Bo-Wen Ping

Visual grounding can now be achieved at flash speed with precise localization by treating it as parallel evidence extraction, not sequential generation.

CameraEditor achieves state-of-the-art precision in camera-controlled image editing by transforming the problem into a temporal sequence prediction task, overcoming the limitations of existing models.

Predictive divergence masks significantly enhance the stability of RL updates in LLMs, outperforming traditional methods by aligning direction criteria with actual divergence changes.

Flow-DPPO outperforms traditional PPO methods by achieving higher rewards and greater training stability through a novel divergence proximal constraint.

AffordanceVLA transforms robotic manipulation by using structured affordance cues to create precise perception-action mappings, outperforming traditional models.

Saliency-guided sparse updates, focusing on high-magnitude activations in query and key vectors, unlock significant performance gains in long-context RL, outperforming uniform update strategies.