-
Peking University
- ningkp.github.io
Stars
recipe for running Qwen3.8-Flash-Next on a single DGX Spark
Official implementation of UniWorld-View
[TMLR] Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows
Minimal AI coding agent (~1,000 lines of Python) inspired by Claude Code. Works with any LLM. Think NanoGPT for coding agents. Formerly NanoCoder.
EddieWu0410 / claude-code
Forked from ultraworkers/claw-codeClaude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
Python port of pi-mono: fully-aligned coding agent with TUI, ai, agent, and coding-agent packages
python clone of openclaw , Jarvis is coming.
The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞
The AI that really does things. Any OS. Any Platform. The lobster way. 🦞
TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.
一站式原生AI PPT生成应用,几分钟内生成一套幻灯片; 支持上传任意模板图片,上传任意素材&智能解析,一句话/大纲/页面描述自动生成PPT,口头修改指定区域、一键导出可编辑ppt、视频等 - An AI-native slides generator based on nano banana/gpt-image🏞️
"RAG-Anything: All-in-One RAG Framework"
repo for paper https://arxiv.org/abs/2504.13837
[ICML 2026🔥] WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation
[ICCV 2025] SimVQ: Addressing Representation Collapse in Vector Quantized Models with One Linear Layer
Official repository of 'Visual-RFT: Visual Reinforcement Fine-Tuning' & 'Visual-ARFT: Visual Agentic Reinforcement Fine-Tuning'’
[ICLR'25] Official code for the paper 'MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs'
MM-EUREKA: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning
Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch
Official Implementation of CVPR'25 paper "Rethinking Epistemic and Aleatoric Uncertainty for Active Open-Set Annotation: An Energy-Based Approach"
Codebase for reproducing the experiments of the semantic uncertainty paper (short-phrase and sentence-length experiments).