6 papers
Closed-Loop Triplet Synergistic Generation for Long-Form Video
Xinlei Yin, Xiulian Peng, Xiao Li +2
Multi-shot long-form video generation remains challenging due to identity drift and compounding inconsistencies across shots. While storyboard-driven pipelines improve controllabil…
From Content to Knowledge: Lightning Fast Long-Video Understanding with Neural Knowledge Representations
Yuchen Guan, Xiao Li, Zongyu Guo +4
We propose a new paradigm for long video understanding by treating a long video as a Neural Knowledge Representation (NKR). NKR represents video contents neither as a stream of tok…
Hierarchical Long Video Understanding with Audiovisual Entity Cohesion and Agentic Search
Xinlei Yin, Xiulian Peng, Xiao Li +2
Long video understanding presents significant challenges for vision-language models due to extremely long context windows. Existing solutions relying on naive chunking strategies w…
Text-Queried Audio Source Separation via Hierarchical Modeling
Xinlei Yin, Xiulian Peng, Xue Jiang +2
Target audio source separation with natural language queries presents a promising paradigm for extracting arbitrary audio events through arbitrary text descriptions. Existing metho…
Universal Speech Token Learning via Low-Bitrate Neural Codec and Pretrained Representations
Xue Jiang, Xiulian Peng, Yuan Zhang +1
Current large speech language models are mainly based on semantic tokens from discretization of self-supervised learned representations and acoustic tokens from a neural codec, fol…
Bitrate-Controlled Diffusion for Disentangling Motion and Content in Video
Xiao Li, Qi Chen, Xiulian Peng +3
We propose a novel and general framework to disentangle video data into its dynamic motion and static content components. Our proposed method is a self-supervised pipeline with les…