Xiaofeng Tan
PulseAugur coverage of Xiaofeng Tan — every cluster mentioning Xiaofeng Tan across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New research highlights RLHF diversity collapse in text-to-image models
Researchers have identified a critical flaw in reinforcement learning from human feedback (RLHF) when applied to flow-matching text-to-image models. While standard policy entropy is often used to maintain diversity in r…
-
MotionRFT framework enhances text-to-motion generation with reinforcement learning
Researchers have introduced MotionRFT, a novel framework for text-to-motion generation that utilizes reinforcement fine-tuning. This approach addresses limitations in existing methods by employing a unified semantic spa…
-
New diffusion model enhances video anomaly detection with frequency guidance
Researchers have developed a novel frequency-guided diffusion model for skeleton-based video anomaly detection. This model enhances robustness by training a generator to produce perturbed samples, which helps the recons…