Benchmarking the Thinking Mode of Multimodal Large Language Models in Clinical Tasks
"推理能力" 相关文章
字节Seed团队发布循环语言模型Ouro，在预训练阶段直接「思考」，Bengio组参与
字节Seed团队发布循环语言模型Ouro，在预训练阶段直接「思考」，Bengio署名
字节Seed团队发布循环语言模型Ouro，在预训练阶段直接「思考」，Bengio组参与
VCORE: Variance-Controlled Optimization-based Reweighting for Chain-of-Thought Supervision
Mechanics of Learned Reasoning 1: TempoBench, A Benchmark for Interpretable Deconstruction of Reasoning System Performance
ToolScope: An Agentic Framework for Vision-Guided and Long-Horizon Tool Use
阿里通义千问能力最强语言模型，Qwen3-Max 已在官网上线深度思考功能
Cross-Platform Evaluation of Reasoning Capabilities in Foundation Models
Reasoning Curriculum: Bootstrapping Broad LLM Reasoning from Math
吴恩达关注的Ling-1T背后，蚂蚁Ling 2.0技术报告解密万亿模型开源配方
吴恩达关注的Ling-1T背后，蚂蚁Ling 2.0技术报告解密万亿模型开源配方
Zero Reinforcement Learning Towards General Domains
RAVR: Reference-Answer-guided Variational Reasoning for Large Language Models
吴恩达关注的Ling-1T背后，蚂蚁Ling 2.0技术报告解密万亿模型开源配方
仅需10%思维链标注，等同全量性能！中科院发布推理监督新范式
Human-Level Reasoning: A Comparative Study of Large Language Models on Logical and Abstract Reasoning
仅需10%思维链标注，等同全量性能！中科院发布推理监督新范式
Dipper: Diversity in Prompts for Producing Large Language Model Ensembles in Reasoning tasks
The Reasoning Trap: How Enhancing LLM Reasoning Amplifies Tool Hallucination
