23 citations · 24 across the 10 of their papers we have counts for
9 papers · 1 filter
Parallel Vision Token Scheduling for Fast and Accurate Multimodal LMMs Inference
Wengyi Zhan, Mingbao Lin, Zhihang Lin +1
Multimodal large language models (MLLMs) deliver impressive vision-language reasoning but suffer steep inference latency because self-attention scales quadratically with sequence l…
Speculative Decoding Reimagined for Multimodal Large Language Models
Luxi Lin, Zhihang Lin, Zhanpeng Zeng +1
This paper introduces Multimodal Speculative Decoding (MSD) to accelerate Multimodal Large Language Models (MLLMs) inference. Speculative decoding has been shown to accelerate Larg…
LightMotion: A Light and Tuning-free Method for Simulating Camera Motion in Video Generation
Quanjian Song, Zhihang Lin, Zhanpeng Zeng +3
Existing camera motion-controlled video generation methods face computational bottlenecks in fine-tuning and inference. This paper proposes LightMotion, a light and tuning-free met…
AccDiffusion v2: Towards More Accurate Higher-Resolution Diffusion Extrapolation
Zhihang Lin, Mingbao Lin, Wengyi Zhan +1
Diffusion models suffer severe object repetition and local distortion when the inference resolution differs from its pre-trained resolution. We propose AccDiffusion v2, an accurate…
AccDiffusion: An Accurate Method for Higher-Resolution Image Generation
Zhihang Lin, Mingbao Lin, Meng Zhao +1
This paper attempts to address the object repetition issue in patch-wise higher-resolution image generation. We propose AccDiffusion, an accurate method for patch-wise higher-resol…
UniPTS: A Unified Framework for Proficient Post-Training Sparsity
Jingjing Xie, Yuxin Zhang, Mingbao Lin +3
Post-training Sparsity (PTS) is a recently emerged avenue that chases efficient network sparsity with limited data in need. Existing PTS methods, however, undergo significant perfo…
Boosting Multimodal Large Language Models with Visual Tokens Withdrawal for Rapid Inference
Zhihang Lin, Mingbao Lin, Luxi Lin +1
Multimodal large language models (MLLMs) demand considerable computations for inference due to the extensive parameters and the additional input tokens needed for visual informatio…
CutDiffusion: A Simple, Fast, Cheap, and Strong Diffusion Extrapolation Method
Mingbao Lin, Zhihang Lin, Wengyi Zhan +2
Transforming large pre-trained low-resolution diffusion models to cater to higher-resolution demands, i.e., diffusion extrapolation, significantly improves diffusion adaptability.…
SMMix: Self-Motivated Image Mixing for Vision Transformers
Mengzhao Chen, Mingbao Lin, ZhiHang Lin +3
CutMix is a vital augmentation strategy that determines the performance and generalization ability of vision transformers (ViTs). However, the inconsistency between the mixed image…