# Research Papers — 2026-03 · bundle page 51 of 243 > Full-text markdown of papers #2501–2550 of 12123 published in 2026-03, newest first. AI-readable mirrors of the full 12123-paper 2026-03 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-03/page/51 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/50.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/52.md) ### SafeFlow: Real-Time Text-Driven Humanoid Whole-Body Control via Physics-Guided Rectified Flow and Selective Safety Gating Authors: Hanbyel Cho, Sang-Hun Kim, Jeonguk Kang, Donghan Koo Published: 2026-03-25 Categories: cs.RO, cs.AI, eess.SY arXiv: https://arxiv.org/abs/2603.23983v2 Recent advances in real-time interactive text-driven motion generation have enabled humanoids to perform diverse behaviors. However, kinematics-only generators often exhibit physical hallucinations, producing motion trajectories that are physically infeasible to track with a downstream motion tracking controller or unsafe for real-world deployment. These failures often arise from the lack of explicit physics-aware objectives for real-robot execution and become more severe under out-of-distribution (OOD) user inputs. Hence, we propose SafeFlow, a text-driven humanoid whole-body control framework that combines physics-guided motion generation with a 3-Stage Safety Gate driven by explicit risk indicators. SafeFlow adopts a two-level architecture. At the high level, we generate motion trajectories using Physics-Guided Rectified Flow Matching in a VAE latent space to improve real-robot executability, and further accelerate sampling via Reflow to reduce the number of function evaluations (NFE) for real-time control. The 3-Stage Safety Gate enables selective execution by detecting semantic OOD prompts using a Mahalanobis score in text-embedding space, filtering unstable generations via a directional sensitivity discrepancy metric, and enforcing final hard kinematic constraints such as joint and velocity limits before passing the generated trajectory to a low-level motion tracking controller. Extensive experiments on the Unitree G1 demonstrate that SafeFlow outperforms diffusion- and retargeting-based baselines in success rate, physical compliance, and inference speed while preserving motion diversity, with consistent gains across three downstream tracking controllers. --- ### SafeFlow: Real-Time Text-Driven Humanoid Whole-Body Control via Physics-Guided Rectified Flow and Selective Safety Gating Authors: Hanbyel Cho, Sang-Hun Kim, Jeonguk Kang, Donghan Koo Published: 2026-03-25 Categories: cs.RO, cs.AI, eess.SY arXiv: https://arxiv.org/abs/2603.23983v1 Recent advances in real-time interactive text-driven motion generation have enabled humanoids to perform diverse behaviors. However, kinematics-only generators often exhibit physical hallucinations, producing motion trajectories that are physically infeasible to track with a downstream motion tracking controller or unsafe for real-world deployment. These failures often arise from the lack of explicit physics-aware objectives for real-robot execution and become more severe under out-of-distribution (OOD) user inputs. Hence, we propose SafeFlow, a text-driven humanoid whole-body control framework that combines physics-guided motion generation with a 3-Stage Safety Gate driven by explicit risk indicators. SafeFlow adopts a two-level architecture. At the high level, we generate motion trajectories using Physics-Guided Rectified Flow Matching in a VAE latent space to improve real-robot executability, and further accelerate sampling via Reflow to reduce the number of function evaluations (NFE) for real-time control. The 3-Stage Safety Gate enables selective execution by detecting semantic OOD prompts using a Mahalanobis score in text-embedding space, filtering unstable generations via a directional sensitivity discrepancy metric, and enforcing final hard kinematic constraints such as joint and velocity limits before passing the generated trajectory to a low-level motion tracking controller. Extensive experiments on the Unitree G1 demonstrate that SafeFlow outperforms prior diffusion-based methods in success rate, physical compliance, and inference speed, while maintaining diverse expressiveness. --- ### Circuit-Inspired High-Order Neural Networks with Unified Neural Dynamics Modeling for PDE Solving and Visual Perception Authors: Tongfei Chen, Jingying Yang, Linlin Yang, Juan Zhang, Jinhu Lü, David Doermann, Chunyu Xie, Long He, Tian Wang, Guodong Guo, Baochang Zhang Published: 2026-03-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.23977v2 Deep networks often rely on architectural heuristics to shape representation evolution, limiting their ability to model data governed by intrinsic dynamics. We present the Circuit-inspired High-Order Neural Network (CHONN), a modular framework that treats representation evolution as a latent potential process and increases its effective order through Kirchhoff-inspired cascade composition. A single Kirchhoff Neural Cell implements a stable first-order update, while serially composed cells form higher-order dynamical operators within one block. This construction is interpretable, numerically stable and compatible with common neural backbones. Theoretical analysis shows that cascaded cells induce end-to-end high-order operators, and controlled experiments demonstrate that intra-block high-order construction differs from generic depth stacking, especially on derivative-sensitive measures. Across steady-state operator learning, long-horizon physical forecasting and ImageNet-1K recognition, CHONN improves structural fidelity, rollout stability and visual representation learning. These results identify high-order circuit composition as a general principle for neural dynamics modeling. --- ### SilLang: Improving Gait Recognition with Silhouette Language Encoding Authors: Ruiyi Zhan, Guozhen Peng, Canyu Chen, Jian Lei, Annan Li Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.23976v1 Gait silhouettes, which can be encoded into binary gait codes, are widely adopted to representing motion patterns of pedestrian. Recent approaches commonly leverage visual backbones to encode gait silhouettes, achieving successful performance. However, they primarily focus on continuous visual features, overlooking the discrete nature of binary silhouettes that inherently share a discrete encoding space with natural language. Large Language Models (LLMs) have demonstrated exceptional capability in extracting discriminative features from discrete sequences and modeling long-range dependencies, highlighting their potential to capture temporal motion patterns by identifying subtle variations. Motivated by these observations, we explore bridging binary gait silhouettes and natural language within a binary encoding space. However, the encoding spaces of text tokens and binary gait silhouettes remain misaligned, primarily due to differences in token frequency and density. To address this issue, we propose the Contour-Velocity Tokenizer, which encodes binary gait silhouettes while reshaping their distribution to better align with the text token space. We then establish a dual-branch framework termed Silhouette Language Model, which enhances visual silhouettes by integrating discrete linguistic embeddings derived from LLMs. Implemented on mainstream gait backbones, SilLang consistently improves state-of-the-art methods across SUSTech1K, GREW, and Gait3D. --- ### HyDRA: Hybrid Domain-Aware Robust Architecture for Heterogeneous Collaborative Perception Authors: Minwoo Song, Minhee Kang, Heejin Ahn Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.23975v1 In collaborative perception, an agent's performance can be degraded by heterogeneity arising from differences in model architecture or training data distributions. To address this challenge, we propose HyDRA (Hybrid Domain-Aware Robust Architecture), a unified pipeline that integrates intermediate and late fusion within a domain-aware framework. We introduce a lightweight domain classifier that dynamically identifies heterogeneous agents and assigns them to the late-fusion branch. Furthermore, we propose anchor-guided pose graph optimization to mitigate localization errors inherent in late fusion, leveraging reliable detections from intermediate fusion as fixed spatial anchors. Extensive experiments demonstrate that, despite requiring no additional training, HyDRA achieves performance comparable to state-of-the-art heterogeneity-aware CP methods. Importantly, this performance is maintained as the number of collaborating agents increases, enabling zero-cost scaling without retraining. --- ### Machine vision with small numbers of detected photons per inference Authors: Shi-Yuan Ma, Jérémie Laydevant, Mandar M. Sohoni, Logan G. Wright, Tianyu Wang, Peter L. McMahon Published: 2026-03-25 Categories: physics.optics, cs.CV, cs.ET, cs.LG, physics.data-an arXiv: https://arxiv.org/abs/2603.23974v1 Machine vision, including object recognition and image reconstruction, is a central technology in many consumer devices and scientific instruments. The design of machine-vision systems has been revolutionized by the adoption of end-to-end optimization, in which the optical front end and the post-processing back end are jointly optimized. However, while machine vision currently works extremely well in moderate-light or bright-light situations -- where a camera may detect thousands of photons per pixel and billions of photons per frame -- it is far more challenging in very low-light situations. We introduce photon-aware neuromorphic sensing (PANS), an approach for end-to-end optimization in highly photon-starved scenarios. The training incorporates knowledge of the low photon budget and the stochastic nature of light detection when the average number of photons per pixel is near or less than 1. We report a proof-of-principle experimental demonstration in which we performed low-light image classification using PANS, achieving 73% (82%) accuracy on FashionMNIST with an average of only 4.9 (17) detected photons in total per inference, and 86% (97%) on MNIST with 8.6 (29) detected photons -- orders of magnitude more photon-efficient than conventional approaches. We also report simulation studies showing how PANS could be applied to other classification, event-detection, and image-reconstruction tasks. By taking into account the statistics of measurement results for non-classical states or alternative sensing hardware, PANS could in principle be adapted to enable high-accuracy results in quantum and other photon-starved setups. --- ### SLAT-Phys: Fast Material Property Field Prediction from Structured 3D Latents Authors: Rocktim Jyoti Das, Dinesh Manocha Published: 2026-03-25 Categories: cs.CV, cs.GR, cs.RO arXiv: https://arxiv.org/abs/2603.23973v1 Estimating the material property field of 3D assets is critical for physics-based simulation, robotics, and digital twin generation. Existing vision-based approaches are either too expensive and slow or rely on 3D information. We present SLAT-Phys, an end-to-end method that predicts spatially varying material property fields of 3D assets directly from a single RGB image without explicit 3D reconstruction. Our approach leverages spatially organised latent features from a pretrained 3D asset generation model that encodes rich geometry and semantic prior, and trains a lightweight neural decoder to estimate Young's modulus, density, and Poisson's ratio. The coarse volumetric layout and semantic cues of the latent representation about object geometry and appearance enable accurate material estimation. Our experiments demonstrate that our method provides competitive accuracy in predicting continuous material parameters when compared against prior approaches, while significantly reducing computation time. In particular, SLAT-Phys requires only 9.9 seconds per object on an NVIDIA RTXA5000 GPU and avoids reconstruction and voxelization preprocessing. This results in 120x speedup compared to prior methods and enables faster material property estimation from a single image. --- ### Grounding Arabic LLMs in the Doha Historical Dictionary: Retrieval-Augmented Understanding of Quran and Hadith Authors: Somaya Eltanbouly, Samer Rashwani Published: 2026-03-25 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2603.23972v1 Large language models (LLMs) have achieved remarkable progress in many language tasks, yet they continue to struggle with complex historical and religious Arabic texts such as the Quran and Hadith. To address this limitation, we develop a retrieval-augmented generation (RAG) framework grounded in diachronic lexicographic knowledge. Unlike prior RAG systems that rely on general-purpose corpora, our approach retrieves evidence from the Doha Historical Dictionary of Arabic (DHDA), a large-scale resource documenting the historical development of Arabic vocabulary. The proposed pipeline combines hybrid retrieval with an intent-based routing mechanism to provide LLMs with precise, contextually relevant historical information. Our experiments show that this approach improves the accuracy of Arabic-native LLMs, including Fanar and ALLaM, to over 85\%, substantially reducing the performance gap with Gemini, a proprietary large-scale model. Gemini also serves as an LLM-as-a-judge system for automatic evaluation in our experiments. The automated judgments were verified through human evaluation, demonstrating high agreement (kappa = 0.87). An error analysis further highlights key linguistic challenges, including diacritics and compound expressions. These findings demonstrate the value of integrating diachronic lexicographic resources into retrieval-augmented generation frameworks to enhance Arabic language understanding, particularly for historical and religious texts. The code and resources are publicly available at: https://github.com/somayaeltanbouly/Doha-Dictionary-RAG. --- ### The Price Reversal Phenomenon: When Cheaper Reasoning Models Cost More Authors: Lingjiao Chen, Chi Zhang, Yeye He, Ion Stoica, Matei Zaharia, James Zou Published: 2026-03-25 Categories: cs.CL, cs.AI, cs.GT, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2603.23971v2 Developers and consumers increasingly choose reasoning models (RMs) based on their listed API prices. However, how accurately do these prices reflect actual inference costs? We conduct the first systematic study of this question, evaluating 8 frontier RMs across 12 diverse tasks covering competition math, science QA, code generation, and multi-domain agents. We uncover the pricing reversal phenomenon: in 32% of model-pair comparisons, the model with a lower listed price actually incurs a higher total cost, with reversal magnitude reaching up to 28x. For example, Gemini 3 Flash's listed price is 80% cheaper than GPT-5.4's, yet its actual cost across all tasks is 38% higher. We build a formal cost attribution framework based on Shapley value, and leverage it to trace the dominating contributors to vast heterogeneity in thinking token consumption and number of interaction turns: on the same query, one model may use 900% more thinking tokens than another, or 10x more turns of environment interactions. We further show that per-query cost prediction is fundamentally difficult: repeated runs of the same query yield thinking token variation up to 9.7x, establishing an irreducible noise floor for any predictor. Thus, we propose cost distribution prediction as an open challenge. Our findings demonstrate that listed API pricing is an unreliable proxy for actual cost, calling for cost-aware model selection and transparent per-request cost monitoring. --- ### Wireless communication empowers online scheduling of partially-observable transportation multi-robot systems in a smart factory Authors: Yaxin Liao, Qimei Cui, Kwang-Cheng Chen, Xiong Li, Jinlian Chen, Xiyu Zhao, Xiaofeng Tao, Ping Zhang Published: 2026-03-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.23967v1 Achieving agile and reconfigurable production flows in smart factories depends on online multi-robot task assignment (MRTA), which requires online collision-free and congestion-free route scheduling of transportation multi-robot systems (T-MRS), e.g., collaborative automatic guided vehicles (AGVs). Due to the real-time operational requirements and dynamic interactions between T-MRS and production MRS, online scheduling under partial observability in dynamic factory environments remains a significant and under-explored challenge. This paper proposes a novel communication-enabled online scheduling framework that explicitly couples wireless machine-to-machine (M2M) networking with route scheduling, enabling AGVs to exchange intention information, e.g., planned routes, to overcome partial observations and assist complex computation of online scheduling. Specifically, we determine intelligent AGVs' intention and sensor data as new M2M traffic and tailor the retransmission-free multi-link transmission networking to meet real-time operation demands. This scheduling-oriented networking is then integrated with a simulated annealing-based MRTA scheme and a congestion-aware A*-based route scheduling method. The integrated communication and scheduling scheme allows AGVs to dynamically adjust collision-free and congestion-free routes with reduced computational overhead. Numerical experiments shows the impacts from wireless communication on the performance of T-MRS and suggest that the proposed integrated scheme significantly enhances scheduling efficiency compared to other baselines, even under high AGV load conditions and limited channel resources. Moreover, the results reveal that the scheduling-oriented wireless M2M communication design fundamentally differs from human-to-human communications, implying new technological opportunities in a wireless networked smart factory. --- ### Policy-Guided Threat Hunting: An LLM enabled Framework with Splunk SOC Triage Authors: Rishikesh Sahay, Bell Eapen, Weizhi Meng, Md Rasel Al Mamun, Nikhil Kumar Dora, Manjusha Sumasadan, Sumit Kumar Tetarave, Elyson De La Cruz Published: 2026-03-25 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.23966v3 With frequently evolving Advanced Persistent Threats (APTs) in cyberspace, traditional security solutions approaches have become inadequate for threat hunting for organizations. Moreover, SOC (Security Operation Centers) analysts are often overwhelmed and struggle to analyze the huge volume of logs received from diverse devices in organizations. To address these challenges, we propose an automated and dynamic threat hunting framework for monitoring evolving threats, adapting to changing network conditions, and performing risk-based prioritization for the mitigation of suspicious and malicious traffic. By integrating Agentic AI with Splunk, an established SIEM platform, we developed a unique threat hunting framework. The framework systematically and seamlessly integrates different threat hunting modules together, ranging from traffic ingestion to anomaly assessment using a reconstruction-based autoencoder, deep reinforcement learning (DRL) with two layers for initial triage, and a large language model (LLM) for contextual analysis. We evaluated the framework against a publicly available benchmark dataset, as well as against a simulated dataset. The experimental results show that the framework can effectively adapt to different SOC objectives autonomously and identify suspicious and malicious traffic. The framework enhances operational effectiveness by supporting SOC analysts in their decision-making to block, allow, or monitor network traffic. This study thus enhances cybersecurity and threat hunting literature by presenting the novel threat hunting framework for security decision-making, as well as promoting cumulative research efforts to develop more effective frameworks to battle continuously evolving cyber threats. --- ### From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments Authors: Lijing Luo, Yiben Luo, Alexey Gorbatovski, Sergey Kovalchuk, Xiaodan Liang Published: 2026-03-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.23964v2 The remarkable progress of reinforcement learning (RL) is intrinsically tied to the environments used to train and evaluate artificial agents. Moving beyond traditional qualitative reviews, this work presents a large-scale, data-driven empirical investigation into the evolution of RL environments. By programmatically processing a massive corpus of academic literature and rigorously distilling over 2,000 core publications, we propose a quantitative methodology to map the transition from isolated physical simulations to generalist, language-driven foundation agents. Implementing a novel, multi-dimensional taxonomy, we systematically analyze benchmarks against diverse application domains and requisite cognitive capabilities. Our automated semantic and statistical analysis reveals a profound, data-verified paradigm shift: the bifurcation of the field into a "Semantic Prior" ecosystem dominated by Large Language Models (LLMs) and a "Domain-Specific Generalization" ecosystem. Furthermore, we characterize the "cognitive fingerprints" of these distinct domains to uncover the underlying mechanisms of cross-task synergy, multi-domain interference, and zero-shot generalization. Ultimately, this study offers a rigorous, quantitative roadmap for designing the next generation of Embodied Semantic Simulators, bridging the gap between continuous physical control and high-level logical reasoning. --- ### GRMLR: Knowledge-Enhanced Small-Data Learning for Deep-Sea Cold Seep Stage Inference Authors: Chenxu Zhou, Zelin Liu, Rui Cai, Houlin Gong, Yikang Yu, Jia Zeng, Yanru Pei, Liang Zhang, Weishu Zhao, Xiaofeng Gao Published: 2026-03-25 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2603.23961v1 Deep-sea cold seep stage assessment has traditionally relied on costly, high-risk manned submersible operations and visual surveys of macrofauna. Although microbial communities provide a promising and more cost-effective alternative, reliable inference remains challenging because the available deep-sea dataset is extremely small ($n = 13$) relative to the microbial feature dimension ($p = 26$), making purely data-driven models highly prone to overfitting. To address this, we propose a knowledge-enhanced classification framework that incorporates an ecological knowledge graph as a structural prior. By fusing macro-microbe coupling and microbial co-occurrence patterns, the framework internalizes established ecological logic into a \underline{\textbf{G}}raph-\underline{\textbf{R}}egularized \underline{\textbf{M}}ultinomial \underline{\textbf{L}}ogistic \underline{\textbf{R}}egression (GRMLR) model, effectively constraining the feature space through a manifold penalty to ensure biologically consistent classification. Importantly, the framework removes the need for macrofauna observations at inference time: macro-microbe associations are used only to guide training, whereas prediction relies solely on microbial abundance profiles. Experimental results demonstrate that our approach significantly outperforms standard baselines, highlighting its potential as a robust and scalable framework for deep-sea ecological assessment. --- ### Leave No Stone Unturned: Uncovering Holistic Audio-Visual Intrinsic Coherence for Deepfake Detection Authors: Jielun Peng, Yabin Wang, Yaqi Li, Long Kong, Xiaopeng Hong Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.23960v1 The rapid progress of generative AI has enabled hyper-realistic audio-visual deepfakes, intensifying threats to personal security and social trust. Most existing deepfake detectors rely either on uni-modal artifacts or audio-visual discrepancies, failing to jointly leverage both sources of information. Moreover, detectors that rely on generator-specific artifacts tend to exhibit degraded generalization when confronted with unseen forgeries. We argue that robust and generalizable detection should be grounded in intrinsic audio-visual coherence within and across modalities. Accordingly, we propose HAVIC, a Holistic Audio-Visual Intrinsic Coherence-based deepfake detector. HAVIC first learns priors of modality-specific structural coherence, inter-modal micro- and macro-coherence by pre-training on authentic videos. Based on the learned priors, HAVIC further performs holistic adaptive aggregation to dynamically fuse audio-visual features for deepfake detection. Additionally, we introduce HiFi-AVDF, a high-fidelity audio-visual deepfake dataset featuring both text-to-video and image-to-video forgeries from state-of-the-art commercial generators. Extensive experiments across several benchmarks demonstrate that HAVIC significantly outperforms existing state-of-the-art methods, achieving improvements of 9.39% AP and 9.37% AUC on the most challenging cross-dataset scenario. Our code and dataset are available at https://github.com/tuffy-studio/HAVIC. --- ### PointRFT: Explicit Reinforcement Fine-tuning for Point Cloud Few-shot Learning Authors: Yankai Wang, Yiding Sun, Qirui Wang, Pengbo Li, Chaoyi Lu, Dongxu Zhang Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.23957v1 Understanding spatial dynamics and semantics in point cloud is fundamental for comprehensive 3D comprehension. While reinforcement learning algorithms such as Group Relative Policy Optimization (GRPO) have recently achieved remarkable breakthroughs in large language models by incentivizing reasoning capabilities through strategic reward design, their potential remains largely unexplored in the 3D perception domain. This naturally raises a pivotal question: Can RL-based methods effectively empower 3D point cloud fine-tuning? In this paper, we propose PointRFT, the first reinforcement fine-tuning paradigm tailored specifically for point cloud representation learning. We select three prevalent 3D foundation models and devise specialized accuracy reward and dispersion reward functions to stabilize training and mitigate distribution shifts. Through comprehensive few-shot classification experiments comparing distinct training paradigms, we demonstrate that PointRFT consistently outperforms vanilla supervised fine-tuning (SFT) across diverse benchmarks. Furthermore, when organically integrated into a hybrid Pretraining-SFT-RFT paradigm, the representational capacity of point cloud foundation models is substantially unleashed, achieving state-of-the-art performance particularly under data-scarce scenarios. --- ### SynMVCrowd: A Large Synthetic Benchmark for Multi-view Crowd Counting and Localization Authors: Qi Zhang, Daijie Chen, Yunfei Gong, Hui Huang Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.23956v1 Existing multi-view crowd counting and localization methods are evaluated under relatively small scenes with limited crowd numbers, camera views, and frames. This makes the evaluation and comparison of existing methods impractical, as small datasets are easily overfit by these methods. To avoid these issues, 3DROM proposes a data augmentation method. Instead, in this paper, we propose a large synthetic benchmark, SynMVCrowd, for more practical evaluation and comparison of multi-view crowd counting and localization tasks. The SynMVCrowd benchmark consists of 50 synthetic scenes with a large number of multi-view frames and camera views and a much larger crowd number (up to 1000), which is more suitable for large-scene multi-view crowd vision tasks. Besides, we propose strong multi-view crowd localization and counting baselines that outperform all comparison methods on the new SynMVCrowd benchmark. Moreover, we prove that better domain transferring multi-view and single-image counting performance could be achieved with the aid of the benchmark on novel new real scenes. As a result, the proposed benchmark could advance the research for multi-view and single-image crowd counting and localization to more practical applications. The codes and datasets are here: https://github.com/zqyq/SynMVCrowd. --- ### VOLMO: Versatile and Open Large Models for Ophthalmology Authors: Zhenyue Qin, Younjoon Chung, Elijah Lee, Wanyue Feng, Xuguang Ai, Serina Applebaum, Minjie Zou, Yang Liu, Pan Xiao, Mac Singer, Amisha Dave, Aidan Gilson et al. Published: 2026-03-25 Categories: cs.CV, cs.ET arXiv: https://arxiv.org/abs/2603.23953v2 Vision impairment affects millions globally, and early detection is critical to preventing irreversible vision loss. Ophthalmology workflows require clinicians to integrate medical images, structured clinical data, and free-text notes to determine disease severity and management, which is time-consuming and burdensome. Recent multimodal large language models (MLLMs) show promise, but existing general and medical MLLMs perform poorly in ophthalmology, and few ophthalmology-specific MLLMs are openly available. We present VOLMO (Versatile and Open Large Models for Ophthalmology), a model-agnostic, data-open framework for developing ophthalmology-specific MLLMs. VOLMO includes three stages: ophthalmology knowledge pretraining on 86,965 image-text pairs from 26,569 articles across 82 journals; domain task fine-tuning on 26,929 annotated instances spanning 12 eye conditions for disease screening and severity classification; and multi-step clinical reasoning on 913 patient case reports for assessment, planning, and follow-up care. Using this framework, we trained a compact 2B-parameter MLLM and compared it with strong baselines, including InternVL-2B, LLaVA-Med-7B, MedGemma-4B, MedGemma-27B, and RETFound. We evaluated these models on image description generation, disease screening and staging classification, and assessment-and-management generation, with additional manual review by two healthcare professionals and external validation on three independent cohorts for age-related macular degeneration and diabetic retinopathy. Across settings, VOLMO-2B consistently outperformed baselines, achieving stronger image description performance, an average F1 of 87.4% across 12 eye conditions, and higher scores in external validation. --- ### From AI Assistant to AI Scientist: Autonomous Discovery of LLM-RL Algorithms with LLM Agents Authors: Sirui Xia, Yikai Zhang, Aili Chen, Siye Wu, Siyu Yuan, Yanghua Xiao Published: 2026-03-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.23951v1 Discovering improved policy optimization algorithms for language models remains a costly manual process requiring repeated mechanism-level modification and validation. Unlike simple combinatorial code search, this problem requires searching over algorithmic mechanisms tightly coupled with training dynamics while reusing empirical evidence across iterations. We propose POISE, a closed-loop framework for automated discovery of policy optimization algorithms for language models. POISE maintains a structured, genealogically linked archive linking proposals, executable implementations, standardized evaluations, and natural-language reflections to support evidence-driven iteration. In mathematical reasoning experiments starting from GRPO, POISE evaluates 64 candidate algorithms and discovers improved mechanisms, including analytic-variance scaling and validity masking. The best variant improves weighted Overall from 47.8 to 52.5 (+4.6) and increases AIME25 pass@32 from 26.7% to 43.3%, demonstrating the feasibility of automated policy optimization discovery while supporting interpretable design principles. --- ### Argument Mining as a Text-to-Text Generation Task Authors: Masayuki Kawarada, Tsutomu Hirao, Wataru Uchida, Masaaki Nagata Published: 2026-03-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.23949v1 Argument Mining(AM) aims to uncover the argumentative structures within a text. Previous methods require several subtasks, such as span identification, component classification, and relation classification. Consequently, these methods need rule-based postprocessing to derive argumentative structures from the output of each subtask. This approach adds to the complexity of the model and expands the search space of the hyperparameters. To address this difficulty, we propose a simple yet strong method based on a text-to-text generation approach using a pretrained encoder-decoder language model. Our method simultaneously generates argumentatively annotated text for spans, components, and relations, eliminating the need for task-specific postprocessing and hyperparameter tuning. Furthermore, because it is a straightforward text-to-text generation method, we can easily adapt our approach to various types of argumentative structures. Experimental results demonstrate the effectiveness of our method, as it achieves state-of-the-art performance on three different types of benchmark datasets: the Argument-annotated Essays Corpus(AAEC), AbstRCT, and the Cornell eRulemaking Corpus(CDCP) --- ### Variable-Length Audio Fingerprinting Authors: Hongjie Chen, Hanyu Meng, Huimin Zeng, Ryan A. Rossi, Lie Lu, Josh Kimball Published: 2026-03-25 Categories: cs.SD, cs.AI, cs.MM arXiv: https://arxiv.org/abs/2603.23947v2 Audio fingerprinting converts audio to much lower-dimensional representations, allowing distorted recordings to still be recognized as their originals through similar fingerprints. Existing deep learning approaches rigidly fingerprint fixed-length audio segments, thereby neglecting temporal dynamics during segmentation. To address limitations due to this rigidity, we propose Variable-Length Audio FingerPrinting (VLAFP), a novel method that supports variable-length fingerprinting. To the best of our knowledge, VLAFP is the first deep audio fingerprinting model capable of processing audio of variable length, for both training and testing. Our experiments show that VLAFP outperforms existing state-of-the-arts in live audio identification and audio retrieval across three real-world datasets. --- ### Variable-Length Audio Fingerprinting Authors: Hongjie Chen, Hanyu Meng, Huimin Zeng, Ryan A. Rossi, Lie Lu, Josh Kimball Published: 2026-03-25 Categories: cs.SD, cs.AI, cs.MM arXiv: https://arxiv.org/abs/2603.23947v1 Audio fingerprinting converts audio to much lower-dimensional representations, allowing distorted recordings to still be recognized as their originals through similar fingerprints. Existing deep learning approaches rigidly fingerprint fixed-length audio segments, thereby neglecting temporal dynamics during segmentation. To address limitations due to this rigidity, we propose Variable-Length Audio FingerPrinting (VLAFP), a novel method that supports variable-length fingerprinting. To the best of our knowledge, VLAFP is the first deep audio fingerprinting model capable of processing audio of variable length, for both training and testing. Our experiments show that VLAFP outperforms existing state-of-the-arts in live audio identification and audio retrieval across three real-world datasets. --- ### ChargeFlow: Flow-Matching Refinement of Charge-Conditioned Electron Densities Authors: Tri Minh Nguyen, Sherif Abdulkader Tawfik, Truyen Tran, Svetha Venkatesh Published: 2026-03-25 Categories: cond-mat.mtrl-sci, cs.LG arXiv: https://arxiv.org/abs/2603.23943v1 Accurate charge densities are central to electronic-structure theory, but computing charge-state-dependent densities with density functional theory remains too expensive for large-scale screening and defect workflows. We present ChargeFlow, a flow-matching refinement model that transforms a charge-conditioned superposition of atomic densities into the corresponding DFT electron density on the native periodic real-space grid using a 3D U-Net velocity field. Trained on 9,502 charged Materials Project-derived calculations and evaluated on an external 1,671-structure benchmark spanning perovskites, charged defects, diamond defects, metal-organic frameworks, and organic crystals, ChargeFlow is not uniformly best on every in-distribution class but is strongest on problems dominated by nonlocal charge redistribution and charge-state extrapolation, improving deformation-density error from 3.62% to 3.21% and charge- response cosine similarity from 0.571 to 0.655 relative to a ResNet baseline. The predicted densities remain chemically useful under downstream analysis, yielding successful Bader partitioning on all 1,671 benchmark structures and high-fidelity electrostatic potentials, which positions flow matching as a practical density-refinement strategy for charged materials. --- ### High-Fidelity Face Content Recovery via Tamper-Resilient Versatile Watermarking Authors: Peipeng Yu, Jinfeng Xie, Chengfu Ou, Xiaoyu Zhou, Jianwei Fei, Yunshu Dai, Zhihua Xia, Chip Hong Chang Published: 2026-03-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.23940v2 The proliferation of AIGC-driven face manipulation and deepfakes poses severe threats to media provenance, integrity, and copyright protection. Existing versatile watermarking systems typically rely on embedding explicit localization payloads, which introduces a fidelity--functionality trade-off: larger localization signals degrade visual quality and often reduce decoding robustness under strong generative edits. Moreover, these methods rarely support content recovery, limiting their forensic value when original evidence must be reconstructed. To address these challenges, we present VeriFi, a versatile watermarking framework that unifies copyright protection, pixel-level manipulation localization, and high-fidelity face content recovery. VeriFi makes three key contributions: (1) it embeds a compact semantic latent watermark that serves as a content-preserving prior, enabling faithful restoration even after severe manipulations; (2) it achieves fine-grained localization without dedicated payloads by correlating image features with decoded provenance signals; and (3) it introduces an AIGC attack simulator that combines latent-space mixing with seamless blending to enhance robustness against realistic deepfake pipelines. Extensive experiments on CelebA-HQ and FFHQ demonstrate that VeriFi consistently outperforms state-of-the-art baselines in watermark robustness, localization accuracy, and recovery quality, providing a practical and verifiable defense for deepfake forensics. --- ### High-Fidelity Face Content Recovery via Tamper-Resilient Versatile Watermarking Authors: Peipeng Yu, Jinfeng Xie, Chengfu Ou, Xiaoyu Zhou, Jianwei Fei, Yunshu Dai, Zhihua Xia, Chip Hong Chang Published: 2026-03-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.23940v1 The proliferation of AIGC-driven face manipulation and deepfakes poses severe threats to media provenance, integrity, and copyright protection. Prior versatile watermarking systems typically rely on embedding explicit localization payloads, which introduces a fidelity--functionality trade-off: larger localization signals degrade visual quality and often reduce decoding robustness under strong generative edits. Moreover, existing methods rarely support content recovery, limiting their forensic value when original evidence must be reconstructed. To address these challenges, we present VeriFi, a versatile watermarking framework that unifies copyright protection, pixel-level manipulation localization, and high-fidelity face content recovery. VeriFi makes three key contributions: (1) it embeds a compact semantic latent watermark that serves as an content-preserving prior, enabling faithful restoration even after severe manipulations; (2) it achieves fine-grained localization without embedding localization-specific artifacts by correlating image features with decoded provenance signals; and (3) it introduces an AIGC attack simulator that combines latent-space mixing with seamless blending to improve robustness to realistic deepfake pipelines. Extensive experiments on CelebA-HQ and FFHQ show that VeriFi consistently outperforms strong baselines in watermark robustness, localization accuracy, and recovery quality, providing a practical and verifiable defense for deepfake forensics. --- ### OmniACBench: A Benchmark for Evaluating Context-Grounded Acoustic Control in Omni-Modal Models Authors: Seunghee Kim, Bumkyu Park, Kyudan Jung, Joosung Lee, Soyoon Kim, Jeonghoon Kim, Taeuk Kim, Hwiyeol Jo Published: 2026-03-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.23938v2 Most testbeds for omni-modal models assess multimodal understanding via textual outputs, leaving it unclear whether these models can properly speak their answers. To study this, we introduce OmniACBench, a benchmark for evaluating context-grounded acoustic control in omni-modal models. Given a spoken instruction, a text script, and an image, a model must read the script aloud with an appropriate tone and manner. OmniACBench comprises 3,559 verified instances covering six acoustic features: speech rate, phonation, pronunciation, emotion, global accent, and timbre. Extensive experiments on eight models reveal their limitations in the proposed setting, despite their strong performance on prior textual-output evaluations. Our analyses show that the main bottleneck lies not in processing individual modalities, but in integrating multimodal context for faithful speech generation. Moreover, we identify three common failure modes-weak direct control, failed implicit inference, and failed multimodal grounding-providing insights for developing models that can verbalize responses effectively. --- ### OmniACBench: A Benchmark for Evaluating Context-Grounded Acoustic Control in Omni-Modal Models Authors: Seunghee Kim, Bumkyu Park, Kyudan Jung, Joosung Lee, Soyoon Kim, Jeonghoon Kim, Taeuk Kim, Hwiyeol Jo Published: 2026-03-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.23938v1 Most testbeds for omni-modal models assess multimodal understanding via textual outputs, leaving it unclear whether these models can properly speak their answers. To study this, we introduce OmniACBench, a benchmark for evaluating context-grounded acoustic control in omni-modal models. Given a spoken instruction, a text script, and an image, a model must read the script aloud with an appropriate tone and manner. OmniACBench comprises 3,559 verified instances covering six acoustic features: speech rate, phonation, pronunciation, emotion, global accent, and timbre. Extensive experiments on eight models reveal their limitations in the proposed setting, despite their strong performance on prior textual-output evaluations. Our analyses show that the main bottleneck lies not in processing individual modalities, but in integrating multimodal context for faithful speech generation. Moreover, we identify three common failure modes-weak direct control, failed implicit inference, and failed multimodal grounding-providing insights for developing models that can verbalize responses effectively. --- ### Dialogue to Question Generation for Evidence-based Medical Guideline Agent Development Authors: Zongliang Ji, Ziyang Zhang, Xincheng Tan, Matthew Thompson, Anna Goldenberg, Carl Yang, Rahul G. Krishnan, Fan Zhang Published: 2026-03-25 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.23937v1 Evidence-based medicine (EBM) is central to high-quality care, but remains difficult to implement in fast-paced primary care settings. Physicians face short consultations, increasing patient loads, and lengthy guideline documents that are impractical to consult in real time. To address this gap, we investigate the feasibility of using large language models (LLMs) as ambient assistants that surface targeted, evidence-based questions during physician-patient encounters. Our study focuses on question generation rather than question answering, with the aim of scaffolding physician reasoning and integrating guideline-based practice into brief consultations. We implemented two prompting strategies, a zero-shot baseline and a multi-stage reasoning variant, using Gemini 2.5 as the backbone model. We evaluated on a benchmark of 80 de-identified transcripts from real clinical encounters, with six experienced physicians contributing over 90 hours of structured review. Results indicate that while general-purpose LLMs are not yet fully reliable, they can produce clinically meaningful and guideline-relevant questions, suggesting significant potential to reduce cognitive burden and make EBM more actionable at the point of care. --- ### Revealing Multi-View Hallucination in Large Vision-Language Models Authors: Wooje Park, Insu Lee, Soohyun Kim, Jaeyun Jang, Minyoung Noh, Kyuhong Shim, Byonghyo Shim Published: 2026-03-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.23934v2 Large vision-language models (LVLMs) are increasingly being applied to multi-view image inputs captured from diverse viewpoints. Despite this growing use, current LVLMs often generate incorrect responses due to visual interference from non-target instances or viewpoints, a phenomenon we term multi-view hallucination (MVH). To systematically analyze this problem, we construct MVH-Bench, a benchmark comprising 4.8k question-answer pairs targeting two types of hallucination: cross-instance and cross-view. Empirical results show that MVH is prevalent across recent LVLMs. To address this issue, we propose Reference Shift Contrastive Decoding (RSCD), a training-free decoding technique that suppresses visual interference by generating negative logits through attention masking. Experiments on MVH-Bench with LLaVA-OneVision and Qwen2.5-VL demonstrate that RSCD improves performance by up to 25.7 and 94.8 points over existing hallucination mitigation methods, highlighting the effectiveness of RSCD. --- ### Revealing Multi-View Hallucination in Large Vision-Language Models Authors: Wooje Park, Insu Lee, Soohyun Kim, Jaeyun Jang, Minyoung Noh, Kyuhong Shim, Byonghyo Shim Published: 2026-03-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.23934v1 Large vision-language models (LVLMs) are increasingly being applied to multi-view image inputs captured from diverse viewpoints. However, despite this growing use, current LVLMs often confuse or mismatch visual information originating from different instances or viewpoints, a phenomenon we term multi-view hallucination. To systematically analyze this problem, we construct MVH-Bench, a benchmark comprising 4.8k question-answer pairs targeting two types of hallucination: cross-instance and cross-view. Empirical results show that recent LVLMs struggle to correctly associate visual evidence with its corresponding instance or viewpoint. To overcome this limitation, we propose Reference Shift Contrastive Decoding (RSCD), a training-free decoding technique that suppresses visual interference by generating negative logits through attention masking. Experiments on MVH-Bench with Qwen2.5-VL and LLaVA-OneVision demonstrate that RSCD consistently improves performance by up to 21.1 and 34.6 points over existing hallucination mitigation methods, highlighting the effectiveness of our approach. --- ### ORACLE: Orchestrate NPC Daily Activities using Contrastive Learning with Transformer-CVAE Authors: Seong-Eun Hong, JuYeong Hwang, RyunHa Lee, HyeongYeop Kang Published: 2026-03-25 Categories: cs.GR, cs.CL, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.23933v1 The integration of Non-player characters (NPCs) within digital environments has been increasingly recognized for its potential to augment user immersion and cognitive engagement. The sophisticated orchestration of their daily activities, reflecting the nuances of human daily routines, contributes significantly to the realism of digital environments. Nevertheless, conventional approaches often produce monotonous repetition, falling short of capturing the intricacies of real human activity plans. In response to this, we introduce ORACLE, a novel generative model for the synthesis of realistic indoor daily activity plans, ensuring NPCs' authentic presence in digital habitats. Exploiting the CASAS smart home dataset's 24-hour indoor activity sequences, ORACLE addresses challenges in the dataset, including its imbalanced sequential data, the scarcity of training samples, and the absence of pre-trained models encapsulating human daily activity patterns. ORACLE's training leverages the sequential data processing prowess of Transformers, the generative controllability of Conditional Variational Autoencoders (CVAE), and the discriminative refinement of contrastive learning. Our experimental results validate the superiority of generating NPC activity plans and the efficacy of our design strategies over existing methods. --- ### Optimal Variance-Dependent Regret Bounds for Infinite-Horizon MDPs Authors: Guy Zamir, Matthew Zurek, Yudong Chen Published: 2026-03-25 Categories: cs.LG, cs.IT, math.OC, stat.ML arXiv: https://arxiv.org/abs/2603.23926v1 Online reinforcement learning in infinite-horizon Markov decision processes (MDPs) remains less theoretically and algorithmically developed than its episodic counterpart, with many algorithms suffering from high ``burn-in'' costs and failing to adapt to benign instance-specific complexity. In this work, we address these shortcomings for two infinite-horizon objectives: the classical average-reward regret and the $γ$-regret. We develop a single tractable UCB-style algorithm applicable to both settings, which achieves the first optimal variance-dependent regret guarantees. Our regret bounds in both settings take the form $\tilde{O}( \sqrt{SA\,\text{Var}} + \text{lower-order terms})$, where $S,A$ are the state and action space sizes, and $\text{Var}$ captures cumulative transition variance. This implies minimax-optimal average-reward and $γ$-regret bounds in the worst case but also adapts to easier problem instances, for example yielding nearly constant regret in deterministic MDPs. Furthermore, our algorithm enjoys significantly improved lower-order terms for the average-reward setting. With prior knowledge of the optimal bias span $\Vert h^\star\Vert_\text{sp}$, our algorithm obtains lower-order terms scaling as $\Vert h^\star\Vert_\text{sp} S^2 A$, which we prove is optimal in both $\Vert h^\star\Vert_\text{sp}$ and $A$. Without prior knowledge, we prove that no algorithm can have lower-order terms smaller than $\Vert h^\star \Vert_\text{sp}^2 S A$, and we provide a prior-free algorithm whose lower-order terms scale as $\Vert h^\star\Vert_\text{sp}^2 S^3 A$, nearly matching this lower bound. Taken together, these results completely characterize the optimal dependence on $\Vert h^\star\Vert_\text{sp}$ in both leading and lower-order terms, and reveal a fundamental gap in what is achievable with and without prior knowledge. --- ### DP^2-VL: Private Photo Dataset Protection by Data Poisoning for Vision-Language Models Authors: Hongyi Miao, Jun Jia, Xincheng Wang, Qianli Ma, Wei Sun, Wangqiu Zhou, Dandan Zhu, Yewen Cao, Zhi Liu, Guangtao Zhai Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.23925v1 Recent advances in visual-language alignment have endowed vision-language models (VLMs) with fine-grained image understanding capabilities. However, this progress also introduces new privacy risks. This paper first proposes a novel privacy threat model named identity-affiliation learning: an attacker fine-tunes a VLM using only a few private photos of a target individual, thereby embedding associations between the target facial identity and their private property and social relationships into the model's internal representations. Once deployed via public APIs, this model enables unauthorized exposure of the target user's private information upon input of their photos. To benchmark VLMs' susceptibility to such identity-affiliation leakage, we introduce the first identity-affiliation dataset comprising seven typical scenarios appearing in private photos. Each scenario is instantiated with multiple identity-centered photo-description pairs. Experimental results demonstrate that mainstream VLMs like LLaVA, Qwen-VL, and MiniGPT-v2, can recognize facial identities and infer identity-affiliation relationships by fine-tuning on small-scale private photographic dataset, and even on synthetically generated datasets. To mitigate this privacy risk, we propose DP2-VL, the first Dataset Protection framework for private photos that leverages Data Poisoning. Though optimizing imperceptible perturbations by pushing the original representations toward an antithetical region, DP2-VL induces a dataset-level shift in the embedding space of VLMs'encoders. This shift separates protected images from clean inference images, causing fine-tuning on the protected set to overfit. Extensive experiments demonstrate that DP2-VL achieves strong generalization across models, robustness to diverse post-processing operations, and consistent effectiveness across varying protection ratios. --- ### DepthArb: Training-Free Depth-Arbitrated Generation for Occlusion-Robust Image Synthesis Authors: Hongjin Niu, Jiahao Wang, Xirui Hu, Weizhan Zhang, Lan Ma, Yuan Gao, Feng Lei Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.23924v2 Text-to-image models often struggle to synthesize correct occlusion relationships among multiple objects, especially in densely overlapping regions. Many training-free layout-guided methods enforce 2D spatial constraints but do not explicitly resolve depth-dependent attention competition, which can cause concept mixing and implausible occlusion. To address this problem, we propose DepthArb, a training-free framework that formulates occlusion generation as attention arbitration within a unified denoising trajectory. DepthArb employs two core occlusion-control mechanisms: Attention Arbitration Modulation suppresses background-object attention within foreground support according to relative depth, while Spatial Compactness Control limits attention dispersion to preserve object coherence. Because interference varies during generation, Occlusion Conflict Estimation constructs a shared spatial conflict field to adaptively weight both objectives. Through a unified spatial-text attention interface, DepthArb operates on U-Net cross-attention and the image-to-text component of MMDiT joint attention without model retraining. We further introduce OcclBench, a benchmark with continuous relative-depth specifications and occlusion-specific evaluation metrics. Experiments on OcclBench and public benchmarks show that DepthArb improves several layout and occlusion metrics over the evaluated baselines while maintaining competitive text-image alignment. --- ### DepthArb: Training-Free Depth-Arbitrated Generation for Occlusion-Robust Image Synthesis Authors: Hongjin Niu, Jiahao Wang, Xirui Hu, Weizhan Zhang, Lan Ma, Yuan Gao Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.23924v1 Text-to-image diffusion models frequently exhibit deficiencies in synthesizing accurate occlusion relationships of multiple objects, particularly within dense overlapping regions. Existing training-free layout-guided methods predominantly rely on rigid spatial priors that remain agnostic to depth order, often resulting in concept mixing or illogical occlusion. To address these limitations, we propose DepthArb, a training-free framework that resolves occlusion ambiguities by arbitrating attention competition between interacting objects. Specifically, DepthArb employs two core mechanisms: Attention Arbitration Modulation (AAM), which enforces depth-ordered visibility by suppressing background activations in overlapping regions, and Spatial Compactness Control (SCC), which preserves structural integrity by curbing attention divergence. These mechanisms enable robust occlusion generation without model retraining. To systematically evaluate this capability, we propose OcclBench, a comprehensive benchmark designed to evaluate diverse occlusion scenarios. Extensive evaluations demonstrate that DepthArb consistently outperforms state-of-the-art baselines in both occlusion accuracy and visual fidelity. As a plug-and-play method, DepthArb seamlessly enhances the compositional capabilities of diffusion backbones, offering a novel perspective on spatial layering within generative models. --- ### Elements of Conformal Prediction Authors: Matteo Sesia, Stefano Favaro Published: 2026-03-25 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2603.23923v2 Predictive inference is a fundamental task in statistics, traditionally addressed using parametric assumptions about the data distribution and detailed analyses of how models learn from data. In recent years, conformal prediction has emerged as an alternative framework that is well suited to modern applications involving high-dimensional data and complex machine learning models. Its appeal stems from being both distribution-free---relying mainly on symmetry assumptions such as exchangeability---and model-agnostic, treating the learning algorithm as a black box. Even under such limited assumptions, conformal prediction provides exact finite-sample guarantees, although these are typically marginal and require careful interpretation. This paper explains the core ideas of conformal prediction and reviews selected methods. Rather than offering an exhaustive survey, it aims to provide a clear conceptual entry point and a pedagogical overview of the field. --- ### Elements of Conformal Prediction for Statisticians Authors: Matteo Sesia, Stefano Favaro Published: 2026-03-25 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2603.23923v1 Predictive inference is a fundamental task in statistics, traditionally addressed using parametric assumptions about the data distribution and detailed analyses of how models learn from data. In recent years, conformal prediction has emerged as a rapidly growing alternative framework that is particularly well suited to modern applications involving high-dimensional data and complex machine learning models. Its appeal stems from being both distribution-free -- relying mainly on symmetry assumptions such as exchangeability -- and model-agnostic, treating the learning algorithm as a black box. Even under such limited assumptions, conformal prediction provides exact finite-sample guarantees, though these are typically of a marginal nature that requires careful interpretation. This paper explains the core ideas of conformal prediction and reviews selected methods. Rather than offering an exhaustive survey, it aims to provide a clear conceptual entry point and a pedagogical overview of the field. --- ### Uncertainty-Aware Vision-based Risk Object Identification via Conformal Risk Tube Prediction Authors: Kai-Yu Fu, Yi-Ting Chen Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.23919v1 We study object importance-based vision risk object identification (Vision-ROI), a key capability for hazard detection in intelligent driving systems. Existing approaches make deterministic decisions and ignore uncertainty, which could lead to safety-critical failures. Specifically, in ambiguous scenarios, fixed decision thresholds may cause premature or delayed risk detection and temporally unstable predictions, especially in complex scenes with multiple interacting risks. Despite these challenges, current methods lack a principled framework to model risk uncertainty jointly across space and time. We propose Conformal Risk Tube Prediction, a unified formulation that captures spatiotemporal risk uncertainty, provides coverage guarantees for true risks, and produces calibrated risk scores with uncertainty estimates. To conduct a systematic evaluation, we present a new dataset and metrics probing diverse scenario configurations with multi-risk coupling effects, which are not supported by existing datasets. We systematically analyze factors affecting uncertainty estimation, including scenario variations, per-risk category behavior, and perception error propagation. Our method delivers substantial improvements over prior approaches, enhancing vision-ROI robustness and downstream performance, such as reducing nuisance braking alerts. For more qualitative results, please visit our project webpage: https://hcis-lab.github.io/CRTP/ --- ### DecepGPT: Schema-Driven Deception Detection with Multicultural Datasets and Robust Multimodal Learning Authors: Jiajian Huang, Dongliang Zhu, Zitong YU, Hui Ma, Jiayu Zhang, Chunmei Zhu, Xiaochun Cao Published: 2026-03-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.23916v4 Multimodal deception detection aims to identify deceptive behavior by analyzing audiovisual cues for forensics and security. In these high-stakes settings, investigators need verifiable evidence connecting audiovisual cues to final decisions, along with reliable generalization across domains and cultural contexts. However, existing benchmarks provide only binary labels without intermediate reasoning cues. Datasets are also small with limited scenario coverage, leading to shortcut learning. We address these issues through three contributions. First, we construct reasoning datasets by augmenting existing benchmarks with structured cue-level descriptions and reasoning chains, enabling models to output auditable reports. Second, we release T4-Deception, a multicultural dataset based on the unified ``To Tell the Truth'' television format implemented across four countries. With 1695 samples, it is the largest non-laboratory deception detection dataset. Third, we propose two modules for robust learning under small-data conditions. Stabilized Individuality-Commonality Synergy (SICS) refines multimodal representations by combining learnable global priors with sample-adaptive residuals and applying polarity-aware recalibration. Distilled Modality Consistency (DMC) aligns modality-specific predictions with the fused multimodal predictions via knowledge distillation to prevent unimodal shortcut learning. Experiments on three established benchmarks and our novel dataset demonstrate that our method achieves state-of-the-art performance in both in-domain and cross-domain scenarios, while exhibiting superior transferability across diverse cultural contexts. The datasets and code are available at this link. --- ### Attention-aware Inference Optimizations for Large Vision-Language Models with Memory-efficient Decoding Authors: Fatih Ilhan, Gaowen Liu, Ramana Rao Kompella, Selim Furkan Tekin, Tiansheng Huang, Zachary Yahn, Yichang Xu, Ling Liu Published: 2026-03-25 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.23914v1 Large Vision-Language Models (VLMs) have achieved remarkable success in multi-modal reasoning, but their inference time efficiency remains a significant challenge due to the memory overhead during decoding, especially when the query and answer of VLMs consist of long sequences of visual and text tokens. This paper presents AttentionPack, an adaptive and attention-aware optimization framework tailored for large vision-language models with improving memory-efficiency during decoding, focusing on addressing the challenges due to the increased high number of visual inputs and interactions, particularly in long-context tasks with multiple high-resolution images or videos. AttentionPack is novel in two aspects: (i) We introduce a multi-head attention compaction method for economically storing key and value matrices by exploiting the implicit low-rank structure, and (ii) we develop a token-specific attention-aware decompression mechanism to reduce latency overhead. Experimental results on multiple benchmarks demonstrate that AttentionPack improves memory efficiency by up to 8x, enabling higher batch sizes and faster batch inference while preserving the model output quality or longer context lengths for superior retrieval performance. We also report the effectiveness of AttentionPack combined with eviction, quantization and kernel fusion, showing further efficiency gains for resource-limited environments. --- ### Self-Distillation for Multi-Token Prediction Authors: Guoliang Zhao, Ruobing Xie, An Wang, Shuaipeng Li, Huaibing Xie, Xingwu Sun Published: 2026-03-25 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.23911v1 As Large Language Models (LLMs) scale up, inference efficiency becomes a critical bottleneck. Multi-Token Prediction (MTP) could accelerate LLM inference by predicting multiple future tokens in parallel. However, existing MTP approaches still face two challenges: limited acceptance rates of MTP heads, and difficulties in jointly training multiple MTP heads. Therefore, we propose MTP-D, a simple yet effective self-distillation method with minimal additional training cost, which boosts MTP head acceptance rates (+7.5\%) while maximumly preserving main-head performance. We also introduce a looped extension strategy for MTP-D, enabling effective and economical MTP head extension and further significant inference speedup to 1-head MTP (+220.4\%). Moreover, we systematically explore and validate key insights on the distillation strategies and the potential scalability of MTP through extensive experiments on seven benchmarks. These results demonstrate that our MTP-D and looped extension strategy effectively enhance MTP-head performance and inference efficiency, facilitating the practical usage of MTP in LLMs. --- ### AnalogAgent: Self-Improving Analog Circuit Design Automation with LLM Agents Authors: Zhixuan Bao, Zhuoyi Lin, Jiageng Wang, Jinhai Hu, Yuan Gao, Yaoxin Wu, Xiaoli Li, Xun Xu Published: 2026-03-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.23910v1 Recent advances in large language models (LLMs) suggest strong potential for automating analog circuit design. Yet most LLM-based approaches rely on a single-model loop of generation, diagnosis, and correction, which favors succinct summaries over domain-specific insight and suffers from context attrition that erases critical technical details. To address these limitations, we propose AnalogAgent, a training-free agentic framework that integrates an LLM-based multi-agent system (MAS) with self-evolving memory (SEM) for analog circuit design automation. AnalogAgent coordinates a Code Generator, Design Optimizer, and Knowledge Curator to distill execution feedback into an adaptive playbook in SEM and retrieve targeted guidance for subsequent generation, enabling cross-task transfer without additional expert feedback, databases, or libraries. Across established benchmarks, AnalogAgent achieves 92% Pass@1 with Gemini and 97.4% Pass@1 with GPT-5. Moreover, with compact models (e.g., Qwen-8B), it yields a +48.8% average Pass@1 gain across tasks and reaches 72.1% Pass@1 overall, indicating that AnalogAgent substantially strengthens open-weight models for high-quality analog circuit design automation. --- ### DUPLEX: Agentic Dual-System Planning via LLM-Driven Information Extraction Authors: Keru Hua, Ding Wang, Yaoying Gu, Xiaoguang Ma Published: 2026-03-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.23909v1 While Large Language Models (LLMs) provide semantic flexibility for robotic task planning, their susceptibility to hallucination and logical inconsistency limits their reliability in long-horizon domains. To bridge the gap between unstructured environments and rigorous plan synthesis, we propose DUPLEX, an agentic dual-system neuro-symbolic architecture that strictly confines the LLM to schema-guided information extraction rather than end-to-end planning or code generation. In our framework, a feed-forward Fast System utilizes a lightweight LLM to extract entities, relations etc. from natural language, deterministically mapping them into a Planning Domain Definition Language (PDDL) problem file for a classical symbolic planner. To resolve complex or underspecified scenarios, a Slow System is activated exclusively upon planning failure, leveraging solver diagnostics to drive a high-capacity LLM in iterative reflection and repair. Extensive evaluations across 12 classical and household planning domains demonstrate that DUPLEX significantly outperforms existing end-to-end and hybrid LLM baselines in both success rate and reliability. These results confirm that The key is not to make the LLM plan better, but to restrict the LLM to the part it is good at - structured semantic grounding - and leave logical plan synthesis to a symbolic planner. --- ### GenMask: Adapting DiT for Segmentation via Direct Mask Generation Authors: Yuhuan Yang, Xianwei Zhuang, Yuxuan Cai, Chaofan Ma, Shuai Bai, Jiangchao Yao, Ya Zhang, Junyang Lin, Yanfeng Wang Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.23906v2 Recent approaches for segmentation have leveraged pretrained generative models as feature extractors, treating segmentation as a downstream adaptation task via indirect feature retrieval. This implicit use suffers from a fundamental misalignment in representation. It also depends heavily on indirect feature extraction pipelines, which complicate the workflow and limit adaptation. In this paper, we argue that instead of indirect adaptation, segmentation tasks should be trained directly in a generative manner. We identify a key obstacle to this unified formulation: VAE latents of binary masks are sharply distributed, noise robust, and linearly separable, distinct from natural image latents. To bridge this gap, we introduce timesteps sampling strategy for binary masks that emphasizes extreme noise levels for segmentation and moderate noise for image generation, enabling harmonious joint training. We present GenMask, a DiT trains to generate black-and-white segmentation masks as well as colorful images in RGB space under the original generative objective. GenMask preserves the original DiT architecture while removing the need of feature extraction pipelines tailored for segmentation tasks. Empirically, GenMask attains state-of-the-art performance on referring and reasoning segmentation benchmarks and ablations quantify the contribution of each component. --- ### Latent Bias Alignment for High-Fidelity Diffusion Inversion in Real-World Image Reconstruction and Manipulation Authors: Weiming Chen, Qifan Liu, Siyi Liu, Yushun Tang, Yijia Wang, Zhihan Zhu, Zhihai He Published: 2026-03-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.23903v1 Recent research has shown that text-to-image diffusion models are capable of generating high-quality images guided by text prompts. But can they be used to generate or approximate real-world images from the seed noise? This is known as the diffusion inversion problem, which serves as a fundamental building block for bridging diffusion models and real-world scenarios. However, existing diffusion inversion methods often suffer from low reconstruction quality or weak robustness. Two major challenges need to be carefully addressed: (1) the misalignment between the inversion and generation trajectories during the diffusion process, and (2) the mismatch between the diffusion inversion process and the VQ autoencoder (VQAE) reconstruction. To address these challenges, we introduce a latent bias vector at each inversion step, which is learned to reduce the misalignment between inversion and generation trajectories. We refer to this strategy as Latent Bias Optimization (LBO). Furthermore, we perform an approximate joint optimization of the diffusion inversion and VQAE reconstruction processes by learning to adjust the image latent representation, which serves as the connecting interface between them. We refer to this technique as Image Latent Boosting (ILB). Extensive experimental results demonstrate that the proposed method significantly improves the image reconstruction quality of the diffusion model, as well as the performance of downstream tasks, including image editing and rare concept generation. --- ### Knowledge-Refined Dual Context-Aware Network for Partially Relevant Video Retrieval Authors: Junkai Yang, Qirui Wang, Yaoqing Jin, Shuai Ma, Minghan Xu, Shanmin Pang Published: 2026-03-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.23902v1 Retrieving partially relevant segments from untrimmed videos remains difficult due to two persistent challenges: the mismatch in information density between text and video segments, and limited attention mechanisms that overlook semantic focus and event correlations. We present KDC-Net, a Knowledge-Refined Dual Context-Aware Network that tackles these issues from both textual and visual perspectives. On the text side, a Hierarchical Semantic Aggregation module captures and adaptively fuses multi-scale phrase cues to enrich query semantics. On the video side, a Dynamic Temporal Attention mechanism employs relative positional encoding and adaptive temporal windows to highlight key events with local temporal coherence. Additionally, a dynamic CLIP-based distillation strategy, enhanced with temporal-continuity-aware refinement, ensures segment-aware and objective-aligned knowledge transfer. Experiments on PRVR benchmarks show that KDC-Net consistently outperforms state-of-the-art methods, especially under low moment-to-video ratios. --- ### SM-Net: Learning a Continuous Spectral Manifold from Multiple Stellar Libraries Authors: Omar Anwar, Aaron S. G. Robotham, Luca Cortese, Kevin Vinsen Published: 2026-03-25 Categories: astro-ph.IM, cs.AI arXiv: https://arxiv.org/abs/2603.23899v2 We present SM-Net, a machine-learning model that learns a continuous spectral manifold from multiple high-resolution stellar libraries. SM-Net generates stellar spectra directly from the fundamental stellar parameters effective temperature (Teff), surface gravity (log g), and metallicity (log Z). It is trained on a combined grid derived from the PHOENIX-Husser, C3K-Conroy, OB-PoWR, and TMAP-Werner libraries. By combining their parameter spaces, we construct a composite dataset that spans a broader and more continuous region of stellar parameter space than any individual library. The unified grid covers Teff = 2,000-190,000 K, log g = -1 to 9, and log Z = -4 to 1, with spectra spanning 3,000-100,000 Angstrom. Within this domain, SM-Net provides smooth interpolation across heterogeneous library boundaries. Outside the sampled region, it can produce numerically smooth exploratory predictions, although these extrapolations are not directly validated against reference models. Zero or masked flux values are treated as unknowns rather than physical zeros, allowing the network to infer missing regions using correlations learned from neighbouring grid points. Across 3,538 training and 11,530 test spectra, SM-Net achieves mean squared errors of 1.47 x 10^-5 on the training set and 2.34 x 10^-5 on the test set in the transformed log1p-scaled flux representation. Inference throughput exceeds 14,000 spectra per second on a single GPU. We also release the model together with an interactive web dashboard for real-time spectral generation and visualisation. SM-Net provides a fast, robust, and flexible data-driven complement to traditional stellar population synthesis libraries. --- ### MMTIT-Bench: A Multilingual and Multi-Scenario Benchmark with Cognition-Perception-Reasoning Guided Text-Image Machine Translation Authors: Gengluo Li, Chengquan Zhang, Yupu Liang, Huawen Shen, Yaping Zhang, Pengyuan Lyu, Weinong Wang, Xingyu Wan, Gangyan Zeng, Han Hu, Can Ma, Yu Zhou Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.23896v1 End-to-end text-image machine translation (TIMT), which directly translates textual content in images across languages, is crucial for real-world multilingual scene understanding. Despite advances in vision-language large models (VLLMs), robustness across diverse visual scenes and low-resource languages remains underexplored due to limited evaluation resources. We present MMTIT-Bench, a human-verified multilingual and multi-scenario benchmark with 1,400 images spanning fourteen non-English and non-Chinese languages and diverse settings such as documents, scenes, and web images, enabling rigorous assessment of end-to-end TIMT. Beyond benchmarking, we study how reasoning-oriented data design improves translation. Although recent VLLMs have begun to incorporate long Chain-of-Thought (CoT) reasoning, effective thinking paradigms for TIMT are still immature: existing designs either cascade parsing and translation in a sequential manner or focus on language-only reasoning, overlooking the visual cognition central to VLLMs. We propose Cognition-Perception-Reasoning for Translation (CPR-Trans), a data paradigm that integrates scene cognition, text perception, and translation reasoning within a unified reasoning process. Using a VLLM-driven data generation pipeline, CPR-Trans provides structured, interpretable supervision that aligns perception with reasoning. Experiments on 3B and 7B models show consistent gains in accuracy and interpretability. We will release MMTIT-Bench to promote the multilingual and multi-scenario TIMT research upon acceptance. --- ### FilterGS: Traversal-Free Parallel Filtering and Adaptive Shrinking for Large-Scale LoD 3D Gaussian Splatting Authors: Yixian Wang, Haolin Yu, Jiadong Tang, Yu Gao, Xihan Wang, Yufeng Yue, Yi Yang Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.23891v1 3D Gaussian Splatting has revolutionized neural rendering with real-time performance. However, scaling this approach to large scenes using Level-of-Detail methods faces critical challenges: inefficient serial traversal consuming over 60\% of rendering time, and redundant Gaussian-tile pairs that incur unnecessary processing overhead. To address these limitations, we introduce FilterGS, featuring a parallel filtering mechanism with two complementary filters that select Gaussian elements efficiently without tree traversal. Additionally, we propose a novel GTC metric that quantifies the redundancy of Gaussian-tile key-value pairs. Based on this metric, we introduce a scene-adaptive Gaussian shrinking strategy that effectively reduces redundant pairs. Extensive experiments demonstrate that FilterGS achieves state-of-the-art rendering speeds while maintaining competitive visual quality across multiple large-scale datasets. Project page: https://github.com/xenon-w/FilterGS --- ### Praxium: Diagnosing Cloud Anomalies with AI-based Telemetry and Dependency Analysis Authors: Rohan Kumar, Jason Li, Zongshun Zhang, Syed Mohammad Qasim, Gianluca Stringhini, Ayse K. Coskun Published: 2026-03-25 Categories: cs.SE, cs.LG arXiv: https://arxiv.org/abs/2603.23890v2 As the modern microservice architecture for cloud applications grows in popularity, cloud services are becoming increasingly complex and more vulnerable to misconfiguration and software bugs. Traditional approaches rely on expert input to diagnose and fix microservice anomalies, which lacks scalability in the face of the continuous integration and continuous deployment (CI/CD) paradigm. Microservice rollouts, containing new software installations, have complex interactions with the components of an application. Consequently, this added difficulty in attributing anomalous behavior to any specific installation or rollout results in potentially slower resolution times. To address the gaps in current diagnostic methods, this paper introduces Praxium, a framework for anomaly detection and root cause inference. Praxium aids administrators in evaluating target metric performance in the context of dependency installation information provided by a software discovery tool, PraxiPaaS. Praxium continuously monitors telemetry data to identify anomalies, then conducts root cause analysis via causal impact on recent software installations, in order to provide site reliability engineers (SRE) relevant information about an observed anomaly. In this paper, we demonstrate that Praxium is capable of effective anomaly detection and root cause inference, and we provide an analysis on effective anomaly detection hyperparameter tuning as needed in a practical setting. Across 75 total trials using four synthetic anomalies, anomaly detection consistently performs at >0.97 macro-F1. In addition, we show that causal impact analysis reliably infers the correct root cause of anomalies, even as package installations occur at increasingly shorter intervals. --- ### Off-Policy Safe Reinforcement Learning with Constrained Optimistic Exploration Authors: Guopeng Li, Matthijs T. J. Spaan, Julian F. P. Kooij Published: 2026-03-25 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2603.23889v1 When safety is formulated as a limit of cumulative cost, safe reinforcement learning (RL) aims to learn policies that maximize return subject to the cost constraint in data collection and deployment. Off-policy safe RL methods, although offering high sample efficiency, suffer from constraint violations due to cost-agnostic exploration and estimation bias in cumulative cost. To address this issue, we propose Constrained Optimistic eXploration Q-learning (COX-Q), an off-policy safe RL algorithm that integrates cost-bounded online exploration and conservative offline distributional value learning. First, we introduce a novel cost-constrained optimistic exploration strategy that resolves gradient conflicts between reward and cost in the action space and adaptively adjusts the trust region to control the training cost. Second, we adopt truncated quantile critics to stabilize the cost value learning. Quantile critics also quantify epistemic uncertainty to guide exploration. Experiments on safe velocity, safe navigation, and autonomous driving tasks demonstrate that COX-Q achieves high sample efficiency, competitive test safety performance, and controlled data collection cost. The results highlight COX-Q as a promising RL method for safety-critical applications. ---