AI.news
主页教程研究工具模型AI创业讨论新闻每日简报WIKI│🚀 创业库★ 投稿
AI+医疗机器人教育金融能源健康娱乐思考
91
0
arxiv.org
研究Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents(arxiv.org)
7天前原文·0 评论·
0
评论
92
0
arxiv.org
研究ZEBRA: Zero-Shot Entropy-Regularized Prompt Learning for Base-to-Novel Generalization in Audio-Language Models(arxiv.org)
7天前原文·0 评论·
0
评论
93
0
arxiv.org
研究WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models(arxiv.org)
7天前原文·0 评论·
0
评论
94
0
arxiv.org
研究Histogram-constrained Image Generation(arxiv.org)
7天前原文·0 评论·
0
评论
95
0
arxiv.org
研究Estimating the Effect of Timing on Coupon Effectiveness(arxiv.org)
7天前原文·0 评论·
0
评论
96
0
arxiv.org
研究When Does Learning to Stop Help? A Cost-Aware Study of Early Exits in Reasoning Models(arxiv.org)
7天前原文·0 评论·
0
评论
97
0
arxiv.org
研究Measuring Reasoning Quality in LLMs: A Multi-Dimensional Behavioral Framework(arxiv.org)
7天前原文·0 评论·
0
评论
98
0
arxiv.org
研究HealthAgentBench: A Unified Benchmark Suite of Realistic Agentic Healthcare Environments for Challenging Frontier AI Agents(arxiv.org)
7天前原文·0 评论·
0
评论
99
0
arxiv.org
研究Improved Upper Bounds for Slicing the Hypercube(arxiv.org)
7天前原文·0 评论·
0
评论
100
0
arxiv.org
研究LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent(arxiv.org)
7天前原文·0 评论·
0
评论
101
0
arxiv.org
研究Toward AI-Resilient Assessment in Computer Science Courses in an AI-Native World(arxiv.org)
7天前原文·0 评论·
0
评论
102
0
arxiv.org
研究Disentangling Reasoning Logic to Resolve Explicit Knowledge Conflicts(arxiv.org)
7天前原文·0 评论·
0
评论
103
0
arxiv.org
研究Z-1: Efficient Reinforcement Learning for Vision-Language-Action Models(arxiv.org)
7天前原文·0 评论·
0
评论
104
0
arxiv.org
研究Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning(arxiv.org)
7天前原文·0 评论·
0
评论
105
0
arxiv.org
研究Learning by Surprise: Adaptive Mitigation of Model Collapse in Large Language Models(arxiv.org)
7天前原文·0 评论·
0
评论
106
0
arxiv.org
研究Modeling Cell-Cycle-Aware Single-Cell Drug Perturbation Responses(arxiv.org)
7天前原文·0 评论·
0
评论
107
0
arxiv.org
研究A Lifecycle and Application-Stack Survey of Large Language Model Vulnerabilities: Attacks, Risks, Defenses, and Open Problems(arxiv.org)
7天前原文·0 评论·
0
评论
108
0
arxiv.org
研究ADAPT: Attention Dynamics Alignment with Preference Tuning for Faithful MLLMs(arxiv.org)
7天前原文·0 评论·
0
评论
109
0
arxiv.org
研究Bridging Local Observation and Global Simulation in Closed-Loop Traffic Modeling(arxiv.org)
7天前原文·0 评论·
0
评论
110
0
arxiv.org
研究Meta-Programming for Linear-time Temporal Answer Set Programming(arxiv.org)
7天前原文·0 评论·
0
评论
111
0
arxiv.org
研究Loc2Repair: A Framework for Evaluating the Impact of File-Level Issue Localization in Repo-Level LLM Repair(arxiv.org)
7天前原文·0 评论·
0
评论
112
0
arxiv.org
研究How Human Feedback Shapes AI-generated Community Notes(arxiv.org)
7天前原文·0 评论·
0
评论
113
0
arxiv.org
研究Diffusion Crossover: Defining Evolutionary Recombination in Diffusion Models via Noise Sequence Interpolation(arxiv.org)
7天前原文·0 评论·
0
评论
114
0
arxiv.org
研究HyPOLE: Hyperproperty-Guided Multi-Agent Reinforcement Learning under Partial Observation(arxiv.org)
7天前原文·0 评论·
0
评论
115
0
arxiv.org
研究Investigating Multi-Agent Deliberation in Law(arxiv.org)
7天前原文·0 评论·
0
评论
116
0
arxiv.org
研究SkillSpotter: Pose-Aware Multi-View Skilled Action Detection and Grading in Ego-Exo Videos(arxiv.org)
7天前原文·0 评论·
0
评论
117
0
arxiv.org
研究BEST-RQ-2: Contextualize-Then-Predict, a Two-Step Approach for Self-Supervised Audio Representations(arxiv.org)
7天前原文·0 评论·
0
评论
118
0
arxiv.org
研究RoPoLL: Robust Panel of LLM Judges(arxiv.org)
7天前原文·0 评论·
0
评论
119
0
arxiv.org
研究Physics-informed Conditional Normalizing Flows for Angles-only Cislunar Orbit Determination(arxiv.org)
7天前原文·0 评论·
0
评论
120
0
arxiv.org
研究Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback(arxiv.org)
7天前原文·0 评论·
0
评论
上一页1234567下一页