Stars
Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models
OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340
[ICLR 2025 Spotlight] OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
Official pytorch Code for mmkd paper "Distilling Grounding DINO for an Edge-Cloud Collaborative Advanced Driver Assistance System"
New generation of CLIP with fine grained discrimination capability, ICML2025
🥈🐉 [CVPRW'25] Official Code for “Enhance Then Search: An Augmentation-Search Strategy with Foundation Models for Cross-Domain Few-Shot Object Detection”
Official code implementation of Perception R1: Pioneering Perception Policy with Reinforcement Learning
Scalable toolkit for efficient model alignment
[CVPR 2025] MatAnyone: Stable Video Matting with Consistent Memory Propagation
D^2-MoE: Delta Decompression for MoE-based LLMs Compression
A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
This repository collects papers for "A Survey on Knowledge Distillation of Large Language Models". We break down KD into Knowledge Elicitation and Distillation Algorithms, and explore the Skill & V…
Code used for sourcing and cleaning the BigScience ROOTS corpus
Apache Arrow is the universal columnar format and multi-language toolbox for fast data interchange and in-memory analytics
RF-DETR is a real-time object detection model architecture developed by Roboflow, SOTA on COCO and designed for fine-tuning.
Official repository of 'Visual-RFT: Visual Reinforcement Fine-Tuning' & 'Visual-ARFT: Visual Agentic Reinforcement Fine-Tuning'’
An easy way to apply LoRA to CLIP. Implementation of the paper "Low-Rank Few-Shot Adaptation of Vision-Language Models" (CLIP-LoRA) [CVPRW 2024].
🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
No fortress, purely open ground. OpenManus is Coming.
The source code of IEEE TPAMI 2025 "Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation".
我的个人技术博客（Python、Django、Docker、Go、Redis、ElasticSearch、Kafka、Linux）
Integrate the DeepSeek API into popular softwares
NTIRE 2025 Challenge on 1-st Cross-Domain Few-Shot Object Detection @ CVPR 2025
Solve Visual Understanding with Reinforced VLMs