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
61
0
arxiv.org
研究Revisiting the Volume Hypothesis(arxiv.org)
7天前原文·0 评论·
0
评论
62
0
arxiv.org
研究Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation(arxiv.org)
7天前原文·0 评论·
0
评论
63
0
arxiv.org
研究Thinking Before Retrieving: Robust Zero-Shot Composed Image Retrieval via Strategic Planning and Self-Criticism(arxiv.org)
7天前原文·0 评论·
0
评论
64
0
arxiv.org
研究Embodied CAD: Solver-Grounded LLM Agents for Parametric B-Rep Assembly Modeling(arxiv.org)
7天前原文·0 评论·
0
评论
65
0
arxiv.org
研究Spatial Reasoning via Modality Switching Between Language and Symbolic Representation(arxiv.org)
7天前原文·0 评论·
0
评论
66
0
arxiv.org
研究Agentic RAG-VLM: Affordance-Aware Retrieval-Augmented Generation with Self-Reflective Planning for Robotic Grasping(arxiv.org)
7天前原文·0 评论·
0
评论
67
0
arxiv.org
研究How Can AI Find My Model? A Model-Finding Experimental Study Considering Data Formats, Embeddings, and Retrieval Strategies(arxiv.org)
7天前原文·0 评论·
0
评论
68
0
arxiv.org
研究Beyond Compilation: Evaluating Faithful Natural-Language-to-Lean Statement Formalization(arxiv.org)
7天前原文·0 评论·
0
评论
69
0
arxiv.org
研究BayesBench: Evaluating LLM Belief Trajectories Under Multi-Turn Evidence Accumulation(arxiv.org)
7天前原文·0 评论·
0
评论
70
0
arxiv.org
研究AETDICE: Unified Framework and Offline Optimization for Nonlinear Multi-Objective RL(arxiv.org)
7天前原文·0 评论·
0
评论
71
0
arxiv.org
研究AI-Assisted Discovery of Convex Relaxations via Dual Agents(arxiv.org)
7天前原文·0 评论·
0
评论
72
0
arxiv.org
研究Towards Inclusive Mobility Modeling: Characterizing and Evaluating Elderly Trajectory Patterns in Urban Systems(arxiv.org)
7天前原文·0 评论·
0
评论
73
0
arxiv.org
研究ReplicatorBench: Benchmarking LLM Agents for Replicability in Social and Behavioral Sciences(arxiv.org)
7天前原文·0 评论·
0
评论
74
0
arxiv.org
研究Prospect-Theory Behavior from Bellman Optimality in MDPs with Catastrophic States(arxiv.org)
7天前原文·0 评论·
0
评论
75
0
arxiv.org
研究ClawArena-Team: Benchmarking Subagent Orchestration and Dynamic Workflows in Language-Model Agents(arxiv.org)
7天前原文·0 评论·
0
评论
76
0
arxiv.org
研究Long-term Traffic Simulation via Structured Autoregressive Modeling(arxiv.org)
7天前原文·0 评论·
0
评论
77
0
arxiv.org
研究OpenRCA 2.0: From Outcome Labels to Causal Process Supervision(arxiv.org)
7天前原文·0 评论·
0
评论
78
0
arxiv.org
研究CryoACE: An Atom-centric Framework for Accurate and Automated Model Building in Cryo-EM(arxiv.org)
7天前原文·0 评论·
0
评论
79
0
arxiv.org
研究A Three-Phase Foundation Model for Tax-Aware Personalized Portfolio Management(arxiv.org)
7天前原文·0 评论·
0
评论
80
0
arxiv.org
研究World-Model Collapse as a Phase Transition(arxiv.org)
7天前原文·0 评论·
0
评论
81
0
arxiv.org
研究Wisdom Of The (AI) Crowd: Investigating Artificial Swarm Intelligence In Large Language Models(arxiv.org)
7天前原文·0 评论·
0
评论
82
0
arxiv.org
研究Learning Structurally Consistent Representations for Multi-View Radar Semantic Segmentation(arxiv.org)
7天前原文·0 评论·
0
评论
83
0
arxiv.org
研究Automating Cause-Effect Specification with Knowledge Graphs and Large Language Models(arxiv.org)
7天前原文·0 评论·
0
评论
84
0
arxiv.org
研究The Past Is Prologue: A Plug-in Controller for Selective Updates in Sequentially Evolving LLM Memory(arxiv.org)
7天前原文·0 评论·
0
评论
85
0
arxiv.org
研究PPT-Eval: A Benchmark for Computer-Use Agents on PowerPoint Tasks(arxiv.org)
7天前原文·0 评论·
0
评论
86
0
arxiv.org
研究Improving LLM Reasoning with Homophily-aware Structural and Semantic Text-Attributed Graph Compression(arxiv.org)
7天前原文·0 评论·
0
评论
87
0
arxiv.org
研究Sparsity-Inducing Divergence Losses for Biometric Verification(arxiv.org)
7天前原文·0 评论·
0
评论
88
0
arxiv.org
研究Improving Certified Robustness via Adversarial Distillation(arxiv.org)
7天前原文·0 评论·
0
评论
89
0
arxiv.org
研究A Tutorial on Autonomous Fault-Tolerant Control Using Knowledge-Grounded LLM Agents(arxiv.org)
7天前原文·0 评论·
0
评论
90
0
arxiv.org
研究LLM-Empowered Agentic MAC Protocols: A Dynamic Stackelberg Game Approach(arxiv.org)
7天前原文·0 评论·
0
评论
上一页1234567下一页