Feng Gao

7

Papers

101

Total Citations

Papers (7)

M-LLM Based Video Frame Selection for Efficient Video Understanding

Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation

NeurIPS 2025arXiv

OmniGuard: Hybrid Manipulation Localization via Augmented Versatile Deep Image Watermarking

ARM: Appearance Reconstruction Model for Relightable 3D Generation

Both Supply and Precision: Sample Debias and Ranking Consistency Joint Learning for Large Scale Pre-Ranking System

PKU-DyMVHumans: A Multi-View Video Benchmark for High-Fidelity Dynamic Human Modeling

Adaptive-Gradient Policy Optimization: Enhancing Policy Learning in Non-Smooth Differentiable Simulations