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
121
0
arxiv.org
研究Budget-Adaptive Routing: Skipping the Weak When the Strong Answers Anyway(arxiv.org)
7天前原文·0 评论·
0
评论
122
0
arxiv.org
研究AgentBound: Verifiable Behavioral Governance for Autonomous AI Agents(arxiv.org)
7天前原文·0 评论·
0
评论
123
0
arxiv.org
研究Wait, am I Being Fair? Characterizing Deductive Stereotyping and Mitigating It with Fair-GCG(arxiv.org)
7天前原文·0 评论·
0
评论
124
0
arxiv.org
研究CHERRY: Compressed Hierarchical Experts with Recurrent Representational Yield(arxiv.org)
7天前原文·0 评论·
0
评论
125
0
arxiv.org
研究Motion Planning in Compressed Representation Spaces(arxiv.org)
7天前原文·0 评论·
0
评论
126
0
arxiv.org
研究Learning Where to Look: A Reinforcement Learning Framework for Robust Micro-Ultrasound Prostate Cancer Detection(arxiv.org)
7天前原文·0 评论·
0
评论
127
0
arxiv.org
研究Quantization Inflates Reasoning: Token Inflation as a Hidden Cost of Low-Bit Reasoning Models(arxiv.org)
7天前原文·0 评论·
0
评论
128
0
arxiv.org
研究Scenario Generation for Testing of Autonomous Driving Systems Using Real-World Failure Records(arxiv.org)
7天前原文·0 评论·
0
评论
129
0
arxiv.org
研究MultiUAV-Plat: An LLM-Oriented Platform, Benchmark and Framework for Multi-UAV Collaborative Task Planning(arxiv.org)
7天前原文·0 评论·
0
评论
130
0
arxiv.org
研究Can LLMs Imagine Moral Alternatives Beyond Binary Dilemmas?(arxiv.org)
7天前原文·0 评论·
0
评论
131
0
arxiv.org
研究Revealing Safety-Critical Scenarios for UTM via Transformer(arxiv.org)
7天前原文·0 评论·
0
评论
132
0
arxiv.org
研究Containment Verification: AI Safety Guarantees Independent of Alignment(arxiv.org)
7天前原文·0 评论·
0
评论
133
0
arxiv.org
研究OpenLife: Toward Open-World Artificial Life with Autonomous LLM Agents(arxiv.org)
7天前原文·0 评论·
0
评论
134
0
arxiv.org
研究DDIAgents: Mechanism-Conditioned Context Flow for Drug-Drug Interaction Prediction(arxiv.org)
7天前原文·0 评论·
0
评论
135
0
arxiv.org
研究Benchmarking Large Language Models on Floating-Point Error Classification(arxiv.org)
7天前原文·0 评论·
0
评论
136
0
arxiv.org
研究Intrinsic decomposition and editing of 3D Gaussian splats(arxiv.org)
7天前原文·0 评论·
0
评论
137
0
arxiv.org
研究LLM-Powered Interactive Robotic Action Synthesis from Multimodal Speech, Gestures, and Music(arxiv.org)
7天前原文·0 评论·
0
评论
138
0
arxiv.org
研究Beyond the Library: An Agentic Framework for Autoformalizing Research Mathematics(arxiv.org)
7天前原文·0 评论·
0
评论
139
0
arxiv.org
研究Measuring Graph-to-Graph Semantic Similarity in Knowledge Graphs: An Empirical Evaluation of Knowledge Graph Embeddings(arxiv.org)
7天前原文·0 评论·
0
评论
140
0
arxiv.org
研究Deductive Logic in Language Models: Horizontal vs Vertical Reasoning(arxiv.org)
7天前原文·0 评论·
0
评论
141
0
arxiv.org
研究LabGuard: Grounding Natural-Language Laboratory Rules into Runtime Guards for Embodied Laboratory Agents(arxiv.org)
7天前原文·0 评论·
0
评论
142
0
arxiv.org
研究Cross-Domain Feature Expansion for Tabular Medical Data via Knowledge Graphs Injection(arxiv.org)
7天前原文·0 评论·
0
评论
143
0
arxiv.org
研究HistoriQA-ThirdRepublic: Multi-Hop Question Answering Corpus for Historical Research, Parliamentary Debates from the French Third Republic (1870-1940)(arxiv.org)
7天前原文·0 评论·
0
评论
144
0
arxiv.org
研究Smart charging of large fleets of Electric Vehicles: Independent Multi-Agent Reinforcement Learning approaches(arxiv.org)
7天前原文·0 评论·
0
评论
145
0
arxiv.org
研究FinPersona-Bench: A Benchmark for Longitudinal Psychometric Stability of Autonomous Financial Agents(arxiv.org)
7天前原文·0 评论·
0
评论
146
0
arxiv.org
研究On the Convergence of Self-Improving Online LLM Alignment(arxiv.org)
7天前原文·0 评论·
0
评论
147
0
arxiv.org
研究Locker-based Truck-Drone Routing with Integrated Considerations of Pickups, Deliveries, and No-Fly Zones(arxiv.org)
7天前原文·0 评论·
0
评论
148
0
arxiv.org
研究3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance(arxiv.org)
7天前原文·0 评论·
0
评论
149
0
arxiv.org
研究Improving multichannel speech enhancement through accurate room-acoustic simulations(arxiv.org)
7天前原文·0 评论·
0
评论
150
0
arxiv.org
研究Listening Between the Lines: Joint Learning of ASR Embeddings and LLM-Augmented Linguistics for Dementia Detection(arxiv.org)
7天前原文·0 评论·
0
评论
上一页1234567下一页