7 papers
Stream4D: 4D-Consistency for Streaming Autoregressive Diffusion Video Models
Yuanhao Ban, Jiaqi Feng, Hengguang Zhou +3
Streaming autoregressive diffusion models enable real-time, long-horizon video generation, but their training objectives optimize local frame prediction rather than the geometry an…
Differentiable Efficient Operator Search
Xiaohuan Pei, Jiyuan Zhang, Yuanfan Guo +4
Efficient multimodal foundation models often rely on manually designed token-reduction operators, such as pruning, merging, pooling, and adaptive reweighting. Although these operat…
Q-Zoom: Query-Aware Adaptive Perception for Efficient Multimodal Large Language Models
Yuheng Shi, Xiaohuan Pei, Linfeng Wen +2
MLLMs require high-resolution visual inputs for fine-grained tasks like document understanding and dense scene perception. However, current global resolution scaling paradigms indi…
Catching the Details: Self-Distilled RoI Predictors for Fine-Grained MLLM Perception
Yuheng Shi, Xiaohuan Pei, Minjing Dong +1
Multimodal Large Language Models (MLLMs) require high-resolution visual information to perform fine-grained perception, yet processing entire high-resolution images is computationa…
Action-aware Dynamic Pruning for Efficient Vision-Language-Action Manipulation
Xiaohuan Pei, Yuxing Chen, Siyu Xu +3
Robotic manipulation with Vision-Language-Action models requires efficient inference over long-horizon multi-modal context, where attention to dense visual tokens dominates computa…
Rethinking Causal Mask Attention for Vision-Language Inference
Xiaohuan Pei, Tao Huang, YanXiang Ma +1
Causal attention has become a foundational mechanism in autoregressive vision-language models (VLMs), unifying textual and visual inputs under a single generative framework. Howeve…