9 papers
Hallucination-aware intermediate representation edit in large vision-language models
Wei Suo, Hanzu Zhang, Lijun Zhang +3
Large Vision-Language Models have demonstrated exceptional performance in multimodal reasoning and complex scene understanding. However, these models still face significant halluci…
Understanding and Mitigating Hallucinations in Multimodal Chain-of-Thought Models
Ji Ma, Wei Suo, Peng Wang +1
Multimodal Chain-of-Thought (MCoT) models have demonstrated impressive capability in complex visual reasoning tasks. Unfortunately, recent studies reveal that they suffer from seve…
Mitigating Information Loss under High Pruning Rates for Efficient Large Vision Language Models
Mingyu Fu, Wei Suo, Ji Ma +3
Despite the great success of Large Vision Language Models (LVLMs), their high computational cost severely limits their broad applications. The computational cost of LVLMs mainly st…
Short-LVLM: Compressing and Accelerating Large Vision-Language Models by Pruning Redundant Layers
Ji Ma, Wei Suo, Peng Wang +1
Although large vision-language models (LVLMs) have demonstrated impressive capabilities in multi-modal understanding and reasoning, their practical applications are still limited b…
Pruning All-Rounder: Rethinking and Improving Inference Efficiency for Large Vision Language Models
Wei Suo, Ji Ma, Mengyang Sun +3
Although Large Vision-Language Models (LVLMs) have achieved impressive results, their high computational costs pose a significant barrier to wide application. To enhance inference…
Language Embedding Meets Dynamic Graph: A New Exploration for Neural Architecture Representation Learning
Haizhao Jing, Haokui Zhang, Zhenhao Shang +3
Neural Architecture Representation Learning aims to transform network models into feature representations for predicting network attributes, playing a crucial role in deploying and…