45 citations · 104 across the 31 of their papers we have counts for
6 papers · 1 filter
ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM
Yujun Wang, Aniri, Jinhe Bi +2
Multimodal large language models (MLLMs) frequently hallucinate by over-committing to spurious visual cues. Prior remedies-Visual and Instruction Contrastive Decoding (VCD, ICD)-mi…
METok: Multi-Stage Event-based Token Compression for Efficient Long Video Understanding
Mengyue Wang, Shuo Chen, Kristian Kersting +2
Recent advances in Video Large Language Models (VLLMs) have significantly enhanced their ability to understand video content. Nonetheless, processing long videos remains challengin…
PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection
Jinhe Bi, Aniri, Zengjie Jin +11
Visual instruction tuning adapts pre-trained Multimodal Large Language Models (MLLMs) to follow human instructions for real-world applications. However, the rapid growth of these d…
LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering
Jinhe Bi, Yujun Wang, Haokun Chen +4
Multimodal Large Language Models (MLLMs) have significantly advanced visual tasks by integrating visual representations into large language models (LLMs). The textual modality, inh…
VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs
Ruotong Liao, Max Erler, Huiyu Wang +4
In the video-language domain, recent works in leveraging zero-shot Large Language Model-based reasoning for video understanding have become competitive challengers to previous end-…
Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models
Shuo Chen, Jindong Gu, Zhen Han +3
Various adaptation methods, such as LoRA, prompts, and adapters, have been proposed to enhance the performance of pre-trained vision-language models in specific domains. The robust…