5 papers
Bend the Basics: Degradation-Aware Deformable Tokenization for All-in-One Image Restoration
Zihao He, Yunfeng Wu, Xinchao Wang +1
All-in-one image restoration seeks a single model that can recover images degraded by diverse and spatially non-uniform corruptions. However, many unified Transformers rely on fixe…
Flow-Map Distillation on Relation Manifolds for Image Restoration
Zihao He, Songhua Liu
Knowledge distillation for image restoration typically aligns intermediate features or relation matrices between teacher and student networks as static targets, ignoring the dynami…
Multi-Task Reinforcement Learning for Enhanced Multimodal LLM-as-a-Judge
Junjie Wu, Xuan Kan, Zihao He +3
Multimodal Large Language Models (MLLMs) have been widely adopted as MLLM-as-a-Judges due to their strong alignment with human judgment across various visual tasks. However, most e…
ViBe: Ultra-High-Resolution Video Synthesis Born from Pure Images
Yunfeng Wu, Hongying Cheng, Zihao He +1
Transformer-based video diffusion models rely on 3D attention over spatial and temporal tokens, which incurs quadratic time and memory complexity and makes end-to-end training for…
Towards Pixel-Level Prediction for Gaze Following: Benchmark and Approach
Feiyang Liu, Dan Guo, Jingyuan Xu +4
Following the gaze of other people and analyzing the target they are looking at can help us understand what they are thinking, and doing, and predict the actions that may follow. E…