热点
"CoT推理" 相关文章
R-Stitch: Dynamic Trajectory Stitching for Efficient Reasoning
cs.AI updates on arXiv.org 2025-07-30T04:12:07.000000Z
Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step
cs.AI updates on arXiv.org 2025-07-24T05:31:33.000000Z
Deep Hidden Cognition Facilitates Reliable Chain-of-Thought Reasoning
cs.AI updates on arXiv.org 2025-07-15T04:24:16.000000Z
Understanding Chain-of-Thought in LLMs through Information Theory
cs.AI updates on arXiv.org 2025-07-11T04:04:26.000000Z
Rationale-Enhanced Decoding for Multi-modal Chain-of-Thought
cs.AI updates on arXiv.org 2025-07-11T04:04:13.000000Z
会“思考”的目标检测模型来了！IDEA提出Rex-Thinker：基于思维链的指代物体检测模型，准确率+可解释性双突破
机器之心 2025-07-01T06:33:23.000000Z
CoT推理大溃败？哈佛华人揭秘：LLM一思考，立刻就“失智”
36kr 2025-05-20T12:27:27.000000Z
文生图进入R1时代：港中文MMLab发布T2I-R1，让AI绘画“先推理再下笔”
量子位 2025-05-14T06:27:25.000000Z
谷歌DeepMind：大模型也很任性，知道最优路径偏要撞南墙
机器之心 2025-05-05T08:36:27.000000Z
最强o1也刚刚及格！中科大等团队测试视频CoT推理能力：多数模型不及格
智源社区 2025-04-18T09:47:48.000000Z
Snowflake Proposes ExCoT: A Novel AI Framework that Iteratively Optimizes Open-Source LLMs by Combining CoT Reasoning with off-Policy and on-Policy DPO, Relying Solely on Execution Accuracy as Feedback
MarkTechPost@AI 2025-04-03T07:40:26.000000Z
TokenSkip: Optimizing Chain-of-Thought Reasoning in LLMs Through Controllable Token Compression
MarkTechPost@AI 2025-02-23T00:53:54.000000Z
图像生成推理大模型，港中文北大等联手破解画质提升难题
智源社区 2025-02-09T09:37:14.000000Z
Z Tech｜图像生成迎来CoT时刻，港中文首次提出文生图o1推理及Inference Scaling新范式
Z Potentials 2025-01-28T04:44:58.000000Z
深度揭秘CoT！普林斯顿耶鲁发布最新报告：大模型既有记忆推理、也有概率推理
智源社区 2024-11-13T05:08:02.000000Z