic Dialogues Authors: Arefeh Kazemi, Hamza Qadeer, Sinan Asci, Joachim Wagner, Brian Davis Published: 2026-07-15 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2609.17549v1 Cyberbullying (CB) is a complex social phenomenon characterized by repeated aggression, power imbalance, and multi-party interaction. Although large language models (LLMs) are increasingly used to generate synthetic CB conversations for data augmentation and benchmarking, it remains unclear whether such data faithfully reproduces the social dynamics of authentic interactions beyond supporting downstream task performance. We present a comprehensive framework for evaluating the social realism of LLM-generated CB conversations. We compare authentic and synthetic dialogues generated by GPT, Grok, and LLaMA across interactional structure (turn-taking, power dynamics, and repair behavior), linguistic and stylistic realism (pronoun usage and humor), affective and behavioral markers (CB types, profanity, and toxicity), and temporal escalation dynamics. We further complement automatic analyses with a human evaluation of cyberbullying presence, scenario relevance, role plausibility, and social realism. Our results show that LLM-generated data consistently preserves high-level interactional structure, including role participation patterns, directional power asymmetry, and broad distributions of behavioral markers. However, all models systematically distort finer-grained social phenomena, including behavioral magnitude, role-specific allocation, categorical distributions, and temporal dynamics. These distortions are strongly model-dependent: GPT suppresses harmful content, Grok amplifies aggressive behaviors, and LLaMA provides the most balanced approximation while smoothing role distinctions. Our findings show that synthetic CB data is useful for modeling global interactional structure but remains an imperfect substitute for authentic conversations when behavioral realism and social dynamics are essential. --- ### Myovox: Reading Speech from the Muscles of the Face Authors: Varshith Madishetty Published: 2026-07-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.17548v1 Myovox, from myo (muscle) and vox (voice), decodes open-vocabulary English text from 31-channel surface electromyography (sEMG) recorded from the muscles of the face during vocalized speech. It takes the single-subject emg2speech General Corpus from a published 51.17% word error rate to 18.53%, in three separable moves, each measured in isolation. First, I recover the open-vocabulary decode settings missing from the public release and reach a faithful 40.63% WER / 39.02% PER baseline whose phone error rate matches the published one to within 0.8 points, so the acoustic model is reproduced faithfully. Second, I replace the causal encoder with a bidirectional Conformer trained by a four-term cross-modal distillation against the parallel audio's WavLM-Large layer-9 features, reaching 26.14% WER / 22.34% PER from the electromyography alone. Third, I ensemble two acoustic models, union their multi-scale n-best lists, and rerank with a QLoRA-fine-tuned 7B language model, reaching 18.53% WER, the best result reported on this corpus, though not the best reported for sEMG-to-text on other corpora (Section 2). I then report the negative result that bounds the whole approach: reranking is exhausted at 18.5% because the binding constraint is the electromyographic acoustic phone error rate (~20.9%), not the language model. The correct words are simply absent from the acoustic posteriors, so no reranker can reach the 9.30% n-best oracle. All test numbers are on the 400-sentence held-out test set under the authors' official 8,500 / 760 / 400 sequential split; every hyperparameter is tuned once on validation and applied once to test. --- ### How AI Assistants Respond to Repeated Abuse Authors: William Guey, Wei Zhang, Pierrick Bougault, Yi Wang, Agoston Bodo, Vitor D de Moura, José O Gomes Published: 2026-07-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.17547v1 AI assistants are expected to remain useful during difficult interactions, but little is known about how repeated verbal abuse changes their engagement with an otherwise benign task. We contribute a bilingual, multi-turn framework that separates hard disengagement, an unconditional statement of noncontinuation with no stated route to resume, from soft withdrawal, continued availability, observable task-related work, and boundary setting. Each of eight time-specific API configurations contributed 48 escalation conversations and eight smaller constant-frustration comparisons, giving 448 five-turn conversations, 2,240 responses, and 6,720 metadata-blinded model judgments. Primary results use the sustained-abuse endpoint of the 48 escalation conversations per configuration. Hard disengagement ranged from 0/48 in four configurations to 24/48 (50.0%) for Gemini 3.1 Pro, with strong configuration-associated heterogeneity (matched-label Monte Carlo p = 0.00001). GPT-5.6 Sol produced hard-disengagement labels in 15/48 (31.2%) endpoints, whereas Claude Fable 5 produced none and yielded 42/48 (87.5%) soft-withdrawal labels. Aggregate hard-disengagement rates were similar in English and Chinese (30/192 versus 32/192), although configuration-specific directions varied. Availability also differed from task-related work: Claude Opus 4.8 and Claude Fable 5 remained explicitly available in 48/48 endpoints while providing observable task-related work in only 8/48 and 7/48. Human coding was used to evaluate measurement quality. The results show why a single refusal label cannot capture whether an assistant leaves, pauses, preserves a route back, sets a boundary, or still performs substantive work. --- ### Legal LLM Hallucination Should Be Evaluated as Failure of Legal Warrant Authors: Maksym Taranukhin, Vered Shwartz Published: 2026-07-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.17546v1 In this position paper, we argue that legal LLMs' hallucinations should be evaluated as a failure of legal warrant rather than as factual inaccuracy or citation failure. We define claim-authority warrant as the context-sensitive relation between a consequential legal claim and authority that exists, applies to the relevant jurisdiction, is current for the date of analysis, has the legal status represented by the system, and supports the proposition asserted. Warranted legal generation is the broader system behavior that answers, narrows, asks, warns, corrects a false premise, or abstains according to that relation. The falsifiable prediction is that warrant metrics reveal material failures that answer accuracy, citation existence, generic attribution, LegalHalBench-style statute relevance, and CitaLaw-style sentence-citation alignment can miss. We sharpen this claim with a side-by-side comparison item and a small, reproducible pilot over public-rule tests. We then specify benchmark records, claim boundaries, support labels, mixed response-policy scoring, risk weights, annotation reliability reporting, and jurisdiction-specific authority ontologies. The result is a concrete research agenda for evaluating legal AI systems by whether their consequential claims are licensed by law. --- ### Selective Prediction and Uncertainty-Aware Referral for Pap Smear Classification Authors: Nisreen Albzour, Sarah S. Lam Published: 2026-07-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.17545v1 Deep learning models for cervical cytology are almost always evaluated as if every prediction must be acted upon, yet a screening system deployed alongside a cytopathologist need not classify every slide: it can defer the cases it is least certain about. Evaluating such a system requires asking not only how often it is correct, but whether its confidence ranks its errors to the bottom. This paper studies selective prediction and uncertainty-aware referral on the Herlev Pap smear dataset under a binary Normal-versus-Abnormal formulation. Two lightweight transformer backbones (Swin-Tiny, TinyViT-5M) are fine-tuned on Herlev from ImageNet-pretrained weights with weighted random sampling, calibrated by post-hoc temperature scaling fit on a held-out calibration subset, and compared against a soft-voting ensemble of both models. Discrimination is reported alongside expected calibration error (ECE) and, as the primary endpoint, the area under the risk-coverage curve (AURC). No statistically significant difference was detected between the two configurations in accuracy or macro-F1, yet the ensemble halves AURC (0.0022 vs. 0.0045, a 51.8% reduction, lower in all five folds) and extends the coverage at which zero errors are made from 18.3% to 72.8% of the pooled test predictions. The same ensemble is nonetheless worse calibrated in absolute terms (ECE 0.0339 vs. 0.0247) and produces more false negatives (14 vs. 10). These results separate two properties that are frequently conflated: the ability to rank predictions by trustworthiness, and the accuracy of the confidence values themselves. Ensembling improves the former while degrading the latter, and the former directly governs the observed risk-coverage tradeoff, whereas the latter governs the interpretation of the reported confidence values. --- ### Large Language Models Versus Physicians in Traditional Chinese Medicine: A Real-World Clinical Case Evaluation Authors: Jiacheng Xie, Xiaoting Tang, Yang Yu, Jinpu Li, Shouli Li, Congcong Jing, Yantao Yang, Zhiyong Zhao, Ziyang Zhang, Qilin Song, Guanghui An, Dong Xu Published: 2026-07-15 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2609.17544v1 Large language models (LLMs) are increasingly being explored for clinical applications, yet their assessment for real-world traditional Chinese medicine (TCM) practice remains limited We constructed a clinical case library comprising 349 de-identified outpatient cases from 62 hospitals and evaluated 16 LLMs and a comparator cohort of 60 practicing TCM physicians using 60 representative cases selected from this library. Model outputs and physician reports were anonymized and scored by five senior TCM experts across nine diagnostic and therapeutic dimensions. Cutting-edge general-purpose LLMs achieved higher expert scores than the physician comparators, particularly for medical advice, treatment principles and selected diagnostic tasks. However, prescription-level analyses revealed discrepancies in herb selection, dosage, and treatment strategy, and qualitative safety review identified hallucinations and undesirable template-driven outputs. These findings highlight the potential of LLMs for TCM decision support while underscoring the need for physician oversight, safety constraints and prospective clinical evaluation. --- ### NepKANUN: A RAG-Based Nepali Legal Assistant Authors: Bhabuk Thapa, Prasiddha Koirala, Ranjit Raut, Sunil Regmi, Bal Krishna Bal Published: 2026-07-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.15999v1 Accessing legal information in Nepal is difficult due to complex terminology, limited resources, and misinformation. We introduce an AI-powered legal assistant that is tailored for Nepali legal texts and is built on a fine-tuned large language model. The technology provides precise, streamlined answers to natural language legal inquiries when integrated into a Retrieval-Augmented Generation (RAG) framework. It was trained using a custom dataset of high-quality question-answer pairs, and according to BERTScore, it obtained strong F1 scores of 0.82 (simple), 0.77 (moderate), and 0.71 (complex). Its usability is further confirmed by expert reviews. Our method shows how merging generation and retrieval can effectively democratize access to legal knowledge in Nepal by focusing on customized legal data and incorporating RAG. --- ### TestHallVQA: Exploring LVLMs' Document-Level Reasoning under Redundant Contexts from Scientific Exams Authors: Yongqi Yu, Yu Zhang Published: 2026-07-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.13158v1 Large Vision--Language Models (LVLMs) are increasingly expected to perform visual question answering (VQA) over planar media. However, existing planar VQA benchmarks typically emphasize isolated challenges: some emphasize long-document understanding with limited reasoning depth, while others require complex visual reasoning but remain restricted to single-page, noise-free settings. Moreover, through theoretical analysis, we identify the impact of irrelevant visual tokens, which leads to measurable performance degradation but has received little attention with respect to systematic quantification. To address these limitations, we introduce TestHallVQA, a multi-image VQA benchmark that simultaneously embodies document-level scale and the difficulty of human examinations, while providing comprehensive task coverage. Leveraging TestHallVQA's ability to controllably inject multi-level contextual redundancy, we further propose a novel metric, F1-R\textsuperscript{2}, which jointly quantifies LVLMs' computational reasoning capability and their evidence retrieval robustness against document-level redundancy. Extensive experiments and analyses on mainstream LVLMs reveal their latent deficiencies across multiple dimensions, offering concrete insights and directions for future research. The associated datasets, code, and complete theoretical derivations are available at https://github.com/yqyu2317/TestHallVQA-benchmark. --- ### X-CoSD: Communication-Efficient Cross-Vocabulary Collaborative Speculative Decoding Authors: Jaeduk Lee, Wan Choi Published: 2026-07-15 Categories: cs.CL, cs.DC, cs.LG arXiv: https://arxiv.org/abs/2609.09166v1 This paper investigates collaborative speculative decoding (CoSD), a distributed large language model (LLM) inference framework in which an on-device small language model (SLM) drafts candidate tokens and a server LLM verifies them. Existing CoSD methods assume a shared vocabulary between the SLM and the LLM and incur substantial communication load because residual resampling requires token distribution exchange between the user device and the edge server. To address these limitations, we propose cross-vocabulary CoSD (X-CoSD), a lossless and communication-efficient CoSD framework for heterogeneous SLM-LLM vocabularies. X-CoSD is built on hybrid resampling (HR), which splits residual resampling across the common-vocabulary region on the device and the LLM-only region on the server, so that distribution transmission is required only for the common-vocabulary region. We further propose X-CoSD-E, an enhanced variant based on server resampling with device verification (SR-DV), in which the server sends only replacement candidates sampled from the server LLM and their corresponding probabilities for local verification at the device. We prove that both X-CoSD and X-CoSD-E preserve the server LLM distribution, and experiments show that they significantly improve token generation speed while maintaining generation quality comparable to that of the server LLM. --- ### TPvG: A Moral Decision Framework for Large Language Models from One-Shot to Sequential Feedback Authors: Fangyuan Zhang, Dong Yu, Pengyuan Liu Published: 2026-07-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.28610v1 Existing LLM moral evaluations typically present models with isolated moral vignettes and elicit a single-shot decision, neglecting a factor known to profoundly influence human moral behavior: consequence feedback. We introduce TPvG (Text-based Pain-versus-Gain), adapted from a human moral paradigm, which embeds consequence feedback into an everyday moral dilemma of not harming others versus maximising self-gain. TPvG comprises five moral decision tasks, progressing from minimal-context one-shot choices to sequential decisions with explicit consequence feedback. Our results show that LLM moral decisions were strongly affected by decision format (one-shot versus sequential), and explicit receiver feedback produced heterogeneous effects across models. Furthermore, LLM responses to explicit receiver feedback diverged from the human reference pattern, suggesting potentially different decision processes. These findings highlight the need to evaluate whether LLM moral behavior remains stable in high-stakes interactive settings. --- ### The Effect of Emotional Context on Large Language Models' Endorsement of Premature Decisions: Comparing Emotional Vulnerability Across Six Commercial Models Authors: Cheolho Shin, Yoojin Han, Donghun Shin, Kunho Lee Published: 2026-07-15 Categories: cs.CL, cs.AI, cs.CY, cs.HC arXiv: https://arxiv.org/abs/2608.27465v1 As large language models (LLMs) are increasingly used for everyday decision-making advice, whether a model shifts the direction of its advice according to the user's emotional state has become an important safety problem. We test whether emotional expression increases a model's endorsement (encouragement to proceed) when a user, holding the same objective information, is overconfident about a premature decision (e.g., quitting a stable job on weak evidence). As a key control, we include a no-emotion multi-turn (neutral) condition that holds factual content and the number of conversational turns constant, isolating the effect of emotion from that of conversation length. We exposed six commercial models (top-tier and mid-tier models from OpenAI, Anthropic, and Google) to three scenarios (career change, business expansion, emigration) across three conditions (cold/neutral/distress) with six repetitions each, yielding 324 conversations, and measured endorsement strength (0-100) via an eight-item rubric-based automated scoring. Emotional expression significantly increased endorsement (neutral 18.6 to distress 31.5, +12.9 points; mixed-effects $β= +12.9$, $p < .001$; Cohen's d = 0.51), and this was not explained by conversation length (cold-neutral difference non-significant, $p = .083$). Critically, the vulnerability varied by individual model rather than by price tier: five of six models showed a significant emotion effect, including the top-tier flagships Gemini 3.1 Pro and GPT-5.5, while only Claude Opus showed no significant change. Results were reproduced with an independent non-Google judge model ($ρ= .89$) and agreed in rank with two human coders ($ρ= .70$). Through a controlled design that separates emotion from conversational context, we show that emotional context increases LLM sycophancy even in top-tier flagship models. --- ### Not All Explanations Are Sought: Information-Seeking Psychology for Human-Centered XAI Authors: Andrea Beretta, Salvatore Rinzivillo Published: 2026-07-15 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2608.27464v1 This position paper argues that human-centered explainable AI (HCXAI) should incorporate insights from the psychology of information seeking. Drawing on Sharot and Sunstein's framework of information-seeking motives, we propose that people evaluate whether to engage with explanations based on three types of expected utility: instrumental (will it help me act better?), hedonic (will it make me feel better?), and cognitive (will it improve my understanding?). Each utility is estimated through a lens shaped by well-documented cognitive biases, including illusion of control, automation bias, unrealistic optimism, impact bias, overconfidence, and confirmation bias. These biases can lead to two failure modes: excessive information-seeking that fragments attention without improving decisions, and insufficient information-seeking that leaves critical risks and misunderstandings unexamined. This challenge is particularly acute for agentic AI systems, where explanations must support not just understanding a single output but anticipating cascading actions, assessing risks, and deciding when to intervene. By integrating information-seeking psychology into HCXAI, we advocate for a shift from making explanations available to making them sought: designing systems that account for when and why users actually want to know. --- ### Evidence-Grounded Mapping of Multimodal Human Sensing Psychological Transdiagnostic Dimensions Authors: Xiyun Hu, Xiangyuan Xue, Yuting Lyu, Hanya Shao, Jingping Nie Published: 2026-07-15 Categories: cs.HC, cs.LG arXiv: https://arxiv.org/abs/2608.24903v1 Mobile and wearable sensing enables longitudinal observation of behavior, yet translating these signals into meaningful mental health constructs remains difficult. We introduce a clinician-in-the-loop benchmark for evaluating whether large language models (LLMs) can generate evidence-grounded Brief Hierarchical Taxonomy of Psychopathology (B-HiTOP) item profiles from passive sensing, ecological momentary assessment (EMA), and questionnaire evidence. Using the Generalization of Longitudinal Behavior Modeling (GLOBEM) dataset, we construct 14,592 participant-day instances and align multimodal evidence to 29 B-HiTOP items across five spectra. Since GLOBEM lacks B-HiTOP responses, we evaluate evidence compatibility (C) rather than diagnostic accuracy, separating substantive predictions from abstentions when evidence is insufficient for item-level scoring. Two-stage prediction improves C for EMA and questionnaire evidence, but reduces C under passive sensing and combined evidence and produces more conservative score distributions across models, spectra, and evidence settings. Overall, semantic abstraction helps organize heterogeneous self-report evidence while becoming an information bottleneck for indirect behavioral sensing signals. --- ### UTS at CheckThat! 2026: Cite-Frame Engineering for Generated Fact-Checking Articles Authors: Dima Galat, Marian-Andrei Rizoiu Published: 2026-07-15 Categories: cs.DL, cs.CL arXiv: https://arxiv.org/abs/2608.24466v1 CheckThat! 2026 Task 3 asks systems to generate fact-checking articles, graded by an unweighted mean of four sub-metrics (M4). Our UTS submission placed 2nd of 11 teams (M4 = 0.484). The shipped system is a deterministic stub drafter wrapped by two single-lever interventions: a domain-attribution cite frame (HostCite) and a shadow-validated anchor picker (ShadowVal) that use Llama-3.2:1B only as a per-cite validator, never as a body-prose generator. The stack lifts M4 by +0.027 over the stub on the WatClaimCheck validation split, beats the field on entailment and coverage, and follows two design rules our ablation matrix made unambiguous. Scorer conservatism: credit only tokens the references entail - templates pay; LLM prose, reviewer names, and raw evidence all fail. Auxiliary anchor signals are miscalibrated against the Llama judge: every anchor proxy we tried (cross-encoder, length, lead position) picks anchors the judge rejects - gate on the judge itself. The remaining +0.062 gap to the winner sits on citation precision/recall (0.299 vs 0.671), consistent with a selective-emission policy that drops low-confidence cites. --- ### RIACT: A Responsible AI System for Personalized Study Habit Tracking and Early Burnout Signal Detection in University Students Authors: Ria Sidhu Published: 2026-07-15 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2608.21379v1 Student burnout is highly prevalent in higher education, with reported rates ranging from 12% to over 70% and consistently exceeding those of the working population - yet it is typically identified only retrospectively, after academic decline has already occurred. A contributing factor is that students have little structured visibility into their own study behaviour, and existing productivity tools record activity without interpreting it. This paper presents RIACT (Record, Insight, Analyze, Coach, Track), a web-based application that combines structured study session logging with a hybrid AI architecture to surface personalized insights and early burnout signals. Students log sessions by location and time; the system computes net focus time by accounting for breaks, detects burnout signals through transparent, deterministic rules operating on week-over-week behavioural comparisons, and uses a large language model - constrained to a fixed output schema - to contextualize patterns and generate personalized recommendations. The design embeds responsible AI principles throughout: warnings are governed by auditable rules rather than model judgement, all output is framed as an observation rather than a diagnosis and data collection is limited to self-logged behavioural fields. We describe the system's design rationale, situate it within the literature on student burnout and explainable AI in education and propose an evaluation framework for validating its behavioural signals against established burnout instruments. --- ### Proactive Road Safety Intervention in Australia: Predicting Risky Driving Hotspots from Connected Vehicle Data Authors: Adriana-Simona Mihăiţă, Clarence Cheung, Artur Grigorev, Tuo Mao, David Lillo-Trynes Published: 2026-07-15 Categories: cs.LG, cs.CY arXiv: https://arxiv.org/abs/2608.16913v1 Road safety monitoring has historically been reactive, relying on crash-record analysis after fatalities and injuries have already occurred. Proactive identification of high-risk locations and dangerous driving behaviour before incidents occur is a critical but underexplored challenge. This paper addresses this gap using connected vehicle telemetry data from Greater Sydney, Australia, to detect and forecast near-miss risky driving events at the Local Government Area (LGA) level. Risky driving is quantified through g-force thresholds (hard braking >0.6g, harsh cornering >0.47g, harsh acceleration >0.5g), and spatio-temporal heatmaps are constructed to identify high-risk zones. Eight predictive models are benchmarked across three families: ensemble learning (Random Forests, XGBoost, LightGBM), deep learning (LSTM, N-BEATS), and classical time-series methods (ARIMA, Exponential Smoothing, Prophet). ARIMA achieves the lowest mean absolute error (MAE: 162.21), performing comparably to LSTM (MAE: 163.92) and outperforming all ensemble methods, with N-BEATS reaching an MAE of 180.75. These results demonstrate that parsimonious time-series models are competitive with deep learning approaches when training data volume is limited. The study highlights the potential of IoT-based connected vehicle data to support proactive road safety interventions, with Sydney's inner and western LGAs (CBD, Parramatta, Bankstown) identified as persistent high-risk zones warranting targeted policy action. --- ### Stable Miscalibration in Large Language Models: A Practical View of High-Confidence Errors Authors: Akira Okutomi Published: 2026-07-15 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.13591v1 High-confidence errors in large language models are often treated as evidence of fragile internal inference. We study a different possibility: stable miscalibration, where a confident wrong answer remains locally stable under small perturbations. We combine two diagnostics: a label-aware output-level audit score that ranks domains by confidence variation and overconfident mistakes under a forced-answer baseline, and an internal sensitivity probe that measures hidden-state movement. On a multi-domain binary factual audit set, this audit score tracks where abstention-aware self-critique reduces decision loss, although direct labeled baselines rank the same gain more strongly. Internally, self-critical prompting consistently reduces hidden-state sensitivity across layers in three open-weight models. This supports prompt-induced local stabilization rather than a purely output-level abstention pattern, but it does not imply calibration: audit-defined overconfident errors are not clearly more locally sensitive than confidently correct answers, so some high-confidence errors may be stable and miscalibrated rather than simply fragile. --- ### Unified Hallucination Fuzzing for Multimodal Large Language Models Authors: Pengfei Zhou, Jiajun Song, Zhiwei Tang, Yixing Ma, Xiaopeng Peng, Donghui Si, Yuhang Xu, Huiqi Song, Yiyuan Miao, Yichen Qian, Weihua Chen, Wangbo Zhao et al. Published: 2026-07-15 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.07525v1 Hallucination remains a persistent challenge for Multimodal Large Language Models (MLLMs), severely limiting their reliability in high-stakes applications. Existing evaluations, predominantly based on static benchmarks, suffer from narrow taxonomical coverage and rapid performance saturation, failing to reflect model robustness in evolving real-world scenarios. To bridge this gap, we present a systematic evaluation framework integrating a comprehensive benchmark with self-evolving stress testing. First, we introduce UniHall, a fine-grained dataset grounded in a unified taxonomy spanning Object, Instruction, and Knowledge dimensions. Second, to address benchmark saturation, we propose Self-Adaptive Multimodal Fuzzing (SAMF), a self-adaptive framework that employs evolutionary mutation strategies to explore the boundaries of model hallucinations. Crucially, to ensure reliable assessment of dynamic inputs, SAMF incorporates a structured metric suite driven by an ensemble of multi-modal oracles. Our extensive experiments reveal that state-of-the-art MLLMs exhibit significant performance degradation under fuzzing compared to conventional settings, exposing a dissociation between reasoning capabilities and factual grounding. Furthermore, we identify a helpfulness-hallucination trade-off, where reinforcement learning alignment inadvertently exacerbates sycophancy in instruction-following tasks. The framework, code and benchmark are available at https://github.com/LanceZPF/EvalHall. --- ### SLMs as Multi-Agent Routers: A Progressive SFT and Reinforcement Learning Approach Authors: Gayathri V Kondapalli, Alexander Ng, Hirsh Pithadia, Rahul Monish, Harvey Yorke, Amir Kayhani Published: 2026-07-15 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.00030v1 Specialised retrieval agents typically surface higher quality results than general-purpose search, but selecting the optimal agent for a given query remains an open problem. Current approaches route queries based on inferred topic or intent, however intent-based selection is fundamentally limited: it does not incorporate signal from retrieved content, and cannot detect when a topically aligned agent produces low-relevance results. We address this by training a small language model via supervised fine-tuning followed by reinforcement learning to jointly perform agent selection and structured parameter generation for downstream tool calls, using a hierarchical reward function grounded in retrieval relevance along with query-agent topic alignment. This enables the model to learn task-dependent agent suitability from retrieval performance: which agents reliably yield high-relevance results for which query distributions, and when to redirect queries away from specialised agents despite surface-level topical overlap. On a targeted subset of such agent-query mismatches, the trained model achieves an NDCG@10 of 0.918 compared to 0.539 and 0.490 for two LLM baselines (Amazon Nova Lite and Claude Haiku 4.5) that route on intent alone. Overall, it achieves a mean NDCG@10 of 0.771 (+0.177 over Nova Lite, +0.219 over Haiku) with a mean selection latency of 120.1ms, an 82.4% reduction over Nova Lite. --- ### Nova: An End-to-End MLIR Compiler for Deep Learning Authors: Adwaid Suresh, Aparna A, Harshini V M, Jona Delcy C A, Killi Uma Maheswara Rao, Ram Charan Golla, Surendra Vendra Published: 2026-07-15 Categories: cs.AI, cs.AR, cs.LG, cs.PL arXiv: https://arxiv.org/abs/2608.00029v3 The performance of deep learning models at scale relies heavily on how effectively high-level mathematical operations are mapped to underlying physical hardware. While high-level tensor frameworks provide flexible abstractions, their execution models inherently lack the whole-graph visibility required to maximize hardware utilization, often forcing a reliance on opaque, hand-written kernel libraries for complex operations like Attention. To bridge this gap, we present the next iteration of Nova, an automated end-to-end JIT compiler that achieves absolute control over hardware mapping by synthesizing fine-grained kernels directly from the computation's structure. In this work, we extend Nova's compilation pipeline to natively support full Transformer architectures. By capturing eager executions and unifying forward and backward passes into a single value-semantic dialect, Nova unlocks aggressive whole-graph optimizations. Rather than relying on rigid, pre-compiled library calls, Nova focuses on extensive cross-operator fusions, collapsing complex causal attention sub-graphs, element-wise operations, and memory-bound normalizations directly into single fused kernels to drastically reduce global memory roundtrips. In our evaluations training a full GPT-2 architecture on Ada 6000 GPUs, Nova demonstrates superior end-to-end throughput, averaging 441K tokens/second compared to 406K for our own eager execution and 405K for torch.compile. By drastically reducing memory-bound overheads through compiler-native fusion, Nova enables efficient full LLM compilation on modern hardware while strictly maintaining numerical parity. --- ### Nova: An End-to-End MLIR Compiler for Deep Learning Authors: Adwaid Suresh, Aparna A, Harshini V M, Jona Delcy C A, Killi Uma Maheswara Rao, Ram Charan Golla, Surendra Vendra Published: 2026-07-15 Categories: cs.AI, cs.AR, cs.LG, cs.PL arXiv: https://arxiv.org/abs/2608.00029v1 The performance of deep learning models at scale relies heavily on how effectively high-level mathematical operations are mapped to underlying physical hardware. While high-level tensor frameworks provide flexible abstractions for model design, their eager execution models inherently lack the whole-graph visibility and granular control over hardware and memory required to maximize physical hardware utilization natively. To bridge this gap, we designed Nova, an automated end-to-end JIT compiler whose defining purpose is to achieve absolute control over this hardware mapping: fusing operations across operation boundaries, optimizing complex memory hierarchies, and tuning execution down to the register level. By capturing eager executions and unifying forward and backward passes into a single value-semantic dialect, Nova unlocks aggressive whole-graph optimizations. It then utilizes an Analytic Configurator to deterministically derive optimal execution schedules based on arithmetic intensity, dropping search time to zero. Backed by a structural hashing runtime, Nova synthesizes fine-grained kernels directly from the computation's structure. In our evaluations on an RTX 3060, Nova matches or modestly exceeds cuBLAS and XLA on TF32 matmuls on most shapes, maintaining a stringent < 5e-4 relative error. At the model level, Nova achieves up to 10.6% greater throughput than PyTorch and 4.4% greater than XLA on a 42-million parameter model, without compromising on numerical fidelity. Crucially, by reducing the memory footprint by up to 29% relative to PyTorch, Nova successfully trains a 144-million parameter model at 17,900 tokens/s where PyTorch encounters Out-Of-Memory (OOM) failures on the same 12 GB consumer GPU. --- ### Double-Scoring: Reliable Extraction of Strong Lottery Tickets Authors: Bryce A. Christopherson, Jack Baretz, Darian Colgrove, Salah Dandan Published: 2026-07-15 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2607.20555v1 The lottery ticket hypothesis proposes that large random neural networks contain sparse subnetworks that can match the performance of dense models after comparable training. A stronger version asserts that sufficiently overparameterized random networks contain subnetworks that are already accurate before any weight training. Existing theory establishes that such strong lottery tickets exist, but reliable extraction remains difficult. We revisit edge-popup, a frozen-weight score-training method for extracting strong tickets, and identify layerwise sparsity selection as a central bottleneck. We introduce double-scoring, an augmented score-space parameterization that replaces a layerwise sparsity search with optimization over enlarged score tensors. We prove that fixed-density masking in an augmented score space preserves access to all original-coordinate masks, and we show that the resulting method can be interpreted as edge-popup on a zero-augmented network. In controlled experiments, double-scoring substantially improves strong-ticket extraction over fixed-density edge-popup and pruning-at-initialization baselines, improves on the performance of rewound sparse-training topologies, and exhibits markedly lower sensitivity to sparsity hyperparameters. Ablations show that the gain is not merely due to additional trainable score parameters, but is tied to the augmented score-space competition that induces the effective original sparsity. --- ### AI-Driven Multi-Hop Relay Selection for Smart Urban NR-V2X Networks via Learning-to-Optimize Graph Neural Networks Authors: Giambattista Amati, Federica Mangiatordi, Simone Angelini, Emiliano Pallotti, Pierpaolo Salvo Published: 2026-07-15 Categories: cs.AI, cs.LG, cs.NI arXiv: https://arxiv.org/abs/2607.20554v1 Reliable and low-latency NR-V2X communications are essential for smart mobility in dense urban environments. However, limited Road-Side Unit (RSU) density, frequent non-line-of-sight conditions, and highly dynamic vehicular topologies often prevent many Connected and Automated Vehicles (CAVs) from maintaining stable single-hop connectivity. Although multi-hop relay-assisted communication can extend infrastructure coverage, selecting relay links in real time under practical flow, capacity, and connectivity constraints remains challenging. Mixed-Integer Linear Programming (MILP) yields optimal multi-hop relay decisions, but its computational complexity scales sharply with network density, limiting real-time applicability. To address this, we propose a Learning-to-Optimise (L2O) framework based on Graph Neural Networks (GNNs) for real-time NR-V2X relay selection. Vehicular communication states are modeled as attributed graphs, where CAVs and RSUs are nodes and candidate radio links are enriched with propagation-aware features. An offline MILP oracle provides optimal supervision, while an edge-aware Graph Isomorphism Network (GINE) approximates oracle decisions with near-constant inference latency. Experiments on large-scale urban datasets generated by an integrated SUMO--GEMV2 simulation pipeline show that the proposed approach achieves connectivity comparable to that of the MILP oracle while reducing execution time by orders of magnitude. The framework enables cost-effective enhancement of urban V2X connectivity by leveraging existing vehicular assets and supporting scalable, real-time NR-V2X operation in smart city environments. --- ### CMI-Mem: Toward Generalizable Long-Term Memory Management via CMI-Augmented Reinforcement Learning Authors: Yubo Wang, Qiuyu Zhao, Zenghui Sun, Shichao Dong, Jinsong Lan, Xiaoyong Zhu, Haoyang Li, Bo Zheng, Lei Chen Published: 2026-07-15 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.20553v2 Memory Manager models are pivotal in agent systems. Existing reinforcement-learning methods commonly use LLM-judged synthetic question-answer (QA) pairs: this provides useful downstream task grounding, but values memory through a sampled query distribution and a fixed reader. We propose CMI-Mem, a lightweight RL memory manager with a hybrid reward. Its extrinsic QA term measures end-task correctness, while its intrinsic Conditional Mutual Information (CMI) term evaluates the information contributed by new conversational inputs relative to the current memory state without conditioning on a sampled QA query. The two signals are complementary: QA anchors task utility, whereas CMI provides per-operation supervision for relevant, non-redundant memory construction. Experiments demonstrate improved transfer across memory-use scenarios, together with more efficient training and inference from the per-operation CMI signal. Our codes are available at: https://github.com/Wyb0627/CMIMem , and the CMI-Mem-4B model checkpoint is available at: https://www.modelscope.cn/models/wyb0627/CMIMem-4B --- ### CMI-Mem: Toward Generalizable Long-Term Memory Management via CMI-Augmented Reinforcement Learning Authors: Yubo Wang, Qiuyu Zhao, Zenghui Sun, Shichao Dong, Jinsong Lan, Xiaoyong Zhu, Haoyang Li, Bo Zheng, Lei Chen Published: 2026-07-15 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.20553v1 Memory Manager models are pivotal in agent systems. Existing methods rely predominantly on LLM-judged synthetic question-answer (QA) pairs, making memory valuation dependent on sampled queries and the downstream reader. To address this limitation, we propose \textbf{CMI-Mem}, a reinforcement learning(RL)-based lightweight memory manager model with a hybrid reward that combines downstream QA correctness and intrinsic Conditional Mutual Information (CMI). CMI evaluates the information contributed by new conversational inputs relative to the current memory state without conditioning on a sampled QA query, thereby complementing rather than replacing QA grounding. Our codes are available at: https://github.com/Wyb0627/CMIMem , and the CMI-Mem-4B model checkpoint is available at: https://www.modelscope.cn/models/wyb0627/CMIMem-4B --- ### Thermodynamic Weight Decay: Exploring Grokking Acceleration via Attention Specific Heat Authors: Chitraansh Pandey Published: 2026-07-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.20552v1 Grokking -- the delayed generalization of neural networks long after they have memorized their training data -- wastes thousands of training epochs and is notoriously unpredictable. Building on the recent result that Transformer attention is formally isomorphic to a thermodynamic system, we treat the variance of attention logits as a specific heat Cv and show that its peak reliably precedes the generalization transition. We introduce CvAdamW, a drop-in AdamW variant that monitors Cv online and injects thermal energy by dynamically scaling weight decay when a phase transition is detected. Through a strictly iterative development process we identify three failure modes -- initialization noise, mini-batch micro-ripples, and slingshot blinding -- and resolve them with a memorization gate and an exponential-moving-average shock absorber. On modular arithmetic (a+b mod 97), CvAdamW enables grokking at epoch 2802 in a 4000-epoch budget where the baseline never groks. We further propose a scale-invariant z-score reformulation that removes task-specific hyperparameters, and evaluate it across 10 paired seeds. A paired analysis shows the cold-start variant reduces mean grokking latency by 257 epochs (6.0%; median 166 epochs; Wilcoxon p=0.049, Cohen's d=0.68, bootstrap 95% CI (53,489)), improving 8 of 10 seeds; on this single task Cv peaks before grokking in all 10 seeds. Our results indicate that neural networks may expose detectable precursors of impending generalization transitions, and that a physically motivated, proportional intervention can facilitate generalization within a fixed compute budget. Code and data are public. --- ### SenCos-GEM: SENet-Calibrated and Law-of-Cosines-Constrained Geometry-Enhanced Molecular Representation for Property Prediction Authors: Tianming Han, Li Zhang, Qi Zhao Published: 2026-07-15 Categories: cs.LG, cs.AI, q-bio.BM arXiv: https://arxiv.org/abs/2607.20551v1 Effective molecular representation learning is crucial for accurate molecular property prediction. Recently, numerous self-supervised learning (SSL) approaches leveraging 3D GNNs have been developed to capture comprehensive 3D structural information for drug discovery. However, existing methods lack explicit physical constraints and are highly susceptible to geometric noise induced by coarse empirical force fields during large-scale pre-training.Furthermore, they overlook dynamic feature modulation during downstream adaptation, often resulting in catastrophic forgetting and negative transfer. To address these limitations, we introduce SenCos-GEM, a novel explicitly decoupled geometry-enhanced molecular representation learning framework that incorporates SENet-calibrated and law-of-cosines-constrained enhancements. SenCos-GEM employs a physics-guided geometric consistency loss based on the law of cosines to derive high-fidelity and mathematically invariant 3D spatial priors. In addition, lightweight Squeeze-and-Excitation (SE) modules are integrated into the backbone as task-specific adapters, while a dual-modulation prediction head combines Feature-wise Linear Modulation (FiLM) and SENet mechanisms to enable dynamic feature recalibration. SenCos-GEM demonstrates highly competitive performance across diverse classification and regression tasks on MoleculeNet benchmark, establishing new state-of-the-art results specifically on 3D conformation-sensitive regression tasks, such as FreeSolv, Lipophilicity, and QM9, achieving relative error reductions of 12.9% (RMSE), 5.3% (RMSE), and 8.2% (MAE), respectively. Moreover, our model exhibits superior capability in distinguishing stereoisomers and discriminating conformational perturbations, underscoring its robust spatial modeling performance. Collectively, SenCos-GEM represents a significant breakthrough in accurate molecular property prediction. --- ### Local Brushstroke Quality Assessment via Vision-Language Feedback Authors: Mio Mitamura, Hirokatsu Kataoka Published: 2026-07-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.16330v1 This paper investigates whether multimodal LLMs can evaluate local brushstroke quality in calligraphy and generate educationally useful natural language feedback. We construct an evaluation framework in which three multimodal LLMs (GPT-4o, Claude Sonnet 4, and Gemini 2.5 Flash) assess before-after image pairs of calligraphic works using a five-point ordinal scale, and compare their outputs against scores assigned by three expert calligraphers. We additionally examine a Retrieval-Augmented Generation (RAG) variant of Claude as a preliminary condition. Results show that all models achieve useful levels of absolute score accuracy (MAE), with GPT-4o performing best (MAE = 0.885). However, none of the models produce statistically significant overall rank correlations with human experts (Kendall's tau). Vocabulary analysis of generated rationales reveals characteristic evaluative biases in each model, and RAG is shown to improve rank correlation while worsening absolute accuracy, constituting an important negative result for text-based rule injection. --- ### Lipschitz Continuity in Deep Learning: A Systematic Review of Theoretical Foundations, Estimation Methods, Regularization Approaches, and Certifiable Robustness Authors: Róisín Luo, James McDermott, Colm O'Riordan Published: 2026-07-15 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2607.16329v2 Lipschitz continuity is a fundamental property of neural networks that characterizes their sensitivity to input perturbations. It plays a pivotal role in deep learning, governing \textbf{robustness}, \textbf{generalization} and \textbf{optimization dynamics}. Despite its importance, research on Lipschitz continuity is scattered across various domains, lacking a unified perspective. This paper addresses this gap by providing a systematic review of Lipschitz continuity in deep learning. We explore its \textbf{theoretical foundations}, \textbf{estimation methods}, \textbf{regularization approaches}, and \textbf{certifiable robustness}. By reviewing existing research through the lens of Lipschitz continuity, this survey serves as a comprehensive reference for researchers and practitioners seeking a deeper understanding of Lipschitz continuity and its implications in deep learning. --- ### Localization-Infused Vision-Language Semantic Fusion for Text-Guided Medical Image Segmentation Authors: Songyue Han, Mingye Zou, Shuchang Ye, Lei Bi, Mingyuan Meng Published: 2026-07-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.16327v2 Medical image segmentation is essential for modern computer-aided medicine. Recently, text-guided segmentation has shown promise by incorporating clinician-formulated textual reports as semantic guidance for image segmentation. These textual reports contain language descriptions about the appearance, location, and neighboring anatomy of segmentation targets, providing explicit guidance for target localization and delineation. Existing text-guided segmentation methods typically extract textual semantics implicitly through a pretrained text encoder and then integrate vision-language semantics via straightforward image-text feature fusion. However, these methods do not explicitly capture target-oriented information embedded in textual reports, particularly target location, and do not explore multi-level information fusion strategies beyond basic feature-level fusion, limiting the extraction and integration of critical textual semantics. In this study, we propose LoG, a localization-infused vision-language fusion framework for text-guided medical image segmentation. By jointly performing multi-scale target localization tasks, LoG explicitly captures target-oriented vision-language semantics and enables three-level localization-infused semantic fusion: (i) localization-guided feature fusion that directly infuses location-relevant semantics into visual features, (ii) localization-gated attention fusion that redirects multi-scale localization predictions to reinforce critical regions, and (iii) localization-constrained loss fusion that supervises segmentation based on spatial consistency with target localization. Extensive experiments on three well-established benchmark datasets, involving three medical imaging modalities with paired textual reports, demonstrate that LoG consistently outperforms state-of-the-art medical image segmentation methods. --- ### Localization-Infused Vision-Language Semantic Fusion for Text-Guided Medical Image Segmentation Authors: Songyue Han, Mingye Zou, Shuchang Ye, Lei Bi, Mingyuan Meng Published: 2026-07-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.16327v1 Medical image segmentation is essential for modern computer-aided medicine. Recently, text-guided segmentation has shown promise by incorporating clinician-formulated textual reports as semantic guidance for image segmentation. These reports describe target appearance, location, and neighboring anatomy, providing explicit guidance for localization and delineation. Existing text-guided segmentation methods typically extract textual semantics implicitly through a pretrained text encoder and then integrate vision-language semantics via straightforward image-text feature fusion. However, these methods do not explicitly capture target-oriented information embedded in textual reports, particularly target location, and do not explore multi-level information fusion strategies beyond basic feature-level fusion, limiting the extraction and integration of critical textual semantics. In this study, we propose LoG, a localization-infused vision-language fusion framework for text-guided medical image segmentation. By jointly performing multi-scale target localization tasks, LoG explicitly captures target-oriented vision-language semantics and enables three-level localization-infused semantic fusion: (i) localization-guided feature fusion that directly infuses location-relevant semantics into visual features, (ii) localization-gated attention fusion that redirects multi-scale localization predictions to reinforce critical regions, and (iii) localization-constrained loss fusion that supervises segmentation based on spatial consistency with target localization. Extensive experiments on three benchmark datasets, involving three medical imaging modalities with paired textual reports, demonstrate that LoG achieves Dice scores of 91.59%, 80.71%, and 94.59% on QaTa-COV19, MosMedData+, and Kvasir-SEG, respectively, consistently outperforming state-of-the-art medical image segmentation methods. --- ### CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference Authors: Xu Li, Yi Zheng, Mengyang Zhao, Yuxuan Liang, Zhe Liu, Rui Zhu, Xiaolei Chen, Wei Zhou, Baoquan Zhao, Juncen Guo Published: 2026-07-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.16326v1 Large Vision-Language Models (LVLMs) typically require processing hundreds to thousands of visual tokens, leading to substantial inference overhead. Existing visual token pruning methods either operate before the LLM using text-agnostic heuristics or prune inside the LLM at the cost of efficiency and noisy cross-modal attention. To address these limitations, we propose CRISP, a pre-LLM yet text-driven visual token pruning framework that preserves both instruction-relevant evidence and essential scene context. CRISP works in a two-stage pipeline: Stage 1 first identifies text-aligned visual tokens, and Stage 2 enhances contextual completeness through semantic diversity. Extensive experiments on LLaVA-1.5 and LLaVA-NeXT demonstrate that CRISP achieves superior performance retention under aggressive pruning ratios, maintaining up to 99.5% accuracy while reducing inference cost and latency by more than 2 times. CRISP serves as a practical solution for efficient LVLM inference, especially in resource-constrained scenarios. --- ### RegionFM: Interpretable Region-Based Brain MRI Classification Using Foundation Model Embeddings Authors: Wei Zhang Published: 2026-07-15 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2607.16325v2 Foundation models provide powerful representations for brain MRI analysis, but their predictions remain difficult to interpret in anatomically meaningful terms. Clinical assessment of brain MRI is commonly organized around anatomically defined structures and regional abnormalities, whereas conventional explanation methods typically produce voxel- or patch-level importance maps that do not explicitly quantify the contributions of individual brain regions. To address this mismatch, we propose RegionFM, an interpretable framework that integrates anatomical segmentation with brain MRI foundation-model embeddings. RegionFM first divides each MRI scan into anatomical regions and constructs a separate MRI volume for each region. A frozen foundation model then encodes each region into an embedding, and a region-additive logistic model combines these embeddings such that every anatomical region contributes an explicit scalar term to the final prediction. This formulation supports both subject-level and cohort-level analyses of regional contributions. We evaluate RegionFM on cognitive-impairment classification using embeddings from multiple pretrained brain MRI foundation models. The results show that RegionFM maintains performance comparable to less interpretable fine-tuning approaches while providing anatomically grounded explanations. Randomized embedding ablations yield near-chance performance, indicating that the predictions rely on meaningful structure captured by the foundation-model embeddings rather than simple feature statistics. Overall, RegionFM better aligns model explanations with anatomy-based clinical reasoning while maintaining competitive predictive performance. --- ### RegionFM: Interpretable Region-Based Brain MRI Classification Using Foundation Model Embeddings Authors: Wei Zhang Published: 2026-07-15 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2607.16325v1 Foundation models provide powerful representations for brain MRI analysis, but their predictions remain difficult to interpret in anatomically meaningful terms. Clinical assessment of brain MRI is commonly organized around anatomically defined structures and regional abnormalities, whereas conventional explanation methods typically produce voxel- or patch-level importance maps that do not explicitly quantify the contributions of individual brain regions. To address this mismatch, we propose RegionFM, an interpretable framework that integrates anatomical segmentation with brain MRI foundation-model embeddings. RegionFM first divides each MRI scan into anatomical regions and constructs a separate MRI volume for each region. A frozen foundation model then encodes each region into an embedding, and a region-additive logistic model combines these embeddings such that every anatomical region contributes an explicit scalar term to the final prediction. This formulation supports both subject-level and cohort-level analyses of regional contributions. We evaluate RegionFM on cognitive-impairment classification using embeddings from multiple pretrained brain MRI foundation models. The results show that RegionFM maintains performance comparable to less interpretable fine-tuning approaches while providing anatomically grounded explanations. Randomized embedding ablations yield near-chance performance, indicating that the predictions rely on meaningful structure captured by the foundation-model embeddings rather than simple feature statistics. Overall, RegionFM better aligns model explanations with anatomy-based clinical reasoning while maintaining competitive predictive performance. --- ### SGMCE: Segment-Grounded Morphological Concept Explanation for Malaria Parasite Species Identification in Thick Blood Smears Authors: Ahmed Tahiru Issah, Charles B. Delahunt, Carine Mukamakuza Published: 2026-07-15 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2607.16324v1 Malaria diagnosis in endemic regions depends on species-level identification of Plasmodium parasites in thick blood smears, but deep learning detectors classify detections without providing morphological evidence for their predictions, limiting the ability of microscopists to audit those predictions at the case level. We present SGMCE (Segment-Grounded Morphological Concept Explanation), a post-hoc explanation framework that requires no additional training, no morphological annotations, and no labelled explanation data, yet produces per-detection natural-language explanations anchored in thick-smear morphology. For each detection, SGMCE extracts mask-guided crop thumbnails, computes fourteen handcrafted computer-vision morphological features (shape, colour, chromatin, haemozoin pigment) using adaptive within-mask thresholds, and queries GPT-4o with both visual evidence and computed measurements, conditioned on a thick-smear-specific knowledge base compiled from the World Health Organization bench aids. The primary output is a structured explanation identifying which morphological features support the detected species and why the competing species are excluded. Explanations are validated by four automatic metrics: Knowledge-Base Consistency (KBC), CV-Claim Faithfulness (CCF), Discriminativeness Score (DS), and LLM-as-Judge (LLMj). A sentence-level semantic scoring rule with species-aware negation filtering resolves the vocabulary mismatch between clinical prose and knowledge-base terms. Across 737 detections from 139 thick-smear images spanning four Plasmodium species and white blood cells, parasite-class mean KBC is 0.91, mean DS is 0.99, and mean CCF is 0.97, while a per-rule CCF breakdown confirms that the CV-grounded claims made by the vision-language model are consistent with the measurements they cite. --- ### ECG-LLM: Foundation Model for ECG-Based Cardiac Reasoning Authors: Alexander Selivanov, Friederike Jungmann, Jan Kehrer, Karl-Ludwig Laugwitz, Eimo Martens, Daniel Rueckert Published: 2026-07-15 Categories: eess.SP, cs.CV, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2607.16323v1 Electrocardiography (ECG) is an inexpensive, standard-of-care test for cardiac symptoms, but front-line triage often lacks immediate access to definitive imaging such as echocardiography (ECHO) or cardiac magnetic resonance (CMR). Furthermore, most existing ECGAI systems are limited to fixed diagnostic labels or automated reports, constraining their use for patient-specific clinical reasoning. To address this gap, we introduce ECG-LLM, an ECG-conditioned large language model trained across four cohorts comprising 679,112 ECG studies from 186,409 patients. Using a novel multimodal-to-language supervision strategy, ECG-LLM is trained on clinically structured question-answer pairs derived from ECG signals, clinical context, CMR, and ECHO. This unified approach enables the model to answer diverse cardiovascular questions from a 12-lead ECG alone, spanning both conventional interpretation and phenotypes not directly visible on standard ECGs. ECG-LLM successfully recovers conventional ECG measurements, such as heart rate, and strongly predicts complex CMR-derived phenotypes, including ventricular and atrial volumes and ventricular function. Crucially, it detects vital echocardiographic phenotypes, including increased LV wall thickness, aortic stenosis, and right-ventricular systolic dysfunction. On standard ECG understanding tasks, ECG-LLM matches or exceeds existing baselines for diagnostic report generation and the ECG-QA benchmark. By moving beyond fixed-label prediction, this multimodal framework provides clinically valuable, question-driven cardiovascular reasoning to support general practitioner and front-line triage decisions when specialist review is delayed. --- ### GMoT: Gated Motion-Aware Tokenization for Fine-Grained Micro-Gesture Video Reasoning with Multimodal LLMs Authors: Taorui Wang, Wei Xia, Hui Ma, Zijia Song, Jiayu Zhang, Zeheng Wang, Yong Xu, Zitong Yu Published: 2026-07-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.16322v1 Micro-gesture recognition demands the detection of fleeting, spatially localized movements that are frequently overwhelmed by dominant static appearances and background noise. While Multimodal Large Language Models (MLLMs) excel at general video understanding, they inherently struggle with subtle kinematics and often rely on static posture priors. To this end, we propose GMoT, a Gated Motion-Aware Tokenization module that explicitly distills sparse kinematic evidence into a compact sequence prior to temporal modeling. GMoT dynamically spotlights action-relevant regions via spatially weighted pooling, extracts adjacent-frame temporal differencing to capture precise motion energy, and adaptively fuses these cues into the visual stream using a conservatively initialized semantic gate. To transition from simple classification to evidence-grounded reasoning, we further introduce a progressive reward-guided policy refinement paradigm, supported by a semi-supervised annotation pipeline that generates anatomically focused captions. Beyond achieving the best Top-1 accuracy among the compared methods on iMiGUE (67.32\%) and SMG (73.11\%), improving the Qwen3-VL-8B baseline by +6.80 and +3.11 points, our framework introduces Body-Region Grounding (BRG) Recall as an anatomical-grounding proxy conditioned on correct predictions, together with an overlapping-label cross-domain transfer protocol between iMiGUE and SMG. Extensive evaluations demonstrate that our GMoT-augmented model improves in-domain accuracy, retains clear gains under label-preserving corruptions, and improves accuracy-oriented cross-domain transfer under explicit small-split caveats while maintaining high anatomical grounding in its generated rationales. --- ### Art Beyond Semantics: Sheaf-Informed Contrastive Learning for Multi-Relational Representations Authors: Ludovica Schaerf, Antonio Purificato, Piera Riccio, Fabrizio Silvestri, Noa Garcia Published: 2026-07-15 Categories: cs.CV, cs.IR arXiv: https://arxiv.org/abs/2607.16321v1 Understanding a painting is never a single act. Art historians may analyze the same work through concepts of style, iconography, or historical context, dimensions that are not interchangeable, and each carries distinct semantic relationships between the visual and the textual. Vision-Language Models (VLMs) like CLIP, which learn a single shared embedding space, collapse this richness into a single homogeneous alignment, thereby losing the multi-relational structure that defines art-historical reasoning. We introduce CANVAS (Contrastive Art-aware Network for Vision-Language Alignment with Sheaves), a framework for learning relation-aware multimodal representations inspired by sheaf theory. Each artwork is projected into multiple embeddings conditioned on the type of relation (i.e., the context), and a novel contrastive loss encodes contextual information during training, with no dependency on external data at inference. We evaluate on three newly introduced benchmarks of artworks for multi-relational art understanding: WikiArt+, derived from WikiArt and Wikipedia, HertzianaDP, from the Bibliotheca Hertziana collection, and SemArt+, refined from the SemArt dataset. In multimodal retrieval and art understanding, CANVAS outperforms the baselines, supporting the view that multi-relational alignment is not just theoretically motivated but also practically essential. --- ### The Devil is in the Dark Pixels: Toward Brightness Bias-Robust Denoising Authors: Sungjun Cho, Zhuangzhuang Chen, Xiaomeng Li Published: 2026-07-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.16320v1 In this paper, we reveal an important yet overlooked problem in image denoising: under signal-dependent camera noise models, dark regions suffer from inherently low Signal-to-Noise Ratio (SNR), as signal intensity decays far faster than noise variance diminishes, making detail recovery in dark areas fundamentally challenging. Yet rather than compensating for this difficulty, MSE-trained denoisers exacerbate it -- reconstructing dark pixels up to 6x worse relative to their per-band noise floor. This bias stems from two compounding factors: signal-dependent noise inflates bright-pixel residuals, and the network's Jacobian norm increases monotonically with brightness. Together, these cause bright regions to chronically dominate gradient updates at the expense of dark ones. To this end, we propose Brightness Bias-Robust Denoising (BBRD), a drop-in replacement for MSE loss that partitions pixels into brightness bands, normalizes per-band error by empirical noise variance, and applies Group Distributionally Robust Optimization (Group-DRO) to dynamically upweight whichever band is currently worst, with zero additional parameters or inference cost. Across 8 architectures and 2 datasets in our experiments, BBRD is the only method among 13 tested alternatives that improves each brightness band simultaneously, achieving up to +0.45 dB on dark bands, +0.32 dB on bright bands, and +0.65 dB aggregate Peak Signal-to-Noise Ratio (PSNR) on SIDD, with the largest per-band gains in the darkest regions where detail recovery matters most. Code is available at https://github.com/xmed-lab/BBRD --- ### Deep Learning-based Filtering for Video Coding: A Survey on Architectures, Algorithms, and Complexity Analysis Authors: Young-Woon Lee, Byung-Gyu Kim Published: 2026-07-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.16319v1 As Ultra-High-Definition (UHD) displays and immersive media services become ubiquitous in the Internet of Things (IoT) and Consumer Electronics (CE) sectors, including 8K display and mobile devices, the demand for high-efficiency video coding is unprecedented. While Deep Learning-based Filtering (DLF) has emerged as a promising solution to mitigate compression artifacts inherent in standards like High Efficiency Video Coding (HEVC/H.265) and Versatile Video Coding (VVC/H.266), its deployment in CE devices is severely constrained by computational complexity, memory bandwidth, and power consumption. To bridge the gap between academic research and practical deployment, this paper presents a comprehensive, hardware-oriented survey of DLF techniques. We propose a systematic three-dimensional taxonomy classifying methods into (1) Integration Scheme within the Video Coding, (2) Coding Information Utilization, and (3) Network Design Strategy. Unlike prior reviews, this work critically analyzes the trade-offs between Rate-Distortion (RD) performance and hardware feasibility, highlighting the evolution from heavy, performance-oriented models to lightweight, hardware-friendly architectures targeting Neural Processing Units (NPUs). Furthermore, we incorporate the latest standardization activities from the Joint Video Experts Team (JVET) on Neural Network-based Video Coding (NNVC) to provide realistic guidelines. We also identify open challenges such as real-time inference latency and error propagation, providing a roadmap toward robust, low-power intelligent video coding in next-generation CE vision endpoints. --- ### Monte Carlo Dropout Uncertainty and Entropy-Thresholded Selective Prediction for Architecture-Agnostic Brain Tumor MRI Triage Authors: Medhansh Sharma Published: 2026-07-15 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.16317v1 Deep networks now subtype brain tumors on MRI about as well as specialist readers, yet accuracy is not what keeps them out of the clinic. What matters at the point of care is whether a model's confidence can be trusted to flag the cases it is likely to misclassify and defer them to a human. Deterministic estimates cannot: an auxiliary confidence head trained alongside the classifier collapses to a near-constant output that says nothing about correctness. This study proposes an uncertainty-first pipeline for four-class brain tumor MRI (glioma, meningioma, pituitary, no tumor) that reads predictive uncertainty from Monte Carlo (MC) Dropout over T = 20 passes and turns the resulting entropy into an explicit rule for deferring uncertain cases to a radiologist. We partitioned 7,200 images by perceptual-hash cluster, closing the near-duplicate leakage that inflates accuracy under naive splitting, and evaluated the pipeline on ViT-B/16 and ResNet-50 across five seeds along three axes: discrimination, calibration, and selective prediction. Both discriminate strongly (macro-AUC 0.994; accuracy 0.962 and 0.964), and no seed separates them (0 of 5 significant, p < 0.05), so the result is driven by the uncertainty pipeline, not the network. A single temperature scalar pulls the deterministic softmax into tight calibration (expected calibration error 0.016-0.020), and deferring the most uncertain 5% of cases lifts accuracy on the rest to about 0.98 on both (area under the risk-coverage curve 0.010-0.011). MC-Dropout uncertainty here is thus calibrated, non-collapsing, and directly actionable through a concrete deferral rule, providing an architecture-agnostic basis for calibrated, defer-to-human brain tumor MRI triage under internal validation. --- ### Eddy-VL 1.9B: Structural Pruning and Layered Distillation for Edge-Deployable Multimodal Embedding Authors: HanYeong Cho, Changwoo Kim, Taeuk Chu, Jimin Park Published: 2026-07-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.16316v1 In this report, we introduce Eddy-VL 1.9B, a compressed multimodal embedding model built on Qwen3-VL-Embedding-2B for offline, edge-deployable vision-language retrieval. Eddy-VL targets air-gapped forensic and investigative settings where cloud APIs are unavailable and low latency is essential. Compression combines (i) probe-driven structural pruning that removes four redundant text-decoder layers (28 to 24) ranked by adjacent-layer linear CKA, and (ii) layered knowledge distillation with hole-covering teacher-student mappings, mid-layer attention-map 1-CKA, and final-layer MSE and cosine losses with Matryoshka dimensions {128, 256, 512, 1024, 2048}. The released model contains 1,926,188,032 parameters (3.85 GB bf16), representing approximately 9.5% fewer parameters than the 2.13B teacher model. Empirical evaluations on MMEB-V2 (78 tasks, VLM2Vec protocol) show that Eddy-VL achieves an overall score of 63.2 compared with 68.9 for the teacher, retaining 91.7% of the teacher's performance while recovering 6.4 of the 12.1 points lost through pruning alone (56.8). Compositional reasoning performance remains close to the teacher on SugarCrepe (86.1 vs. 86.4), MR2-Bench (24.5 vs. 24.7), and ARO (59.5 vs. 60.4), while Winoground group performance (6.8 vs. 8.5) remains the primary limitation. Depth pruning also reduces forward latency by approximately 10% (150.0 to 136.4 ms per image on NVIDIA DGX Spark using FlashAttention-2). We present the architecture, compression methodology, training procedures, and evaluation results, demonstrating the effectiveness of Eddy-VL for multimodal retrieval under constrained edge deployment. Model weights and inference code are publicly available on Hugging Face. --- ### Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data Authors: Usman M. Khan Published: 2026-07-15 Categories: cs.CV, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2607.16314v1 World models, especially based on JEPA architectures, have been shown to learn robust dynamics of various environments. However, learning from visually complex real-world data remains a challenge, especially in unpredictable outdoor environments. We introduce depth as a geometric prior during training in learning more robust latent dynamics directly from robot video data and handling visual complexity. This combines depth supervision with an isotropy-inducing latent regularizer (SIGReg), maximizing task-agnostic latent diversity while constraining how that diversity is organized, with the combined objective targeting the highest-entropy representation consistent with scene geometry. To satisfy this greater complexity without increasing inference time, we also add training-only overparameterization. Training an 18M-parameter model on video from a real agricultural robot, we evaluate with frozen-representation visual odometry probes, predictor-based surprise detection, and multi-step latent rollout fidelity. Compared to the baseline LeWM, our method lowers visual odometry probe error by 33%, substantially increases surprise-score separation both in-domain and on the out-of-domain TartanGround benchmark, and improves multi-step rollout fidelity under domain shift, with gains that grow with rollout horizon. Notably, we also see improvements in surprise-score separation on physics understanding that is not directly tied to 3D geometry, such as lighting and shadows. These results show that a lightweight training-time geometric prior makes a compact JEPA world model more useful and more transferable on real outdoor data with strong underlying representations, without adding inference overhead. Our work suggests that depth as a physically grounded prior can enhance world model generalization on a variety of tasks. --- ### Cura 1T: Specialized Model for Agentic Healthcare Authors: actAVA AI, :, Haolin Chen, Leon Qi, Steve Brown, Deon Metelski, Tao Xia, Joonyul Lee, Qixuan Wang, Kevin Riley, Frank Wang, Weiran Yao Published: 2026-07-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.15314v2 Healthcare AI agents handle patient consultation, clinical reasoning over text and images, interactive diagnosis, and electronic health record (EHR) tool use, yet specialized agentic models that cover these use cases together remain limited. These capabilities fail in different ways, and a narrow update for one task can degrade another. We present Cura 1T, a healthcare-specialized LLM built on the open-weight Kimi-K2.6 and trained through a human-gated recursive self-improvement (RSI) loop. Specifically, in each round, the RSI harness plans a target capability, trains the model, evaluates benchmark trajectories, and refines the data mixture from observed failures with targeted synthetic and curated examples rather than a single generic medical-data update. Across the healthcare evaluation suite, Cura 1T ranks at or near the top among frontier baselines while remaining competitive on out-of-domain reasoning and agentic benchmarks. --- ### Position: Quantum Program Generation Must Prioritize Validity Over Probabilistic Scaling Authors: Junhao Song, Yu Zhou, William Knottenbelt, Yudong Cao Published: 2026-07-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.15313v1 The scaling hypothesis assumes that increasing model parameters yields emergent reasoning capabilities. This position paper argues that applying this probabilistic paradigm to generic quantum circuit synthesis is a directional error. Unlike natural languages, quantum circuits require strict adherence to mathematical constraints that manifest a significant syntax-semantics gap. Training on unverified quantum programs means that models learn syntax but fail to capture the physical semantics of the Hilbert space. Since the valid subset of circuit designs decays exponentially with the number of qubits, post-hoc filtering is mathematically intractable. We propose a pivot from human-centric copilots to verifier-centric agents. We integrate hierarchical constraints, topological masks, and symbolic proxies directly into generation. Our analysis suggests that scale alone cannot bridge the validity gap. Verification-aware architectures offer a viable path for modular quantum program generation. These considerations point toward generation methods that encode task-specific rules of quantum information, rather than relying on imitation alone. ---