Highlights
- Pro
Lists (19)
Stars
dInfer: An Efficient Inference Framework for Diffusion Language Models
Reinforcement Learning via Self-Distillation (SDPO)
Dream-VL and Dream-VLA, a diffusion VLM and a diffusion VLA.
MoE training for Me and You and maybe other people
II-Agent: a new open-source framework to build and deploy intelligent agents
Anthropic's original performance take-home, now open for you to try!
MrlX: A Multi-Agent Reinforcement Learning Framework
An interface library for RL post training with environments.
An End-to-End Infrastructure for Training and Evaluating Various LLM Agents
MiroThinker is an open source deep research agent optimized for research and prediction. It achieves a 80.8% Avg@8 score on the challenging GAIA benchmark.
MiroRL is an MCP-first reinforcement learning framework for deep research agent.
DFlash: Block Diffusion for Flash Speculative Decoding
A collection of AI Agents papers (Updated biweekly)
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning
[NeurIPS 2025] TTRL: Test-Time Reinforcement Learning
SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
Code search MCP for Claude Code. Make entire codebase the context for any coding agent.
[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards
The official implementation of Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight
Fully Open Framework for Democratized Multimodal Reinforcement Learning.
LLaDA2.0 is the diffusion language model series developed by InclusionAI team, Ant Group.
Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs
A framework for efficient model inference with omni-modality models