6 papers
DTP: A Simple yet Effective Distracting Token Pruning Framework for Vision-Language Action Models
Chenyang Li, Jieyuan Liu, Bin Li +5
Vision-Language Action (VLA) models have shown remarkable progress in robotic manipulation by leveraging the powerful perception abilities of Vision-Language Models (VLMs) to under…
GARDO: Reinforcing Diffusion Models without Reward Hacking
Haoran He, Yuxiao Ye, Jie Liu +7
Fine-tuning diffusion models via online reinforcement learning (RL) has shown great potential for enhancing text-to-image alignment. However, since precisely specifying a ground-tr…
GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clipping
Jing Wang, Jiajun Liang, Jie Liu +10
Recently, GRPO-based reinforcement learning has shown remarkable progress in optimizing flow-matching models, effectively improving their alignment with task-specific rewards. With…
Inference-Time Alignment Control for Diffusion Models with Reinforcement Learning Guidance
Luozhijie Jin, Zijie Qiu, Jie Liu +5
Denoising-based generative models, particularly diffusion and flow matching algorithms, have achieved remarkable success. However, aligning their output distributions with complex…
Goal-Oriented Sequential Bayesian Experimental Design for Causal Learning
Zheyu Zhang, Jiayuan Dong, Jie Liu +1
We present GO-CBED, a goal-oriented Bayesian framework for sequential causal experimental design. Unlike conventional approaches that select interventions aimed at inferring the fu…
LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL
Yingzhe Peng, Gongrui Zhang, Miaosen Zhang +7
Enhancing reasoning in Large Multimodal Models (LMMs) faces unique challenges from the complex interplay between visual perception and logical reasoning, particularly in compact 3B…