OpenRLHF
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
- 10k
- Python
- Apache-2.0
- 3 wk ago
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
🦀️ CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents. https://crab.camel-ai.org/
The official repo of One RL to See Them All: Visual Triple Unified Reinforcement Learning
🧠 Awesome Memory-VLA: A curated list of Visual-Language-Action models with memory
Code implementation for paper titled "HOI-Ref: Hand-Object Interaction Referral in Egocentric Vision"
This repository contains the data and code of the paper titled "IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models"
[NAACL 2024] Official Implementation of paper "Self-Adaptive Sampling for Efficient Video Question Answering on Image--Text Models"