16 papers
ObjectAdd: Adding Objects into Image via a Training-Free Diffusion Modification Fashion
Ziyue Zhang, Mingbao Lin, Quanjian Song +2
We introduce ObjectAdd, a training-free diffusion modification method to add user-expected objects into user-specified area. The motive of ObjectAdd stems from: first, describing e…
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…
Test-Time Temporal Sampling for Efficient MLLM Video Understanding
Kaibin Wang, Mingbao Lin
Processing long videos with multimodal large language models (MLLMs) poses a significant computational challenge, as the model's self-attention mechanism scales quadratically with…
UniVST: A Unified Framework for Training-free Localized Video Style Transfer
Quanjian Song, Mingbao Lin, Wengyi Zhan +3
This paper presents UniVST, a unified framework for localized video style transfer based on diffusion models. It operates without the need for training, offering a distinct advanta…
CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models
Zhihang Lin, Mingbao Lin, Yuan Xie +1
This paper introduces Completion Pruning Policy Optimization (CPPO) to accelerate the training of reasoning models based on Group Relative Policy Optimization (GRPO). GRPO, while e…
I&S-ViT: An Inclusive & Stable Method for Pushing the Limit of Post-Training ViTs Quantization
Yunshan Zhong, Jiawei Hu, Mingbao lin +2
Albeit the scalable performance of vision transformers (ViTs), the dense computational costs (training & inference) undermine their position in industrial applications. Post-traini…