7 papers
SymRegFlow: Symmetry-Regularized Flow Matching for Video World Models
Xi Ye, Yuzhu Wang, Xiaoyang Liu +6
Flow-matching-based multi-view world models generate realistic videos, but are commonly restricted to fixed camera rigs. Extending them to continuously varying camera poses require…
Task-State Adaptation with Prototype Memory for Multi-Task Dense Prediction
Yangyang Xu, Haobo Yuan, Yuzhu Wang +4
Vision foundation backbones provide strong representations for dense prediction, yet a single shared feature still needs to support tasks with different, image-dependent adaptation…
SHIFT: Motion Alignment in Video Diffusion Models with Adversarial Hybrid Fine-Tuning
Xi Ye, Wenjia Yang, Yangyang Xu +4
Image-conditioned video diffusion models achieve impressive visual realism but often suffer from weakened motion fidelity, e.g., reduced motion dynamics or degraded long-term tempo…
MaLoRA: Gated Modality LoRA for Key-Space Alignment in Multimodal LLM Fine-Tuning
Xinhan Zheng, Huyu Wu, Xueting Wang +2
Multimodal large language models (MLLMs) exhibit a pronounced preference for textual inputs when processing vision-language data, limiting their ability to reason effectively from…
Diffusion Models as Dataset Distillation Priors
Duo Su, Huyu Wu, Huanran Chen +4
Dataset distillation aims to synthesize compact yet informative datasets from large ones. A significant challenge in this field is achieving a trifecta of diversity, generalization…
Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts
Yangyang Xu, Xi Ye, Duo Su
Multi-task learning (MTL) for dense prediction has shown promising results but still faces challenges in balancing shared representations with task-specific specialization. In this…
Towards Unifying Understanding and Generation in the Era of Vision Foundation Models: A Survey from the Autoregression Perspective
Shenghao Xie, Wenqiang Zu, Mingyang Zhao +6
Autoregression in large language models (LLMs) has shown impressive scalability by unifying all language tasks into the next token prediction paradigm. Recently, there is a growing…