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
31
0
研究RadOnc-Agent: An LLM-Orchestrated Framework for AI Workflows Across the Radiotherapy Care Pathway(arxiv.org)
3天前原文·0 评论·
0
评论
32
0
研究AttSVD:Prompt-Adaptive Low-Rank KV Cache Compression via Attention-Guided SVD(arxiv.org)
3天前原文·0 评论·
0
评论
33
0
研究TEMPEST: Temporal Embeddings for Scalable Driver Identification via Angular Margin Learning(arxiv.org)
3天前原文·0 评论·
0
评论
34
0
研究When Does External Guidance Help LLM Reasoning? A Bias-Variance Theory of Guidance-Augmented GRPO(arxiv.org)
3天前原文·0 评论·
0
评论
35
0
研究AegisFlow: A Multi-Agent Agentic AI Framework for Autonomous Remediation and Self-Healing in Fragile Data Ecosystems(arxiv.org)
3天前原文·0 评论·
0
评论
36
0
研究When better traffic forecasts fail to improve signal control: a layered diagnostic study of forecast-to-decision value(arxiv.org)
3天前原文·0 评论·
0
评论
37
0
研究Beyond Refusal Patterns: Safe-Role Internalization for Robust and Generalizable LLM Safety Alignment(arxiv.org)
3天前原文·0 评论·
0
评论
38
0
研究Topology-Consistent Task Planning over Cellular Workflow Complexes for LLM-based Agents(arxiv.org)
3天前原文·0 评论·
0
评论
39
0
研究EPOCH: Reliable Discovery through Evidence-Governed Search(arxiv.org)
3天前原文·0 评论·
0
评论
40
0
研究Weight-loss drugs show signs of slowing biological aging, say drugmakers(technologyreview.com)
4天前原文·0 评论·
0
评论
41
0
研究The Download: 10 climate tech companies to watch(technologyreview.com)
4天前原文·0 评论·
0
评论
42
0
研究The Sequence Knowledge - Issue 945: Learning RSI: Agents that Rewrite their Own Scaffolding(thesequence.substack.com)
4天前原文·0 评论·
0
评论
43
0
研究Brimstone and its one-stop process for making cleaner cement and critical minerals(technologyreview.com)
4天前原文·0 评论·
0
评论
44
0
研究2026 Climate Tech Companies to Watch(technologyreview.com)
4天前原文·0 评论·
0
评论
45
0
研究Here’s how our climate team picked 10 promising companies to watch(technologyreview.com)
4天前原文·0 评论·
0
评论
46
0
研究WaveSave and its portable rubber dam(technologyreview.com)
4天前原文·0 评论·
0
评论
47
0
研究The Triumph of Tech-Fueled Propaganda(cset.georgetown.edu)
5天前原文·0 评论·
0
评论
48
0
jack-clark.net
研究Import AI 475: Swarm scaling; Google DeepMind watermarks biology; and the AI science economy(jack-clark.net)
5天前原文·0 评论·
0
评论
49
0
研究China has cracked down on AI relationships. Is it ahead of the game?(cset.georgetown.edu)
8天前原文·0 评论·
0
评论
50
0
研究Redefining enterprise intelligence with autonomous AI(technologyreview.com)
8天前原文·0 评论·
0
评论
51
0
研究A new contest pits competitors against each other in a race to biological youth(technologyreview.com)
8天前原文·0 评论·
0
评论
52
0
研究Don’t be fooled—LLMs don’t reason(technologyreview.com)
8天前原文·0 评论·
0
评论
53
0
研究K-Dense BYOK: An Open-Source AI Research Assistant That Runs Locally and Keeps a Hash-Chained Lab Notebook(arxiv.org)
8天前原文·0 评论·
0
评论
54
0
研究Conformal Adversarial Generative Ensemble(arxiv.org)
8天前原文·0 评论·
0
评论
55
0
研究Measuring the Microtask Eligibility Gap: When Is an Off-the-Shelf SLM Enough for an Agent Harness?(arxiv.org)
8天前原文·0 评论·
0
评论
56
0
研究A Moving-Horizon Approximate Branch-and-Reduce Method for Deep Classification Trees(arxiv.org)
8天前原文·0 评论·
0
评论
57
0
研究Comedic Fool's Gold: Reward Exploits and Countermeasures in Conversational Humor(arxiv.org)
8天前原文·0 评论·
0
评论
58
0
研究Scientific Agents: Evaluating Profession-Specific System Prompts on Scientific Tasks(arxiv.org)
8天前原文·0 评论·
0
评论
59
0
研究What Do Rationales Communicate? A Message-Intervention Study in Role-Specialized QA(arxiv.org)
8天前原文·0 评论·
0
评论
60
0
研究Robust Is Salient: An Informed Adversary Moves the Optimal Signal onto the Salience Pole(arxiv.org)
8天前原文·0 评论·
0
评论
上一页1234567下一页