Stars
《代码随想录》LeetCode 刷题攻略：200道经典题目刷题顺序，共60w字的详细图解，视频难点剖析，50余张思维导图，支持C++，Java，Python，Go，JavaScript等多语言版本，从此算法学习不再迷茫！🔥🔥 来看看，你会发现相见恨晚！🚀
Harness engineering beginner tutorial, from 0 to 1
CVPR and NeurIPS poster examples and templates
The code of Advancing Expert Specialization for Better MoE (NeurIPS2025 oral)
Digital Agents Meet World Models: A Survey
SGLang is a high-performance serving framework for large language models and multimodal models.
A high-throughput and memory-efficient inference and serving engine for LLMs
PaperBanana: Automating Academic Illustration For AI Scientists
high-performance linear attention kernel library built on TileLang
A kernel library written in tilelang
FlashKDA: high-performance Kimi Delta Attention kernels
A framework for few-shot evaluation of language models.
A curated list of resources related to linear attention mechanisms.
The first continuous diffusion language model that rivals discrete counterparts on standard language modeling benchmarks like LM1B and OpenWebText.
🔥🔥🔥 [Awesome] Latest Papers, Codes & Datasets on Streaming / Online Video Understanding — Building Always-on, Real-time Video AI 🤖
LPM 1.0: Video-based Character Performance Model
🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!
Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models
official repo for `thinking with images through-self-calling`
Code for "LMEB: Long-horizon Memory Embedding Benchmark"
智能记忆系统 MCP 服务器 - 为 Kimi Code CLI 提供持久化记忆能力
CUDA kernels for linear attention variants, written in CuTe DSL and CUTLASS C++.
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Documentation that simply works
The official GitHub repo for the survey paper "A Survey on Diffusion Language Models".