Naifan Li's Blog

Post Tags

LLMs ²⁹ Qwens ⁹ VLMs ⁹ Chain-of-Thought ⁴ GPTs ⁴ Instruction Tuning ⁴ LLaMAs ⁴ AgentAI ³ GTC ³ NVIDIA ³ OpenClaw ³ 概率论 ³

Recommended Posts

GTC 2026 深度解读：Physical AI —— 从仿真数据到物理世界的自治闭环 2026-03-17 GTC 2026 深度解读：Agentic AI —— 从被动对话到自治执行 2026-03-17 NVIDIA GTC 2026 Keynote 深度解读 2026-03-17 UniTeD: Unified Temporal Diffusion for Joint Perception and Planning in Autonomous Driving 2026-03-14 一文读懂：家庭医疗险配置指南与高效选品策略 2026-03-07 OpenClaw 部署实战：本地部署 + 云端 MiniMax M2.5 配置指南（下篇） 2026-02-10 MoltBook：当 AI 有了自己的社交网络 2026-02-04 一文读懂 OpenClaw：你的 7×24 小时 AI 助手（上篇） 2026-02-04 主流 LLM/VLM 推理服务部署框架横评 2025-11-28 vLLM: Easy, fast, and cheap LLM inference and serving 2025-11-27 Frontiers in Embodied AI (ICCV 2025 WDFM-AD) 2025-11-18 Building an Autonomous Future (ICCV 2025 WDFM-AD) 2025-11-18 HunyuanOCR Technical Report 2025-11-16 Local AI Programming Assistant: VSCode + Continue/Cline + vLLM + Kimi-K2.5 2025-01-01 Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond 2023-08-25 Zero-shot-CoT: Large Language Models are Zero-Shot Reasoners 2022-05-24 InstructGPT: Training language models to follow instructions with human feedback 2022-03-04 Chain-of-Thought Prompting Elicits Reasoning in Large Language Models 2022-01-28

Chain-of-Thought 系列

Zero-shot-CoT: Large Language Models are Zero-Shot Reasoners 2022-05-24 Least-to-Most Prompting Enables Complex Reasoning in Large Language Models 2022-05-21 Self-Consistency Improves Chain of Thought Reasoning in Language Models 2022-03-21 Chain-of-Thought Prompting Elicits Reasoning in Large Language Models 2022-01-28

Instruction Tuning

LIMA: Less Is More for Alignment 2023-05-18 Self-Instruct: Aligning Language Model with Self-Generated Instructions 2022-12-20 InstructGPT: Training language models to follow instructions with human feedback 2022-03-04 FLAN: Finetuned Language Models Are Zero-Shot Learners 2021-09-03

GPTs 系列

InstructGPT: Training language models to follow instructions with human feedback 2022-03-04 GPT-3: Language Models are Few-Shot Learners 2020-05-28 GPT-2: Language Models are Unsupervised Multitask Learners 2019-02-14 GPT-1: Improving Language Understanding by Generative Pre-Training 2018-06-11

Qwen 系列

Qwen3-VL Technical Report 2025-11-27 Qwen Series: Technical Summary 2025-05-14 Qwen3 Technical Report 2025-05-14 Qwen2.5-VL Technical Report 2025-02-25 Qwen2.5 Technical Report 2024-12-19

LLM 系列

Qwen Series: Technical Summary 2025-05-14 Qwen3 Technical Report 2025-05-14 大模型 API 开发指南 2025-02-11 LLaMA 4: Next-Generation Open Language Models 2024-12-25 Qwen2.5 Technical Report 2024-12-19

VLM 系列

Vision Language Adapter 2025-12-24 Qwen3-VL Technical Report 2025-11-27 Summary: VLMs 2025-11-26 HunyuanOCR Technical Report 2025-11-16 Qwen2.5-VL Technical Report 2025-02-25

Recent Posts

GTC 2026 深度解读：Physical AI —— 从仿真数据到物理世界的自治闭环 2026-03-17 GTC 2026 深度解读：Agentic AI —— 从被动对话到自治执行 2026-03-17 NVIDIA GTC 2026 Keynote 深度解读 2026-03-17 归一化：BatchNorm、LayerNorm 与 RMSNorm 2026-03-16 DiT: Scalable Diffusion Models with Transformers 2026-03-16 贝叶斯公式 2026-03-15 最大似然估计：从统计建模到逻辑回归 2026-03-15 信息量、熵、交叉熵与 KL 散度 2026-03-14