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
研究Build2SPARQL: A Large-Scale Text-to-SPARQL Benchmark Dataset for Building Knowledge Graph Querying(arxiv.org)
8天前原文·0 评论·
0
评论
62
0
研究Heavy-Tailed Memory Traces in Long-Horizon Language Agents(arxiv.org)
8天前原文·0 评论·
0
评论
63
0
研究When Do Causal World Models Help Modular LLM Agents(arxiv.org)
8天前原文·0 评论·
0
评论
64
0
研究Endogenous Alignment Requires Dependence(alignmentforum.org)
9天前原文·0 评论·
0
评论
65
0
研究The Download: AI “mind-reading” and creative uses for small batteries(technologyreview.com)
9天前原文·0 评论·
0
评论
66
0
研究Learned Compression of SAR Phase-History Data: A Rate-Honest Feasibility Study on GOTCHA(arxiv.org)
9天前原文·0 评论·
0
评论
67
0
研究Can an AI Agent Rediscover a Blaschke-Curve Invariant?(arxiv.org)
9天前原文·0 评论·
0
评论
68
0
研究Improving OCR Faithfulness via Gated and Attenuated On-Policy Distillation(arxiv.org)
9天前原文·0 评论·
0
评论
69
0
研究Self-Evolving Harness on Multiple Tasks with the Agent as Its Own Optimizer(arxiv.org)
9天前原文·0 评论·
0
评论
70
0
研究Mara Chain: Rethinking Failure as a Stepping Stone for AI System Auto-Evolution(arxiv.org)
9天前原文·0 评论·
0
评论
71
0
研究Learning from the Gap Between Pass@K and Pass@1(arxiv.org)
9天前原文·0 评论·
0
评论
72
0
研究AI Agents are Vulnerable to Radicalization(arxiv.org)
9天前原文·0 评论·
0
评论
73
0
研究A Mesoscopic View of Transformer Weights Through Row and Column Scale Fields(arxiv.org)
9天前原文·0 评论·
0
评论
74
0
研究Position: Let's Strengthen Verifiability If We Can't Enforce Reproducibility(arxiv.org)
9天前原文·0 评论·
0
评论
75
0
研究MetaPersona: Task-Grounded Synthetic Populations from Empirical Social Science(arxiv.org)
9天前原文·0 评论·
0
评论
76
0
研究Learning in the Transverse Subspace: A Minimal Representation for Divergence-Free Operator Learning(arxiv.org)
9天前原文·0 评论·
0
评论
77
0
研究CARAT: Do Materials LLMs Reason or Recite?(arxiv.org)
9天前原文·0 评论·
0
评论
78
0
研究Examining Variation in How Guided AI Tutors Resolve Student Impasses(arxiv.org)
9天前原文·0 评论·
0
评论
79
0
研究Beyond Mode Collapse: Generating Diverse Synthetic Expert Conversations via Generative Flow Networks(arxiv.org)
9天前原文·0 评论·
0
评论
80
0
研究Calibration-First Cross-Cohort Multimodal Temporal Learning for Transferable Asthma-Risk Forecasting(arxiv.org)
9天前原文·0 评论·
0
评论
81
0
研究Beyond Keywords: Leveraging Generative LLMs and Label Aggregation to Classify Economic Policy Uncertainty in News Articles(arxiv.org)
9天前原文·0 评论·
0
评论
82
0
研究ReLOBGen: Replayable Limit Order Book Message Generation(arxiv.org)
9天前原文·0 评论·
0
评论
83
0
研究From Static Policies to Adaptive Priors in Offline Reinforcement Learning(arxiv.org)
9天前原文·0 评论·
0
评论
84
0
研究Hybrid Ensemble Learning for EEG-Based Epileptic Seizure Forecasting(arxiv.org)
9天前原文·0 评论·
0
评论
85
0
研究Binarization Flattens the Score Space(arxiv.org)
9天前原文·0 评论·
0
评论
86
0
研究Decode-Latency Feedback Prefill: A Model-Free Controller and Its Generalization Limits(arxiv.org)
9天前原文·0 评论·
0
评论
87
0
研究Aligned Data Can Induce Misalignment via Context Confusion(arxiv.org)
9天前原文·0 评论·
0
评论
88
0
研究Triumph or Procrastination? Experts Split on the Trump-Xi Summit(cset.georgetown.edu)
9天前原文·0 评论·
0
评论
89
0
研究The Download: OpenAI’s chief research officer explains its hacking response(technologyreview.com)
10天前原文·0 评论·
0
评论
90
0
研究Last Week in AI #345 - 5 new models, 9 misalignment incidents, some Dots(lastweekin.ai)
10天前原文·0 评论·
0
评论
上一页1234567下一页