8 papers
OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models
Yue Ding, Yiyan Ji, Jungang Li +12
Omni-modal Large Language Models (Omni-LLMs) have demonstrated strong capabilities in audio-video understanding tasks. However, their reliance on long multimodal token sequences le…
RealChart2Code: Advancing Chart-to-Code Generation with Real Data and Multi-Task Evaluation
Jiajun Zhang, Yuying Li, Zhixun Li +13
Vision-Language Models (VLMs) have demonstrated impressive capabilities in code generation across various domains. However, their ability to replicate complex, multi-panel visualiz…
STRIVE: Structured Reasoning for Self-Improvement in Claim Verification
Haisong Gong, Jing Li, Junfei Wu +3
Claim verification is the task of determining whether a claim is supported or refuted by evidence. Self-improvement methods, where reasoning chains are generated and those leading…
DHScore: Reasoning-Aware Hallucination Detection via Semantic Breadth and Depth Analysis in LLMs
Yue Ding, Xiaofang Zhu, Tianze Xia +4
Although large Language Models (LLMs) have achieved remarkable success, their practical application is often hindered by the generation of non-factual content, which is called "hal…
Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing
Junfei Wu, Jian Guan, Kaituo Feng +5
As textual reasoning with large language models (LLMs) has advanced significantly, there has been growing interest in enhancing the multimodal reasoning capabilities of large visio…
Mixture of Decoding: An Attention-Inspired Adaptive Decoding Strategy to Mitigate Hallucinations in Large Vision-Language Models
Xinlong Chen, Yuanxing Zhang, Qiang Liu +3
Large Vision-Language Models (LVLMs) have exhibited impressive capabilities across various visual tasks, yet they remain hindered by the persistent challenge of hallucinations. To…