10 papers
Transition Models: Rethinking the Generative Learning Objective
Zidong Wang, Yiyuan Zhang, Xiaoyu Yue +4
A fundamental dilemma in generative modeling persists: iterative diffusion models achieve outstanding fidelity, but at a significant computational cost, while efficient few-step al…
Native-Resolution Image Synthesis
Zidong Wang, Lei Bai, Xiangyu Yue +2
We introduce native-resolution image synthesis, a novel generative modeling paradigm that enables the synthesis of images at arbitrary resolutions and aspect ratios. This approach…
Multimodal Long Video Modeling Based on Temporal Dynamic Context
Haoran Hao, Jiaming Han, Yiyuan Zhang +1
Recent advances in Large Language Models (LLMs) have led to significant breakthroughs in video understanding. However, existing models still struggle with long video processing due…
Breaking the Encoder Barrier for Seamless Video-Language Understanding
Handong Li, Yiyuan Zhang, Longteng Guo +2
Most Video-Large Language Models (Video-LLMs) adopt an encoder-decoder framework, where a vision encoder extracts frame-wise features for processing by a language model. However, t…
OneLLM: One Framework to Align All Modalities with Language
Jiaming Han, Kaixiong Gong, Yiyuan Zhang +6
Multimodal large language models (MLLMs) have gained significant attention due to their strong multimodal understanding capability. However, existing works rely heavily on modality…
Vision Search Assistant: Empower Vision-Language Models as Multimodal Search Engines
Zhixin Zhang, Yiyuan Zhang, Xiaohan Ding +1
Search engines enable the retrieval of unknown information with texts. However, traditional methods fall short when it comes to understanding unfamiliar visual content, such as ide…