热点
"大型推理模型" 相关文章
R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge
cs.AI updates on arXiv.org 2025-08-04T04:27:22.000000Z
MemShare: Memory Efficient Inference for Large Reasoning Models through KV Cache Reuse
cs.AI updates on arXiv.org 2025-07-30T04:11:56.000000Z
REST: A Stress-Testing Framework for Evaluating Multi-Problem Reasoning in Large Reasoning Models
MarkTechPost@AI 2025-07-26T21:51:13.000000Z
Thinking Isn't an Illusion: Overcoming the Limitations of Reasoning Models via Tool Augmentations
cs.AI updates on arXiv.org 2025-07-24T05:30:59.000000Z
Inverse Scaling in Test-Time Compute
少点错误 2025-07-22T22:07:41.000000Z
Inverse Scaling in Test-Time Compute
cs.AI updates on arXiv.org 2025-07-22T04:34:02.000000Z
Adaptive Multi-Agent Reasoning via Automated Workflow Generation
cs.AI updates on arXiv.org 2025-07-22T04:34:01.000000Z
Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey
cs.AI updates on arXiv.org 2025-07-15T04:24:14.000000Z
Controlling Thinking Speed in Reasoning Models
cs.AI updates on arXiv.org 2025-07-08T06:58:13.000000Z
Rethinking the Illusion of Thinking
cs.AI updates on arXiv.org 2025-07-03T04:07:37.000000Z
Why Apple’s Critique of AI Reasoning Is Premature
MarkTechPost@AI 2025-06-22T06:20:58.000000Z
Claude为一作发表了一篇论文，逐条反击苹果的“大模型推理能力崩溃论”
DeepTech深科技 2025-06-17T05:31:26.000000Z
苹果最新研究：现有 AI 大模型“更像是在记忆，而非真正的推理”
IT之家 2025-06-08T08:18:22.000000Z
Done Is Better than Perfect: Unlocking Efficient Reasoning by Structured Multi-Turn Decomposition
cs.AI updates on arXiv.org 2025-05-27T05:05:00.000000Z
WebThinker：一个边思考、边搜索、边写作的深度研究智能体
PaperAgent 2025-05-14T20:07:30.000000Z
WebThinker：一个边思考、边搜索、边写作的深度研究智能体
PaperAgent 2025-05-14T14:58:06.000000Z
一篇142页全面复盘DeepSeek R1思考推理技术综述
PaperAgent 2025-05-08T07:22:58.000000Z
WebThinker：一个边思考、边搜索、边写作的深度研究智能体
PaperAgent 2025-05-08T07:22:56.000000Z
一文读懂「AI大模型高效推理」：分类、局限性和3大提升方法
智源社区 2025-04-07T01:07:40.000000Z
250多篇论文，上海AI Lab综述推理大模型高效思考
机器之心 2025-04-05T07:57:04.000000Z