Optimizing Stochastic Policy Geometry for Few-Step Flow Reinforcement Learning
cs.AI, cs.LG
Submitted: 2026-10-30
Updated: 2026-10-30
Code: https://github.com/ModelTC/LightX2V
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing
- MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE
- DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Denoising Diffusion Implicit Models
- LongCat-Video Technical Report
- Wan: Open and Advanced Large-Scale Video Generative Models
- Coefficients-Preserving Sampling for Reinforcement Learning with Flow Matching
- Qwen-Image Technical Report
- DanceGRPO: Unleashing GRPO on Visual Generation
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents