Lists (20)
AgentDropoutV2
AI infra
classic models
Cuda
dl
github pages
hpc_learning
LLM
LLM Agent
LLM Compression
LLM Inference Acceleration
LLM Reasoning
LLM Speculative Decoding
ml
MLLM
Multimodel LLM
power_system
project_learning
real-time bidding
Thinking Budget
Stars
[ICLR 2026] Rectifying LLM Thought From Lens of Optimization
Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".
Official code for AAAI2026 {Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Extreme Reasoning Efficiency in Large Language Models}
A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
[NeurIPS 2025] Thinkless: LLM Learns When to Think
Free ChatGPT&DeepSeek API Key，免费ChatGPT&DeepSeek API。免费接入DeepSeek API和GPT4 API，支持 gpt | deepseek | claude | gemini | grok 等排名靠前的常用大模型。
Repository of notes, code and notebooks in Python for the book Pattern Recognition and Machine Learning by Christopher Bishop
清华大学计算机系课程攻略 Guidance for courses in Department of Computer Science and Technology, Tsinghua University
A large-scale, fine-grained, diverse preference dataset (and models).
本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）
Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team | Netflix级字幕切割、翻译、对齐、甚至加上配音，一键全自动视频搬运AI字幕组
主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题
📰 Must-read papers and blogs on Speculative Decoding ⚡️
Awesome LLM compression research papers and tools.
Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...
📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉
Awesome-LLM: a curated list of Large Language Model
✨✨Latest Advances on Multimodal Large Language Models
From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓
A framework for few-shot evaluation of language models.
[EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/MCP/Docker/Zotero
DFloat11 [NeurIPS '25]: Lossless Compression of LLMs and DiTs for Efficient GPU Inference
A TTS model capable of generating ultra-realistic dialogue in one pass.
Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step