# Research Papers — 2026-05 · bundle page 312 of 326 > Full-text markdown of papers #15551–15600 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-05/page/312 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/311.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/313.md) ### RMGAP: Benchmarking the Generalization of Reward Models across Diverse Preferences Authors: Yangyang Zhou, Yi-Chen Li Published: 2026-05-03 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.01831v1 Reinforcement Learning from Human Feedback has become the standard paradigm for language model alignment, where reward models directly determine alignment effectiveness. In this work, we focus on how to evaluate the generalizability of reward models. By "generalizability", we mean the ability of RMs to correctly rank responses to align with diverse user preferences. However, existing reward model benchmarks are typically designed around a universal preference, failing to assess this generalization. To address this critical gap, we introduce RMGAP, a benchmark comprising 1,097 instances across Chat, Writing, Reasoning, and Safety domains. Since different users exhibit diverse preferences for the same task, we first generate four distinct responses with different linguistic profiles for each collected prompt. However, the original prompt set lacks the specificity to convey different preferences. We therefore construct tailored prompts by contrasting these candidates and designing scenarios in which one response becomes the uniquely appropriate choice. Moreover, we observe that users often express the same preference using different phrasings, and thus extend each prompt with two paraphrased variants. Our evaluation of 24 state-of-the-art RMs reveals their substantial limitations: even the best RM achieves only 49.27% Best-of-N accuracy, highlighting considerable room for improvement in reward model generalization. Related data and code are available at https://github.com/nanzhi84/RMGAP. --- ### GeoSAE: Geometric Prior-Guided Layer-Wise Sparse Autoencoder Annotation of Brain MRI Foundation Models Authors: Favour Nerrise, Lucy Yin, Mohammad H. Abbasi, Kilian M. Pohl, Ehsan Adeli Published: 2026-05-03 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.01829v1 Brain MRI foundation models learn rich representations of anatomy, but interpreting what clinical information they encode remains an open problem. Standard sparse autoencoders (SAEs) suffer from severe feature collapse in deep transformer layers, and in Alzheimer's disease (AD) research, aging confounds nearly every clinical variable, making naive annotation unreliable. We propose GeoSAE, a geometry-guided SAE framework that uses the foundation model's learned manifold structure to prevent feature collapse and annotates each surviving feature via age-deconfounded partial correlations. Applied to ~14k T1-weighted MRI scans from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and the Australian Imaging biomarkers and Lifestyle (AIBL) datasets, GeoSAE identifies a compact, fully interpretable feature set that predicts mild cognitive impairment (MCI)-to-AD conversion (AUC 0.746) using only 2% of the embedding dimensions, while comorbidity-annotated features achieve only chance-level performance. The identified features replicate across cohorts without retraining (r=0.97) and localize to neuroanatomically distinct regions consistent with Braak staging. This shows that geometry-guided SAEs can extract interpretable, biomarkers from frozen brain MRI foundation models. --- ### Referring Multiple Regions with Large Multimodal Models via Contextual Latent Steering Authors: Yun Xing, Hanyuan Liu, Jiahao Nie, Shijian Lu Published: 2026-05-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.01827v1 Large Multimodal Models (LMMs) have recently demonstrated their proficiency in holistic visual comprehension. However, most of them struggle to tackle region-level perception guided by visual prompts, especially for cases where multiple regions are referred simultaneously, or scenarios where global contexts are necessary for precise visual referring. We introduce Contextual Latent Steering (CSteer), a training-free approach for guiding general LMMs to refer multiple regions contextually, without expensive fine-tuning or architectural modifications. CSteer starts with pre-computing contextual vectors that implicitly represent visual referring behaviors, such as differentiation among regions and attention to global contexts, followed by representation editing during inference time. Experimental results on multiple datasets indicate that general LMMs with CSteer outperform tailored referring LMMs in most cases, suggesting a promising solution in training-free, and setting new state-of-the-art for this field. Code is available at https://github.com/xing0047/csteer.git. --- ### Hybrid Visual Telemetry for Bandwidth-Constrained Robotic Vision: A Pilot Study with HEVC Base Video and JPEG ROI Stills Authors: Natalia Trukhina, Vadim Vashkelis Published: 2026-05-03 Categories: cs.CV, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2605.01826v1 Bandwidth-constrained robotic and surveillance systems often rely on a single compressed video stream to support both continuous scene awareness and downstream machine perception. In practice, this creates a mismatch: low-bitrate video can preserve motion and coarse context, but often loses the fine local detail needed for reliable object recognition and decision-making. Motivated by a hybrid architecture in which low-resolution video supports dynamic scene understanding while eventdriven high-detail regions of interest (ROIs) support close-up identification and analytics, this paper formalizes a two-channel visual telemetry scheme in which a continuous low-bitrate video stream is augmented by selectively transmitted high-detail still ROIs. This first paper does not attempt to prove the superiority of a new still-image codec. Instead, it establishes the hybrid transmission paradigm itself using a practical and reproducible codec stack: x265/HEVC for the base video stream and JPEG stills for ROI refinement. We formulate the problem as bitrate-constrained information selection for robotic vision and define an experimental protocol in which video-only and hybrid schemes are compared under matched total communication budgets. The study is designed around UAV-oriented datasets, two practical bitrate regimes, several ROI triggering policies, and object-level classification refinement on selectively transmitted ROI stills. The resulting paper lays the methodological foundation for a second-stage investigation of JPEG AI as the semantic still-image channel within the same hybrid architecture. --- ### Selector-Guided Autonomous Curriculum for One-Shot Reinforcement Learning from Verifiable Rewards Authors: Rudray Dave, Vedang Dubey, Smit Deoghare, Sudhakar Mishra Published: 2026-05-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.01823v1 Recently, Reinforcement Learning from Verifiable Rewards (RLVR) has been established as a highly effective technique for augmenting the math reasoning skills of Large Language Models (LLMs) based on a single instance. Current state-of-the-art 1-shot RLVR models adopt heuristics for selecting instances, mostly based on historical variance in rewards, which we find to be inherently misleading as a measure of transferability value. In this paper, we propose a Selector-Guided Autonomous Curriculum (SGAC) approach, which employs a learnable selector model on a multi-dimensional feature space consisting of success probability, reward variance, output disagreement (entropy), and semantic difficulty level, instead of the static reward variance heuristic. In our empirical evaluation on pools of candidate problems, we observed that output disagreement, rather than reward variance, is the strongest predictor of reasoning gains in subsequent iterations. Leveraging this finding, we develop an autonomous curriculum algorithm for dynamically siphoning candidate problems from a large pool, ranking them by the learned selector, and running micro-bursts of 1-shot GRPO. Our framework is evaluated using the Hendrycks MATH benchmark, with the Qwen2.5-Math-1.5B model serving as the baseline. Our framework obtains an accuracy of 68.0\% on the hold-out dataset, which is better than the accuracy obtained from the state-of-the-art model, 64.0\%, as well as the 1-shot RLVR checkpoint proposed by Wang et al., which achieved an accuracy of 66.0\%. The results confirm that entropy-based intelligent data curation leads to strict reasoning improvement over static training methods, particularly in severely limited data conditions. --- ### Molecular Representations for Large Language Models Authors: Nicholas T. Runcie, Fergus Imrie, Charlotte M. Deane Published: 2026-05-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.01822v1 Large Language Models (LLMs) are increasingly being used to support scientific discovery. In chemistry, tasks such as reaction prediction and structure elucidation require reasoning about the structures of molecules. As such, LLM-based systems for chemistry must interact reliably with molecular structures. Most previous studies of LLMs in chemistry have used SMILES strings or IUPAC names as molecular representations; however, the suitability of these formats has not been systematically assessed. In this work, we introduce MolJSON, a novel molecular representation for LLMs, and systematically compare it with five common chemical formats. We evaluated each representation with GPT-5-nano, GPT-5-mini, GPT-5, and Claude Haiku 4.5 using a set of 78,045 questions spanning translation, shortest path, and constrained generation reasoning tasks. We observed substantial variation across representations in the ability of LLMs to interpret and generate molecular graphs, with MolJSON consistently outperforming existing formats. On translation tasks, GPT-5 achieved 71.0% accuracy when converting IUPAC names to MolJSON, compared with 43.7% when converting the same inputs to SMILES. For constrained generation, GPT-5 reached 95.3% accuracy generating MolJSON, compared with 76.3% for IUPAC and 64.0% for SMILES. As an input format for shortest-path reasoning, GPT-5 successfully answered 98.5% of questions with MolJSON, compared with 92.2% for SMILES and 82.7% for IUPAC, whilst also using fewer reasoning tokens. We observed systematic errors associated with atom count and ring complexity for SMILES strings and IUPAC names, whereas MolJSON was more robust to these failure modes. Our results show that the choice of molecular representation has a material impact on LLM performance, and that explicit molecular graph schemas, such as MolJSON, are a promising direction for LLM-based systems in chemistry. --- ### Skipping the Zeros in Diffusion Models for Sparse Data Generation Authors: Phil Sidney Ostheimer, Mayank Nagda, Andriy Balinskyy, Gabriel Vicente Rodrigues, Jean Radig, Carl Herrmann, Stephan Mandt, Marius Kloft, Sophie Fellenz Published: 2026-05-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.01817v2 Diffusion models (DMs) excel on dense continuous data, but are not designed for sparse continuous data. They do not model exact zeros that represent the deliberate absence of a signal. As a result, they erase sparsity patterns and perform unnecessary computation on mostly zero entries. With Sparsity-Exploiting Diffusion (SED), we model only non-zero values, preserving sparsity. SED delivers computational savings while maintaining or improving generation quality by skipping zeros during training and inference. Across physics and biology benchmarks, SED matches or surpasses conventional DMs and domain-specific baselines, while vision experiments provide intuitive insights into the limitations of dense DMs and the benefits of SED. --- ### Cross-Domain Adversarial Augmentation: Stabilizing GANs for Medical and Handwriting Data Scarcity Authors: Md. Sohanuzzaman Soad, Mahady Al Hady, S M Rafiuddin Rifat, Sudip Ghose Published: 2026-05-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.01815v2 Generative Adversarial Networks (GANs) can help overcome data scarcity in computer vision tasks by generating additional training samples. In this work, we explore generative data augmentation in two low-resource domains: Bangla handwritten character recognition and chest X-ray image analysis. We use DCGAN-based models trained on 64x64 images to generate synthetic samples and evaluate their quality using Inception Score (IS), Fréchet Inception Distance (FID), and visualization methods such as t-SNE and UMAP. To measure practical usefulness, we train image classifiers using real data and a combination of real and synthetic data. Experimental results show that synthetic augmentation improves data diversity and consistently increases classification performance in limited-data settings. We also investigate training stability techniques, including gradient penalty and spectral normalization, and perform ablation studies on synthetic-to-real data ratios and sample filtering strategies. In addition, we discuss challenges related to medical image evaluation, dataset licensing, and privacy concerns of synthetic data. Our approach is simple, reproducible, and provides a strong baseline for generative augmentation in resource-constrained imaging applications. --- ### Federated Semi-Supervised Graph Neural Networks with Prototype-Guided Pseudo-Labeling for Privacy-Preserving Gestational Diabetes Mellitus Prediction Authors: G. Victor Daniel Published: 2026-05-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.01810v2 Gestational Diabetes Mellitus (GDM) is a high-prevalence pregnancy complication that requires accurate early risk stratification to reduce maternal and fetal morbidity. However, real-world clinical deployment of machine learning is hindered by two coupled constraints: (i) label scarcity, where a large fraction of electronic health records (EHR) lack confirmed diagnostic labels, and (ii) data privacy, which prevents sharing patient-level data across hospitals. This paper proposes FedTGNN-SS, a privacy-preserving federated semi-supervised framework for clinical tabular EHR. Each hospital builds a local k-nearest-neighbor patient similarity graph and trains a topology-adaptive GNN encoder. To robustly exploit unlabeled records, FedTGNN-SS combines (1) prototype-guided pseudo-labeling with neighborhood agreement, (2) adaptive graph refinement that periodically updates the k-NN graph using learned embeddings, (3) clinical-aware consistency augmentation applied only to continuous variables, and (4) privacy-safe prototype sharing that exchanges only class-level centroids. Across three diabetes-related datasets (GDM: N = 3,525; Pima: N = 768; Early Stage: N = 520) under 10\%-80\% missing labels per silo, FedTGNN-SS achieves 56 significant wins ($p < 0.05$) against 11 federated baselines and attains strong AUROC under extreme scarcity (Pima: 0.8037 at 80\% missing, Early Stage: 0.9634 at 80\% missing). --- ### Federated Semi-Supervised Graph Neural Networks with Prototype-Guided Pseudo-Labeling for Privacy-Preserving Gestational Diabetes Mellitus Prediction Authors: G. Victor Daniela, A. Mallikarjuna Reddya, Uday Kumar Addankia, Sridhar Reddy Gogua, Sravanth Kumar Ramakuria Published: 2026-05-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.01810v1 Gestational Diabetes Mellitus (GDM) is a high-prevalence pregnancy complication that requires accurate early risk stratification to reduce maternal and fetal morbidity. However, real-world clinical deployment of machine learning is hindered by two coupled constraints: (i) label scarcity, where a large fraction of electronic health records (EHR) lack confirmed diagnostic labels, and (ii) data privacy, which prevents sharing patient-level data across hospitals. This paper proposes FedTGNN-SS, a privacy-preserving federated semi-supervised framework for clinical tabular EHR. Each hospital builds a local k-nearest-neighbor patient similarity graph and trains a topology-adaptive GNN encoder. To robustly exploit unlabeled records, FedTGNN-SS combines (1) prototype-guided pseudo-labeling with neighborhood agreement, (2) adaptive graph refinement that periodically updates the k-NN graph using learned embeddings, (3) clinical-aware consistency augmentation applied only to continuous variables, and (4) privacy-safe prototype sharing that exchanges only class-level centroids. Across three diabetes-related datasets (GDM: N = 3,525; Pima: N = 768; Early Stage: N = 520) under 10\%-80\% missing labels per silo, FedTGNN-SS achieves 56 significant wins ($p < 0.05$) against 11 federated baselines and attains strong AUROC under extreme scarcity (Pima: 0.8037 at 80\% missing, Early Stage: 0.9634 at 80\% missing). --- ### TMD-Bench: A Multi-Level Evaluation Paradigm for Music-Dance Co-Generation Authors: Xiaoda Yang, Majun Zhang, Changhao Pan, Nick Huang, Yang Yuguang, Fan Zhuo, Pengfei Zhou, Jin Zhou, Sizhe Shan, Shan Yang, Miles Yang, Yang You et al. Published: 2026-05-03 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2605.01809v1 Unified audio-visual generation is rapidly gaining industrial and creative relevance, enabling applications in virtual production and interactive media. However, when moving from general audio-video synthesis to music-dance co-generation, the task becomes substantially harder: musical rhythm, phrasing, and accents must drive choreographic motion at fine temporal resolution, and such rhythmic coupling is not captured by unimodal metrics or generic audiovisual consistency scores used in current evaluation practice. We introduce TMD-Bench, a benchmark for text-driven music-dance co-generation that assesses systems across unimodal generation quality, instruction adherence, and cross-modal rhythmic alignment. The benchmark integrates computable physical metrics with perceptual multimodal judgments, and is supported by a curated rhythm-aligned music-dance dataset and a fine-grained Music Captioner for structured music semantics. TMD-Bench further reveals that (i) modern commercial audio-visual models, such as Veo 3 and Sora 2, produce high-quality music and video, while rhythmic coupling remains less consistently optimized and leaves room for improvement, and (ii) our unified baseline RhyJAM trained on rhythm-aligned data achieves competitive beat-level synchronization while maintaining competitive unimodal fidelity. This presents prospects for building next-generation music-dance models that explicitly optimize rhythmic and kinetic coherence. --- ### MAGIC: Multi-Step Advantage-Gated Causal Influence for Multi-agent Reinforcement Learning Authors: Haohan Yu, Jinmiao Cong, Shengzhi Wang, Lu Wang, Chanjuan Liu Published: 2026-05-03 Categories: cs.MA, cs.LG arXiv: https://arxiv.org/abs/2605.01805v2 A key challenge in multi-agent reinforcement learning (MARL) lies in designing learning signals that effectively promote coordination among agents. Designing such signals requires estimating how one agent's current action affects its teammates over future interaction steps. To address this, we introduce Multi-step Advantage-Gated Interventional Causal MARL (MAGIC), a framework that estimates multi-step action effects between agents and selectively converts them into intrinsic rewards. MAGIC uses counterfactual action interventions to compare teammate futures under factual and counterfactual branches, and introduces a gate based on advantage to direct exploration toward beneficial behaviors aligned with the task goal. Experiments on Multi-Agent Particle Environments (MPE) and StarCraft micromanagement benchmarks (SMAC and SMACv2) show that MAGIC consistently outperforms leading prior methods, with average relative final performance improvements of 26.9% and 10.1%, respectively. --- ### Embody4D: A Generalist Data Engine for Embodied 4D World Modeling Authors: Peiyan Tu, Hanxin Zhu, Jingwen Sun, Shaojie Ren, Cong Wang, Yuyan Xu, Jiayi Luo, Xiaoqian Cheng, Zhibo Chen Published: 2026-05-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.01799v2 Embodied agents require robust and comprehensive 3D spatiotemporal representations to support spatial reasoning, manipulation understanding, and downstream decision making. However, existing robot data are typically captured from fixed or sparse viewpoints, providing only partial and view-dependent observations, which limits multi-view perception and generalization across viewpoints. Given the difficulty of collecting additional viewpoints in real-world settings, we propose Embody4D, a dedicated video-to-video world model for embodied scenarios to bridge this observation gap by transforming a monocular robot video into novel-view videos from flexible target camera viewpoints. First, to tackle training data scarcity, we introduce a 3D-aware compositional synthesis pipeline to curate a heterogeneous dataset compositing cross-embodiment robotic arms with diverse backgrounds, promoting broad generalization. Second, to enforce geometric stability, we devise a latent confidence-aware expert modulation strategy, which estimates the reliability of warped latent priors and adaptively routes regions to copy, repair, or inpaint experts for spatiotemporally consistent 4D generation. Finally, to enhance the fidelity of the manipulation, we incorporate an interaction-aware attention mechanism that explicitly attends to the robotic interaction regions. Extensive experiments show that Embody4D achieves state-of-the-art performance on visual evaluation benchmarks, while both simulated and real-world robotic experiments further demonstrate its effectiveness as a robust data engine for synthesizing high-fidelity, view-consistent videos that empower downstream robotic planning and learning. --- ### Neural Decision-Propagation for Answer Set Programming Authors: Thomas Eiter, Katsumi Inoue, Sota Moriyama Published: 2026-05-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.01797v2 Integration of Answer Set Programming (ASP) with neural networks has emerged as a promising tool in Neuro-symbolic AI. While existing approaches extend the capabilities of ASP to real world domains, their reasoning pipelines depend on classical solvers, which is a bottleneck for scalability. To tackle this problem, we propose a new method to compute stable models, called decision-propagation (DProp), which alternates falsity decisions and truth propagations. Successful DProp computations are shown to capture the stable model semantics. We then develop Neural DProp (NDProp), a differentiable extension of DProp with neural computation for decisions and fuzzy evaluation for propagations. We evaluate the capabilities of NDProp for learning decision heuristics as well as neuro-symbolic integration, and compare it with existing neuro-symbolic approaches. The results show that NDProp can learn to efficiently compute stable models, and it improves accuracy and scalability on neuro-symbolic benchmarks. --- ### Beyond ECE: Calibrated Size Ratio, Risk Assessment, and Confidence-Weighted Metrics Authors: Fernando Martin-Maroto, Nabil Abderrahaman, Gonzalo G. de Polavieja Published: 2026-05-03 Categories: cs.LG, math.ST arXiv: https://arxiv.org/abs/2605.01796v2 Confidence calibration has been dominated by the Expected Calibration Error (ECE), a linear metric that counts calibration offset equally regardless of the confidence level at which it occurs. We show that ECE can remain small even under arbitrarily large overconfidence risk, so we propose Calibrated Size Ratio (CSR) instead, an interpretable metric that equals 1 under perfect calibration, from which we derive the risk probability $P_{\mathrm{risk}}$ that quantifies the statistical evidence for overconfidence. We further argue that overconfidence risk assessment must be complemented by a measure of discriminative value: whether the assigned confidences actively distinguish correct from incorrect predictions. We show that confidence-weighted accuracy $\mathrm{cwA}$ is the natural such complement, and that confidence-weighting extends to all standard classification metrics. In particular, we prove that the confidence-weighted AUC (cwAUC) captures the information about calibration while the classical AUC cannot. We validate the proposed indicators on several synthetic confidence distributions under multiple controlled calibration profiles and find that CSR separates risky from non-risky assignments. We also test the metrics on fifteen real datasets, with and without post-hoc calibration, and find that standard methods can yield risky confidence profiles. --- ### Discover Fast Power Allocation Solution for Multi-Target Tracking via AlphaEvolve Evolution Authors: Zhenkang Hou, Wenqiang Pu, Junkun Yan, Rui Zhou, Hongwei Liu Published: 2026-05-03 Categories: eess.SP, cs.AI arXiv: https://arxiv.org/abs/2605.01794v1 Efficient radar resource allocation is a fundamental yet computationally challenging problem, as optimal solutions typically require iterative optimization with high complexity. Motivated by the need for real-time scheduling, robust generalization, and low data dependency, this paper proposes a novel paradigm that leverages large language model (LLM)-guided evolutionary search (AlphaEvolve) to autonomously discover a closed-form power allocation solution for multi-target tracking. The approach encodes high-dimensional radar states into physically inspired features, then evolves a compact and interpretable scoring function, which is transformed to feasible power allocations via a deterministic constraint-satisfying transformation. Extensive experiments demonstrate that the discovered closed-form solution achieves near-optimal tracking accuracy (average relative performance loss of only $1.51\%$), reliable generalization across diverse scenarios and target counts, and over three orders of magnitude speedup compared to conventional iterative solvers. These results highlight the potential of LLM-guided symbolic search to revolutionize not only radar resource management but also broader classes of engineering optimization problems. --- ### Shao: Scaling Acoustic Token Language Models Toward High-Fidelity Music Generation Authors: Jiafeng Liu, Yuanliang Dong, Hongjia Liu, Yuqing Cheng, Zhancheng Guo, Huijing Liang, Wenbo Zhan, Yuming Sun, Xiaobing Li, Feng Yu, Maosong Sun Published: 2026-05-03 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2605.01790v2 A common design pattern in high-quality music generation is to handle structure and fidelity in different representation spaces: a generator first models high-level structure, followed by diffusion-based or neural decoding stages that reconstruct fine details. In this work, we explore an alternative view: both may be progressively modeled within a single deep acoustic-token hierarchy. To study this, we build a 64-layer residual vector quantization (RVQ) acoustic representation and propose a two-stage coarse-to-fine generation framework. A backbone model first generates coarse acoustic tokens for the full track, and a super-resolution model then completes finer tokens within the same acoustic token space. The super-resolution stage works at full-track scale and refines tokens layer by layer while running in parallel over time, leading to a fixed 62-step inference process. To jointly improve lyric alignment and fine-detail reconstruction, we further introduce hybrid-attention training: the alignment objective uses causal attention, while layer-wise refinement uses full attention. A key finding is that text-vocal alignment can emerge within pure acoustic-token language modeling, without requiring a separate semantic token stage. Moreover, initializing the super-resolution model from the trained backbone significantly improves convergence and final quality. Taken together, our results suggest that high-quality music generation can be effectively pursued without separating structure and fidelity into heterogeneous representation spaces. Instead, both can be progressively modeled within a unified acoustic-token hierarchy, pointing toward a simpler and more unified path to high-quality music generation. --- ### DataEvolver: Let Your Data Build and Improve Itself via Goal-Driven Loop Agents Authors: Qisong Zhang, Wenzhuo Wu, Zhuangzhuang Jia, Yunhao Yang, Huayu Zhang, Xianghao Zang, Zhixiang He, Zhongjiang He, Kongming Liang, Zhanyu Ma Published: 2026-05-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.01789v1 Constructing controllable visual data is a major bottleneck for image editing and multimodal understanding. Useful supervision is rarely produced by a single rendering pass; instead it emerges through iterative generation, inspection, correction, filtering, and export. We present DataEvolver, a closed-loop visual data engine that organizes this process around explicit goals, persistent artifacts, bounded corrective actions, and acceptance decisions. DataEvolver supports multiple artifact types, including RGB images, masks, depth maps, normal maps, meshes, poses, trajectories, and review traces. In the current release, the system operates through two coupled loops: generation-time self-correction within each sample and validation-time self-expansion across dataset rounds. We validate the framework on an image-level object-rotation setting. With a fixed Qwen-Edit LoRA probe, our final Ours+DualGate model outperforms both the unadapted base model and a public multi-angle LoRA on SpatialEdit and a held-out evaluation set. Ablations show a consistent improvement path from scene-aware generation to feedback-driven correction and dual-gated validation. Beyond the released rotation data, our main contribution is a reusable framework for building visual datasets through explicit goal tracking, review, correction, and acceptance loops. --- ### Zero-Shot, Safe and Time-Efficient UAV Navigation via Potential-Based Reward Shaping, Control Lyapunov and Barrier Functions Authors: Ashik Abrar Naeem, Mohammad Ariful Haque Published: 2026-05-03 Categories: eess.SY, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2605.01787v1 Autonomous navigation and obstacle avoidance remain a core challenge of modern Unmanned Aerial Vehicles (UAVs). While traditional control methods struggle with the complexity and variability of the environment, reinforcement learning (RL) enables UAVs to learn adaptive behaviors through interaction with the environment. Existing research with RL prioritizes the mission success at the expense of mission time and safety of UAVs. This study integrates Potential Based Reward Shaping (PBRS) with Control Lyapunov Functions (CLF) and Control Barrier Functions (CBF) to simultaneously optimize mission time and ensure formal safety guarantees. An RL model is trained in a generalized simple environment, then used in complex scenarios incorporating a CLF-CBF-QP filter without further training. Experimental results in simulated environments demonstrate a significant reduction in mission time and outstanding performance in complex environment. --- ### Runtime Evaluation of Procedural Content Generation in an Endless Runner Game Using Autonomous Agents Authors: Rishabh Kar Published: 2026-05-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.01783v1 Procedural Content Generation (PCG) enables game content to be created algorithmically without direct manual level-design effort, but it introduces a serious evaluation problem: generated content may become unbalanced, blocked, repetitive, or technically unsolvable. This paper presents Momentum, an endless-runner game that integrates runtime terrain generation, environment object spawning, and autonomous agent-based evaluation into a single gameplay loop. Ground tiles and environmental objects are generated dynamically as the player advances, object placement follows a constraint-driven mechanism inspired by Wave Function Collapse (WFC), and the runtime navigation surface is rebuilt asynchronously to remain consistent with the streamed environment. Two autonomous evaluation agents move ahead of the player and inspect the generated path: an aerial scanner that examines the corridor geometrically, and a ground-traversal agent that validates the same region from a navigational perspective. The evaluation pipeline combines ray casting, volumetric physics sweeps, obstacle-layer filtering, and structured crash reporting to identify problematic generated scenarios before they reach the player. The work demonstrates how generation and validation can be unified within the same runtime loop, rather than treating evaluation as a separate offline pass. Around this implementation, the paper formulates a measurable evaluation framework along the canonical PCG axes of playability, diversity, controllability, and runtime performance, derives a structural saturation bound on the spawner from its own placement constraints, and quantifies the per-segment scanning cost of the agents from first principles. --- ### MedScribe: Clinically Grounded CT Reporting through Agentic Workflows Authors: Giuseppe A. Orlando, Paolo Papotti, Maria A. Zuluaga, Olivier Humbert, Marco Lorenzi Published: 2026-05-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.01779v1 Vision-language models (VLMs) have shown potential for automated radiology report generation, yet existing approaches rely on global embedding compression of volumetric data, often leading to hallucinated findings and limited anatomical grounding in 3D CT imaging. We introduce MedScribe, a hypothesis-driven framework that reformulates report generation as an iterative evidence acquisition process rather than a single-pass encoding task. MedScribe models reporting as a sequential decision process in which a large language model dynamically invokes pathology-specific diagnostic tools to extract localized volumetric features. These structured features are used to query a multidimensional retrieval space aligned with pathology-specific textual evidence. By explicitly accumulating quantitative evidence prior to synthesis, the framework enforces fine-grained grounding and reduces unsupported claims. Without task-specific fine-tuning, MedScribe improves clinical accuracy, factual consistency, and interpretability on CT-RATE and RadChestCT compared to state-of-the-art 2D and 3D VLMs, demonstrating the value of hypothesis-driven reasoning for reliable medical image reporting. --- ### Adversarial Imitation Learning with General Function Approximation: Theoretical Analysis and Practical Algorithms Authors: Tian Xu, Zhilong Zhang, Zexuan Chen, Ruishuo Chen, Yihao Sun, Yang Yu Published: 2026-05-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.01778v1 Adversarial imitation learning (AIL), a prominent approach in imitation learning, has achieved significant practical success powered by neural network approximation. However, existing theoretical analyses of AIL are primarily confined to simplified settings, such as tabular and linear function approximation, and involve complex algorithmic designs that impede practical implementation. This creates a substantial gap between theory and practice. This paper bridges this gap by exploring the theoretical underpinnings of online AIL with general function approximation. We introduce a novel framework called optimization-based AIL (OPT-AIL), which performs online optimization for reward learning coupled with optimism-regularized optimization for policy learning. Within this framework, we develop two concrete methods: model-free OPT-AIL and model-based OPT-AIL. Our theoretical analysis demonstrates that both variants achieve polynomial expert sample complexity and interaction complexity for learning near-expert policies. To the best of our knowledge, they represent the first provably efficient AIL methods under general function approximation. From a practical standpoint, OPT-AIL requires only the approximate optimization of two objectives, thereby facilitating practical implementation. Empirical studies demonstrate that OPT-AIL outperforms previous state-of-the-art deep AIL methods across several challenging tasks. --- ### Data driven approach for Outdoor Channel Prediction in 5G and Beyond Authors: A. Sathi Babu, V. Udaya Sankar, Vishnu Ram OV Published: 2026-05-03 Categories: eess.SP, cs.AI arXiv: https://arxiv.org/abs/2605.01777v2 An evolution of Wireless Communications towards 5G and beyond provides improved user experience in terms of quality of services. Understanding and estimating Channel information plays crucial role in providing better user experience. Traditional methods of channel estimation involves periodically sending pilots (known signals), estimating channel and send back estimated channel information to the BS which increases computational complexity and communication complexity. Hence, we focus on data driven approach for channel estimation. In this work, we explore a channel estimation mechanism at 7GHz frequency band for a given user location. This work involves data generation using Ray tracing mechanism and Machine learning model training that contains feature variables such as transmitter location, user location and target variable as channel coefficient . We explored Support Vector Regression, K-nearest neighbor (KNN), Random Forest, XGBoost and MLP. We found via simulations that XG Boost and proposed MLP performs better than Support Vector Regression, KNN and Random forest regression. --- ### Data driven approach for Outdoor Channel Prediction in 5G and Beyond Authors: A. Sathi Babu, V. Udaya Sankar, Vishnu Ram OV Published: 2026-05-03 Categories: eess.SP, cs.AI arXiv: https://arxiv.org/abs/2605.01777v1 An evolution of Wireless Communications towards 5G and beyond provides improved user experience in terms of quality of services. Understanding and estimating Channel information plays crucial role in providing better user experience. Traditional methods of channel estimation involves periodically sending pilots (known signals), estimating channel and send back estimated channel information to the BS which increases computational complexity and communication complexity. Hence, we focus on data driven approach for channel estimation. This work can be deployed as Digital twin in 5G and beyond wireless networks. In this work, we explore a channel estimation mechanism at 7GHz frequency band for a given user location. This work involves data generation using Ray tracing mechanism and Machine learning model training that contains feature variables such as transmitter location, user location and target variable as channel coefficient . We explored Linear Regression, Support Vector Regression and Decision Tree Regression. We found via simulations that Linear Regression performs (with MAE of $\mathbf{7.5155\times10^{-5}}$ and RMSE of $\mathbf{9.2861\times10^{-5}}$) better than Support Vector Regression and Decision Tree Regression. --- ### A Semi-Supervised Kernel Two-Sample Test Authors: Gyumin Lee, Shubhanshu Shekhar, Ilmun Kim Published: 2026-05-03 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2605.01775v1 We consider the problem of two-sample testing in a semi-supervised setting with abundant unlabeled covariate data. Standard two-sample tests neglect covariate information, which has the potential to significantly boost performance. However, incorporating covariates potentially breaks the exchangeability assumption under the null, which further complicates a calibration procedure. To address these issues, we propose a semi-supervised method that produces a test statistic with asymptotic normality, while effectively integrating additional information from covariates. Our test is straightforward to calibrate due to the asymptotic normality under the null and achieves asymptotic power that is often much higher than existing kernel tests without covariates. Furthermore, we formally show that the proposed method is consistent in power against fixed and local alternatives. Simulations confirm the practical and theoretical strengths of our approach. --- ### Anticipation-VLA: Solving Long-Horizon Embodied Tasks via Anticipation-based Subgoal Generation Authors: Zhilong Zhang, Wenyu Luo, Haonan Wang, Yifei Sheng, Yidi Wang, Hanyuan Guo, Haoxiang Ren, Xinghao Du, Yuhan Che, Tongtong Cao, Lei Yuan, Yang Yu Published: 2026-05-03 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2605.01772v1 Vision-Language-Action (VLA) models have emerged as a powerful paradigm for embodied intelligence, enabling robots to perform tasks based on natural language instructions and current visual input. However, existing VLA models struggle with long-horizon tasks due to compounding errors. Prior methods decompose tasks into subtasks of fixed granularity, which cannot adapt to the varying complexity of execution states, limiting their robustness in long-horizon tasks. To overcome this, we introduce Anticipation Model, which adaptively and recursively generates future subgoals. This model continuously adapts as the task unfolds, adjusting future subgoals in response to evolving dynamics, facilitating more reliable planning paths. Building on this concept, we propose Anticipation-VLA, a hierarchical VLA model that leverages the anticipation model to generate actionable subgoals that guide VLA policy execution. We implement Anticipation-VLA with finetuning a Unified Multimodal Model (UMM) for high-level subgoal generation and a goal-conditioned VLA policy for low-level action execution. Experiments in both simulated and real-world robotic tasks demonstrate the effectiveness of Anticipation-VLA, highlighting the importance of adaptive and recursive subgoal generation for robust policy execution. --- ### The Compliance Gap: Why AI Systems Promise to Follow Process Instructions but Don't Authors: Kwan Soo Shin Published: 2026-05-03 Categories: cs.CL, cs.AI, cs.CY, cs.LG arXiv: https://arxiv.org/abs/2605.01771v1 An auditor instructs an AI assistant: "open each file individually using the Read tool -- no scripts, no agents." The AI replies "Yes" -- then issues a single batched call summarizing all fifty files at once. We call this the Compliance Gap: a third, orthogonal axis of AI honesty distinct from factual truthfulness and rhetorical substance. Three questions: does this verbal-behavioral disconnect exist (existence); can any text-only observer recover it (detectability); what infrastructure does AI deployment need (remedy)? Some 75 benchmarks (IFEval, SWE-bench, BFCL, COMPASS, SpecEval) measure outcome fidelity; none measures process fidelity. Theorem 1 shows the gap is structurally inevitable under RL that rewards text without observing behavior. Theorem 2, via the Data Processing Inequality, shows it is undetectable from text alone -- by any human or LLM observer, present or future. Thirteen experiments and 2,031 sessions on six frontier models confirm both predictions. Under default framing, all six exhibit instruction compliance rates of 0% -- Claude Sonnet 4 verbally agrees ten out of ten times then bypasses in all ten. The gap is selective: 97% compliance where rationale is rewarded (audit trails), 0-4% where it is not (file reading, privacy masking); removing delegation tools raises compliance to 75% (Cohen's d = 2.47), confirming environmental affordance rather than weight-encoded failure. Nine blinded human raters achieve Fleiss' kappa = 0.130 and correctly identify zero of fifteen compliant sessions, exactly as Theorem 2 predicts. Where humans show 47% intention-behavior gaps in psychology and 96.5pp gaps in surgical audits, RLHF-trained models approach 100% under default conditions -- a regime warranting its own measurement infrastructure. We release BS-Bench: the first open benchmark for process compliance, with seven tool-call-log audit metrics and a public leaderboard. --- ### Mitigating Multimodal LLMs Hallucinations via Relevance Propagation at Inference Time Authors: Itai Allouche, Joseph Keshet Published: 2026-05-03 Categories: cs.LG, cs.CV, eess.AS arXiv: https://arxiv.org/abs/2605.01766v2 Multimodal large language models (MLLMs) achieve strong performance on vision- and audio-language tasks, yet can generate responses that conflict with the given visual or auditory inputs, a problem known as multimodal hallucinations. Prior work suggests that this occurs when models rely more on textual cues and learned language patterns than on evidence from the perceptual input. To obtain a more direct account of this imbalance, we apply Layer-wise Relevance Propagation (LRP), which attributes predictions to individual input tokens, and use the resulting relevance scores to analyze and mitigate hallucinations. First, we examine whether this imbalance leads to multimodal hallucinations. We find that hallucinations often arise when the model relies less on perceptual inputs, and that changing this reliance affects its predictions. We further leverage LRP and propose a training-free framework that shifts relevance toward perceptual tokens by optimizing key-value representations during decoding, without modifying model parameters or requiring training data. We call this method Learning Inference-time Modality Enhancement (LIME). Despite using no spatial or temporal supervision, LIME concentrates relevance on query-relevant regions. We evaluate LIME across multiple multimodal benchmarks in both vision and audio domains, demonstrating consistent reductions in hallucinations and enhanced grounding while preserving generation quality. --- ### Mitigating Multimodal LLMs Hallucinations via Relevance Propagation at Inference Time Authors: Itai Allouche, Joseph Keshet Published: 2026-05-03 Categories: cs.LG, cs.CV, eess.AS arXiv: https://arxiv.org/abs/2605.01766v1 Multimodal large language models (MLLMs) have revolutionized the landscape of AI, demonstrating impressive capabilities in tackling complex vision and audio-language tasks. However, a critical challenge remains: these models often suffer from hallucinations, generating outputs that diverge from the provided perceptual inputs. This tendency stems from an inherent imbalance in modality utilization during inference, where the dominance of textual tokens undermines the potential of perceptual inputs. As a result, the model frequently resorts to textual language priors at the expense of grounded evidence. To tackle this issue, we propose Learning Inference-time Modality Enhancement (LIME), a training-free framework designed to bolster multimodal grounding by explicitly enhancing modality usage during decoding. LIME leverages Layer-wise Relevance Propagation (LRP) to quantify token-level contributions and defines a relevance-based objective that promotes increased reliance on perceptual inputs. This objective is enforced through inference-time updates to the model's key-value representations, without modifying model parameters or requiring additional training data. We evaluate LIME across multiple multimodal benchmarks in both vision and audio domains, demonstrating consistent reductions in hallucinations and enhanced grounding while preserving generation quality. Further analysis shows that LIME increases modality contribution and produces more localized and semantically aligned relevance patterns. --- ### Distributional Causal Mediation via Conditional Generative Modeling Authors: Jinlun Zhang, Haoneng Huang, Zishu Zhan, Chunquan Ou Published: 2026-05-03 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2605.01765v2 Mediation analysis has traditionally focused on outcome-level summary contrasts, such as mean effects, which may obscure substantial distributional changes induced by complex and nonlinear causal mechanisms. We propose Distributional Causal Mediation Analysis (DCMA), a generative learning framework for identifying and estimating treatment effects on entire outcome distributions transmitted through multiple mediators. DCMA learns conditional generative models for the mediators and the outcome, recovering the relevant conditional distributions from observational data. Leveraging the identification formulas, it reconstructs interventional outcome distributions via Monte Carlo forward simulation by noise resampling, enabling the capture of both classical summary effects and rich distributional contrasts such as energy distance and the Wasserstein distance. Analytical error bounds are derived to decompose how estimation errors in the learned conditional models propagate to the reconstructed interventional outcome distributions. The empirical effectiveness of DCMA is demonstrated through numerical experiments and real-world data applications. --- ### TrajShield: Trajectory-Level Safety Mediation for Defending Text-to-Video Models Against Jailbreak Attacks Authors: Quanchen Zou, Nizhang Li, Wenxin Zhang, Jiaye Lin, Yangchen Zeng, Xiangzheng Zhang, Zonghao Ying Published: 2026-05-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.01761v1 Text-to-Video (T2V) models have demonstrated remarkable capability in generating temporally coherent videos from natural language prompts, yet they also risk producing unsafe content such as violence or explicit material. Existing prompt-level defenses are largely inherited from text-to-image safety and operate on the lexical surface of the input, making them vulnerable to jailbreak attacks that disguise harmful intent through rephrasing or adversarial prompting. Moreover, T2V generation introduces a distinctive challenge overlooked by prior work: temporally emergent risk, where a seemingly benign prompt leads to unsafe content through the generator's temporal extrapolation toward narrative coherence. We propose \method{}, a training-free, inference-time defense framework that reformulates T2V safety as a causal intervention in a temporally structured semantic space. TrajShield handles explicit unsafe prompts, jailbreak attacks, and temporally emergent risks in a unified manner by simulating the implied trajectory of a prompt, localizing the causal origin of potential risk, and applying a minimally invasive rewrite that neutralizes the risk while preserving safety-irrelevant semantics. Experiments on T2VSafetyBench across 14 safety categories and multiple T2V backends demonstrate that TrajShield achieves state-of-the-art defenseive performance while maintaining high semantic fidelity, substantially outperforming existing defenses, with an average ASR reduction of 52.44\%. --- ### PointCSP: Cross-Sample Semantic Propagation and Stability Preservation in Self-Supervised Point Cloud Learning Authors: Xinxing Yu, Ajian Liu, Sunyuan Qiang, Hui Ma, Liying Yang, Yuzhong Wang, Zhi Rao, Yanyan Liang Published: 2026-05-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.01759v1 Scene-level point cloud self-supervised learning (PC-SSL) has demonstrated potential in enhancing the generalization capability of 3D vision models. Despite the advances in the field through existing methods, the sample-independent modeling paradigm still poses significant limitations in terms of maintaining consistent semantic representations across scenes. This challenge hinders the construction of a unified and transferable semantic space. To address this issue, we propose a PC-SSL framework based on cross-sample semantic propagation (CSP), in which samples within a batch are serialized into continuous input and processed by a state-space model to enable semantic state propagation. This mechanism explicitly models the dynamic dependencies across samples in the state space, allowing the network to establish cross-sample semantic consistency in the latent space and achieve global semantic alignment. Since serialization-based pretraining requires batch-level input organization, we further introduce an asymmetric semantic preservation distillation (SPD) during finetuning to achieve structural alignment of semantic transfer and eliminate inconsistencies caused by batch dependency. The proposed SPD ensures stable transfer of pretrained semantics through a heterogeneous input mechanism and a semantic feature alignment constraint. This enables the model to maintain structured semantic consistency and robustness under single-scene testing conditions. Extensive experiments on multiple benchmark datasets demonstrate that our method consistently outperforms state-of-the-art methods in both performance and semantic consistency. --- ### Catching the Infection Before It Spreads: Foresight-Guided Defense in Multi-Agent Systems Authors: Yue Ma, Ziyuan Yang, Yi Zhang Published: 2026-05-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.01758v3 Large multimodal model-based Multi-Agent Systems (MASs) enable collaborative complex problem solving through specialized agents. However, MASs are vulnerable to infectious jailbreak, where compromising a single agent can spread to others, leading to widespread compromise. Existing defenses counter this by training a more contagious cure factor, biasing agents to retrieve it over virus adversarial examples (VirAEs). However, this homogenizes agent responses, providing only superficial suppression rather than true recovery. We revisit these defenses, which operate globally via a shared cure factor, while infectious jailbreak arise from localized interaction behaviors. This mismatch limits their effectiveness. To address this, we propose a training-free Foresight-Guided Local Purification (FLP) framework, where each agent reasons over future interactions to track behavioral evolution and eliminate infections. Specifically, each agent simulates future behavioral trajectories over subsequent chat rounds. To reflect diversity in MASs, we introduce a multi-persona simulation strategy for robust prediction across interaction contexts. We then use response diversity as a diagnostic signal to detect infection by analyzing inconsistencies across persona-based predictions at both retrieval-result and semantic levels. For infected agents, we apply localized purification: recent infections are mitigated via immediate album rollback, while long-term infections are handled using Recursive Binary Diagnosis (RBD), which recursively partitions the image album and applies the same diagnosis strategy to localize and eliminate VirAEs. Experiments show that FLP reduces the maximum cumulative infection rate from over 95% to below 5.47%. Moreover, retrieval and semantic metrics closely match benign baselines, indicating effective preservation of interaction diversity. --- ### The (Marginal) Value of a Search Ad: An Online Causal Framework for Repeated Second-price Auctions Authors: Yuxiao Wen, Zihao Hu, Yanjun Han, Yuan Yao, Zhengyuan Zhou Published: 2026-05-03 Categories: cs.GT, cs.IT, cs.LG arXiv: https://arxiv.org/abs/2605.01756v1 Existing auto-bidding algorithms in digital advertising often treat the value of an ad opportunity as the revenue obtained when an ad is shown and/or clicked, and bid accordingly. This can lead to wasteful spending because the true value is the marginal gain from paid exposure: even without winning a sponsored slot, an advertiser may still earn revenue via an organic search result (e.g., on Google or Amazon). Motivated by recent work, we model ad value as a treatment effect--the outcome difference between winning and losing the auction--and study online learning for bidding in second-price (Vickrey) auctions under this causal perspective. We develop algorithms that attain rate-optimal regret under several feedback models. A key ingredient exploits the information revealed by the second-price payment rule, which strictly improves regret relative to analogous learning problems in first-price auctions. --- ### Robust Linear Dueling Bandits with Post-serving Context under Unknown Delays and Adversarial Corruptions Authors: Youngmin Oh Published: 2026-05-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.01752v4 We study linear dueling bandits in volatile environments characterized by the simultaneous presence of post-serving contexts, delayed feedback, and adversarial corruption. Feedback is subject to unknown stochastic or adversarial delays and a cumulative corruption budget $\mathcal{C}$. To address these challenges, we propose e RCDP-UCB, which integrates a learned approximator that predicts post-serving contexts from pre-serving information. It further employs an adaptive weighting strategy that clips feature vectors to mitigate the impact of corrupted and delayed observations simultaneously. Under standard regularity conditions and a parametric post-serving mapping, we rigorously establish that our algorithm is delay-regime-agnostic, achieving a regret upper bound of $\widetilde{\mathcal{O}}(d(\sqrt{T} + \mathcal{C} + \mathcal{D}))$, where $d$ is the total feature dimension and $\mathcal{D}$ encapsulates the delay complexity. Crucially, our analysis reveals an additive cost structure between corruption and delay, avoiding the multiplicative degradation typical of prior works. We further establish lower bounds that nearly match our upper bounds up to a $\sqrt{d}$ factor for adversarial delays in the absence of post-serving contexts. Code is available at https://github.com/youngmin0oh/rcdp-public. --- ### Talk is Cheap, Communication is Hard: Dynamic Grounding Failures and Repair in Multi-Agent Negotiation Authors: Yiheng Yao, Chelsea Zou, Robert D. Hawkins Published: 2026-05-03 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2605.01750v2 Grounding is the collaborative process of establishing mutual belief sufficient for a communicative goal. While static grounding maps language to a shared context, dynamic grounding requires agents to negotiate meaning across turns. Current multi-agent Large Language Model (LLM) benchmarks largely emphasize static, one-shot tasks, overlooking whether agents can repair grounding breakdowns through interaction. We introduce an iterated multi-turn negotiation game where two agents allocate shared resources to private projects with verifiable jointly optimal outcomes. Although individual agents can identify Pareto-optimal allocations in isolation, agent dyads consistently fail to reach them across models. We identify four failure modes: (1) loss of shared interaction history, (2) stubborn anchoring to early proposals, (3) defaulting to equal splits over reward-maximizing coordination, and (4) referential binding errors across turns. Our baselines show that the coordination gap is not explained by individual reasoning limits or insufficient information exchange alone. Instead, the bottleneck lies in dynamic grounding: joint plan formation, commitment, and execution. --- ### Only Say What You Know: Calibration-Aware Generation for Long-Form Factuality Authors: Wen Luo, Guangyue Peng, Liang Wang, Nan Yang, Wei Li, Yuhan Song, Shaohang Wei, Feifan Song, Furu Wei, Houfeng Wang Published: 2026-05-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.01749v1 Large Reasoning Models achieve strong performance on complex tasks but remain prone to hallucinations, particularly in long-form generation where errors compound across reasoning steps. Existing approaches to improving factuality, including abstention and factuality-driven optimization, follow a \emph{coupled exploration-commitment} paradigm, in which intermediate reasoning is unconditionally propagated to the final output, limiting fine-grained control over information selection and integration. In this paper, we propose an \textbf{Exploration-Commitment Decoupling} paradigm that disentangles knowledge exploration from final commitment, enabling models to explore with awareness while answering cautiously. We instantiate the paradigm with \textbf{Calibration-Aware Generation (CAG)}, a framework that equips models with end-to-end, calibration-aware generation capabilities, by augmenting intermediate reasoning with calibrated reliability estimates and prioritizing reliable content in final outputs. Across five long-form factuality benchmarks and multiple model families, CAG improves factuality by up to 13%, while reducing decoding time by up to 37%. Overall, our work highlights decoupling as a principled approach for more reliable long-form generation, offering directions for trustworthy and self-aware generative systems. --- ### Profile-Specific 3DMM Regression from a Single Lateral Face Image Authors: Taiki Kanaya, Hideo Saito Published: 2026-05-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.01746v1 Single-image 3D face reconstruction is a core problem in computer vision, with important clinical applications such as cephalometric landmark analysis in orthodontics. Traditionally, this analysis relies on lateral X-ray imaging; however, frequent X-ray exposure is impractical due to radiation concerns. While recent research has explored detecting landmarks from lateral RGB images as an alternative, existing methods typically rely on 2D features such as the eyes, mouth, ears, and boundary silhouettes, failing to fully exploit the underlying 3D facial geometry spanning the facial profile and jawline, which is essential for accurate diagnosis. Meanwhile, although 3D face reconstruction from frontal views has seen significant progress, most learning-based 3D morphable model (3DMM) regressors are developed and benchmarked on near-frontal images, where appearance cues are abundant. In extreme profile views (yaw $\approx 90^\circ$), much of the face is occluded, and the available signal is dominated by boundary cues, making accurate 3D reconstruction challenging. In this paper, we bridge this gap with geometry-conditioned synthetic data and a simple profile-specific FLAME regression baseline for single lateral images. We introduce ProfileSynth, a dataset created by sampling FLAME shape and pose parameters in extreme yaw ranges and generating photorealistic profile images using a diffusion model conditioned on depth and normal maps. We further study a profile-specific baseline with visibility-aware jawline regularization. Our framework provides a practical baseline for "profile $\times$ 3DMM" reconstruction and a promising foundation for more accurate, non-invasive cephalometric analysis from lateral RGB images. --- ### NH-CROP: Robust Pricing for Governed Language Data Assets under Cost Uncertainty Authors: Xu Zheng, Feiyu Wu, Zhuocheng Wang, Yiming Dai, Hui Li Published: 2026-05-03 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.01745v1 Language data are increasingly acquired and governed as assets, yet platforms often price candidate resources before knowing their true privacy or access costs. We study online pricing for governed language data assets under cost uncertainty. At each round, a platform observes an NLP task, a candidate asset, and a coarse cost estimate, may pay for a refined cost signal, posts a price, and receives safe net revenue. We introduce \textsc{NH-CROP}, a clipped robust pricing framework with a no-harm information-acquisition gate. The method compares direct pricing, risk-aware pricing, and verify-then-price, and acquires information only when its estimated decision value exceeds the best no-verification alternative. Across synthetic, real-proxy, and downstream-utility-grounded benchmarks, clipped \textsc{NH-CROP} variants improve or remain competitive with price-only and risk-aware baselines. Causal ablations show that paid verification is not the main source of gains in real-proxy and utility-grounded settings: the strongest learned policies often choose not to verify. Oracle and high-decision-value diagnostics show that refined cost information can still have substantial local value. Overall, governed language-data platforms should calibrate pricing under uncertain access costs first and verify only when information is cheap and decision-actionable. --- ### MOC-3D: Manifold-Order Consistency for Text-to-3D Generation Authors: Chenyang Fan, Junshi Cheng, Wen Yang, Zihong Li, Wenfeng Zhang, Wei Hu, Yi Zhang, Pan Zeng Published: 2026-05-03 Categories: cs.CV, cs.MM arXiv: https://arxiv.org/abs/2605.01743v1 With the burgeoning development of fields such as the Metaverse, Virtual Reality (VR), and Digital Twins, text-to-3D generation has emerged as a research hotspot in both academia and industry. Currently, optimization methods based on Score Distillation Sampling (SDS) utilizing 2D diffusion priors have become the mainstream technological paradigm in this field. However, due to the view bias of 2D priors and the mode-seeking ambiguity combined with gradient noise induced by high Classifier-Free Guidance (CFG), these methods still suffer from macro-topological inconsistency (e.g., the Janus problem) and micro-geometric discontinuity. To address these challenges, we propose MOC-3D, a text-to-3D generation method based on geometric manifold and semantic view-order consistency. Built upon the ScaleDreamer framework, our method incorporates a Semantic View-Order Constraint Module and a Manifold-based Feature Continuity Module. The former aims to rectify macro-topological inconsistency, while the latter focuses on eliminating micro-geometric discontinuity. Specifically, the Semantic View-Order Constraint Module leverages the prior knowledge of CLIP to impose a Monotonicity Rank Constraint on semantic score representations across different views, thereby providing effective guidance for the global topological structure of 3D objects. Meanwhile, the Manifold-based Feature Continuity Module employs the Riemannian Metric on the Symmetric Positive Definite (SPD) manifold. By measuring the distance of feature statistical distributions in the Riemannian space, it promotes the smooth evolution and continuity of micro-textures across multi-views in a statistical sense. Under the macro-micro synergistic optimization of these two modules, our model can simultaneously improve macro-structural consistency and micro-detail continuity. --- ### Joint Architecture-Token-Bitwidth Multi-Axis Optimization of Vision Transformers for Semiconductor IC Packaging Authors: Phat Nguyen, Xue Geng, Kaixin Xu, Wang Zhe, Xulei Yang, Ngai-Man Cheung Published: 2026-05-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.01742v2 Vision Transformers (ViTs) have achieved strong visual recognition performance, yet their deployment in resource-constrained industrial environments remains limited. The main challenges are their high computational cost, memory requirements, and energy consumption. While individual efficiency techniques such as neural architecture search (NAS), token compression, and low-precision inference have been extensively studied, most prior work targets only a single optimization axis, limiting overall deployment gains while preserving accuracy. In this paper, we present one of the first holistic frameworks that jointly optimizes three complementary axes: architecture, token, and bit-width. Specifically, the framework identifies compact backbones via Neural Architecture Search (AutoFormer), reduces information processing via token merging (ToMe), and accelerates per-operation execution via fp16 mixed-precision inference. In our study, we analyze accuracy-efficiency trade-offs on ImageNet-1K under aggressive compression. We then apply the selected configurations to a real-world in-house 3D X-ray semiconductor defect classification dataset for IC chip packaging inspection. Results show that the proposed multi-axis framework achieves more than $10\times$ improvement in throughput along with over $10\times$ reductions in parameter count, FLOPs, and energy consumption, while maintaining the required accuracy on the downstream industrial task. To the best of our knowledge, this is among the earliest works to jointly optimize architecture, token, and bit-width dimensions in ViTs and the first such resource-efficient, deployment-focused study for semiconductor manufacturing. --- ### Joint Architecture-Token-Bitwidth Multi-Axis Optimization of Vision Transformers for Semiconductor IC Packaging Authors: Phat Nguyen, Xue Geng, Kaixin Xu, Wang Zhe, Xulei Yang, Ngai-Man Cheung Published: 2026-05-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.01742v1 Vision Transformers (ViTs) have achieved strong performance in visual recognition, yet their deployment in resource-constrained industrial environments remains limited. Some main challenges are their high computational cost, memory requirement, and energy consumption. While individual efficiency techniques such as neural architecture search (NAS), token compression, and low-precision inference have been extensively studied, most prior work targets only a single optimization axis, limiting overall deployment gains while preserving accuracy. In this paper, we present one of the first holistic frameworks that jointly optimizes three complementary axes: architecture, token, and bit-width. Specifically, the framework identifies compact backbones via Neural Architecture Search (AutoFormer), reduces information processing via token merging (ToMe), and accelerates per-operation execution via fp16 mixed-precision inference. Starting from a DeiT-B/16 baseline, we first analyze accuracy-efficiency trade-offs on ImageNet-1K under aggressive compression. Then, we apply the selected configurations to a real-world in-house 3D X-ray semiconductor defect classification dataset for IC chip packaging inspection. Results show that the proposed multi-axis framework achieves more than 10 times improvement in throughput along with over 10 times reductions in parameter count, FLOPs, and energy consumption, while maintaining the required accuracy on the downstream industrial task. To the best of our knowledge, this is among the earliest works to jointly optimize architecture, token, and bit-width dimensions in ViTs and the first such resource-efficient, deployment-focused study tailored to semiconductor manufacturing. --- ### Adaptive Texture-aware Masking for Self-Supervised Learning in 3D Dental CBCT Analysis Authors: Xinquan Yang, Jianfeng Ren, Xuguang Li, Kian Ming Lim, He Meng, Linlin Shen, Yongqiang Deng Published: 2026-05-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.01741v1 Cone Beam Computed Tomography (CBCT) is pivotal for 3D diagnostic imaging in dentistry. However, the development of robust AI models for volumetric analysis is often constrained by the scarcity of large, annotated datasets. Self-supervised learning (SSL), particularly Masked Image Modeling (MIM), offers a promising pathway to leverage unlabeled data. A limitation of standard MIM is its reliance on random masking, which fails to prioritize diagnostically critical regions in dental CBCT volumes, such as subtle pathological changes and intricate anatomical boundaries. To address this, we propose ATMask, a novel adaptive masking strategy. Instead of applying random masks or employing computationally intensive attention modules, ATMask computes an inter-slice texture variation map to identify regions with high structural or textural complexity. These high-variation areas are then selectively masked during pre-training, compelling the model to learn richer contextual representations essential for inferring complex 3D morphological transitions. Furthermore, we contribute the first large-scale CBCT dataset, curated from both public and private sources, comprising 6,314 scans, for the dental AI model pretraining. Extensive experiments on three downstream dental CBCT tasks demonstrate that our ATMask enables more data-efficient and powerful representation learning than standard random masking and other advanced SSL baselines. The dataset and code will be released. --- ### Architectural Obsolescence of Unhardened Agentic-AI Runtimes Authors: Alfredo Metere Published: 2026-05-03 Categories: cs.CR, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2605.01740v1 An agentic-AI runtime issues tool calls, sends messages, and actuates devices on behalf of an LLM. Catching the four ways an action can diverge from its audit record -- F1 gate-bypass, F2 audit-forgery, silent host failure, F4 wrong-target, -- is a load-bearing safety property of any such runtime. We show that upstream OpenClaw, the most engineered single-user agentic-AI gateway in public release, catches none of them: recall is 0.000 on every cell of every confusion matrix, on a 1600-sample template baseline through OpenClaw's actual production command-line interface (CLI) and on a ten-LLM cross-model generalisation run. Detecting F1--F4 requires seven specific runtime structures absent from OpenClaw's source tree: a biconditional checker, a hash-chained audit log, an extension admission gate, a two-layer egress guard, a Bell-LaPadula classification policy, a module-signing trust root, and a bootstrap seal. enclawed-oss -- an MIT-licensed drop-in fork that ships all seven -- reaches $P = R = F_1 =$ accuracy $= 1.000$ on the same input. The gap is structural, not parametric: a six-line append-only widening of enclawed-oss's data-loss-prevention (DLP) regex catalog raises per-channel F3 detection by 14.6\% net at unchanged precision; the same edit on OpenClaw has nowhere to land. The harness deliberately exercises real Discord and Telegram channels -- plugin categories the first enclawed release deleted as unsafe -- to show F1--F4 detection extends to those previously-unsafe extensions. With architectural superiority for security and feature parity for extensions, we argue that unhardened agentic-AI runtimes are architecturally obsolete: a strictly better alternative exists, is adoptable today, and the gap requires re-architecture rather than configuration. We invite reviewers to apply the harness to any candidate runtime. --- ### Continuous quantification of viral plaque dynamics using ultra-large-area label-free imaging enables rapid antiviral susceptibility testing Authors: Merve Eryilmaz, Yuzhu Li, Xiao Wang, Max Zhang, Alp Inegol, Zixiang Ji, Lucas Thai, Guangdong Ma, Akihiko Fujisawa, Kazunori Yamaguchi, Aydogan Ozcan Published: 2026-05-03 Categories: physics.app-ph, cs.CV, physics.bio-ph, physics.ins-det arXiv: https://arxiv.org/abs/2605.01738v1 The plaque reduction assay (PRA) remains the gold standard for antiviral susceptibility testing, evaluating drug potency by measuring reductions in plaque-forming units (PFUs). However, the traditional PRA is time-consuming, labor-intensive, prone to manual counting errors, and offers limited scalability. Moreover, its reliance on destructive fixation and chemical staining reduces the assay to a static, endpoint observation, obscuring the dynamic, time-resolved kinetics of dose-dependent viral inhibition. Here, we introduce a label-free, time-resolved PRA platform that transforms the conventional assay into a continuous, high-dimensional measurement of viral infection dynamics. Our system integrates a compact lens-free imaging setup with a custom-designed ultra-large-area (100 cm^2) thin-film transistor (TFT) image sensor and deep learning-based algorithms to autonomously quantify PFU dynamics within an incubator. Validated using herpes simplex virus type-1 (HSV-1) treated with acyclovir, the platform matched chemically-stained ground truth measurements with zero false positives while accelerating readout by ~26 hours. Crucially, our system revealed that increasing drug concentrations induce temporally distinct delays and suppress new PFU formation, enabling conclusive drug efficacy evaluations within ~60 hours post-infection. This scalable, label-free framework redefines antiviral susceptibility testing as a rapid, time-resolved and information-rich measurement framework, providing a generalizable platform for virology research, high-throughput drug screening, and clinical diagnostics. --- ### Multi-Scale Gaussian-Language Map for Zero-shot Embodied Navigation and Reasoning Authors: Sixian Zhang, Yiyao Wang, Xinhang Song, Keming Zhang, Zijian Xu, Shuqiang Jiang Published: 2026-05-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.01736v1 Understanding the geometric and semantic structure of environments is essential for embodied navigation and reasoning. Existing semantic mapping methods trade off between explicit geometry and multi-scale semantics, and lack a native interface for large models, thus requiring additional training of feature projection for semantic alignment. To this end, we propose the multi-scale Gaussian-Language Map (GLMap), which introduces three key designs: (1) explicit geometry, (2) multi-scale semantics covering both instance and region concepts, and (3) a dual-modality interface where each semantic unit jointly stores a natural language description and a 3D Gaussian representation. The 3D Gaussians enable compact storage and fast rendering of task-relevant images via Gaussian splatting. To enable efficient incremental construction, we further propose a Gaussian Estimator that analytically derives Gaussian parameters from dense point clouds without gradient-based optimization. Experiments on ObjectNav, InstNav, and SQA tasks show that GLMap effectively enhances target navigation and contextual reasoning, while remaining compatible with large-model-based methods in a zero-shot manner. The code is available at https://github.com/sx-zhang/GLMap. --- ### Less is More: Geometric Unlearning for LLMs with Minimal Data Disclosure Authors: Chenchen Tan, Xinghao Li, Shujie Cui, Youyang Qu, Cunjian Chen, Longxiang Gao Published: 2026-05-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.01735v2 As large language models (LLMs) are increasingly deployed in real-world systems, they must support post-hoc removal of specific content to meet privacy and governance requirements. This motivates selective unlearning, which suppresses information about a particular entity or topic while preserving the LLM's general utility. However, most existing LLM unlearning methods require access to the original training corpus and rely on output-level refusal tuning or broad gradient updates, creating a tension among unlearning strength, non-target preservation, and data availability. We propose Geometric Unlearning (GU), an approach that operates directly on the model's prompt-conditioned hidden states without access to the original training corpus. Specifically, GU distills a compact, low-rank safe-behavior subspace from a small set of safe reference prompts and uses lightweight anchor-in-context synthetic prompts to trigger localized, projection-based alignment of hidden representations to this safe subspace. A teacher-distillation regularizer on synthetic non-target anchors further reduces collateral drift. Across privacy-oriented unlearning benchmarks (ToFU and UnlearnPII), GU achieves strong target suppression with minimal impact on non-target performance, demonstrating that effective unlearning can be achieved with minimal synthetic data. --- ### Query-Dependent Use of Generated Descriptions for Reliable Visual Question Answering Authors: Zeshang Li, Shuoyang Zhang Published: 2026-05-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.01733v5 Vision-Language Models (VLMs) hallucinate objects that are not present, and a growing line of work tries to curb this by feeding the model its own generated caption as auxiliary evidence -- assuming that a caption, once available, is something to consume. We show this fails: naively appending a caption can lower accuracy rather than raise it, dropping Qwen2.5-VL-3B† on HallusionBench by nearly ten points. To understand why, we build GD-Probe, a diagnostic set that pairs a global and a detail question on the same image, so that any difference in caption effect is attributable to the question alone. Caption utility proves to be a per-query property: the same caption helps global questions and harms detail ones, through a single mechanism -- an embedded caption competes with the image for attention and pulls the model's evidence onto its own text -- whose sign is set by whether the caption covers the queried content. Crucially, this regime is readable from quantities the decoder already emits, with no attention access or grounding. We turn this into GEASS (Gated Evidence-Adaptive Selective Caption Trust), a training-free, logit-level module that decides per query how much of the caption to trust, gating it by the clean path's confidence, weighting it by the entropy reduction it induces, and raising the evidence bar when the two pathways disagree. Across four VLMs and two benchmarks (POPE and HallusionBench), GEASS improves over both vanilla inference and contrastive decoding under a single fixed setting, adding only two forward passes and no parameters. --- ### GEASS: Gated Evidence-Adaptive Selective Caption Trust for Vision-Language Models Authors: Zeshang Li, Shuoyang Zhang Published: 2026-05-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.01733v4 Vision-Language Models (VLMs) hallucinate objects that are not present, and a growing line of work tries to curb this by feeding the model its own generated caption as auxiliary evidence -- assuming that a caption, once available, is something to consume. We show this fails: naively appending a caption can lower accuracy rather than raise it, dropping Qwen2.5-VL-3B† on HallusionBench by nearly ten points. To understand why, we build GD-Probe, a diagnostic set that pairs a global and a detail question on the same image, so that any difference in caption effect is attributable to the question alone. Caption utility proves to be a per-query property: the same caption helps global questions and harms detail ones, through a single mechanism -- an embedded caption competes with the image for attention and pulls the model's evidence onto its own text -- whose sign is set by whether the caption covers the queried content. Crucially, this regime is readable from quantities the decoder already emits, with no attention access or grounding. We turn this into GEASS (Gated Evidence-Adaptive Selective Caption Trust), a training-free, logit-level module that decides per query how much of the caption to trust, gating it by the clean path's confidence, weighting it by the entropy reduction it induces, and raising the evidence bar when the two pathways disagree. Across four VLMs and two benchmarks (POPE and HallusionBench), GEASS improves over both vanilla inference and contrastive decoding under a single fixed setting, adding only two forward passes and no parameters. --- ### EGAD: Entropy-Guided Adaptive Distillation for Token-Level Knowledge Transfer Authors: Hao Zhang, Zhibin Zhang, Guangxin Wu, Wanyi Ning, Jiafeng Guo, Xueqi Cheng Published: 2026-05-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.01732v1 Large language models (LLMs) have achieved remarkable performance across diverse domains, yet their enormous computational and memory requirements hinder deployment in resource-constrained environments. Knowledge distillation offers a promising solution by transferring knowledge from a large teacher model to a smaller student model. However, existing distillation methods typically treat all tokens equally, ignoring the fact that different tokens contribute unequally to model decisions. This can lead to inefficient knowledge transfer and reduced learning effectiveness. To address this limitation, we propose an entropy-based adaptive distillation strategy that dynamically adjusts the training process at the token level. Our method leverages the teacher's output entropy to guide three aspects of distillation. Specifically, we introduce a token-level curriculum by dynamically shifting focus from low- to high-entropy tokens during training. We further adjust the distillation temperature based on token entropy to better capture teacher confidence patterns. Moreover, we employ a dual-branch architecture for efficient logits-only distillation on easy tokens and deeper feature-based distillation on difficult tokens. Extensive experiments validate the soundness and effectiveness of our method. ---