9 papers
SeeMe: Mitigating Hallucinations in Large Vision-Language Models through Effective Visual Token Engineering
Kai Tang, Jinhao You, Bohua Zhang +6
Large Vision-Language Models (LVLMs) have achieved remarkable progress in visual understanding tasks such as image captioning and visual question answering. However, they remain su…
Mitigating Hallucinations via Inter-Layer Consistency Aggregation in Large Vision-Language Models
Kai Tang, Jinhao You, Yichen Guo +8
Despite the impressive capabilities of Large Vision-Language Models (LVLMs), they remain susceptible to hallucinations, where generated content is inconsistent with the input image…
WildRoadBench: A Wild Aerial Road-Damage Grounding Benchmark for Vision-Language Models and Autonomous Agents
Bingnan Liu, Chenhang Cui, Rui Huang +7
We introduce WildRoadBench, a wild aerial road-damage grounding benchmark that couples direct visual grounding by vision-language models with autonomous research-and-engineering by…
Mitigating Hallucinations in Large Language Models Via Decoder Layer Skipping
Hanze Li, Jinhao You, Yichen Guo +3
Large Language Models (LLMs) have achieved strong performance across diverse natural language tasks, yet their outputs often suffer from hallucinations -- content that is misaligne…
Enhancing Layer Attention Efficiency through Pruning Redundant Retrievals
Hanze Li, Yaosong Du, Zhibo Yao +3
Growing evidence suggests that layer attention mechanisms, which enhance interaction among layers in deep neural networks, have significantly advanced network architectures. Howeve…
Models as Lego Builders: Assembling Malice from Benign Blocks via Semantic Blueprints
Chenxi Li, Xianggan Liu, Dake Shen +9
Despite the rapid progress of Large Vision-Language Models (LVLMs), the integration of visual modalities introduces new safety vulnerabilities that adversaries can exploit to elici…