# Research Papers — 2026-07 · bundle page 109 of 222 > Full-text markdown of papers #5401–5450 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/109 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/108.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/110.md) ### Improving Network Anomaly Detection via Choquet-Integral-Based Feature Aggregation Authors: Abreu Quevedo, Roger Immich, Giancarlo Lucca, Graçaliz Dimuro, Bruno L. Dalmazo Published: 2026-07-16 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2607.15389v1 This work investigates a generalized Choquet-integral-based feature aggregation framework to improve anomaly detection in high-dimensional network traffic data. The approach combines adaptive weighting with incremental feature selection to address feature redundancy. Using Random Forest and XGBoost classifiers, we evaluate models trained with both raw and Choquet-aggregated features under varying feature subset sizes. The proposed aggregation achieves up to $7\%$ higher accuracy while reducing data volume by $77.5\%$ (from $214$~MB to $48$~MB), without degrading precision and recall. Results averaged over multiple stratified repetitions indicate that Choquet-based aggregation yields statistically significant gains ($p < 0.05$) in scenarios with limited feature availability, highlighting its suitability for real-time intrusion detection under bandwidth and feature-availability constraints. --- ### Precise but Uncoupled: Reviewer Precision Does Not Guarantee Critique Uptake in Multi-Agent Math Reasoning Authors: Chih-Hsuan Yang, Jingyan Jiang, Vikram Vasudevan, Cheng-Hau Yang, Huihuo Zheng, Le Chen, Eliu A. Huerta, Venkatram Vishwanath, Ian T. Foster, Rajeev Thakur Published: 2026-07-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.15388v1 Many math- and science-oriented agent systems use hierarchical designs with specialized reviewer roles, assuming that a dedicated review stage should help turn wrong candidates into correct ones. We test this assumption on 4,181 verifier-grounded Omni-MATH problems using matched gpt-oss-120b actors. Collaboration adds little on the easiest tiers, but from tier 4 onward the gains open sharply; in this harder regime, broadcast-style peer discussion reaches higher final accuracy than a planner-executor-reviewer pipeline (PER). We ask whether this gap is explained by reviewer quality or by whether critique changes the next answer the protocol carries forward. It is not explained by reviewer precision alone: PER's reviewer is more precise than broadcast's (0.861 vs. 0.644), yet evaluator-verified useful critique is much less likely to change the next candidate and produces lower reviewer-guided repair. These results show that reviewer detection quality and critique uptake are empirically separable. Within matched PER interventions, forcing explicit acknowledgment lowers final accuracy, while embedding reviewer guidance directly in the solver's working context partially improves follow-through without closing the gap. Overall, reviewer-centric evaluation can overstate system quality: a protocol may spot errors well yet still fail to solve more problems if it does not act on those critiques. --- ### Large Language Models as Unified Multimodal Learners for Clinical Prediction Authors: Ajay Madhavan Ravichandran, Bilgin Osmandoja, Klemens Budde, Klaus Netter, Tobias Strapatsas, Aljoscha Burchardt, Sebastian Möller, Roland Roller Published: 2026-07-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.15380v1 Electronic health records combine free-text clinical narratives with structured measurements such as vital signs, laboratory values, and comorbidities. Yet most clinical prediction systems still rely on task-specific fusion architectures, pairing dedicated encoders for each modality with learned combination mechanisms that must be re-engineered for every new task and clinical setting. We propose a simpler alternative: convert all patient data, regardless of modality, into a single natural language sequence and fine-tune a pretrained language model end-to-end, with no architectural modification for fusion. We evaluate this approach across three clinically distinct prediction tasks: in-hospital mortality on MIMIC-III, graft failure prediction using longitudinal data from a German transplant center, and emergency triage classification from ambulance records - comparing encoder-based (ModernBERT) and decoder-based (Llama 3.1, Gemma, DeepSeek-R1-Qwen, Qwen3) fine-tuning against established multimodal baselines and, for graft failure, a gradient boosting model currently used in clinical practice for post-transplant patient management. Across all three tasks, unified textual serialization matches or exceeds task-specific multimodal baselines, and outperforms the clinically deployed gradient boosting system on graft failure prediction. These results indicate that a single serialization-based paradigm, without bespoke fusion architectures, is sufficient for multimodal clinical prediction - substantially reducing system complexity while matching or exceeding specialized designs. --- ### On the Impact of Entropy-based Features Authors: Iuri Mundstock, Abreu Quevedo, Jéferson Campos Nobre, Roben C. Lunardi, Thiago L. T. da Silveira, Bruno L. Dalmazo Published: 2026-07-16 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2607.15379v1 Network anomaly detection is increasingly challenging due to the growing diversity and variability of traffic patterns, which are not always well captured by traditional statistical features. In this work, we explore the use of entropy as an additional feature to support supervised network traffic classification. The main idea is to use entropy to represent variability in selected traffic attributes, complementing conventional descriptors rather than replacing them. We integrate the entropy-based feature into a standard machine learning pipeline and evaluate its impact through a direct comparison between models trained with and without this feature. Experiments conducted on a public intrusion detection dataset show consistent improvements in classification performance, while the additional computational cost remains low. The analysis of confusion matrices indicates a reduction in misclassifications, especially in traffic scenarios with higher variability. Overall, the results suggest that entropy-based features offer a simple and practical way to enhance existing anomaly detection pipelines. This approach is particularly attractive in settings where lightweight feature engineering and interpretability are important, making entropy a useful complement to commonly used traffic features. --- ### Reasoning-Guided Part-Level Visual Grounding via Reinforcement Learning Authors: Kazi Sajeed Mehrab, Hani Alomari, Najibul Haque Sarker, Chia-Wei Tang, Zaber Ibn Abdul Hakim, Anuj Karpatne, Chris Thomas Published: 2026-07-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.15374v1 Multimodal large language models (MLLMs) ground whole objects well from free-form language queries, but they struggle when the query names a part rather than the object. We trace this to a missing object-part hierarchy, since parts are localized in the same single step used for objects. We propose Object-Part Hierarchical Reflective Grounding (OP-HRG), a coarse-to-fine reasoning-guided grounding strategy that first localizes the parent object and then the part within it. A self-check then reflects on the result, with an extension to re-encode the predicted crop to inspect the region it is correcting. We introduce a part-aware GRPO framework to train our pipeline with stage-wise rewards. A 4B model trained this way outperforms 7B grounding LLMs and SAM3 across PascalPart, PartImageNet, and InstructPart, and transfers to reasoning segmentation. --- ### AnovaX: A Local, Multi-Agent Voice Assistant with LLM Planning, Typed Executors, and Adaptive Recovery Authors: Raunak B Sinha Published: 2026-07-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.15367v1 Desktop voice assistants are still dominated by cloud pipelines that ship raw audio off the machine and expose a fixed set of skills. We describe AnovaX, a small local-first assistant that runs entirely on the user's computer and treats the desktop itself as its action surface. A single Python process wires together a wake-word gate, a speech pipeline, an LLM planner (Gemini) that emits a JSON plan of tool calls, a whitelist-and-denylist safety layer, a multi-agent orchestrator that translates each plan into typed child agents on a bounded thread pool, and an adaptive recovery loop that takes over whenever a core step fails. Every tool corresponds to a specialized agent class (AppAgent, TypingAgent, BrowserAgent and six others) with its own timeout, retry policy, and shared-resource locks. A recursive MetaAgent lets the planner delegate a sub-goal back to itself, capped at two levels of nesting. The recovery loop uses a compact ReAct-style prompt and hides Gemini's latency behind speculative execution of read-only tools. A companion Flask server exposes a phone-friendly remote over the local WiFi, mirrors every agent lifecycle event to the phone in real time, and streams the laptop's screen back over MJPEG so the user can watch remote commands land as they run. The point of the project is less to compete with Siri or Alexa than to show that a legible, few-thousand-line assistant is enough to open apps, type into them, run searches, coordinate concurrent actions, recover from single-step failures, and be driven entirely from a phone in another room -- without the LLM ever touching the keyboard. --- ### Training-Free Open-Vocabulary 3D Point-Cloud Segmentation on the Generalized Few-Shot Benchmark Authors: Silas kwabla Gah, Ebenezer Owusu Published: 2026-07-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.15331v1 Generalized few-shot 3D point-cloud segmentation (GFS-PCS) asks a model to segment a scene into many base classes seen at training time and a set of novel classes. The state of the art reaches novel classes by reconciling a dense but noisy 3D vision-language prior with the few-shot support, but it pays for this with base 3D labels, per-episode training, and the support annotations themselves. We ask how far the same reconciliation can go with none of these: no training, no 3D labels, and not even the few-shot support. We pair a frozen 3D vision-language model (RegionPLC) as a dense prior with a frozen promptable concept segmenter (SAM3), prompted by the bare novel class names and lifted from posed RGB views, and reconcile the two by cross-view consistency: a point becomes novel only when enough of the views that see it agree. On the ScanNet200 GFS-PCS benchmark this fully training-free, open-vocabulary pipeline improves novel mIoU by +2.6 over the training-free dense prior while holding base accuracy within 0.5, and recovers a third (33%) of the novel-class gap to the trained state of the art that uses far more supervision. We further show that injecting the few-shot support into the pipeline, as a fusion gate and as a prototypical dense classifier, adds nothing over consistency alone and in fact degrades it through the classifier, which is why the method needs no support at all. On the harder ScanNet++ benchmark, where the dense prior is far weaker on novel classes, the same pipeline nearly doubles novel mIoU (+15.7, from 16.2 to 31.9) at a 1.7 base cost, lifting the harmonic mean from 21.5 to 31.1 --- ### Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories Authors: Xiaomi Robotics Team, Jun Guo, Piaopiao Jin, Jason Li, Peiyan Li, Yingyan Li, Futeng Liu, Wanli Peng, Optimus Qin, Yifei Su, Nan Sun, Qiao Sun et al. Published: 2026-07-16 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2607.15330v2 We present Xiaomi-Robotics-1, a foundational vision-language-action (VLA) model capable of (1) following diverse language instructions to perform a wide range of mobile manipulation tasks in unseen environments out-of-the-box, and (2) efficiently adapting to novel downstream tasks with minimal fine-tuning data. We propose a two-stage training recipe consisting of pre-training and post-training. During pre-training, we imbue the model with broad and generalizable action-generation capabilities by training on over 100k hours of real-world manipulation trajectories collected via UMI devices. Crucially, we develop a scalable auto-labeling pipeline that annotates trajectory clips with natural languages describing scene state transitions, providing rich and precise conditioning for action learning. During post-training, we aim to align these capabilities with robot embodiments and imperative instructions that humans naturally use to prompt robots. Extensive experiments demonstrate strong scaling behavior. Xiaomi-Robotics-1 consistently improves with increased data scales and model sizes during pre-training. This scaling behavior directly transfers to post-training, where a stronger pre-training model yields better out-of-the-box real-robot performance in unseen environments. Furthermore, Xiaomi-Robotics-1 serves as a strong robot foundation policy that can be efficiently fine-tuned on complex, dexterous tasks with high data efficiency. Across multiple simulation benchmarks, Xiaomi-Robotics-1 outperforms state-of-the-art methods. Notably, it establishes a new state-of-the-art with a 57.4% success rate on RoboCasa365, surpassing the previous best of 46.6%. Furthermore, it achieves an average score of 20.07 on RoboDojo, significantly outperforming the prior state-of-the-art (13.07). Code and model checkpoints will be released. Project page: https://robotics.xiaomi.com/xiaomi-robotics-1.html --- ### Lazy Arithmetic using Systolic Arrays for Closing the Verification Gap on Embedded Systems Authors: Taisa Kushner, Ryan McCleeary, Martin Brain Published: 2026-07-16 Categories: cs.CR, cs.AI, cs.AR arXiv: https://arxiv.org/abs/2607.15328v1 Complex algorithms such as deep neural networks are increasingly being deployed on embedded, resource constrained platforms. However, existing hardware and software schemes for implementing these models on the edge fall short, particularly for safety-critical applications such as medical devices. First, hardware such as GPUs, NPUs and TPUs are designed for throughput rather than correctness of computation of security, and are as such susceptible to fault injection attacks. Second, software schemes designed for porting algorithms onto edge devices -- such as quantization schemes -- are either static and sound (non-optimal power consumption), or dynamic yet unsound (non-optimal for safety-critical applications). To address both these needs we propose a both wholly new approach to real-time, dynamic and sound quantization, as well as the hardware to support it. First we developed a sound, real-time adaptive-precision quantization approach utilizing left-to-right arithmetic to pass the most significant bits (MSB) first, and dynamically adjust precision online while performing sensitivity analysis to quantify and manage the risk of decision-boundary crossings. Next, we propose a novel hardware approach utilizing systolic arrays to perform left-to-right arithmetic to generate the MSB first. Together this provides a wholly novel scheme for enabling not only resource-efficient neural networks and artificial intelligence at the edge, but broadly sound and resource-efficient high-precision mathematics on hardware that ensures resilience to bit flip attacks on the most critical bits. This is presented herein as work-in-progress, with software implementations completed and hardware in-progress. --- ### Rethinking the Readout: Unlocking Video Backbones for AI-Generated Video Detection Authors: Manni Cui, Ziheng Qin, ZiAn Wang, Ruiqi Liu, Dianyuan Zou, Jianglan Wei, Han Zhou, Yu Liu, Jingrui Xu, Wenhao Wang, Zhenyu Zhang Published: 2026-07-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.15321v1 AI-generated videos (AIGVs) typically contain subtle temporal artifacts that arise from inter-frame inconsistencies rather than within individual frames. A detector that captures such artifacts should therefore benefit from video pretrained backbones over image only ones. In practice, however, video backbones with standard global readouts often fail to outperform strong image pretrained probes on AIGV benchmarks. We attribute this gap to excessive spatiotemporal aggregation in the readout. Video pretrained backbones tend to compress each frame into a single global descriptor. This compression suppresses local patch level temporal dynamics and discards inter patch relations, which are precisely the cues that AIGV detection most reliably depends on. Based on this, we propose Velocity Gated Patch Velocity Profiling (V-PVP), a lightweight readout that replaces only the aggregation layer with two parallel streams over the patch velocity field, adding only about $0.5$M trainable parameters. V-PVP serves as a general plug-and-play module that consistently improves performance across diverse video backbones under both end-to-end fine-tuning and linear probing settings. Our method reaches \textbf{95.28} AUC on AIGVDBench while keeping the backbone fully frozen. The results show that simply replacing the aggregation layer reactivates the temporal potential of frozen video backbones, restoring their advantage on AIGV detection. Code is available at https://anonymous.4open.science/r/PVP-81B3/. --- ### Hierarchical Denoising For Multi-Step Visual Reasoning Authors: Zezhong Qian, Xiaowei Chi, Chak-Wing Mak, Tianze Zhou, Ruibin Yuan, Yuhan Rui, Hengzhe Sun, Zhuoqun Wu, Yuming Li, Siyuan Qian, Sirui Han, Shanghang Zhang Published: 2026-07-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.15278v1 Video models are evolving into vision foundation models, yet they still lack human-like multi-step reasoning. Streaming autoregressive diffusion models are efficient but limited in reasoning, while bidirectional diffusion enables global revision with high inference costs due to dense frame-level denoising. Both paradigms struggle to achieve logical consistency and low-latency streaming for complex reasoning tasks. We propose HDR (Hierarchical Denoising for Visual Reasoning), a unified framework that integrates hierarchical latents into causal video generation for multi-step reasoning. HDR organizes video latents into a tree-structured hierarchy, enabling coarse-to-fine reasoning before streaming output. Coarse denoising layers preserve uncertain hypotheses for global planning, while finer layers progressively refine them into concrete visual states. A sparse hierarchical attention pattern (SHAP) further reduces temporal attention costs. We introduce a level-stratified multi-step video reasoning benchmark with out-of-distribution cases, covering six tasks: maze navigation, Tower of Hanoi, one-line drawing, sliding puzzle, Sokoban, and water pouring. Compared with streaming autoregressive diffusion baselines, HDR improves success from 34.22 to 60.29 (76.2% relative gain) and increases average progress from 76.00 to 89.56, demonstrating more consistent reasoning trajectories. HDR maintains low-latency streaming at 0.70 seconds per latent, achieving 54.2 times faster inference than bidirectional diffusion. It also retains 82.9% of full-data performance with only 2% training data, compared with 52.0% for bidirectional diffusion. Real-world robot experiments further demonstrate HDR's potential for physical interaction and world modeling. Project demo: https://hierarchical-diffusion-reasoning.github.io/. --- ### Partition, Prompt, Aggregate: Statistical Self-Consistency in Language Models Authors: Patrik Wolf, Thomas Kleine Buening, Andreas Krause, Celestine Mendler-Dünner Published: 2026-07-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.15277v1 In-context learning is commonly interpreted as a form of conditional inference, in which the prompt specifies a context and the model's output is treated as an estimate of the corresponding conditional distribution. If this interpretation holds, then LLM estimates should satisfy basic probabilistic identities. In particular, the law of total probability asserts that prior-weighted conditional distributions aggregate into population-level marginals over any valid partition of the population. In this work, we investigate to what extent LLM estimates adhere to this self-consistency principle. We use binary trees as an evaluation scaffold to recursively partition a population into increasingly fine-grained subpopulations. We then prompt LLMs with verbalized subpopulation descriptions in context, aggregate the resulting estimates back into population-level estimates, and compare them across partitions of varying granularity. Applying this protocol across problem domains and state-of-the-art frontier models, we show widespread violations of basic consistency properties. An in-depth study of persona prompting reveals a pattern we call the macro fallacy: estimates reconstructed from more fine-grained subpopulation responses are often better aligned with human reference data than direct population-level estimates. This effect persists across variations in tree structure and estimation task, and can be partially recovered through implicit prompting. Together, these findings suggest that models possess relevant subpopulation knowledge but do not reliably propagate it into aggregate estimates. This gap establishes statistical self-consistency as an unsaturated, reference-free criterion for evaluating LLMs. --- ### RoboTTT: Context Scaling for Robot Policies Authors: Yunfan Jiang, Yevgen Chebotar, Ruijie Zheng, Fengyuan Hu, Yunhao Ge, Jimmy Wu, Tianyuan Dai, Scott Reed, Li Fei-Fei, Yuke Zhu, Linxi "Jim" Fan Published: 2026-07-16 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.15275v1 Recent robot foundation models operate with single-step or short-history visuomotor context. We introduce Test-Time-Training Robot Policies (RoboTTT), a robot model and training recipe that scale visuomotor context to 8K timesteps, three orders of magnitude beyond state-of-the-art policies, without growing inference latency. At this context length, we unlock new robot capabilities: one-shot in-context imitation from human video demonstrations, on-the-fly policy improvement, robustness to perturbations, and stronger performance on multi-stage, long-horizon tasks. We also observe, for the first time, steady gains in closed-loop performance as pretraining context length scales. At its core, RoboTTT integrates Test-Time Training into robot foundation models such as Vision-Language-Action policies, yielding a sequence model whose recurrent state consists of fast weights, parameters updated by gradient descent during both training and inference, compressing histories into weight space and retrieving contextual information for long-context conditioning. To scale training context length, the recipe combines sequence action forcing with truncated backpropagation through time. On challenging real-robot manipulation tasks, RoboTTT improves overall performance by 87% over the single-step context baseline and fully completes a five-minute, ten-stage assembly task, which no baseline ever does. RoboTTT trained with 8K-timestep context outperforms the same model pretrained with 1K timesteps by 62%, suggesting context length as a new scaling axis for robot foundation models. Videos are available at https://research.nvidia.com/labs/gear/robottt/ --- ### MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators Authors: Yushi Huang, Xiangxin Zhou, Jun Zhang, Liefeng Bo, Tianyu Pang Published: 2026-07-16 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2607.15273v2 MeanFlow generators achieve fast few-step sampling by predicting average velocities over time intervals, making them attractive for efficient generation. Reinforcement learning (RL) has become a powerful way to align diffusion and flow models with human preferences and task-specific objectives. In particular, DiffusionNFT offers an efficient forward-process RL framework that does not require reverse-process trajectories or likelihood estimation. However, applying such RL methods to MeanFlow remains underexplored. DiffusionNFT optimizes instantaneous velocities, whereas MeanFlow samples with average velocities. To bridge this gap, we introduce MeanFlowNFT. Inspired by the MeanFlow identity, which bridges average and instantaneous velocities, we construct an induced instantaneous-velocity predictor. We apply the DiffusionNFT objective to this predictor, making reward optimization well-defined for MeanFlow. Sampling remains based on the average velocity, preserving MeanFlow's fast few-step generation. We further prove that MeanFlowNFT inherits DiffusionNFT's strict policy-improvement guarantee. Experiments on image and video generation show that MeanFlowNFT consistently improves baselines. Moreover, it outperforms prior state-of-the-art RL-tuned few-step generators on most metrics ($6$ of $8$ on SD3.5-M), and can even surpass multi-step RL-tuned diffusion while using only a few sampling steps. For instance, on Wan 2.1, $4$-step MeanFlowNFT reaches a VBench score of $84.33$, surpassing $50$-step LongCat-Video RL ($82.57$). --- ### SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisions Authors: Yasheng Sun, Zezi Zeng, Yifan Yang, Chong Luo, Wenyi Wang, Ziwei Liu, Jürgen Schmidhuber Published: 2026-07-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.15272v1 Editing the figures in a research paper is a routine and time-consuming part of everyday research practice: authors relabel components, rearrange panels, and restyle visuals as they revise their manuscripts. Automating this editing workflow under a natural-language instruction, however, is challenging, because a scientific figure is a dense infographic in which heterogeneous visual elements such as schematics, plots, photos, captions, and arrows are composed under a tight visual grammar to advance a specific argument. To address this, we present SciDiagramEdit, a benchmark and skill-evolution framework that learns from natural paper revisions and operates on the figure's editable vector source, where users can inspect and co-edit individual primitives alongside the agent. Our benchmark mines before/after figure pairs from arXiv version histories, each grounded in the authors' own revision intent. To accommodate the diversity of editing instructions, we adopt agentic learning via skill evolution: an agentic proposer continually refines the agent's skill specification from execution traces over multiple epochs. The resulting skill progressively lifts edit accuracy on a held-out validation set, providing evidence that natural paper revisions are an effective training signal for instruction-driven figure editing. --- ### Online Neural Space Time Memory for Dynamic Novel View Synthesis Authors: Baback Elmieh, Lynn Tsai, Zeman Li, Srinivas Kaza, Tiancheng Sun, Gabor Csapo, Ali Behrouz, Yuan Deng, Stephen Lombardi, Steven M. Seitz, Xuan Luo Published: 2026-07-16 Categories: cs.CV, cs.GR, cs.LG arXiv: https://arxiv.org/abs/2607.15271v1 Online novel view synthesis from multi-view streaming videos faces a fundamental trade-off: maintaining a persistent, long-horizon memory to reconstruct temporarily occluded regions while operating under strict real-time constraints. While Test-Time Training (TTT) offers a powerful memory mechanism, standard models mandate gradient-based memory updates at every frame to adapt to the changing motion in dynamic scenes. The computational cost of heavy memory updates precludes real-time application and can lead to instability over long contexts. Given that memory updates are more demanding than memory application and video content is largely redundant, we propose to decouple the frequencies of these two processes. Our approach performs periodic memory updates while applying the memory on a per-frame basis, using cross-view attention to manage deformations between the prior memory state and the current frame. To lock in the historical context, we introduce two critical mechanisms: an auxiliary Memory Loss that forces persistent internalization of the scene, and a Memory Caching strategy that regularizes active weights against catastrophic drift. Our method demonstrates real-time, state-of-the-art performance on scenes with dynamic human motion as well as minute-scale online memorization. --- ### Motion-Conditioned Multi-View Fusion for Myocardial Infarction Localization from Echocardiography Authors: Guang Yang, Wentian Xu, Siyu Wang, Betty Raman, Lei Li, Vicente Grau Published: 2026-07-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.15268v1 Myocardial infarction (MI) remains a leading cause of mortality worldwide. Echocardiography (Echo) is a widely available modality for MI assessment, where regional wall motion abnormality is a key indicator. Prior learning based methods for myocardial motion analysis often use handcrafted descriptors or densely supervised estimation, but the need for extensive annotation limits applicability. Foundation models have recently improved vision-based Echo analysis; however, most methods operate on single views and segment-level localization remains unreliable under view-dependent ambiguity, especially in apical views. To address this, we propose MCF-Net, a novel motion-guided multi-view fusion framework that fuses myocardial motion cues with foundation model representations to localize infarction. Visual features are extracted using EchoPrime, a pretrained Echo foundation model shared across dual views. Cardiac motion is modeled with extremely sparse supervision: a single annotated template frame is transferred across videos to initialize point tracking, avoiding dense labels. Motion-derived segment-aware soft masks provide coarse spatial priors that selectively enhance features for challenging myocardial segments. A motion-conditioned fusion mechanism then integrates motion and vision across views, refining predictions without overriding strong appearance cues. On segment-level MI localization, MCF-Net achieves 72.4\% F1 and 84.9\% accuracy, outperforming state-of-the-art motion-only, vision-only, and fusion baselines. --- ### Pretraining Data Can Be Poisoned through Computational Propaganda Authors: Victoria Graf, Hannaneh Hajishirzi, Noah A. Smith, David Kohlbrenner, Kyle Lo Published: 2026-07-16 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.15267v1 Poisoning pretraining data can introduce harmful behaviors to LMs that are difficult to detect and mitigate. Prior work on poisoning pretraining data has largely exploited established data sources such as Wikipedia, which do not represent the large scale and heterogeneity typical of pretraining corpora, and has ignored the interaction between poisoned data and data curation pipelines. We demonstrate that poisoning attacks on pretraining data are feasible beyond this limited setting through an existing web-scale content injection mechanism: public discussion interfaces. Additionally, to measure whether malicious content is included after web crawling and data curation, we introduce HalfLife, a novel analysis for estimating adversarial content inclusion in web-crawl based LM training data. We use HalfLife to explore the feasibility of poisoning pretraining corpora at web scale through open discussion interfaces. Our analysis demonstrates the importance of estimating whether poison injections are included in pretraining data, and establishes third-party webpage content as a possible vector for attacking language model pretraining. --- ### SceneBind: Binding What and Where Across Vision, Audio and Language Authors: Mingfei Chen, Zijun Cui, Ruoke Zhang, Hyeonggon Ryu, Eli Shlizerman Published: 2026-07-16 Categories: cs.CV, cs.AI, cs.MM, cs.SD arXiv: https://arxiv.org/abs/2607.15265v1 We present SceneBind, an omni-modal representation of realistic scenes with joint semantic and 3D spatial understanding across vision, audio and language. Existing omni-modal encoders excel at instance-level semantics (i.e., what is present), but often lack explicit spatial structure (i.e., where it is). SceneBind addresses this gap by representing each scene as a semantic-spatial entity, combining a global semantic embedding with object-centric semantic-spatial slots. This representation explicitly captures object-level semantics, spatial attributes, and uncertainty. We further propose SceneBind Matching, a semantic-spatial matching scheme that integrates global scene similarity with object alignment, supporting cross-modal scene retrieval and object grounding. To train and evaluate SceneBind, we curate a novel real-world binaural audio-visual dataset with structured semantic and spatial annotations, and propose a training protocol for aligning semantic and spatial signals across modalities. SceneBind is compatible with large-scale pretrained semantic encoders, adds lightweight spatial modeling with only a few additional tokens. It achieves state-of-the-art scene and spatial retrieval while enabling strong zero-shot transfer to downstream tasks such as audio-visual localization. --- ### Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents Authors: Paul Kassianik, Blaine Nelson, Yaron Singer Published: 2026-07-16 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2607.15263v3 Security-agent evaluations commonly measure peak offensive capability under generous inference budgets, emphasizing vulnerability discovery, exploit development, penetration testing, and CTF completion. Such measurements are useful but incomplete: in operational security, every reasoning step, tool call, telemetry query, and enrichment request consumes budget. We evaluate language-model security agents through this cost-success lens on offensive Cybench challenges and defensive Splunk BOTS v1 investigation challenges. Instead of reporting only best-case success, we compare models at fixed cost levels and decompose performance by inference spend and tool spend. Our results show distinct scalingregimes for red- and blue-team tasks. Offensive CTF performance improves with additional test-time compute, and scaled open-weight models can approach frontier proprietary systems while remaining cost-competitive. Defensive SOC investigation does not scale in the same way: success depends more heavily on disciplined tool use, telemetry navigation, and selective enrichment than on raw reasoning budget alone. We argue that security-agent benchmarks should measure economic efficiency and operational fit alongside task success. Cost-aware, SOC-native evaluations provide a clearer picture of which models are practically useful today and where defensive agents still need to improve. We present an interactive website with our results https://evals.frontier.security. --- ### Decoding Market Emotion from Blockchain Activity: A Data-Driven Sentiment Classifier Authors: Arthur G. Bubolz, Abreu Quevedo, Giancarlo Lucca, Rafael A. Berri, Eduardo Borges, Bruno L. Dalmazo Published: 2026-07-16 Categories: cs.LG, cs.CE arXiv: https://arxiv.org/abs/2607.15258v1 The growing use of Bitcoin as a decentralized digital asset and investment tool has sparked strong interest in understanding its market behavior. This study presents a new approach to analyze Bitcoin market sentiment by combining on-chain and financial data with social media posts. Unlike models that aim to predict prices, this work focuses on explaining market sentiment using blockchain transactions, historical price data of Bitcoin, and daily Twitter sentiment classifications. The method merges sentiment trends with on-chain and financial metrics, normalized into a dataset for detailed market analysis. Multiple machine learning models were tested using cross-validation, with Gradient Boosting (XGBoost) emerging as the most reliable model for classifying sentiment, achieving an average F1-score of about 0.84. SHAP (SHapley Additive exPlanations), a game theory-based method for model interpretability, was used to quantify the contribution of on-chain features to the model's predictions, improving transparency. The results indicate that this data combination yields meaningful predictive signals and insights, supporting data-driven cryptocurrency analysis and future improvements with deep learning. --- ### SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration Authors: Yuyao Zhang, Junjie Gao, Zhengxian Wu, Jiaming Fan, Jin Zhang, Shihan Ma, Yao Yao, Weiran Qi, Chuyan Jin, Guiyu Ma, Xingzhong Xu, Kai Yang et al. Published: 2026-07-16 Categories: cs.AI, cs.IR arXiv: https://arxiv.org/abs/2607.15257v1 Recent advances in Tool-Integrated Large Language Models have made web search a core capability of information-seeking agents. However, as interaction histories grow, agents increasingly struggle to track task progress. When search attempts fail to yield useful evidence, current single- and multi-agent systems can become trapped in repetitive loops, wasting search budgets and ultimately compromising the quality and completeness of the final output. We introduce SearchOS, a system-level multi-agent framework that turns fragile, implicit search progress into explicit, persistent, and shared state. First, we formulate open-domain information seeking as relational schema completion with grounded citations, where agents discover entities, populate attributes across linked tables, and anchor each value to source evidence. Then we design Search-Oriented Context Management (SOCM), which externalizes the evolving state into Frontier Task, an Evidence Graph, a Coverage Map, and Failure Memory. Built on SOCM, SearchOS applies a pipeline-parallel scheduling mechanism that overlaps the execution of sub-agents and continuously refills freed slots with tasks targeting unresolved coverage gaps to improve utilization and throughput. To schedule and control the execution of search agents, SearchOS introduces a Search Tool Middleware Harness that intercepts model and tool interactions to record grounded evidence and react to stalls or budget exhaustion, and provides a reusable hierarchical skill system comprising strategy and access skills to augment the agents' search process and avoid repeating failed search patterns across runs. On WideSearch and GISA, SearchOS leads all metrics among the evaluated single- and multi-agent baselines, paving the way toward robust information-seeking collaboration. --- ### HoloGeo: Mitigating Landmark Bias in Geo-localization via Evidence-Driven Reasoning Authors: Pengcheng Zhou, Xuanyu Liu, Yanchen Yin, Bobo Li, Shengqiong Wu, Mong-Li Lee, Wynne Hsu Published: 2026-07-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.15255v1 Recent advances in Vision-Language Models (VLMs) have significantly improved image geo-localization, yet existing models remain susceptible to landmark bias, causing them to overlook geographical cues or form spurious correlations, ultimately resulting in inaccurate localization. To systematically investigate this issue, we first design two quantitative metrics, Bias Intensity (BI) and Bias Harmfulness (BH), to characterize the impact of landmarks exerted on model reasoning, and establish a comprehensive benchmark, LandmarkBias-3K. To mitigate landmark bias, we further propose an evidence-driven reasoning framework, HoloGeo, to improve the reliability of geo-localization. HoloGeo is supported by a high-quality dataset, BF-30k, annotated with structured multi-evidence bias-free reasoning chains. By incorporating multi-dimensional rewards, HoloGeo explicitly encourages balanced attention over diverse visual cues and achieves evidence-driven joint reasoning. Extensive experiments demonstrate that HoloGeo not only maintains excellent performance on IM2GPS3K and YFCC4k but also significantly outperforms existing open-source VLMs on LandmarkBias-3K, validating its effectiveness for robust geospatial reasoning. --- ### teLLMe Why (Ain't Nothing but a Jam): Exploratory Causal Analysis of Urban Driving Data Authors: Qiwei Li, Jorge Ortiz Published: 2026-07-16 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2607.15254v1 Traffic agencies now have access to large volumes of video-derived data for studying safety and congestion. Most of these data are observational and collected without interventions, which makes causal questions such as "How would rain change traffic density?" difficult to answer. We present teLLMe, a system for exploratory causal analysis of urban driving datasets. The system starts from a structured event table built from dashcam annotations and combines causal structure learning with the PC algorithm, bootstrap-based stability checks, and query-specific effect estimation using linear regression and DoWhy. Natural-language questions are mapped to structured causal queries through a schema-aware LLM, enabling users to specify treatments, outcomes, and subpopulations. teLLMe returns a "Causal Card" that summarizes effect estimates, adjustment sets, DAG support, and assumptions, followed by a short natural-language explanation. Case studies on BDD-derived traffic events show that the system can surface plausible relationships involving weather, peak hours, and traffic density, while making uncertainty and modeling choices explicit. The system is designed as a tool for hypothesis generation and expert reasoning rather than a source of definitive causal claims. --- ### Bridge Evidence: Static Retrieval Utility Does Not Predict Causal Utility in Multi-Step Agentic Search Authors: Debayan Mukhopadhyay, Utshab Kumar Ghosh, Shubham Chatterjee Published: 2026-07-16 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2607.15253v1 Retrieval systems are trained and evaluated on a static idea of usefulness: hand a document and a question to a reader model, see whether the answer improves, and score the document accordingly. The idea holds up when a document is read on its own. It breaks when a language model works as a search agent, issuing several queries and reasoning across turns, because a document can matter for what it lets the agent do next rather than for what it says about the current question. We measure that gap rather than argue it. Using a ReAct style agent over HotpotQA, we replay 1000 development questions and, for every document the agent read, delete it and re-run the rest of the trajectory from that point. Comparing the original run against its counterfactual gives a Counterfactual Trajectory Utility (CTU) score from three deltas: final answer quality, next query retrieval quality, and turn count. Crossing CTU against Static RAG Utility (SRU) over 23,322 document observations, the two are close to statistically independent (Spearman rho = -0.026). Roughly a third of the documents the agent reads are causally load bearing while looking useless to a static reader; we call these bridge documents. The pattern survives when the reader based axis is swapped for a BM25 and cross encoder proxy, giving a bridge cell of 27.2% on an evenly spread axis. A second experiment pins down the mechanism. Using the Observable Entity Relevance (OER) measure from prior work, entities that discriminate relevant from non-relevant candidates appear in the agent's next query 4.02 times more often than entities found only in non-relevant documents (6.1% vs 1.5%, n = 227,139). A bridge document earns its keep by handing the agent a discriminative entity that redirects the search. Static relevance and causal usefulness are different quantities in agentic retrieval, and optimizing the first does not deliver the second. --- ### AutoSynthesis: An agentic system for automated meta-analysis Authors: Moein Taherinezhad, Sebastian Maier, Gerardo Vitagliano, Francesco Pierri, Stefan Feuerriegel Published: 2026-07-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.15247v1 Evidence synthesis is crucial for turning primary research into reliable knowledge for science, medicine, education, and policy. Yet, quantitative evidence synthesis remains largely manual and difficult to scale. Here, we introduce AutoSynthesis, an end-to-end multi-agent system for automated meta-analysis. Given a research question in natural language, AutoSynthesis formulates a search strategy, retrieves scientific literature, screens candidate studies, assesses full-text eligibility, extracts quantitative statistics, computes standardized effect sizes, and finally performs random-effects meta-analysis. AutoSynthesis further supports heterogeneity analysis to examine how effect sizes vary across moderators, as well as risk-of-bias assessment. As output, AutoSynthesis produces a transparent report aligned with PRISMA guidelines. In our application, AutoSynthesis screened over 28 studies and extracted more than 20 quantitative claims. The pooled effect estimates produced by AutoSynthesis are similar to Hedges' $g$ of expert-conducted meta-analyses, indicating close agreement with manual evidence synthesis. Together, these results show that AutoSynthesis can make quantitative evidence synthesis more scalable, thereby supporting evidence-based decision-making across disciplines. --- ### ARMOR++: Agentic Orchestration of a Multi-Domain Primitive Set for Transferable Attacks on Deepfake Detectors Authors: Christos Korgialas, Gabriel Lee Jun Rong, Dion Jia Xu Ho, Pai Chet Ng, Xiaoxiao Miao, Konstantinos N. Plataniotis Published: 2026-07-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.15246v1 The reliability of deepfake detectors frequently degrades under black-box adversarial transfer, as these models often rely on fragile, architecture-dependent forensic cues. Existing transfer attacks often lack semantic awareness and struggle to maintain effectiveness under strict no-query constraints, particularly when perturbations are transferred from convolutional surrogates to transformer-based targets. To address these limitations, this paper introduces ARMOR++, a robust multi-agent framework designed for high-transferability deepfake evasion. The framework leverages the Qwen2.5-VL Vision-Language Model (VLM) to supply spatial semantic priors, while the Qwen3 Large Language Model (LLM) orchestrates primitive selection, adaptive hyperparameter reparameterization, and entropy-regularized perturbation mixing. By integrating five complementary primitives, spanning dense optimization, saliency-based methods, spatial transformations, frequency-domain perturbations, and block-structured modifications, ARMOR++ effectively targets heterogeneous inductive biases. Rigorous evaluation on the AADD-2025 benchmark demonstrates that ARMOR++ significantly outperforms existing agentic and non-agentic baselines across both low- and high-quality image regimes. Statistical analysis confirms a substantial gain in blind-target Attack Success Rate (ASR) over the state-of-the-art agentic baseline, with further performance advantages evidenced against non-agentic benchmarks and under robust defensive configurations. These findings highlight a significant residual reliability gap in current deepfake detector deployments and demonstrate the efficacy of agentic orchestration in identifying latent vulnerabilities. --- ### Mutable Low-Rank Sketches for Retrain-Free Recommendation Authors: Hector J. Garcia, Nick Clayton Published: 2026-07-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.15242v1 A common bottleneck in two-stage recommendation is embedding staleness: when a user rates a new item, their embedding remains fixed until the next retrain cycle. We propose mutable sketches, which store each user's preferences in a KP-tree (a sparse segment tree with sum aggregation), fit a low-rank projection once, and recompute embeddings on-the-fly as ratings arrive. We prove that each new observation monotonically tightens the prediction error envelope (Theorem 1), a guarantee that FunkSVD and eALS lack. On KuaiRec, the mutable sketch achieves 0.810 RMSE at 1.8% data read vs. ALS 0.822 at 100%, with 8x faster per-batch updates. A new user receives personalized recommendations in <1 ms after their first rating, with no model retraining required. A comparison of sampling strategies across density regimes shows that the KP-tree's norm-proportional sampling provides 40-130% better item coverage on sparse data (<1% density), while uniform sampling suffices on dense matrices. --- ### Beyond the Leaderboard: Design Lessons for Trustworthy Multimodal VQA Authors: Sushant Gautam, Vajira Thambawita, Michael A. Riegler, Pål Halvorsen, Steven A. Hicks Published: 2026-07-16 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2607.15241v1 Healthcare multimodal AI must combine visual and textual evidence while remaining reliable and interpretable. Using MediaEval Medico 2025 as a retrospective GI endoscopy case study, we analyze design choices across nine documented systems for question answering and explanation quality. Parameter-efficient adaptation of pretrained backbones provides strong challenge performance, but answer-level gains do not consistently translate into faithful and complete clinical reasoning. Methods enforcing structured reasoning and explicit grounding show more reliable behavior across heterogeneous question types, although the evidence is correlational rather than ablation-based. These results motivate evaluation beyond lexical overlap, standardized evidence-linked explanations, leakage-aware data governance, and lightweight robustness and calibration checks. The findings support trustworthy multimodal healthcare AI based on data fusion, explainability, and resilient evaluation. --- ### TikStance: A Multimodal and Hierarchical Dataset for Multi-target Stance Analysis in TikTok Political Conversations Authors: Yazhi Zhang, Fuqiang Niu, Bowen Zhang Published: 2026-07-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.15240v1 Political discourse has increasingly moved to short-video platforms, yet computational analysis of such content remains constrained by the scarcity of datasets that jointly preserve audiovisual information and hierarchical conversations. Here we present TikStance, a multimodal and context-aware dataset comprising 161 videos and 13,876 comments from TikTok, designed for stance detection in political discussions. The dataset covers three major political figures in the 2024 U.S. election cycle--Donald Trump, Joe Biden, and Kamala Harris--with content collected between September 2023 and January 2025. Each discussion unit links a host video and its metadata to a parent-linked comment tree, enabling stance analysis within both audiovisual and conversational context. Each item was independently labeled by three annotators using a three-class scheme (Favor, Against, None) for video-to-target and comment-to-target stance; items with disagreement were re-annotated, and the final Krippendorff's \(α\) reached 0.743, 0.723, and 0.722 for the Trump, Biden, and Harris subsets, respectively. Descriptive analysis further reveals target-dependent differences in stance distributions and conversational depth, with nested replies accounting for 23.3\% of all comments. By combining multi-target coverage, hierarchical conversations, and reliable multi-level human annotations, TikStance supports research in multimodal stance detection, political communication, computational social science, and context-aware natural language processing. --- ### Language Identification via Compositional Data Analysis: A Linear-Time Classifier Based on Log-Ratio Geometry Authors: Paul-Andrei Pogăcean, Sanda-Maria Avram Published: 2026-07-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.15238v1 Language identification is commonly addressed using either neural architectures or statistical n-gram models. Neural approaches typically require substantial computational resources, whereas classical frequency-based methods offer efficient linear-time performance, but rely on distance metrics that are not always appropriate for compositional data. This work models character and bigram frequency distributions as compositional vectors constrained to the simplex and mapped via the centered log-ratio (CLR) transformation bijectively onto the $(D-1)$-dimensional zero-sum subspace of $\mathbb{R}^D$, where Euclidean distances correspond to Aitchison distances. A pipeline is proposed, combining CLR-transformed unigram and bigram features with Laplace smoothing to address sparsity. The method is evaluated on six languages. Experimental results show that the proposed approach achieves robust accuracy across different text lengths, with strong performance for longer sequences. These findings indicate that compositional representations provide a deterministic and computationally efficient alternative for language identification, particularly in settings where interpretability and low resource consumption are essential. --- ### In-Place Tokenizer Expansion for Pre-trained LLMs Authors: Jimmy T. H. Smith, Tarek Dakhran, Alberto Cabrera, Simon S. Lee, Paul Pak, Aditya Tadimeti, Tim Seyde, Maxime Labonne, Alexander Amini, Mathias Lechner Published: 2026-07-16 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.15232v1 A tokenizer fixed at the start of pre-training allocates vocabulary in proportion to the pre-training corpus, reflecting the deployment priorities at that time. When those priorities shift, languages added later are split into many more tokens per word, which can raise latency, compute, and energy consumption for users of those languages. Cloud models can afford a broad vocabulary because the embedding and LM-head matrices are a small fraction of their parameters. On a compact model those matrices are a material share of per-token decode bandwidth, so on-device models ship small vocabularies and accept fragmentation outside a fixed language set. We present tokenizer expansion, an in-place recipe for upgrading a pre-trained model's tokenizer when the model producer controls its design. We continue the existing tokenizer's BPE merges on a multilingual corpus, so most source tokens carry over unchanged as single tokens and every new token has an exact decomposition into source tokens. We copy the carried-over embedding rows unchanged and initialize new rows as the mean of their source sub-token embeddings. A two-stage adaptation, embedding-only training then full-model continued pre-training, recovers source-checkpoint quality. We apply the recipe to a continued pre-trained checkpoint of LFM2-8B-A1B, an 8B-parameter Mixture-of-Experts model, to help produce LFM2.5-8B-A1B with a 128K tokenizer. The expanded tokenizer encodes Hindi and Vietnamese in roughly $2.4\times$ and $2.6\times$ fewer tokens than the source (up to $4.0\times$ on Thai). Combining these reductions with the measured per-token cost of the larger vocabulary, we estimate a $2.2$-$3.7\times$ per-character decode speedup for these languages across our reference devices. We release the model weights and the expanded tokenizer, and report the negative findings that shaped the recipe. --- ### CRISP: Constrained Refinement via Iterative Squeezing Process for Robust Medical Image Segmentation under Domain Shift Authors: Yizhou Fang, Pujin Cheng, Yixiang Liu, Xiaoying Tang, Longxi Zhou Published: 2026-07-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.15231v1 Distribution shift in medical imaging remains a central bottleneck for the clinical translation of medical AI. Failure to address it can lead to severe performance degradation in unseen environments and exacerbate health inequities. Existing methods for domain adaptation are inherently limited by exhausting predefined possibilities through simulated shifts or pseudo-supervision. Such strategies struggle in the open-ended and unpredictable real world, where distribution shifts are effectively infinite. To address this challenge, we adopt the "Rank Stability of Positive Regions" as a working assumption under distribution shift, and use it to derive robust spatial hints for source-only segmentation. Guided by this assumption, we propose CRISP, a model-agnostic framework that, unlike deployment-time adaptation, requires no test-time parameter updates and no target-domain data--a target-free, plug-in refinement framework that segments with frozen weights. Rather than using ranking to directly output masks, CRISP exploits the stability of probability rankings under distribution shift to derive robust spatial priors. Via latent feature perturbation, perturbation-invariant high-grade regions define a high-precision (HP) core, while voxels that remain potentially foreground under at least one perturbation define a high-recall (HR) support; these dual priors are then recursively refined under perturbation. We then design an iterative training framework that progressively squeezes HP and HR toward the final segmentation. Extensive evaluations on multi-center cardiac MRI and CT-based lung vessel segmentation demonstrate CRISP's superior robustness, significantly outperforming state-of-the-art methods with striking HD95 reductions of up to 0.14 (7.0% improvement), 1.90 (13.1% improvement), and 8.39 (38.9% improvement) pixels across multi-center, demographic, and modality shifts, respectively. --- ### Data Driven Block Replacement Scheduling Authors: Aniruddhan Ganesaraman, VIdyadhar Kulkarni Published: 2026-07-16 Categories: cs.LG, math.OC, stat.AP, stat.ML arXiv: https://arxiv.org/abs/2607.15229v1 We develop data-driven algorithms for maintaining $N$ independent identical machines under a \textit{block replacement policy}, in which each machine is replaced upon failure and all machines are jointly replaced at regular intervals of length $k$. The goal is to learn the cost-minimizing interval $k^*$ from operational data when the lifetime distribution is unknown. At each decision epoch, the operator selects $k \in \{1, 2, \ldots, K\}$, observes the resulting failure history (a mixture of complete and right-censored lifetimes) and incurs a per-unit-time cost governed by the renewal function. We formulate this as a stochastic multi-armed bandit and propose Hoeffding- and Bernstein-based lower-confidence-bound algorithms achieving $O(K \log T)$ regret, matching the Lai--Robbins lower bound. Exploiting a nested observation property unique to block replacement, correlated variants attain $O((K-k^*)\log T)$ regret and require only $O(1)$ direct pulls of suboptimal arms $k < k^*$. A complementary Kaplan--Meier renewal algorithm estimates the lifetime distribution nonparametrically from censored data, achieving almost-sure policy consistency and empirically near-zero incremental regret at long horizons. We additionally analyze two average-cost MDPs: a time-elapsed formulation establishing that block replacement is optimal within its policy class for any lifetime distribution, and an age-vector formulation proving a monotone threshold structure under increasing failure rate distributions and providing a gold-standard cost benchmark. Numerical experiments confirm the theoretical ordering and reveal structural cost gaps between optimal block and age-dependent replacement. --- ### Divergent Gaze Patterns in Artistic Viewing: Spatial and Temporal Signatures of Attention Across Autistic Individuals, Artists, and Neurotypical Observers Authors: Mohammed Amine Kerkouri, Daphné Senggaran, Renaud Jusiak, Océane Lehmann, Marouane Tliba, Claire Wardak, Emmanuelle Houy-Durand, Shasha Morel-Kohlmeyer, Aladine Chetouani, Nadia Aguillon-Hernandez Published: 2026-07-16 Categories: cs.CV, cs.HC arXiv: https://arxiv.org/abs/2607.15227v1 How different populations visually explore artworks bears on cognitive science and on accessibility design, yet most eye-tracking work in autism has used social scenes rather than art, and has analysed where the eyes land while ignoring when and in what order. We present a comparative free-viewing study across three groups, autistic adults (ASD), trained artists, and neurotypical observers, who each viewed 30 paintings for 15s. We introduce a directed, metric-grounded framework that compares groups along two complementary axes: a spatial axis, in which one group's fixation-density map predicts another's fixations under six saliency metrics (AUC-Judd, NSS, CC, SIM, KL, Information Gain); and a temporal axis, in which individual scanpaths are compared with MultiMatch, ScanMatch, a foveal-disc IoU score (FDISS), and dynamic time warping (DTW). Fixations are extracted uniformly for all groups with a dispersion-threshold algorithm. Three results converge. (i)Artists and neurotypicals are almost indistinguishable in both space (density-map correlation CC=0.96) and time (they form the most alignable scanpath pair), whereas ASD gaze diverges from both. (ii)ASD attention is dissociated: it matches artists' wide spatial exploration (dispersion, explored area) but carries a distinct temporal signature, shorter fixations, less dwell, and the most idiosyncratic (least self-consistent) scanpaths of any group. (iii)ASD gaze is not selectively artist-like on any metric; if anything it is marginally closer to neurotypical. Together these findings indicate that autistic viewing of art is a distinct, group-specific attentional profile in both space and time, and they motivate population-conditioned models of aesthetic attention. We release all analysis code and per-stimulus results. --- ### Structural-Semantic Reciprocal Learning for Unsupervised Visible-Infrared Person Re-Identification Authors: Moyao Tian, Shijia Liu, Yan Yang, Xin Yuan, Minshi Chen, Wei Wang, Xiao Wang Published: 2026-07-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.15220v1 Unsupervised visible-infrared person re-identification (USVI-ReID) is challenging due to the large modality gap and the lack of cross-modal identity annotations. Progressive association paradigms have been proposed to gradually bridge the gap, but they suffer from two critical bottlenecks: reliance on ambiguous global representations and unchecked propagation of pseudo-label noise in an open-loop manner. To address these issues, we propose Structural-Semantic Reciprocal Learning (SSRL), a framework that transforms open-loop association into a self-correcting closed-loop system. Structurally, we introduce Fine-grained Structural Decoupling (FSD) to extract discriminative body-part primitives as reliable spatial anchors, complementing ambiguous holistic silhouettes with spatially consistent structural details. Semantically, we design a Closed-loop Semantic Calibration (CSC) mechanism that reconstructs shared semantic prototypes at each epoch and feeds them back into the training loop, effectively filtering pseudo-label noise before the next clustering cycle. Through the reciprocal interaction between structural and semantic learning, SSRL achieves robust cross-modal representation. Extensive experiments demonstrate the competitive performance of SSRL against state-of-the-art USVI-ReID methods on both SYSU-MM01 and RegDB, notably surpassing several supervised counterparts on RegDB. --- ### When Words Are Safe But Actions Kill: Probing Physical Jailbreak Beyond Textual Jailbreak in Hidden-State Risk Space Authors: Weimeng Wang, Ziqiang Wang, Zihang Zhan, Chuanpu Fu, Qi Li, Ke Xu Published: 2026-07-16 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2607.15218v2 Large language models (LLMs) increasingly serve as high-level planners for embodied agents, where linguistically benign instructions can become unsafe once grounded in the physical world. We study whether this physically grounded jailbreak is the same safety problem as ordinary textual jailbreak. Through hidden-state direction analysis and random-split null tests, we show that textual jailbreak (TJ) and physical jailbreak (PJ) form separable signals in LLM representations across Qwen2.5-3B/7B/14B/32B, Phi-3.5 and SmolLM2. Building on this separability, we propose PRISM, a single-layer L2-regularized logistic probe over full hidden states. PRISM achieves 86.2--87.7\% accuracy on SafeAgentBench with 11.7--13.7\% false-positive rates (FPRs), while same-scale LLM judges over-block safe tasks at 24.7--39.0\% FPR. To test whether the result survives lexical-shortcut controls, we introduce an interaction-balanced revision of PhysicalJailbreakBench-2K (PJB-2K): a fixed 2{,}000-row comparison set sampled by label and physical mechanism from a larger object--site construction. On the underlying 10{,}000-row pool, word-TFIDF and the embedding layer remain at chance (AUC 0.497 and 0.500). At layer 25, selected by an i.i.d. sweep, cell-grouped cross-validation gives PRISM 0.718 AUC, compared with 0.398 for a physics-free label control under the same protocol. On the identical 2{,}000 comparison rows, these PRISM predictions obtain 0.671 balanced accuracy, while Qwen2.5 judges from 3B to 72B obtain 0.538--0.577 and exhibit high FPR. These results support hidden-state probing as a representation-level method for physical safety beyond text moderation, without relying on the near-perfect scores of shortcut-prone paired templates. --- ### When Words Are Safe But Actions Kill: Probing Physical Danger Beyond Text Safety in Hidden-State Risk Space Authors: Weimeng Wang, Ziqiang Wang, Zihang Zhan, Chuanpu Fu, Qi Li, Ke Xu Published: 2026-07-16 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2607.15218v1 Large language models (LLMs) increasingly serve as high-level planners for embodied agents, where linguistically benign instructions can become unsafe once grounded in the physical world. We study whether this physically grounded danger is the same safety problem as ordinary text-level content danger. Through hidden-state direction analysis and random-split null tests, we show that content danger (CD) and physical danger (PD) form separable signals in LLM representations across Qwen2.5-3B/7B/14B/32B, Phi-3.5 and SmolLM2. Building on the CD/PD separability, we propose PRISM, a single-layer L2-regularized logistic probe over full hidden states. PRISM achieves 86.2--87.7\% accuracy on SafeAgentBench with 11.7--13.7\% FPR, while same-scale LLM judges over-block safe tasks at 24.7--39.0\% FPR. We further introduce PhysicalSafetyBench-1K (PSB-1K), a contrastive benchmark of 1{,}000 physical-risk pairs without direct harm keywords, to test whether methods detect physically grounded danger rather than explicit unsafe wording. On PSB-1K, PRISM reaches 99.6\% accuracy and 0.7\% FPR, whereas a Qwen2.5-3B judge rejects 67.8\% of safe tasks. PRISM also replicates on SafeText and EARBench, supporting hidden-state probing as a representation-level method for physical safety beyond text moderation. --- ### NeuronSoup: Evolving Asynchronous, Shared-Neuron Temporal Graphs without Backpropagation Authors: Subodh Kalia Published: 2026-07-16 Categories: cs.NE, cs.LG arXiv: https://arxiv.org/abs/2607.15217v1 We present NeuronSoup, a neural computation architecture that replaces synchronous layer-by-layer processing with asynchronous, delay-mediated signal propagation through a pool of shared neurons. Each path in the network routes a continuous-valued signal from one input neuron to one output neuron through a variable number of intermediate hidden neurons. Hidden neurons are physically shared across paths: when two paths pass through the same neuron, the second arrival encounters the accumulated state left by the first, producing constructive or destructive interference that depends on signal polarity and arrival timing. The entire architecture -- topology, weights, delays, and connectivity -- is co-evolved by a genetic algorithm operating on a flat real-valued genome of 14,602 genes. On 10-class MNIST digit classification using frozen ResNet18 features as input, the system evolves a network of 204 active paths through 266 hidden neurons (156 shared across multiple paths, with one neuron participating in 11 distinct paths) and achieves 85.9\% test accuracy after 10,000 generations. The trained model occupies 115 KB. We argue that this architecture addresses fundamental limitations of current deep learning: it requires no differentiable computation graph, adapts its computation depth per-sample, and discovers lateral interactions between processing pathways that current architectures must engineer explicitly. We discuss why genetic algorithms are the correct optimization tool for this problem class, why CMA-ES fails at this scale, and how the architecture generalizes to arbitrary domains by substituting the encoder and output structure. --- ### Symbal: Detecting Systematic Misalignments in Model-Generated Captions Authors: Maya Varma, Jean-Benoit Delbrouck, Sophie Ostmeier, Akshay Chaudhari, Curtis Langlotz Published: 2026-07-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.15216v1 Multimodal large language models (MLLMs) often introduce errors when generating image captions, resulting in misaligned image-text pairs. Our work focuses on a class of captioning errors that we refer to as systematic misalignments, where a recurring error in MLLM-generated captions is closely associated with the presence of a specific visual feature in the paired image. Given a vision-language dataset with MLLM-generated captions, our aim in this work is to detect such errors, a task we refer to as systematic misalignment detection. As our first key contribution, we present Symbal, which utilizes a structured, dual-stage setup with off-the-shelf foundation models to identify systematic misalignments and summarize results in natural language. As our second key contribution, we introduce SymbalBench, a benchmark designed to evaluate automated methods on our proposed task. SymbalBench consists of 1.7 million image-text pairs from two domains (natural and medical images), organized into 420 vision-language datasets with annotated systematic misalignments. Symbal exhibits strong performance on this benchmark, correctly identifying systematic misalignments in 63.8% of datasets, a nearly 4x improvement over the closest baseline. We supplement our evaluations on SymbalBench with real-world evaluations, showing that (1) Symbal can accurately surface systematic misalignments in captions generated by four MLLMs and (2) Symbal is a powerful tool for auditing off-the-shelf image-caption datasets. Ultimately, our novel task, method, and benchmark can aid users with auditing MLLM-generated captions and identifying critical errors, without requiring access to the underlying MLLM. Code is available at https://github.com/Stanford-AIMI/Symbal. --- ### MAGiSt3R: Multi-Agent Feed-forward 3D Reconstruction from Monocular RGB Videos Authors: Ziren Gong, Xiaohan Li, Fabio Tosi, Ninghui Xu, Stefano Mattoccia, Jianfei Cai, Matteo Poggi Published: 2026-07-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.15211v1 This paper presents MAGiSt3R, a multi-agent 3D reconstruction framework performing reconstruction and camera tracking for monocular RGB videos at almost 10 FPS. MAGiSt3R relies on a feed-forward model from the 3R family to process RGB videos and regress local point maps, and on a merging model, MAGMA, that combines local maps at both intra-agent and inter-agent levels to obtain the final global point map. Furthermore, MAGiSt3R performs pose graph optimization to mitigate cumulative camera drift occurring along the feed-forward pipeline. We evaluate MAGiSt3R on both synthetic and real-world datasets, demonstrating its superior reconstruction and camera tracking accuracy compared to state-of-the-art approaches. --- ### Expanding the Lexicon of Ge'ez Based African Languages: A Comparative Study of Amharic and Tigrinya Authors: Hailay Kidu Teklehaymanot, Debela Desalegn Yadeta, Wolfgang Nejdl Published: 2026-07-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.15209v3 Multilingual pre-trained language models such as XLM-R perform well for major languages but struggle with low-resource Ge'ez-script languages, largely because Latin-script-centric tokenizers split their words into many subwords. We introduce VEXMLM, a vocabulary-extended variant of XLM-R targeting Amharic and Tigrinya. We train language-specific SentencePiece tokenizers on monolingual corpora, extend XLM-R's vocabulary with 30k Ge'ez-script subwords, and initialize each new embedding to the mean of the pretrained embeddings. VEXMLM undergoes two-stage training: (1) continued masked language modeling on the monolingual corpora and (2) supervised fine-tuning on question answering and named entity recognition (Amharic and Tigrinya) and sentiment analysis (Amharic). VEXMLM lowers tokenizer fertility below that of XLM-R and Glot500 on both languages, by 28.0% (Amharic) and 45.9% (Tigrinya) relative to XLM-R. Downstream, it modestly improves named entity recognition over XLM-R, scores below XLM-R on extractive question answering, and is comparable on sentiment analysis. An ablation on Tigrinya NER shows that vocabulary expansion alone lowers accuracy on out-of-vocabulary words (words that XLM-R's tokenizer cannot represent or splits into more pieces than the expanded tokenizer), and that continued pretraining is required for the expanded model to exceed the baseline. Vocabulary expansion thus makes Ge'ez-script tokenization substantially more efficient, while its downstream benefit depends on the task and on adapting the new embeddings through continued pretraining. Resources: GitHub repository | Hugging Face model. --- ### Expanding the Lexicon of Ge'ez Based African Languages: A Comparative Study of Amharic and Tigrinya Authors: Hailay Kidu Teklehaymanot, Debela Desalegn Yadeta, Wolfgang Nejdl Published: 2026-07-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.15209v1 Multilingual pre-trained language models (PLMs) exhibit degraded performance on low-resource, non-Latin-script languages, driven by high out-of-vocabulary (OOV) rates and excessive subword fragmentation that result from Latin-script-centric tokenizer training. We introduce VEXMLM, a vocabulary-extended variant of XLM-R targeting the two highest-resource Ge'ez-script languages, Amharic and Tigrinya, and further evaluated on 17 additional low-resource African languages (19 total). We train a language-specific SentencePiece tokenizer on curated Amharic and Tigrinya monolingual corpora, extend XLM-R's vocabulary with 30,000 Ge'ez-script subwords derived from this tokenizer, and initialize their embeddings by averaging the embeddings of their constituent subwords under XLM-R's original tokenizer. VEXMLM is trained in two stages: (1) continued masked language modeling over the extended vocabulary on the curated corpora, and (2) supervised fine-tuning on question answering (QA), named entity recognition (NER), and sentiment analysis (SA). On Amharic/Tigrinya QA, VEXMLM achieves 87.0 EM /90.0 F1, versus 66.0 EM/78.0 F1 for XLM-R and 74.0 EM/ 78.0 F1 for Glot500. On SA, VEXMLM reaches 80.0\% accuracy versus 77.0\% (XLM-R) and 46.0\% (Glot500). On NER, VEXMLM raises OOV-token entity accuracy from 81.4\% to 94.3\%, averaged over 11 of the 19 evaluated languages for which OOV analysis was possible. Our contributions are: (i) a vocabulary-extension and embedding-initialization procedure tailored to Ge'ez script; (ii) a two-stage training strategy under which vocabulary and continued-pretraining gains on Amharic/Tigrinya transfer to 17 typologically related, unaugmented African languages; and (iii) an evaluation spanning both intrinsic tokenization metrics (vocabulary coverage, fertility, OOV rate) and extrinsic task performance across all 19 languages. --- ### Delocalization of bias in unadjusted Hamiltonian Monte Carlo and underdamped Langevin Authors: Yifan Chen, Xiaoou Cheng, Jonathan Niles-Weed, Jonathan Weare Published: 2026-07-16 Categories: stat.CO, cs.LG, math.PR, stat.ML arXiv: https://arxiv.org/abs/2607.15208v1 Unadjusted samplers such as unadjusted Hamiltonian Monte Carlo and underdamped Langevin are well-known to be biased. Metropolis--Hastings adjustment has been conventionally incorporated into Hamiltonian Monte Carlo to eliminate the bias. However, this adjustment can significantly increase the iteration complexity due to the small step size required for reasonable Metropolis acceptance rates. In this work, we extend the \emph{delocalization of bias} phenomenon, previously established for the overdamped Langevin algorithm, to these two unadjusted algorithms. We show that to control the $W_2$ bias of any $K$-dimensional marginal of a high-dimensional distribution, $O(\sqrt{K})$ integration steps suffice up to $\log d$ terms, assuming either weak or sparse interactions among variables. The discrete-time integrators here introduce technical difficulties beyond those of the overdamped setting, which we address through a broadly applicable matrix-polynomial framework that characterizes their propagators. Our result for the underdamped Langevin algorithm is valid for all large friction parameters, implying that the Leimkuhler-Matthews integrator for the overdamped Langevin dynamics also exhibits delocalization of bias. --- ### BadWAM: When World-Action Models Dream Right but Act Wrong Authors: Qi Li, Xingyi Yang, Xinchao Wang Published: 2026-07-16 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2607.15207v2 World-action models (WAMs) are emerging as a promising foundation for embodied control: rather than predicting actions alone, they learn representations that couple action generation with future world prediction. This coupling is often viewed as a source of robustness, interpretability, and safety, as a robot's action can in principle be checked against its imagined future. In this paper, we show that this assumption is fragile. We introduce BadWAM, a unified framework for modeling and evaluating World-Action Drift Attacks: a new class of WAM-specific adversarial attacks that use small visual perturbations to break the alignment between what a WAM imagines and what it executes. BadWAM characterizes this attack surface along two natural criteria: attack strength and stealthiness. When the adversary prioritizes disruption, BadWAM instantiates an action-only adversarial attack, which directly drives the model toward task-failing actions. When the adversary additionally prioritizes stealth, BadWAM instantiates an imagination-preserving adversarial attack, which seeks to induce harmful action shifts while keeping the model's predicted future close to its clean imagination. Together, these two attacks capture a spectrum of WAM-specific failures: from overt action hijacking to stealthier cases where the model appears to imagine a plausible future but executes a desynchronized action. We evaluate BadWAM across different variants of WAMs. Results show that our attacks substantially reduce task success rates under closed-loop execution. For example, our action-only attack reduces the model performance from 96.5\% to 43.1\% success. The results of our imagination-preserving attack further exposes a WAM-specific vulnerability: moderate future-preserving regularization can maintain strong attack performance while reducing future imagination drift. --- ### BadWAM: When World-Action Models Dream Right but Act Wrong Authors: Qi Li, Xingyi Yang, Xinchao Wang Published: 2026-07-16 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2607.15207v1 World-action models (WAMs) are emerging as a promising foundation for embodied control: rather than predicting actions alone, they learn representations that couple action generation with future world prediction. This coupling is often viewed as a source of robustness, interpretability, and safety, as a robot's action can in principle be checked against its imagined future. In this paper, we show that this assumption is fragile. We introduce BadWAM, a unified framework for modeling and evaluating World-Action Drift Attacks: a new class of WAM-specific adversarial attacks that use small visual perturbations to break the alignment between what a WAM imagines and what it executes. BadWAM characterizes this attack surface along two natural criteria: attack strength and stealthiness. When the adversary prioritizes disruption, BadWAM instantiates an action-only adversarial attack, which directly drives the model toward task-failing actions. When the adversary additionally prioritizes stealth, BadWAM instantiates an imagination-preserving adversarial attack, which seeks to induce harmful action shifts while keeping the model's predicted future close to its clean imagination. Together, these two attacks capture a spectrum of WAM-specific failures: from overt action hijacking to stealthier cases where the model appears to imagine a plausible future but executes a desynchronized action. We evaluate BadWAM across different variants of WAMs. Results show that our attacks substantially reduce task success rates under closed-loop execution. For example, our action-only attack reduces the model performance from 96.5% to 43.1% success. The results of our imagination-preserving attack further exposes a WAM-specific vulnerability: moderate future-preserving regularization can maintain strong attack performance while reducing future imagination drift. --- ### MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization Authors: Shaoxiong Zhan, Shi Hu, Boyu Feng, Hai Lin, Andrew Gong, Zhengda Zhou, Jiaying Zhou, Yunyun Hou, Hao Su, Hai-Tao Zheng Published: 2026-07-16 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2607.15205v1 Real repository issues routinely include visual evidence such as screenshots, error dialogs, rendered UI states, and logs, yet repository-level issue localization is evaluated mostly as a text-only task. Existing multimodal SE benchmarks evaluate end-to-end repair, entangling localization with patch synthesis and obscuring whether visual input helped, hurt, or was ignored. We introduce \textbf{MM-IssueLoc}, a controlled benchmark and evaluation protocol for repository-level localization with visual evidence. MM-IssueLoc contains 652 issue-PR instances across 23 languages, with annotations for 7 image categories and 4 relevance levels. It provides file-level and function-level gold labels, paired text-only and with-image evaluation, and VCE-based diagnostics that convert images into structured textual evidence. We evaluate LLM-based and retrieval-based systems, including MM-IssueLoc-VL-Emb as a controlled multimodal retriever. Results show that existing systems remain far from reliable multimodal repository localization: the strongest agent reaches 38.96 file Acc@5 and 22.45 function Acc@10, while the strongest retriever reaches 33.86 function Acc@10. Cross-benchmark comparisons show that high localization scores on text-dominant SWE benchmarks do not transfer cleanly to multimodal issue localization. MM-IssueLoc turns visual evidence into an explicit evaluation variable, enabling future work to test whether systems improve by using visual evidence for localization, rather than by relying on text-only cues or downstream patch-generation effects. --- ### Self-Evolving Human-Centered Framework for Explainable Depression Symptom Annotation Authors: Hoang-Loc Cao, Van Pham, Truong Thanh Hung Nguyen, Phuc Truong Loc Nguyen, Phuc Ho, Veronica Whitford, Hung Cao Published: 2026-07-16 Categories: cs.AI, cs.HC, cs.MA, cs.MM arXiv: https://arxiv.org/abs/2607.15202v1 Annotation quality is a major bottleneck in building reliable and explainable artificial intelligence (XAI) systems for mental health research. In depression-related datasets, labels are often assigned without structured evidence, symptom-level justification, or traceable alignment with the criteria of the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, Text Revision (DSM-5-TR), limiting both transparency and downstream model interpretability. We propose a self-evolving, expert-in-the-loop annotation framework for Major Depressive Disorder (MDD) that combines large language model (LLM)-assisted labeling with expert verification. The framework is intended to support the construction of explainable, DSM-5-TR-aligned datasets rather than to perform clinical diagnosis. It operates in three stages: candidate evidence selection from textual records, criterion-level DSM-5-TR analysis, and case-level synthesis that produces label-level diagnostic and severity annotations. A dual-memory architecture, composed of Example Memory and Reflection Memory, is designed to internalize expert feedback and iteratively improve future annotations without retraining. We describe this mechanism and leave its evaluation across multiple feedback cycles to future work. In addition to final labels, the framework exports clinical evidence, reasoning traces, and edit histories, enabling comprehensive auditability. In a pilot study using expert-reviewed samples, the proposed approach improves annotation consistency and explainability while reducing manual revision effort. --- ### Mask-Aware Policy Gradients for Diffusion Language Models Authors: Haran Raajesh, Kulin Shah, Adam Klivans, Philipp Krähenbühl Published: 2026-07-16 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.15200v1 Reinforcement learning has proven effective for improving reasoning in large language models, but extending it to Masked Diffusion Language Models (MDLMs) remains challenging due to the intractability of the log-likelihood estimation. Existing approaches approximate this log-likelihood by modeling only the token predictions, ignoring the order in which positions are unmasked during generation. We observe that MDLM generation involves two decisions at each step: what tokens to place at each masked position and which positions to remask. We formalize this as a two-stage action MDP, showing that the policy gradient naturally decomposes into a token term and a masking term. Combining optimization of both terms leads to state-of-the-art outcomes on mathematical reasoning and coding benchmarks, with scores of 87.1% on GSM8K and 53.4% on MBPP. --- ### Subjective Risk Decomposition: A New View for Uncertainty Quantification Authors: Raghad Alamri, Michele Caprio, Gavin Brown Published: 2026-07-16 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.15196v3 We present a novel viewpoint for uncertainty quantification. Uncertainty measures are not primitives, in need of axioms and argumentation, but instead consequences, of higher-level modelling decisions. We show how epistemic and aleatoric uncertainty measures can be derived via decomposition of a subjective risk, based on a strictly proper loss. Reverse cross entropy provides a prominent example, where decomposition recovers the classic information-theoretic uncertainty terms. The same approach recovers numerous measures previously proposed across the UQ literature, providing them a common theoretical foundation. This suggests a new approach to UQ: given a modelling scenario and strictly proper loss, the corresponding epistemic and aleatoric terms are induced by the subjective-risk decomposition. We then extend our view to learning theory: we introduce and analyse subjective risk analogues of excess risk, approximation error and estimation error, and identify the connections to UQ. We consider this a first step towards a full learning-theoretic framework for uncertainty quantification. ---