Accelerating Disaggregated RL for Visual Generative LLMs with Diffusion-Based Parallelism and Trainer-Assisted Generation
cs.AI, cs.DC, cs.NI, cs.PF
Submitted: 2026-06-23
Updated: 2026-09-22
Code: https://github.com/ModelTC/GenRL
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Denoising Diffusion Probabilistic Models
- OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework
- Auto-Encoding Variational Bayes
- Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation
- HunyuanVideo: A Systematic Framework For Large Video Generative Models
- Flow Matching for Generative Modeling
- Flow-GRPO: Training Flow Matching Models via Online RL
- Training language models to follow instructions with human feedback
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model
- ZeRO: Memory Optimizations Toward Training Trillion Parameter Models
- Proximal Policy Optimization Algorithms
- MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE
- Qwen3-VL Technical Report
- Scaling RL to Long Videos
- Kimi k1.5: Scaling Reinforcement Learning with LLMs
- Diffusion Models Beat GANs on Image Synthesis
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- HybridFlow: A Flexible and Efficient RLHF Framework
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection