4 papers
NaviCache: Test-Time Self-Calibration Caching for Video Generation
Zheqi Lv, Zhibo Zhu, Jinke Wang +6
Video Diffusion Models (VDMs) is constrained by immense computational costs. While offline calibration-based acceleration suffers from calibration data dependency, prohibitive cali…
ZeroGVC: Zero-Shot Generative Video Compression with Autoregressive Diffusion Priors
Yixin Gao, Xiaohan Pan, Lin Liu +3
Recent generative video compression methods leverage powerful generative priors to achieve perceptually pleasing reconstructions. However, most existing approaches require addition…
Essential Subspace Merging for Multi-Task Learning
Longhua Li, Lei Qi, Xin Geng +1
Model merging aims to enable multi-task learning by integrating the capabilities of multiple models fine-tuned from the same pre-trained checkpoint into a single model. Its core ch…
Reasoning as Intersection: Consensus-Frame Alignment for Visual Focus in Video-MLLMs
Chengwen Liu, Zhe Huang, Jisheng Dang +3
Reinforcement learning has improved the reasoning ability of large language models, but applying outcome-only rewards to video multimodal large language models (Video-MLLMs) provid…