9 papers
GSMap: 2D Gaussians for Online HD Mapping
Zhenxuan Zeng, Lingxuan Wang, Sheng Yang +4
Accurate High-Definition (HD) map construction is critical for autonomous driving, yet existing methods face a fundamental trade-off: vectorization-based approaches preserve topolo…
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…
Reasoning-Driven Anomaly Detection and Localization with Image-Level Supervision
Yizhou Jin, Yuezhu Feng, Jinjin Zhang +3
Multimodal large language models (MLLMs) have recently demonstrated remarkable reasoning and perceptual abilities for anomaly detection. However, most approaches remain confined to…
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…
Octopus: Alleviating Hallucination via Dynamic Contrastive Decoding
Wei Suo, Lijun Zhang, Mengyang Sun +3
Large Vision-Language Models (LVLMs) have obtained impressive performance in visual content understanding and multi-modal reasoning. Unfortunately, these large models suffer from s…
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…
Visual Prompt Selection for In-Context Learning Segmentation
Wei Suo, Lanqing Lai, Mengyang Sun +3
As a fundamental and extensively studied task in computer vision, image segmentation aims to locate and identify different semantic concepts at the pixel level. Recently, inspired…