3 papers
cs.CV2026
Dynamic-TreeRPO: Breaking the Independent Trajectory Bottleneck with Structured Sampling
Xiaolong Fu, Lichen Ma, Zipeng Guo +9
The integration of Reinforcement Learning (RL) into flow matching models for text-to-image (T2I) generation has driven substantial advances in generation quality. However, these ga…
cs.CV2025
STONE: Pioneering the One-to-N Universal Backdoor Threat in 3D Point Cloud
Dongmei Shan, Wei Lian, Chongxia Wang
Backdoor attacks pose a critical threat to deep learning, especially in safety-sensitive 3D domains such as autonomous driving and robotics. While potent, existing attacks on 3D po…
cs.CV2025
Multi-GRPO: Multi-Group Advantage Estimation for Text-to-Image Generation with Tree-Based Trajectories and Multiple Rewards
Qiang Lyu, Zicong Chen, Chongxiao Wang +9
Recently, Group Relative Policy Optimization (GRPO) has shown promising potential for aligning text-to-image (T2I) models, yet existing GRPO-based methods suffer from two critical…