# Research Papers — 2026-06 · bundle page 186 of 260 > Full-text markdown of papers #9251–9300 of 12993 published in 2026-06, newest first. AI-readable mirrors of the full 12993-paper 2026-06 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-06/page/186 [← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/185.md) [Next bundle →](https://aipod.dev/papers/archive/2026-06/page/187.md) ### What Should a Skill Remember? Quality--Cost Trade-offs in Cost-Aware Skill Rewriting for Language Model Agents Authors: Qinghua Xing, Yinda Chen, Yaping Jin, Zhenhe Wu, Bohan Lin, Hang Zhou, Xinghao Chen, Hanting Chen, Zhiwei Xiong Published: 2026-06-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.09421v3 Large language model agents increasingly rely on skills: reusable procedural documents encoding workflows, tool use, implementation patterns, validation checks, and domain rules. Skill rewriting is often treated as prompt compression, but shorter skills can make agents more expensive by removing sparse operational anchors that prevent exploration, debugging, and recovery. We study skill rewriting through this economic lens. Our controlled framework profiles skill structure, rewrites skills using information-preservation strategies, and evaluates the rewrites under fixed task instructions, environments, and verifiers. Experiments on SkillsBench reveal distinct quality--cost trade-offs across strategies: API/code anchoring, workflow guarding, and rule/formula anchoring benefit different task families, with no universally dominant template. In the main held-out evaluation, the learned policy reduces total cost by 7.0% and downstream agent-token cost by 6.0%; in frozen cross-model transfer, the corresponding reductions average 14.7% and 13.7%, while verifier quality is preserved. These results position skill design as cost-aware operational knowledge engineering rather than prompt compression. Resources: https://github.com/1Reminding/Skill_EE. --- ### Context-Aware Deep Learning for Defect Classification in Atomic-Resolution STEM Authors: Jiadong Dan, Cheng Zhang, Leyi Loh, Ivan Verzhbitskiy, Yuan Chen, Goki Eda, Michel Bosman, N. Duane Loh Published: 2026-06-08 Categories: cond-mat.mtrl-sci, cs.AI arXiv: https://arxiv.org/abs/2606.09419v1 Artificial intelligence is rapidly advancing materials characterization, yet most applications in electron microscopy rely solely on image contrast, overlooking the chemical and experimental context that shapes image formation. This limitation makes defect classification inherently ambiguous, as similar contrasts can arise from different materials or imaging conditions. Here we develop a context-aware learning framework that integrates image-derived contrast with metadata describing composition, beam energy, and detector geometry. Using a systematically constructed dataset of ~55 million simulated patches spanning 576 cases across 96 doped monolayer transition-metal dichalcogenides, we show that conditioning on contextual variables transforms defect classification from an ill-posed image-only task into a well-posed, physically grounded problem. The framework achieves over 98% accuracy on simulations and near-human agreement on experimental data, with a 94% reduction in posterior entropy. By emphasizing contextual grounding over architectural complexity, this approach links experimental image contrast to the underlying chemical and imaging conditions, supporting physically grounded defect assignments and a general pathway toward multimodal AI models for autonomous materials characterization. --- ### Harness Engineering for Physical AI: Robot Middleware Is the Harness Layer Authors: Sanghoon Lee, Jiyeong Chae, Kyung-Joon Park Published: 2026-06-08 Categories: cs.RO, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2606.09416v1 Robot middleware faces a new role in the era of Physical AI. Learned policies, planners, and vision-language-action (VLA) models now enter deployed robots as causal participants on the control path, but the layer that integrates them with timing, scheduling, and network has not been named. Recent language-agent work names this layer the harness, the external system that mediates tools, manages state, bounds resources, and records execution. The robotics community has not yet adopted this framing, and we propose that robot middleware is that harness. A Physical AI harness differs from a software harness in where it intervenes. A software harness mediates at tool-call boundaries. A Physical AI harness must mediate at control, computing, and communication simultaneously, because a learned policy's output crosses all three: its commands shift the trajectory, its inference time shifts the schedule, and its payload shifts the bandwidth. Robot middleware is the lowest robot-stack layer with mediating abstractions over all three, so it is best positioned to compose their enforcement. It already provides most of what a harness needs but lacks the enforcement for an AI model. We name this missing enforcement as three functions: Projection gates each output at emission, Isolation bounds the model's execution and transmission slot, and Transfer falls back to a verified baseline when checks fail. Each appears today as hand-built application code in deployed robot systems, built on surfaces robot middleware already provides. Robot middleware should host them not as the best single-axis enforcer but as the layer that composes all three. We sketch this as a ROS 2 Harness Profile, a deployment artifact that carries an AI model's declared output region, inference budget, and operating regime while the middleware enforces them across ROS 2, DDS, and Zenoh. --- ### AI Assurance in UK Defence: Challenges in Operationalising JSP 936 Authors: Callum Cockburn, Sam Farrow Published: 2026-06-08 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2606.09414v1 This report examines practical challenges in operationalising JSP 936 Part 1 for AI assurance in UK Defence. Using a structured interpretive review of the directive's requirements, the analysis identifies eight thematic challenge areas adequacy of evidence and argument, management of human interaction with AI, definition of the operational environment, integration of AI within systems of systems, assessment and maintenance of AI performance, analysis of safety and security, measurement of ethicality, and mitigation of the inherent complexities of AI. The report argues that JSP 936 provides a useful governance basis, but that implementation depends on unresolved technical, organisational, and assurance questions. These challenges stem from the socio-technical nature of AI-enabled systems, uncertainty in real-world deployment contexts, limitations in current assurance methodologies, and tensions between performance, safety, human oversight, security, and ethical acceptability. The report identifies areas where further methods, guidance, and organisational capability are needed for the ambitious, safe, and responsible adoption of AI across Defence. This is consistent with MOD's own framing of JSP 936 as requiring iterative implementation and supporting guidance. --- ### Now You (Still) See Me: Detecting Evasive Steganographic Payloads in LLMs Authors: Charles Westphal, Timothy Douglas, Keivan Navaie, Tiago Pimentel, Fernando E. Rosas Published: 2026-06-08 Categories: cs.CR, cs.IT, cs.LG arXiv: https://arxiv.org/abs/2606.09411v1 Large language models can be fine-tuned to encode prompt-borne secrets into fluent, seemingly benign outputs. This creates a steganographic exfiltration risk that is difficult to detect with output-level steganalysis. Recent work proposes mechanistic detection using linear probes that recover the secret from internal activations. We show that this defense can be systematically evaded, but that detectability can be recovered through a targeted data-level intervention. First, we extend the detection setup to include a non-linear MLP probe. We then adversarially fine-tune steganographic trojans across five base models: Qwen3-8B, Llama-3.1-8B, Ministral-8B, Qwen3-14B, and Phi-4-14B. The resulting models retain $58$--$79\%$ exact-match secret recovery while evading both ridge and held-out MLP probes, with $1$--$8\%$ average capability degradation across six benchmarks. We then give an information-theoretic characterization of this evasion. Successful evasion preserves recoverability while reducing low-order extractability of the secret from the content-aligned representation, forcing the payload into synergistic interaction with residual degrees of freedom. This motivates a recontextualization dataset that restricts these residual degrees of freedom. On this distribution, both ridge and MLP detectability are restored across all five evasive trojans. Overall, our findings show that activation-based steganography detection is vulnerable to adaptive evasion, but also that theory-guided evaluation distributions can expose otherwise hidden payloads. --- ### Capacity, Not Format: Rethinking Structured Reasoning Failures Authors: Hengxin Fan Published: 2026-06-08 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.09410v1 Prior work treats structured output as a reasoning tax, but this framing is incomplete: the cost of formatting depends strongly on a model's spare capacity. Using information-matched prose controls and a four-level schema complexity gradient, we separate format-specific effects from prompt-length confounds across 4 models and 5 benchmarks with 0% parse failures on successfully generated responses. We find that structured formats are capacity-dependent. Models with sufficient headroom absorb JSON constraints without degradation (Sonnet: $88.7\pm4.0$% JSON vs. $89.3\pm1.7$% CoT on MATH-Hard). In contrast, formats severely degrade models operating near their limits through two distinct mechanisms. First, under standard token budgets, Haiku drops 36.2pp ($p < 0.0001$) largely due to truncation. Second, even with extended budgets eliminating truncation, GPT-4o-mini drops 28.0pp ($p < 0.001$), revealing pure capacity competition independent of token exhaustion. This format penalty scales with schema complexity (McNemar $p < 0.0001$) and cannot be explained by prompt length alone. Furthermore, these results qualify claims of frontier model immunity: on AIME competition math, Opus 4.7 drops from 96.2% to 91.0% under JSON ($-5.3$pp; the displayed percentages are independently rounded, exact difference is $7/133 = 5.26$pp $\approx 5.3$pp). A delayed-structure ablation -- reasoning freely before formatting -- recovers most of the lost accuracy (3-run mean: 80--87%), supporting the capacity competition mechanism. The practical implication is not to avoid structured output, but to match it to capacity: when a model is near its limits, think first, format later. --- ### Correct Looks Better: Pairwise Comparisons Reveal Accuracy Rankings Authors: Mina Remeli, Moritz Hardt Published: 2026-06-08 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.09409v1 Pairwise comparisons combined with aggregation methods like Elo have become central to evaluating generative models, yet concerns remain that they reward superficial stylistic cues or display judge biases. In a more positive turn, we show that model rankings from pairwise comparisons strongly agree with ground-truth-based accuracy rankings when such ground truth is available for comparison. By converting five well-known benchmarks into free-form generative evaluations, we find that Elo rankings achieve a Spearman correlation above 0.9 with accuracy rankings and substantially outperform direct evaluation when the judge is weak. Furthermore, style and judge bias have only minor effects on model rankings, despite most judgments occurring on pairs where both candidate answers are correct (or incorrect). On such pairs, we find that repetition after the final answer (echo) is a causal driver of judge preference. --- ### Can Data Work be Reparative? Authors: Srravya Chandhiramowuli, Ding Wang, Alex Taylor Published: 2026-06-08 Categories: cs.CY, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2606.09408v1 We present an ethnographic study of an alternative approach to data work, developed by a civic-tech initiative that builds datasets for training and benchmarking online safety systems. They aim to respond to online safety concerns from a feminist perspective, by building safety datasets collaboratively with those most impacted by online harms. In this paper, we examine how this approach aims to reorient data work as a site for repair and redress, and trace the struggles they encounter in the process. Specifically, we draw attention to the challenges and tensions involved in advancing just reward for data work and collective governance of AI datasets. Examining these challenges through an STS-informed lens of reparative justice and repair, we argue that the work of repairing data work (and AI) lies, fundamentally, in resetting the ties of accountability. At a time heightened emphasis on efforts like safety evaluations and red teaming to make AI more responsible, we highlight the need to confront foundational questions about how the humans involved in these efforts relate to the datasets and systems they help produce. A reparative lens demands that we interrupt prevailing norms of data work and place at their centre, not AI or datasets, but those most harmed by the neglect, oversight and exclusion animated in the current modes of dataset production. This, we argue, offers a bold vision for responsibility and contributes towards a critical agenda for building alternative futures of data and AI practice. --- ### SAILS: Surrogate-based Analysis of Interactions via Local Effect Smooths Authors: Timo Heiß, Julia Herbinger, Bernd Bischl, Giuseppe Casalicchio Published: 2026-06-08 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.09404v2 Feature interactions drive much of the predictive power of machine learning models, yet existing explanation methods only detect and quantify interactions without revealing their functional form, or visualize only restricted interaction types. We propose Surrogate-based Analysis of Interactions via Local Effect Smooths (SAILS), a model-agnostic framework that analyzes pairwise interactions through generalized additive model (GAM) surrogates fitted to the local effects of a black-box model. For each interval of a feature of interest, the surrogate smooth terms isolate the interaction components on derivative level, enabling (i) interaction detection through a heuristic derived from significance tests on smooth terms, (ii) interaction form categorization into linear, product-separable, and non-product-separable types, and (iii) tailored, interpretable visualizations for each interaction type. We empirically validate the framework through controlled simulations and a real-world task, showing its effectiveness for pairwise interactions, with limitations under strong feature correlations and higher-order interactions. SAILS fills a notable gap in the eXplainable AI (XAI) toolbox, going beyond detecting interactions alone to characterizing their functional form. --- ### SAILS: Surrogate-based Analysis of Interactions via Local Effect Smooths Authors: Timo Heiß, Julia Herbinger, Bernd Bischl, Giuseppe Casalicchio Published: 2026-06-08 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.09404v1 Feature interactions drive much of the predictive power of machine learning models, yet existing explanation methods only detect and quantify interactions without revealing their functional form, or visualize only restricted interaction types. We propose Surrogate-based Analysis of Interactions via Local effect Smooths (SAILS), a model-agnostic framework that analyzes pairwise interactions through interpretable generalized additive model (GAM) surrogates fitted to the local effects of a black-box model. For each interval of a feature of interest, the surrogate smooth terms isolate the interaction components on derivative level, enabling (i) interaction detection through a heuristic derived from significance tests on smooth terms, (ii) interaction form categorization into linear, product-separable, and non-product-separable types, and (iii) tailored, interpretable visualizations for each interaction type. We empirically validate the framework through controlled simulations and a real-world task, demonstrating its effectiveness for pairwise interactions, with limitations under strong feature correlations and higher-order interactions. SAILS fills a notable gap in the XAI toolbox, going beyond detection of interactions alone to characterizing their functional form. --- ### Introducing multiplex semantic networks as multifaceted representations of creative associative knowledge across multilingual samples Authors: Edith Haim, Kurt Haim, Roger E. Beaty, Cynthia S. Q. Siew, Massimo Stella Published: 2026-06-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.09403v1 Creativity is a complex cognitive ability that relies on knowledge organisation and retrieval from semantic memory. Yet most research uses a single task to measure it, capturing only a fraction of this complexity. This study investigates multiplex networks - layered semantic networks obtained from six cognitive tasks - as a more comprehensive approach to modelling the associative knowledge underlying creativity. We collected data from N=518 individuals from four countries (Austria, USA, Singapore, Italy). From their responses to verbal fluency, sentence-chain, free association, and narrative writing tasks, we constructed semantic networks and assembled them in a multiplex structure. AI persona-based responses provided a comparison baseline. Structural reducibility analyses showed that different task layers captured distinct, non-redundant information about semantic organisation, supporting the use of multiple tasks over any single one. The networks from high- and low-creative groups remained structurally distinct, while AI-generated networks showed near-identical structures regardless of creativity group. Finally, we used 12 features (network measures, emotional scores, and spreading activation simulations) in a machine learning model using ridge regression to predict individual creativity scores. The combination of structurally similar layers, as identified in the previous stage, improved a proof-of-concept prediction accuracy by 50%. Structural measures showed the highest feature importance, with spreading activation dynamics providing additional predictive power. Together, these findings indicate that multiplex semantic networks capture a richer, cross-cultural picture of associative knowledge underlying creativity. We also release our diverse dataset and code to foster diverse computational approaches within the creativity community. --- ### Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models Authors: Bartłomiej Marek, Lorenzo Rossi, Vincent Hanke, Xun Wang, Michael Backes, Franziska Boenisch, Adam Dziedzic Published: 2026-06-08 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2606.09401v1 Recent work has applied differential privacy (DP) to adapt large language models (LLMs) for sensitive applications, offering theoretical guarantees. However, its practical effectiveness remains unclear, partly due to LLM pretraining, where overlaps and interdependencies with adaptation data can undermine privacy despite DP efforts. To analyze this issue in practice, we investigate privacy risks under DP adaptations in LLMs using state-of-the-art attacks such as robust membership inference and canary data extraction. We benchmark these risks by systematically varying the adaptation data distribution, from exact overlaps with pretraining data, through in-distribution (IID) cases, to entirely out-of-distribution (OOD) examples. Additionally, we evaluate how different adaptation methods and different privacy regimes impact the vulnerability. Our results show that distribution shifts strongly influence privacy vulnerability: the closer the adaptation data is to the pretraining distribution, the higher the practical privacy risk at the same theoretical guarantee, even without direct data overlap. We find that parameter-efficient fine-tuning methods, such as LoRA, achieve the highest empirical privacy protection for OOD data. Our benchmark identifies key factors for achieving practical privacy in DP LLM adaptation, providing actionable insights for deploying customized models in sensitive settings. Looking forward, we propose a structured framework for holistic privacy assessment beyond adaptation privacy, to identify and evaluate risks across the full pretrain-adapt pipeline of LLMs. --- ### vesselFM-CT: Segmenting All Blood Vessels in CT Images for System-Level Cardiovascular Analysis Authors: Bastian Wittmann, Chinmay Prabhakar, Suprosanna Shit, Bjoern Menze Published: 2026-06-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.09400v1 The vascular network in the human body is characterized by blood vessels exhibiting drastic structural variations in radius, length, topological properties, and branching patterns. This heterogeneity, together with location-specific anatomical background variations, poses a significant challenge for robust, large-scale analysis of the entire cardiovascular system. As a result, most research has focused on narrow, isolated segments of the vascular network. While such targeted studies provide valuable insights, they inherently limit the ability to assess the systemic health and functional integrity of the vascular network as a whole. In this work, we aim to bridge this gap to advance both clinical diagnostics and our fundamental understanding of vascular physiology. We propose the task of segmenting all vessels in CT images, ranging from the largest components of the cardiovascular system to even minuscule mesenteric vessels. To this end, we introduce vesselFM-CT, the first model capable of robustly segmenting all blood vessels in 3D CT images. VesselFM-CT is trained via an iterative, multi-step process and optimizes our proposed TubeLoss loss function, effectively addressing the inherent heterogeneity of the cardiovascular system. We demonstrate that vesselFM-CT outperforms all baselines and enables automated, precise extraction of the cardiovascular system from CT images, thereby unlocking a wide range of clinical and technical perspectives, including automated disease classification and synthetic CT image generation. --- ### RunAgent SuperBrowser: A Theory of Autonomous Web Navigation Grounded in Human Browsing Behaviour Authors: Radeen Mostafa, Sawradip Saha Published: 2026-06-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.09399v1 We present SUPERBROWSER, an autonomous web-navigation agent designed against a single guiding hypothesis: a web agent should browse the way a person browses. A human reading a page does not retain every pixel they have seen; they look at a few candidate targets, decide on one, and remember only what is needed to keep the goal alive. We operationalize this perception-cognition-action triad as three coupled mechanisms. First, a vision-first bounding-box pipeline labels candidate interactive regions on every screenshot and feeds them, asynchronously prefetched, to the language model so that the "eye" precedes the "hand". Second, a three-role brain -- an Orchestrator that classifies and routes, a Planner that evaluates progress every few steps, and a Worker that emits per-step actions -- separates strategic from operational reasoning. Third, a structured Ledger stores only what a person would: the goal, the last three actions, a small set of facts and dead-ends, and a handful of checkpoints; a six-phase eviction loop systematically discards stale screenshots, state blobs, and reasoning traces from the live context. Action execution is a three-tier click cascade (Chrome DevTools Protocol to Puppeteer to scripted) with humanized Bezier motion, plus a chevron-aware bounding-box snapper that resolves the "small arrow beside a large label" ambiguity. On the Mind2Web Hard benchmark (66 tasks), SUPERBROWSER attains 89.47% success, placing third overall and ahead of every published open/research browser-agent baseline by a large margin. We argue that the gain comes not from any single trick but from the consistent application of a cognitive contract throughout the system. --- ### PriFT: Prior-Support Guided Supervised Fine-Tuning Authors: Ke Wang, Shuangqi Li, Mathieu Salzmann, Pascal Frossard Published: 2026-06-08 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.09396v1 Supervised fine-tuning (SFT) is an efficient approach for downstream task adaptation and often serves as the initialization stage for reinforcement learning (RL), but it can show weaker generalization than RL. A key limitation is its off-policy objective: SFT fits fixed demonstrations token by token, including targets poorly aligned with the model's pretrained distribution, which can lead to overfitting. A recent line of work addresses this issue by assigning larger training weights to tokens better aligned with the current model's predictive distribution, with the intuition that fitting these tokens are less distortive to the model's pretrained knowledge and representations. However, computing the token weights from the model that is currently fine-tuned entangles token weights with the optimization trajectory, inducing a self-reinforcing dynamics as the distribution rapidly departs from the pretrained model. To address this, we propose PriFT (Prior-support guided Fine-Tuning), which derives token weights from a frozen pretrained reference to obtain a stable reweighting signal unaffected by fine-tuning. This signal estimates prior support: the extent to which each target token is supported by the pretrained distribution. Across multiple existing token-reweighting rules, replacing the reweighting signal from the online model to pretrained model consistently improves performance. We introduce two instantiations: PriFT-prob uses pretrained token probability, while PriFT-mass selects tokens by cumulative probability mass under the pretrained distribution. Extensive experiments on mathematical reasoning, code generation, and medical question answering show that PriFT achieves state-of-the-art results among SFT baselines and provides a better initialization for subsequent RL training. --- ### CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video Captioning Authors: Penghui Yang, Long Xing, Xiaoyi Dong, Yuhang Zang, Yuhang Cao, Yibin Wang, Yujie Zhou, Jiazi Bu, Jianze Liang, Qidong Huang, Jiaqi Wang, Feng Wu et al. Published: 2026-06-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.09393v1 Image and video captioning are fundamental tasks that bridge the visual and linguistic domains, playing a critical role in pre-training Large Vision-Language Models (LVLMs). Current state-of-the-art captioning models are typically trained with Supervised Fine-Tuning (SFT), a paradigm that relies on expensive, non-scalable annotations and often causes models to memorize specific ground-truth answers, limiting their generality and ability to generate diverse, creative descriptions. To overcome these limitations, we propose applying Reinforcement Learning with Verifiable Rewards (RLVR) to the open-ended task of multimodal captioning. We introduce Captioning Reinforcement Learning++ (CapRL++), a novel reference-free training framework that redefines caption quality through its utility: a high-quality caption should enable a non-visual language model to accurately answer questions about the corresponding visual content. CapRL++ employs a decoupled two-stage pipeline where an LVLM generates a caption, and the objective reward is derived from the accuracy of a separate, vision-free LLM answering Multiple-Choice Questions based solely on that caption. Evaluations on more than 20 image and video benchmarks show that CapRL++ improves dense caption quality and strengthens caption-based pretraining across tasks such as spatial and temporal understanding. Pretraining on scalable image and video caption datasets annotated by CapRL++ yields substantial downstream gains. Furthermore, within the Prism Framework for caption quality evaluation, compact models trained with CapRL++ achieve dense captioning performance comparable to substantially larger models such as Qwen2.5-VL-72B and Qwen3-VL-235B-A22B. These results validate that CapRL++ effectively trains models to produce generalizable, high-fidelity descriptions, establishing a robust foundation beyond the limitations of traditional SFT. --- ### From Coarse to Fine: Managing Temporal Granularity in Spatio-Temporal Data for Fine-Grained Traffic Prediction Authors: Shuhao Li, Weidong Yang, Yue Cui, Zizhuo Xu, Lipeng Ma, Fan Zhang, Xiaofang Zhou Published: 2026-06-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.09392v1 Efficient acquisition, storage, and utilization of traffic data are critical challenges in spatio-temporal data management. Most traffic data systems collect and store observations at fixed, coarse-grained temporal intervals to reduce storage and computation costs. However, such coarse-grained data severely limits downstream applications that require predictions at a finer temporal granularity. Collecting and maintaining fine-grained traffic data across all locations and time periods would impose a substantial burden on database storage and preprocessing pipelines. To address this temporal granularity mismatch, we formulate a novel problem: predicting fine-grained future traffic using coarse-grained sampled data. We propose the Spatial-Temporal Refinement Predictor (STRP), a granularity-aware framework for spatio-temporal data systems. STRP integrates two components: Tree Convolution for efficient and interpretable spatial dependency modeling, and Inverse Dilated Convolution for progressive temporal extrapolation. STRP supports two practical prediction settings: window-based and duration-based, to handle different forms of granularity mismatch. Experiments on six benchmark datasets show that STRP significantly outperforms state-of-the-art baselines in both accuracy and efficiency. Our work offers a practical and interpretable approach to managing granularity mismatches in spatio-temporal traffic data systems. --- ### Real-time body pose non-verbal communication with a consistency-based reliability measure Authors: Alina Marcu, Dragos Costea, Cristina Lazar, Marius Leordeanu Published: 2026-06-08 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2606.09390v1 Body movement communicates intent at distances and in conditions where neither the face, nor speech can be captured. We study the recognition of communicative intent from 2D body pose alone. We argue that body motion is a reliable signal especially in scenarios that require real time low-cost on-device person-to-robot communication in long distance environments, such as rescue missions. However, existing resources do not isolate this signal. Affective corpora combine body, face, voice and text, while skeleton action-recognition benchmarks label the action performed rather than the message conveyed. We release a dataset of real frames of full-body pose covering ten communicative intents and we compare it against other real (IPC) and synthetic (MotionLCM, VEO3.1, Kimodo) ones that span a range of difficulty. We target systems that can run on a robot's limited onboard hardware. We benchmark multiple models, from skeleton graph classifiers to joint motion-forecasting networks, and report performance metrics together with frame rate on an embedded GPU (NVIDIA Orin~Nano), since speed matters as much as accuracy in our scenario. Finally, we show that a model's own autoregressive self-consistency works as an unsupervised reliability signal. We give a short proof that bounds the probability that a self-consistent prediction is correct, show that this probability grows with the number of consistent steps, and identify the conditions under which a confident prediction can still be false, benchmarked against industry-standard metrics. --- ### LexRubric: A Rubric-Guided Diagnostic Benchmark for Open-Ended Legal Tasks Authors: Yifan Chen, Haitao Li, Yiran Hu, Kaisong Song, Jun Lin, Yueyue Wu, Qingyao Ai, Min Zhang, Yiqun Liu Published: 2026-06-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.09389v2 As large language models (LLMs) are increasingly applied to real-world legal tasks, evaluating the reliability of their open-ended legal responses has become essential. These tasks require context-sensitive answers and allow little room for error, motivating fine-grained and diagnostic evaluation that can identify specific sources of response quality failures. We introduce LexRubric, a rubric-based benchmark for evaluating open-ended Chinese legal tasks. LexRubric contains 649 instances from legal consultation and judicial examination, which reflect both everyday legal needs and professional legal reasoning and cover 14 legal scenarios. It further includes 12,337 expert-written atomic scoring criteria organized under a unified six-dimensional framework, enabling accurate evaluation and diagnostic analysis across tasks and evaluation dimensions. To validate the reliability of the evaluation, we test multiple judge models and compare model-based judgments with human judgments. We further evaluate 18 recent general and legal-domain LLMs on LexRubric. Results show that different models exhibit distinct capability profiles, and that open-ended legal tasks remain challenging for current LLMs. Data is available at: https://github.com/foggpoy/LexRubric. --- ### LexRubric: A Rubric-Guided Diagnostic Benchmark for Open-Ended Legal Tasks Authors: Yifan Chen, Haitao Li, Yiran Hu, Kaisong Song, Jun Lin, Yueyue Wu, Qingyao Ai, Min Zhang, Yiqun Liu Published: 2026-06-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.09389v1 As large language models (LLMs) are increasingly applied to real-world legal tasks, evaluating the reliability of their open-ended legal responses has become essential. These tasks require context-sensitive answers and allow little room for error, motivating fine-grained and diagnostic evaluation that can identify specific sources of response quality failures. We introduce LexRubric, a rubric-based benchmark for evaluating open-ended Chinese legal tasks. LexRubric contains 649 instances from legal consultation and judicial examination, which reflect both everyday legal needs and professional legal reasoning and cover 14 legal scenarios. It further includes 12,337 expert-written atomic scoring criteria organized under a unified six-dimensional framework, enabling accurate evaluation and diagnostic analysis across tasks and evaluation dimensions. To validate the reliability of the evaluation, we test multiple judge models and compare model-based judgments with human judgments. We further evaluate 18 recent general and legal-domain LLMs on LexRubric. Results show that different models exhibit distinct capability profiles, and that open-ended legal question remains challenging for current LLMs. Data is available at: https://github.com/foggpoy/LexRubric. --- ### Distilling Safe LLM Systems via Soft Prompts for On Device Settings Authors: Motasem Alfarra, Cristina Pinneri, Dana Kianfar, Mohammed Almousa, Christos Louizos Published: 2026-06-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.09388v1 Deploying safe large language models (LLMs) on resource-constrained edge devices presents a critical challenge: while dual-model systems combining LLMs with guard models provide effective safety guarantees, their substantial memory and computational demands make them prohibitively expensive for on-device deployment. This paper presents a comprehensive study of parameter-efficient safety alignment methods for resource-constrained settings. Through systematic evaluation across multiple LLM architectures, training objectives, and parameter-efficient fine-tuning approaches, we identify that soft prompts combined with distillation-based training consistently outperform alternative methods. We introduce distillation frameworks based on total variation and KL divergence that effectively transfer safety behaviors from guard models into learned soft prompts. Our evaluations on various benchmarks demonstrate that this combination achieves superior safety-usefulness trade-offs compared to LoRA adapters, steering vectors, and direct optimization methods, while requiring minimal additional memory and compute at inference time. These findings establish soft prompt distillation as the preferred approach for safety alignment in on-device LLM deployment. --- ### An Opticalmechanics Framework for Dynamic Estimation of Multibody Systems Authors: Banglei Guan, Xuanyu Bai, Qingquan Chen, Zibin Liu, Dongcai Tan, Zhenbao Yu, Yang Shang, Qifeng Yu Published: 2026-06-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.09383v1 Conventional dynamics analysis of the human body is often constrained by the need for contact force and torque sensors and controlled laboratory environments. To address this issue, this study proposes an opticalmechanics kinematic-dynamic integrated estimation framework for multibody systems. Specifically, a constrained multibody model is established to describe the system dynamics, while image-measured kinematic quantities are used as non contact inputs for dynamic estimation. The unknown joint torque is then identified through a genetic-algorithm based optimization by minimizing the discrepancy between model-predicted and image-measured kinematic quan tities. Experimental validation on an air-bearing platform showed that the wrist joint torque estimated from image data achieved a mean absolute error of 0.46 Nm compared with sensor measurements. In the forward prediction test, the model-predicted angular velocity achieved a mean absolute error of 0.006 rad/s relative to the image-measured results. This study demonstrates the potential of combining image measurement and mechanical modeling for non-contact dynamic estimation in scenarios where direct force and torque measurement is difficult. --- ### Reasoning Arena: Trace Tournaments When Verifiable Rewards Fall Short Authors: Han Zhou, Adam X. Yang, Laurence Aitchison, Anna Korhonen, Albert Q. Jiang Published: 2026-06-08 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.09380v1 Reinforcement learning with verifiable rewards (RLVR) has become a leading paradigm for improving the reasoning ability of large language models through outcome-based supervision. However, verifiable rewards frequently become uninformative at the group level: when all sampled traces of a given prompt receive identical rewards, group-relative advantage estimation provides no gradient signal, even though the traces may differ substantially in reasoning quality. We propose Reasoning Arena, an adaptive training framework that routes such non-diverse reward groups to a judge system instead of discarding them. Beyond examining the final answer, Reasoning Arena constructs trace tournaments, where reasoning traces are compared head-to-head to expose finer-grained preferences within the group, converting reasoning quality into rich relative reward signals. To make reward estimation efficient, rather than exhaustively comparing every pair, each new trace is evaluated against a small, dynamically updated pool of previously generated traces as anchors to efficiently establish a relative ranking. We then fit a Bradley-Terry model on the incomplete comparison graph, enabling scalable RL integration without quadratic pairwise comparisons. Empirical results demonstrate that Reasoning Arena consistently outperforms the RLVR baseline by 7.6% on average in competition mathematics and coding benchmarks. By converting otherwise wasted zero-advantage samples into useful gradient updates, our method accelerates training by 27% to 41%, saving nearly 50% of generation compute, and substantially improves overall reasoning performance. --- ### Echo-DM: Ultrasound Marker Removal via Conditional Latent Diffusion and Region-Aware Fusion Authors: Zhiwei Wang, Tao Huang, Wentao Jiang, Muyi Li, Jianxin Liu, Jian Chen, Jie Zou, Yong Luo, Bo Du, Jing Zhang Published: 2026-06-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.09378v1 Clinical ultrasound images often contain artificial markers, such as measurement calipers and text, to assist diagnostic interpretation and comparison. However, these markers can introduce shortcut bias in downstream automated analysis, encouraging deep learning models to rely on marker-related cues rather than clinically meaningful anatomy. Existing marker removal methods are either mask-dependent and vulnerable to error propagation, or mask-free deterministic restorers that may over-smooth ultrasound texture and perturb unaffected background regions. To address these challenges, we present Echo-DM, a framework for ultrasound marker removal via conditional latent diffusion and region-aware fusion. Echo-DM follows a common encoder-diffusion-decoder pipeline, where a DiT-based conditional latent diffusion network performs global restoration and a region-aware fusion module enforces preservation-aware image-space refinement under end-to-end mask-free inference. Building on this fixed core design, we further instantiate Echo-DM-V and Echo-DM-R with VAE-based and RAE-based latent modules, respectively, which demonstrates that the Echo-DM architecture is compatible with diverse latent-module instantiations. Extensive experiments on Echo-PAIR, a large-scale paired clinical ultrasound dataset, demonstrate superior marker removal and strong anatomical fidelity compared with representative two-stage baselines, while providing favorable quality--efficiency trade-offs across deployment settings. Data, code and models will be released at https://github.com/MiliLab/Echo-DM. --- ### Scaling Neural Network Verification with Tensor Parallelism and Fully Sharded Data Parallelism Authors: Sergei Vorobyov, Eugene Ilyushin Published: 2026-06-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.09377v2 Formal neural network verification -- proving that a network satisfies safety properties for *all* inputs in a specified domain -- is bounded in practice by GPU memory: standard implementations of bound-propagation algorithms (IBP, CROWN, $α$-CROWN) require weight and relaxation-coefficient matrices to reside entirely on one accelerator. We adapt two parallelism techniques originally developed for large-scale model training to the auto_LiRPA / $α,β$-CROWN verification framework. Tensor Parallelism (TP) shards both weight and $A$-matrices across GPUs, achieving ${\approx}2\times$ peak-memory reduction at $P{=}2$; soundness is confirmed on VNN-COMP 2022 MNIST-FC benchmarks, though bound tightness degrades with the number of sharded zones due to forced IBP substitution for intermediate bounds inside sharded zones. Fully Sharded Data Parallelism (FSDP) shards only weight matrices with a per-layer AllGather, producing bounds that are bitwise identical to the single-GPU baseline: baseline memory drops by 80--90%, peak memory by 34--39% on wide MLPs. FSDP integrates cleanly with complete verification ($β$-CROWN + Branch-and-Bound) and with convolutional layers (BoundConv); a complete unsat result is obtained for CIFAR-100 ResNet-large (VNN-COMP 2024) under FSDP. Across all experiments the memory bottleneck in $α$-CROWN+BaB mode proves to be per-neuron alpha tensors, not weight matrices, pointing to the key direction for future work. --- ### Precision Is Not Faithfulness: Coverage-Aware Evaluation of Grounded Generation with a Complete Oracle Authors: Juan S. Santillana Published: 2026-06-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.09376v2 Reference-free faithfulness metrics verify each atomic claim a model makes against ground truth, and are increasingly used to evaluate grounded generation. We show they share a blind spot: they measure only precision -- are the stated claims supported? -- and therefore reward abstention, since a model can score near-perfect faithfulness by saying almost nothing. We make this measurable using Formula 1 telemetry, a domain where strategic ground truth is derived deterministically and, crucially, completely: for each decision we know the full set of facts that mattered. This completeness -- absent in open-domain faithfulness benchmarks -- lets us measure recall (coverage of the relevant facts) exactly, alongside precision. On a multilingual (EN/ES/PT) benchmark of 7,253 decision instances spanning 157 races, the most precise frontier model covers under half of the relevant facts and ranks last by F1, so requiring coverage reorders the systems; the same effect reappears in a second complete-oracle domain (NOAA weather forecasts). Fine-tuning small models (1B-7B) on the complete oracle closes the precision-recall gap entirely (F1 ~0.98), beating every zero-shot frontier system regardless of scale. We pair faithfulness with coverage into a single score, validate the metric (controlled perturbation; agreement across a model-free regex extractor and a cross-family LLM extractor, system-level Spearman 1.0), and give a verifier-guided generation method that improves precision and recall without references. We release the benchmark, structured annotations, metric, baselines, and an interactive demo. --- ### Capability-Aligned Hierarchical Learning for Tool-Augmented LLMs Authors: Haotong Yang, Ting Long, Yi Chang Published: 2026-06-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.09371v1 Tool learning enables LLMs to invoke external tools to accomplish tasks. Prior studies have demonstrated the effectiveness of a hierarchical structure: a high-level policy handles global planning and decomposes tasks into manageable sub-tasks, and a low-level policy focuses on invoking tools to solve these sub-tasks. However, these works typically optimize the high-level and low-level policies separately, leading to planner-executor misalignment and limiting LLM performance on tool-use tasks. In this paper, we propose a method called Capability-Aligned Hierarchical Learning (CAHL), which leverages RLVR to jointly optimize both policies, enabling better alignment between the high-level planner and the low-level executor. Experiments on constrained tool-use benchmarks (API-Bank and BFCL) and an open-ended environment (Bamboogle) demonstrate the effectiveness of CAHL. --- ### PhysScene: A Scene Graph Dataset for Scientific Visual Reasoning in Physics Experiments Authors: Minghao Zou, Qingtian Zeng, Shangkun Liu, Yanda Meng, Guanghui Yue, Baoquan Zhao, Abdulmotaleb El Saddik, Wei Zhou Published: 2026-06-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.09368v2 Scene Graphs (SGs) provide structured representations of visual scenes by modeling objects and their pairwise relationships. Despite recent progress, existing datasets primarily focus on generic natural contexts, leaving domain-specific and function-oriented scenes largely underexplored. This limitation restricts the evaluation of relational reasoning in scientific experimental scenes, thereby hindering the development of intelligent monitoring, analysis, and related applications in such scenes. To address this gap, we introduce PhysScene, the first SG dataset tailored to physics experiments. PhysScene encompasses specialized instruments, structured experimental setups, and functional relations intrinsic to experimental environments, enabling reasoning that extends beyond spatial co-occurrence to logical dependencies. Rather than pursuing large data scale, PhysScene focuses on strong semantic constraints and high relation density in experimental scenes, posing new challenges for existing scene parsing algorithms while offering opportunities for further improvements. Extensive analyses and experiments show that PhysScene complements existing benchmarks and establishes a valuable testbed for advancing scientific visual reasoning. The dataset is publicly available at https://github.com/ZMH-SDUST/PhysScene. --- ### RT-SDGOD: Real-Time Single-Domain Generalized Object Detection Authors: Yupeng Zhang, Fangzhuo Gao, Ruize Han, Wei Feng, Liang Wan Published: 2026-06-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.09367v1 In real-world deployment under strict real-time constraints, weather and imaging variations induce significant distribution shifts, severely degrading detectors. Single-Domain Generalized Object Detection aims to mitigate this issue, yet existing methods rarely investigate-at the level of problem formulation-the generalization capability of real-time detectors under such constrained inference budgets. To this end, we introduce Real-Time Single-Domain Generalized Object Detection (RT-SDGOD), which focuses on how real-time detectors can achieve cross-domain generalization under zero extra inference overhead by relying solely on training-time representation learning. We observe that, under domain shift, DETR-based real-time detectors mainly degrade through increased missed detections, rooted in limited and unstable object-level discriminative evidence. Based on this, we propose RT-SDGDet, a multi-evidence collaborative modeling framework for RT-SDGOD. The core idea is to enable multiple queries of the same object to collaboratively cover more sufficient discriminative evidence while maintaining the stability of such evidence modeling across views. Specifically, we use one-to-many (O2M) supervision to construct stable object-specific query groups, and further design Discriminative Evidence Diversity Learning (DEDL) and Dual-view Evidence Consistency Learning (DvECL) to expand object-level evidence coverage and improve evidence stability under appearance perturbations, respectively. Since all components are introduced only during training, our method incurs no extra inference overhead. Extensive experiments show that the proposed method achieves better generalization performance than existing approaches across multiple unseen target domains. --- ### Is Text All You Need? Text as a Universal Information Bottleneck for Speech LLMs Authors: Ming-Hao Hsu, Yuxuan Hu, Shujie Liu, Jinyu Li, Yan Lu, Zhizheng Wu Published: 2026-06-08 Categories: cs.CL, eess.AS arXiv: https://arxiv.org/abs/2606.09366v1 Large language models (LLMs) provide a powerful reasoning backbone for speech understanding, but integrating continuous acoustic signals into a frozen LLM remains challenging. Existing speech-to-LLM interfaces typically operate at two extremes: either enforcing near-discrete token alignment, which benefits transcription but loses paralinguistic information, or learning unconstrained continuous representations, which can drift away from the LLM's input space and degrade autoregressive decoding. In this work, we propose Convex Gate (C-Gate), a speech-to-LLM bridge that constrains all speech representations to lie within the LLM's input embedding manifold with an architectural convex-hull constraint. Concretely, each frame is represented as a convex combination of token embeddings, ensuring compatibility with the pretrained LLM while preserving continuous expressivity. Across automatic speech recognition (ASR) and emotion recognition, C-Gate achieves strong joint performance, improving LibriSpeech WER by up to 48.7% relative while matching or exceeding single-task emotion accuracy. Beyond performance, our analysis reveals a key insight: information is not carried by discrete token identities, but by time-resolved trajectories in the embedding space. Causal interventions confirm that both the trajectory structure and alignment to the pretrained embedding manifold are critical for performance. These results suggest that geometry, rather than token discreteness, is the fundamental design factor in speech-to-LLM interfaces, and provide a controlled regime for studying multimodal integration in frozen LLMs. We release the checkpoint, per-sample outputs, mechanism dumps, and intervention suite for replication. --- ### Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory Authors: Haoran Sun, Wenjie Li, Yujie Zhang, Zekai Lin, Fanrui Zhang, Kaitao Chen, Xingqi He, Yichen Li, Mianxin Liu, Lei Liu, Yankai Jiang Published: 2026-06-08 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.09365v3 Medical agent systems are increasingly expected to support interactive clinical decision making rather than only static question answering. In such settings, effective agents must reuse prior experience across evolving cases, yet existing memory mechanisms often retain raw historical traces that are redundant, noisy, and difficult to govern. More importantly, they rarely distinguish which memories are truly useful for future reasoning. This limits their ability to accumulate compact and reliable experience for long-horizon clinical reasoning. To close this gap, we propose SkeMex, a post-deployment self-evolution framework that improves medical agents through a skill-based memory without updating model weights. SkeMex distills informative interaction trajectories into structured skills that encode reusable procedural knowledge, and organizes them into a multi-branch repository spanning general, task-specific, and action-level experience. To determine which memories should be reused and retained, SkeMex estimates context-dependent utility from environment feedback and uses it to guide value-aware retrieval and repository governance. A closed-loop ``Read--Write--Assess--Govern" lifecycle further supports continual evolution by writing new skills, updating utilities, promoting useful memories, and removing harmful entries. Experiments across diverse clinical tasks show that SkeMex consistently outperforms representative memory-based agents in both offline and online settings. It also generalizes across model backbones and supports transferable skill memory. All data and code will be released publicly. --- ### Zero-Shot Semantic Re-Identification for Autonomous Driving: A VLM Baseline Study Authors: Eduardo Borges, Manuel Abreu, Luís Garrote, Urbano J. Nunes Published: 2026-06-08 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2606.09362v1 Re-Identification (ReID) in autonomous driving is typically formulated as a visual matching problem, where observations of vehicles, pedestrians, and cyclists are associated across time, frames, or camera views using learned appearance embeddings, often complemented by motion, geometric, or multimodal cues. However, purely visual representations may be sensitive to viewpoint, occlusion, illumination, and sensor-domain variations, limiting their interpretability and robustness in complex driving scenes. We propose a baseline study of a zero-shot pipeline using Vision-Language Models (VLMs) to generate textual descriptions of detected traffic participants and evaluate whether these descriptions can support identity matching across observations. Instead of relying only on low-level visual similarity, the proposed formulation represents each object through structured semantic attributes, including category, color, shape, pose, visible parts, spatial context, and distinctive visual cues. This study provides an initial benchmark for language-based re-identification in autonomous-driving scenarios, discussing and evaluating the strengths and limitations of current VLMs for this task. Results demonstrate that zero-shot semantic descriptions can support effective object re-identification, achieving retrieval performance comparable to a supervised CNN baseline while offering greater interpretability through explicit identity cues. However, the experiments also reveal important challenges, including attribute inconsistency across viewpoints and limited fine-grained discrimination between visually similar instances. --- ### ExDet: Open-Domain Open-Vocabulary Detection with Cross-modal Extrapolation and Rectification Authors: Yupeng Zhang, Yuzhong Feng, Ruize Han, Zhiwei Chen, Wei Feng, Liang Wan Published: 2026-06-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.09360v1 Open-domain open-vocabulary detection (ODOVD) requires detectors to generalize to both novel categories and unseen domains, making it more challenging than open-vocabulary detection. Existing methods typically train open-vocabulary detectors together with domain generalization modules from scratch, leading to high training cost. we propose ExDet, a lightweight category-domain collaborative generalization framework for ODOVD that enhances the cross-category and cross-domain generalization of existing detectors. ExDet consists of Text-Guided Extrapolation (TGE), a lightweight Detector-Compatible Rectification (DCR) module, and ExRPN. Specifically, TGE exploits the DeltaSpace property of vision-language models (VLMs) to infer category- and domain-aware proxy visual prototypes from text. DCR is learned from the TGE-generated prototypes in a detector training-free and real-data-free manner, and is inserted after the classification head at inference to rectify representations toward a detector-compatible source-domain visual distribution, thereby enhancing classification for targets from novel categories and unseen domains. ExRPN recalibrates proposal scores by combining semantic similarity with RPN confidence, improving recall for novel and domain-shifted objects while providing better support for subsequent classification and DCR. ExDet achieves SOTA performance on OD-LVIS, OV-LVIS, Objects365, and MSOSB. --- ### Beyond Humans: Multispecies Animal Face Recognition Using Transfer Learning Authors: Maria De Marsico, Anil K. Jain, Annalaura Miglino Published: 2026-06-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.09353v1 Individual animal recognition can be useful in the search for lost or stolen pets, the tracking of individuals of endangered species, and the recognition of animals in crowded farms. Present recognition techniques mostly use physical devices, e.g., microchips, often impractical and difficult to apply. These could be replaced by remote recognition via the animal's face; if accurate enough, it provides several advantages: it is non-invasive, can work at a distance, and is difficult to counterfeit, as, for instance, in the case of substituting sick animals for healthy ones in the food industry. The few existing datasets with sufficient per-subject images annotated with a single animal identity are not large enough to train current deep learning architectures. We rather investigate the possibility of transfer learning, exploiting pre-trained network models as backbones. Our experiments compared FaceNet, which is specifically trained on large databases of human faces, with the Vision Transformer (ViT) pre-trained on ImageNet, i.e., on object categories. We used three face datasets of very different animals: dogs, primates (lemurs, golden monkeys, and chimpanzees), and cattle. We report the results and, for each dataset, compare them with the state of the art (SOTA) ad hoc-trained deep networks. The capture conditions differ among the three datasets. Image quality (resolution, motion blur, diverse poses, etc.) decreases from dogs to cattle to primates. The best performance was achieved with dogs, where ViT reached a mean verification accuracy of 96.85% and a Rank-1 Identification Rate of 84.34%. The results for endangered primates are still encouraging, but performance varies across animal classes and tasks (verification or identification), and does not always outperform SOTA. For cattle, the ViT results outperform SOTA, while FaceNet is still competitive. --- ### In-Context Learning for the Imputation of Public Opinion Data with Large Language Models Authors: Tobias Holtdirk, Georg Ahnert, Joseph W Sakshaug, Anna-Carolina Haensch Published: 2026-06-08 Categories: cs.CL, stat.ME arXiv: https://arxiv.org/abs/2606.09351v1 Large language models have been widely evaluated as simulators of individual survey responses. In practice, however, fully unobserved responses are rare; the dominant problem is partial non-response. Imputation aims to restore the overall structure of a survey dataset by filling in these missing values. It has its own well-defined evaluation criteria and differs fundamentally from prediction. We propose to impute missing survey data through in-context learning (ICL). We systematically evaluate ICL design choices across different missingness mechanisms (MCAR, MAR, MNAR) on 150 opinion variables spanning 15 waves of the American Trends Panel. Compared to well-established statistical methods for data imputation like MICE PMM, our ICL approach consistently reduces absolute error across all missingness mechanisms, with the largest gains under non-random missingness (MNAR). Notably, the best-performing specification (gpt-oss-120b with 100 in-context examples) achieves near-nominal aggregate coverage (approaching the 95% level) with confidence intervals two to five times narrower than MICE PMM. We publish a Python package with an sklearn-like API to enable easy deployment of our method using local and proprietary LLMs. --- ### Taming Perception Jitter: Uncertainty-Aware LiDAR Object Detection for Reliable Motion Classification Authors: Cornelius Schröder, Žygimantas Marcinkus, Markus Lienkamp Published: 2026-06-08 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2606.09350v1 Reliable motion classification is critical for autonomous driving, as false dynamic predictions of static objects can cascade into unnecessary planner interventions. Unstable bounding box predictions can lead to spurious velocity estimates in tracking and falsely predicted trajectories. We present a deployment-friendly mitigation strategy that augments a 3D object detector with aleatoric uncertainty estimates and applies a two-sample z-test over short observation windows to separate true motion from jitter. Integrated into Autoware with minimal changes, the approach reuses existing data association for minimal compute overhead. Empirical results show parity with velocity thresholding on nuScenes, but substantially fewer false dynamic predictions and unnecessary stops in real-world test drives, explained by the presence of an intermediate jitter band in the recorded data that speed-only rules misclassify. This demonstrates that uncertainty-aware detection and lightweight statistical testing can deliver practical performance gains for autonomous driving in noisier real-world settings. --- ### PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment Authors: Yang Tian, Rui Wang, Xumeng Wen, Junjie Li, Shizhao Sun, Lei Song, Jiang Bian, Bo Zhao Published: 2026-06-08 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2606.09348v2 Long-horizon agentic tasks pose a fundamental credit assignment challenge for outcome-base reinforcement learning: trajectory-level rewards verify final correctness but provide limited guidance on which intermediate reasoning steps or tool interactions contribute to the outcome. The difficulty is especially pronounced in multi-turn search agents, where successful trajectories may contain misleading actions and failed trajectories may contain valuable evidence-gathering steps. We propose PBSD (Privileged Bayesian Self-Distillation), a Bayes-calibrated self-distillation method for fine-grained credit assignment under sparse final rewards. PBSD measures trajectory quality through the posterior-to-prior probability ratio of the verified answer and applies Bayes' rule to convert this hard-to-estimate answer-side ratio into a tractable likelihood ratio between a standard student model and a privileged answer-conditioned teacher model. Autoregressive decomposition of this Bayesian evidence score yields turn-level signals that identify whether each intermediate turn supports or undermines the verified outcome. Consequently, PBSD provides a principled and elegant reweighting scheme that transforms sparse outcome supervision into Bayes-calibrated turn-level credit signals, while remaining fully compatible with standard policy optimization. Experiments demonstrate that PBSD consistently enhances performance across both in-domain and out-of-domain settings, and effectively transfers knowledge from short-context training to long-context inference, suggesting that its fine-grained credit assignment mechanism facilitates more effective policy learning and yields improved generalization. --- ### IB-HFN: Information Bottleneck-Driven SAR-Optical Fusion Network for High-Fidelity Cloud Removal Authors: Haojun Guo, Fan Feng, Ziquan Wang, Yongsheng Zhang, Ying Yu Published: 2026-06-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.09347v2 Synthetic aperture radar (SAR)-assisted optical cloud removal aims to recover surface information obscured by clouds in optical remote sensing images by exploiting complementary SAR observations. Existing multimodal fusion methods typically rely on direct spatial concatenation and pixel-wise supervision, which can propagate SAR speckle noise into optical reconstruction and lead to over-smoothed results. To address these limitations, we propose an Information Bottleneck-driven High-Fidelity Network (IB-HFN) for SAR-assisted optical cloud removal. IB-HFN employs a dual-stream backbone to preserve modality-specific representations before deep semantic fusion, thereby mitigating premature cross-modal contamination. At the fusion stage, we introduce a Spatial Information Bottleneck Fusion module that compresses SAR features through a channel-wise variational information bottleneck to suppress unstructured speckle noise. In parallel, a local-global gating mechanism predicts clear-sky regions and routes reliable optical details through a Dirac-initialized skip connection, decoupling noise suppression from texture preservation. We further develop a joint optimization strategy that integrates feature-level bottleneck regularization with image-level constraints on reconstruction accuracy, structural consistency, spectral fidelity, and contrastive sharpness. A dynamic weighting schedule balances these objectives to stabilize training and reduce hazy artifacts. Experiments on the SEN12MS-CR dataset under challenging spatio-temporal splits demonstrate that IB-HFN achieves superior structural preservation and spectral fidelity over existing methods. --- ### Leveraging Structural Constraints for Diffusion-based Neural TSP Solvers Authors: Mickaël Basson, Philippe Preux Published: 2026-06-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.09343v1 Neural combinatorial optimization has recently achieved strong results on the Euclidean Traveling Salesman Problem (TSP) using generative models such as diffusion and consistency models. State-ofthe-art approaches like FT2T combine fast consistency-based prediction with gradient-based inference time refinement. However, gradient search often incurs significant computational overhead and may not align with the discrete structure of feasible solutions. We introduce Projected Consistency Inference (PCI), a plug-and-play, retraining-free alternative that replaces gradient refinement with structure-aware projections: PCI decodes valid Hamiltonian tours from the consistency model output and applies a lightweight local search (e.g., 2-opt). PCI achieves an average optimality gap (OG) of 0.17% on TSP with 500 cities, and 0.31% on TSP with 1000 cities, outperforming FT2T best settings (OG 0.22% and 0.36%, respectively) while reducing the inference time up to 30 to 40%. PCI also exhibits lower variance and memory usage, and can surpass classical heuristics such as LKH3 in rapid solution generation. Our results demonstrate that structure-aware inference time operations provide a practical and principled path for neural TSP solvers, complementing training time objectives. --- ### Thresholded Local Hyper-Flow Diffusion Authors: Meher Chaitanya, Sebastian Dalleiger, Luana Ruiz Published: 2026-06-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.09340v1 Local Hyper-Flow Diffusion (HFD) gives an edge-size-independent Cheeger-type guarantee for seeded clustering in general submodular hypergraphs, but existing HFD solvers do not keep intermediate computation local at every iteration. We introduce Thresholded Local HFD (TL-HFD), a first-order method that maintains an active region around the seeds, performs projected subgradient updates on that region and its immediate boundary, and expands via thresholded (top-k) boundary activation. We prove that the local update is exact: the degree-preconditioned projected subgradient step restricted to the active region and its boundary coincides with the unrestricted global update. We establish finite-time dual suboptimality for both exact and thresholded updates, treating the latter as inexact projected subgradient steps with explicit skipped-boundary error. We further derive an additive activated-volume bound controlled by realized local subgradient norms and the minimum boundary-push among newly activated vertices, and translate approximate dual optimality with localized support into a robust sweep-cut guarantee for early-stopped iterates. For general submodular cut-costs, each iteration is local in the scanned region and oracle-sensitive in the hyperedge primitive. Empirically, TL-HFD often matches or improves over HFD while activating less volume, with the largest gains on noisy instances where diffusion tends to absorb non-target vertices. --- ### Multi-Hop Knowledge Composition is Bound by Pretraining Exposure Authors: Yannis Karmim, Luis Marti, Djamé Seddah, Valentin Barrière Published: 2026-06-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.09338v2 Large Language Models fail at implicit multi-hop reasoning: a model answers "When was $X$ born?" and "Who is $Y$'s closest friend?" correctly but fails on "When was $Y$'s closest friend born?" in a single forward pass, even when both facts are perfectly memorized and individually retrievable. We study this failure in a controlled natural language setting with a strict separation between individuals exposed to compositional contexts during pretraining and those that never appear in any such context. We confirm that compositional failure persists even at 97% 1-hop accuracy, establishing the gap as a pretraining failure rather than a knowledge absence. We propose and test nine data-centric augmentation formats and find that compositional pretraining transfers to unseen questions for exposed individuals, but never to individuals absent from compositional pretraining, suggesting that exposure to compositional contexts during pretraining is a necessary condition for implicit multi-hop reasoning. Code is available at https://github.com/ykrmm/composition-bound . --- ### Multi-Hop Knowledge Composition is Bound by Pretraining Exposure Authors: Yannis Karmim, Luis Marti, Djamé Seddah, Valentin Barrière Published: 2026-06-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.09338v1 Large Language Models fail at implicit multi-hop reasoning: a model answers "When was $X$ born?" and "Who is $Y$'s closest friend?" correctly but fails on "When was $Y$'s closest friend born?" in a single forward pass, even when both facts are perfectly memorized and individually retrievable. We study this failure in a controlled natural language setting with a strict separation between individuals exposed to compositional contexts during pretraining and those that never appear in any such context. We confirm that compositional failure persists even at 97% 1-hop accuracy, establishing the gap as a pretraining failure rather than a knowledge absence. We propose and test nine data-centric augmentation formats and find that compositional pretraining transfers to unseen questions for exposed individuals, but never to individuals absent from compositional pretraining, suggesting that exposure to compositional contexts during pretraining is a necessary condition for implicit multi-hop reasoning. --- ### How Far Can Prompting Go for Minimal-Edit Ukrainian Grammatical Error Correction? Authors: Kateryna Karpo, Artem Chernodub Published: 2026-06-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.09334v1 Fine-tuned Large Language Models (LLMs) dominate in Ukrainian grammatical error correction (GEC), while API-accessed LLMs remain nearly untested on minimal-edit benchmarks. We evaluate 11 commercial LLMs from four providers and one open-source Ukrainian model on the UNLP 2023 GEC-only benchmark, comparing zero-shot, few-shot, minimal-edits, and LLM-assisted prompt optimization strategies. Our best configuration (Gemini 3.1-Pro) reaches F0.5=69.22, closing over 90% of the gap to fine-tuned SOTA (F0.5=73.14). For zero-shot prompts, only Claude models benefit from Ukrainian instructions. However, the best overall results for all models use Ukrainian minimal-edits prompts, whose language-specific rules require Ukrainian to express precisely. LLM-assisted prompt optimization on top of minimal-edits + few-shot achieves the highest score. Detailed minimal-edits instructions yield the largest gains for punctuation and case errors but cause the model to abandon several low-frequency categories. Delving into error analysis, we identify five recurring overcorrection patterns tied to Ukrainian-specific linguistic phenomena. Code, prompts, and outputs are publicly available. --- ### Conan-embedding-v3: Fusing Modality-Specific Models for Omni-Modal Embedding Authors: Shiyu Li, Zhiyuan Hu, Yifan Wang, Peiming Li, Zheng Wei, Yang Tang Published: 2026-06-08 Categories: cs.MM, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.09331v2 Omni-modal retrieval promises a single embedding space for text, image, video, document, and audio inputs, but building such a unified retriever is difficult since these modalities differ in data distribution, architecture, and optimization dynamics. In this work, we present Conan-embedding-v3, a decouple--fuse--recover framework for omni-modal retrieval. Conan-embedding-v3 first trains modality specialists independently and fuses their task vectors into a single dense backbone, a strategy we call Decoupled Specialist Fusion. We show that this fusion composes visual, video, and document retrieval capabilities, but also exposes a failure mode for projector-based modalities: when audio is attached through an external encoder and projector, fusing the backbone leaves the projector calibrated to the audio-specialist backbone, causing a large audio retrieval regression despite copying all audio-specific modules unchanged. We call this failure Projector Drift. To repair it, Conan-embedding-v3 applies Projector Recovery (i.e., full-parameter fine-tuning of the projector while keeping the backbone frozen) followed by balanced multi-modal rehearsal. The resulting model supports these retrieval pathways in one backbone, achieving 74.9 scores on MMEB while obtaining 55.61 on the 30-task MAEB audio suite. --- ### A Universal Dense Football Event Representation Based on TabTransformer Authors: Weiran Yang, Daniel Memmert, Maximilian Klemp-Weins Published: 2026-06-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.09327v1 Football event data constitute a rich spatiotemporal source for quantitative analysis of player actions in team sports. These datasets contain heterogeneous features, combining continuous location coordinates with categorical variables such as action type, action outcome, and body part. Such data have been applied in sports analytics for match outcome forecasting, player evaluation, and tactical pattern recognition. However, existing approaches predominantly encode categorical features using one-hot or ordinal embedding representations, overlooking the intrinsic semantics of action descriptors. The Transformer is a deep neural network architecture based on self-attention that captures dependencies between input features at arbitrary positions. We propose and implement a Transformer-based model to learn latent dependencies among categorical event features and produce dense representations of football events. By encoding categorical features as learned embedding vectors, sport-specific action semantics are captured during pretraining, enabling the representations to support downstream tasks such as action value estimation and play style recognition. Empirical evaluation shows that the embedding representations yield superior probability calibration over task-specific baselines on the downstream prediction tasks, as measured by Brier score. --- ### TRL-Bench: Standardizing Cross-Paradigm Representation-Level Evaluation of Tabular Encoders Authors: Wei Pang, Xiangru Jian, Hehan Li, Zhixuan Yu, Alex Xue, Jinyang Li, Zhengyuan Dong, Xinjian Zhao, Hao Xu, Chao Zhang, Reynold Cheng, M. Tamer Özsu et al. Published: 2026-06-08 Categories: cs.AI, cs.DB arXiv: https://arxiv.org/abs/2606.09323v1 Tabular encoders are usually evaluated inside task-specific end-to-end pipelines, so models from different training paradigms are difficult to compare directly even when they operate on similar tabular signals. We introduce TRL-Bench, a multi-granular tabular representation learning (TRL) benchmark that standardizes cross-paradigm representation-level evaluation: each encoder exports row-, column-, or table embeddings through its supported wrapper, and shared lightweight heads probe them across three suites: TRL-CTbench (column/table), TRL-Rbench (row), and TRL-DLTE (compositional Data-Lake Table Enrichment spanning all three granularities). To support this standardized setting, we release curated benchmark assets and task reformulations, including 50 OpenML tables with 123 verified targets, 16 row-pair linkage rewrites, and a 47,772-table DLTE lake derived from 1,379 parent tables. Across 20 models and 16 tasks, TRL-Bench shows that once downstream conditions are standardized, encoder quality is capability-specific rather than captured by a single leaderboard. In TRL-CTbench, generic text encoders often lead on tasks with strong surface-text signal, while tabular specialists win where their pretraining objective aligns with the task. In TRL-Rbench, within-table prediction and cross-table linkage favor different training regimes, with atomic linkage performance correlating strongly with the row-matching stage of DLTE pipelines. In TRL-DLTE, the strongest pipelines combine capability-matched specialists rather than reuse a single encoder, and top end-to-end quality depends on non-additive compositional fit rather than per-stage marginal rank alone. TRL-Bench provides a common protocol for measuring reusable signal in exported tabular representations under shared downstream conditions. Code and data: https://github.com/LOGO-CUHKSZ/TRL-Bench --- ### Anything2Skill: Compiling External Knowledge into Reusable Skills for Agents Authors: Qianjun Pan, Yutao Yang, Junsong Li, Jie Zhou, Kai Chen, Xin Li, Qin Chen, Liang He Published: 2026-06-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.09316v3 Retrieval-augmented generation (RAG) enables agents to access external knowledge at inference time, but it primarily retrieves fragmented declarative evidence, leaving agents to repeatedly infer task procedures from passages, manuals, examples, logs, or trajectories. This raises a fundamental question: can skills extracted from external knowledge bases be installed into an agent, enabling it to rapidly approximate domain expertise? In this paper, we propose Anything2Skill, a taxonomy-guided framework that compiles heterogeneous external knowledge into reusable, retrievable, and executable skills for agents. Given a corpus of knowledge records, \textsc{Anything2Skill} first decomposes each record into evidence windows and performs plan-and-expand skill extraction under a skill-tree prior. The extracted candidates are then converted into structured skill contracts that specify invocation conditions, contraindications, action moves, workflow steps, constraints, output specifications, supporting evidence, and confidence scores. To construct a deployable procedural memory, Anything2Skill manages the extracted skills in a persistent SkillBank through taxonomy-aware compilation, registry-level reconciliation, lifecycle tracking, versioned updates, and visible skill-tree projection. At inference time, agents retrieve both task-specific passages from the original knowledge base and relevant procedural skills from the SkillBank, allowing RAG to provide declarative evidence while compiled skills provide reusable procedural guidance. Experiments on qsv and GitHub-CLI show that Anything2Skill combined with RAG achieves 98.85\% and 94.10\% success rates, respectively, substantially outperforming RAG-only agents. These results suggest that compiling latent procedural knowledge into explicit skills is an effective way to extend retrieval-augmented agents from knowledge access toward capability reuse. --- ### Brain-Prompt Injection: A Route-Safety Audit for BCI-LLM Agents Authors: Jianwei Tai Published: 2026-06-08 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2606.09315v1 BCI-to-agent pipelines turn decoded neural activity into an authorization channel for tool-use agents, exposing a new attack surface we call \emph{brain-prompt injection}: signal-side perturbations, context-only injections, and adaptive dual-decoder attacks can all change the routed action while EEG-side or text-side monitors remain blind. Route safety in this stack depends on what the audit log can observe, not on decoder accuracy or agreement alone. We define a Route-Safety Audit Contract: a minimal log schema, denominator hierarchy, and endpoint specification, and prove an audit-schema separation theorem together with a C3 attacked-dependence decomposition; clean agreement and marginal robustness do not identify the joint term that controls C3 routing. As a calibration layer on top of the contract, we apply split-conformal calibration to a non-oracle EEG confirmation channel and report the resulting false-accept frontier under an explicit threat-archetype matrix. We instantiate the contract on EEGMMI native left/right command-control over 5{,}400 events, harmless tool stubs, and seed/case denominators. Provenance blocks C2 routes ($0.000$); agreement-plus-provenance routes C3 flips ($1.000$); confirmation-plus-provenance routes them ($0.000$). The conformal frontier reaches FAR $0.000$ at clean utility $0.150$ for $α=.005$ and FAR $0.119$ at clean utility $0.452$ for $α=.10$ under acquisition isolation; an attacker-controllable confirmation channel breaks the bound to $\approx\!1$. Subject-cluster bootstrap confirms these intervals on $60$ subjects; cross-architecture (TinyEEGNet, EEGNetV4) and capacity-sweep results show within-regime saturation. Mediation and confirmation reduce risk; they are not intent certificates. --- ### Machine-Learning Emulation of Satellite Greenhouse Gas Retrievals: Stability over Time Authors: Nugzar Gognadze, Motonobu Kanagawa, Yu Someya, Hisashi Yashiro Published: 2026-06-08 Categories: cs.LG, stat.AP arXiv: https://arxiv.org/abs/2606.09313v2 Retrieval algorithms are used to estimate atmospheric concentrations of greenhouse gases (GHGs), such as carbon dioxide (CO2) and methane (CH4), by solving inverse problems from high-spectral-resolution satellite radiance measurements. However, these algorithms are computationally expensive, which makes real-time estimation at scale difficult. Machine-learning models have therefore been proposed as fast emulators of retrieval algorithms. Most existing studies, however, evaluate them only on test data from the same period as the training data. We study the stability over time of such emulators using data from the Greenhouse Gases Observing SATellite (GOSAT). We show that prediction accuracy generally deteriorates when the test period moves away from the training period. We also show that including time as an input feature substantially improves XCH4 prediction for Lasso and neural-network models. Among the methods considered, a simple Lasso model performs as well as or better than more complex methods such as neural networks, and yields more stable predictions over time. We further validate the results using the Total Carbon Column Observing Network (TCCON), a ground-based observation network. On the TCCON-matched dataset, the time-augmented Lasso achieves errors against TCCON that are comparable to the disagreement between GOSAT and TCCON for both XCO2 and XCH4. --- ### Toward Compiler World Models: Learning Latent Dynamics for Efficient Tensor Program Search Authors: Haolin Pan, Lianghong Huang, Xvlin Zhou, Mingjie Xing, Yanjun Wu Published: 2026-06-08 Categories: cs.LG, cs.PL arXiv: https://arxiv.org/abs/2606.09312v1 Tensor program optimization is essential for modern machine learning systems, but its search space is enormous. Existing auto-schedulers reduce measurement cost with learned cost models, yet they usually evaluate each candidate as a static code snapshot, ignoring the schedule trajectory that produced it. This makes them insensitive to action dependencies and vulnerable to superficial code variations. We propose a \emph{world-model-inspired} evaluator that models schedule evaluation as action-conditioned latent dynamics over program states. Starting from the initial program, it rolls out scheduling actions in a continuous latent space with a lightweight transition model, avoiding expensive AST mutation and repeated code encoding. The final dynamic representation is combined with action and hardware features to rank candidates. Implemented in TVM AutoScheduler, our method improves representative-subgraph latency over Ansor by 1.37$\times$ on GPU and 1.54$\times$ on CPU under the same 64-trial budget. It also matches Ansor-10K within 2.2% geometric mean using 10$\times$ fewer measurements, and accelerates full-model inference over PyTorch/PyTorch-opt(cuDNN) by 4.61$\times$/3.67$\times$ geometric mean. ---