Author

Kaihang Pan

h-index 13 View on Semantic Scholar

We have 3 of 33 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generation

Using reinforcement learning to post-train joint video-audio generation models requires a reward signal. Existing methods construct this reward by combining metrics for individual quality dimensions, including audio quality, visual fidelity, and synchronization. However, these metrics evaluate perceptual dimensions sep...

Yin-Ming Huang, Shu-Yuan Tu, Xi Yan et al. · 4 citations

Preprint Aug 2026

Iron: Intent-Aligned and Retrospective Dual Learning Framework for Enhancing Generalist Virtual Agents

Achieving virtual agents capable of automating tasks across diverse digital environments remains a pivotal challenge in Embodied AI. While Multimodal Large Language Models (MLLMs) offer enhanced visual perception and reasoning, their agentic deployment faces three challenges: costly data annotation, imprecise action-in...

Jia-He Ying, Wendong Bu, Kaihang Pan et al. · 0 citations

2025

Selftok-Zero: Reinforcement Learning for Visual Generation via Discrete and Autoregressive Visual Tokens

This work states that existing visual generative models are not yet ready for RL due to the following two fundamental drawbacks that undermine the foundations of RL.

Bohan Wang, Min Zhou, Zhongqi Yue et al. · Neural Information Processin... · 0 citations