7 papers
OmniSparse: Training-Aware Fine-Grained Sparse Attention for Long-Video MLLMs
Feng Chen, Yefei He, Shaoxuan He +9
Existing sparse attention methods primarily target inference-time acceleration by selecting critical tokens under predefined sparsity patterns. However, they often fail to bridge t…
ACT as Human: Multimodal Large Language Model Data Annotation with Critical Thinking
Lequan Lin, Dai Shi, Andi Han +7
Supervised learning relies on high-quality labeled data, but obtaining such data through human annotation is both expensive and time-consuming. Recent work explores using large lan…
Sparsity Forcing: Reinforcing Token Sparsity of MLLMs
Feng Chen, Yefei He, Lequan Lin +4
Sparse attention mechanisms aim to reduce computational overhead with minimal accuracy loss by selectively processing salient tokens. Despite their effectiveness, most methods mere…
Neighboring Autoregressive Modeling for Efficient Visual Generation
Yefei He, Yuanyu He, Shaoxuan He +4
Visual autoregressive models typically adhere to a raster-order ``next-token prediction" paradigm, which overlooks the spatial and temporal locality inherent in visual content. Spe…
ZipAR: Parallel Auto-regressive Image Generation through Spatial Locality
Yefei He, Feng Chen, Yuanyu He +4
In this paper, we propose ZipAR, a training-free, plug-and-play parallel decoding framework for accelerating auto-regressive (AR) visual generation. The motivation stems from the o…
Evaluating and Advancing Multimodal Large Language Models in Perception Ability Lens
Feng Chen, Chenhui Gou, Jing Liu +6
As multimodal large language models (MLLMs) advance rapidly, rigorous evaluation has become essential, providing further guidance for their development. In this work, we focus on a…