5 papers
Learning What Matters: Dynamic Dimension Selection and Aggregation for Interpretable Vision-Language Reward Modeling
Qiyuan Chen, Hongsen Huang, Jiahe Chen +6
Vision-language reward modeling faces a dilemma: generative approaches are interpretable but slow, while discriminative ones are efficient but act as opaque "black boxes." To bridg…
MM-DADM: Multimodal Drug-Aware Diffusion Model for Virtual Clinical Trials
Qian Shao, Bang Du, Zepeng Li +6
High failure rates in cardiac drug development necessitate virtual clinical trials via electrocardiogram (ECG) generation to reduce risks and costs. However, existing ECG generatio…
Curing Semantic Drift: A Dynamic Approach to Grounding Generation in Large Vision-Language Models
Jiahe Chen, Jiaying He, Qiyuan Chen +6
Large Vision-Language Models (LVLMs) face a tug-of-war between powerful linguistic priors and visual evidence, often leading to \emph{semantic drift}: a progressive detachment from…
CC-GSEO-Bench: A Content-Centric Benchmark for Measuring Source Influence in Generative Search Engines
Qiyuan Chen, Jiahe Chen, Hongsen Huang +7
Generative Search Engines (GSEs) synthesize conversational answers from multiple sources, weakening the long-standing link between search ranking and digital visibility. This shift…
Icon: Aligning Large Language Models Using Self-Synthetic Preference Data via Inherent Regulation
Qiyuan Chen, Hongsen Huang, Qian Shao +6
Large Language Models (LLMs) require high quality preference datasets to align with human preferences. However, conventional methods for constructing such datasets face significant…