2 papers
cs.CV2026
TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs
Kejia Zhang, Keda Tao, Zhiming Luo +3
Multimodal large language models (MLLMs) are prone to hallucinations, generating plausible but visually ungrounded outputs, partly because direct preference optimization (DPO) over…
cs.CV2025
Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs
Kejia Zhang, Keda Tao, Jiasheng Tang +1
Large vision-language models (LVMs) extend large language models (LLMs) with visual perception capabilities, enabling them to process and interpret visual information. A major chal…