Lists (1)
Stars
A high-efficiency Flash model for real-world agents.
A kernel library written in tilelang
CL-bench: A Benchmark for Context Learning
First Visual Reinforcement Learning Framework for Image Metaphors, including Datasets, Benchmarks, and Methods
The official CLI and Python client for the Hugging Face Hub.
The official Lark/飞书 CLI tool, maintained by the larksuite team — built for humans and AI Agents. Covers core business domains including Messenger, Docs, Base, Sheets, Calendar, Mail, Tasks, Meetin…
Post-training with Tinker
Fast, Sharp & Reliable Agentic Intelligence
PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning
OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions (NeurIPS 2025)
LightRFT: Light, Efficient, Omni-modal & Reward-model Driven Reinforcement Fine-Tuning Framework
[NeurIPS 2025 AI for Music Workshop] Vocal Reaction Model and Benchmark
A toolbox for spectral compressive imaging reconstruction including MST (CVPR 2022), CST (ECCV 2022), DAUHST (NeurIPS 2022), BiSCI (NeurIPS 2023), HDNet (CVPR 2022), MST++ (CVPRW 2022), etc.
Fourth iteration of my personal website built with Gatsby
Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (LLM).
Rembg is a tool to remove images background
This is for ACL 2025 Findings Paper: From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalitiesModels
The loss landscape of Large Language Models resemble basin!
Official Repo for Open-Reasoner-Zero
A curated list of reinforcement learning with verifiable rewards (continually updated)
SGLang is a high-performance serving framework for large language models and multimodal models.
[ICCV 2025] Pretrained Reversible Generation as Unsupervised Visual Representation Learning
[ICML 2025 Tokenization Workshop] HH-Codec: High Compression High-fidelity Discrete Neural Codec for Spoken Language Modeling
🔥🔥🔥 专业版iOS混淆工具，马甲工具包、ipa静态分析工具（相似度对比、敏感词检测），提供试用版本，100%过机器审核，解决 AppStore 4.3，2.3.1问题，支持语言 c、c++、objc、dart、swift 并支持各种资源改名，混淆、傻瓜化操作、一键出包，提供良好的UI界面，支持多包管理一包一特征、支持Unity3d、cocos2d全家桶、swiftUI、flutter、虚幻…
slime is an LLM post-training framework for RL Scaling.
Let Androids Dream of Electric Sheep: A Human-Inspired Image Implication Understanding and Reasoning Framework
[ACL 2025] Can MLLMs Understand the Deep Implication Behind Chinese Images?