6 papers
Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual Guidance
Xinrong Chen, Xu Chu, Yingmin Qiu +8
Large Vision-Language Models (LVLMs) can reason from image-text inputs and perform well in various multimodal tasks. Despite this success, they are affected by language priors and…
EntropyPrune: Matrix Entropy Guided Visual Token Pruning for Multimodal Large Language Models
Yahong Wang, Juncheng Wu, Zhangkai Ni +6
Multimodal large language models (MLLMs) incur substantial inference cost due to the processing of hundreds of visual tokens per image. Although token pruning has proven effective…
Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning
Apoorv Vyas, Heng-Jui Chang, Cheng-Fu Yang +9
We introduce Perception Encoder Audiovisual, PE-AV, a new family of encoders for audio and video understanding trained with scaled contrastive learning. Built on PE, PE-AV makes se…
InstructMoLE: Instruction-Guided Mixture of Low-rank Experts for Multi-Conditional Image Generation
Jinqi Xiao, Qing Yan, Liming Jiang +8
Parameter-Efficient Fine-Tuning of Diffusion Transformers (DiTs) for diverse, multi-conditional tasks often suffers from task interference when using monolithic adapters like LoRA.…
When Token Pruning is Worse than Random: Understanding Visual Token Information in VLLMs
Yahong Wang, Juncheng Wu, Zhangkai Ni +8
Vision Large Language Models (VLLMs) incur high computational costs due to their reliance on hundreds of visual tokens to represent images. While token pruning offers a promising s…
Oasis: One Image is All You Need for Multimodal Instruction Data Synthesis
Letian Zhang, Quan Cui, Bingchen Zhao +1
The success of multi-modal large language models (MLLMs) has been largely attributed to the large-scale training data. However, the training data of many MLLMs is unavailable due t…