Showing 2026Show all
3 papers · 1 filter
cs.CV2026
CapProbe: Evaluating Detailed Image Captions via Full-Scene Dense Question Answering
Mouxiao Huang, Qiangyu Yan, Borui Jiang +1
Evaluating detailed image captions from Vision-Language Models (VLMs) requires going beyond surface-level semantic similarity. Reference-based metrics (e.g., CIDEr and SPICE) and L…
cs.CL2026
Thinking-while-speaking: A Controlled, Interleaved Reasoning Method for Real-Time Speech Generation
Xuan Du, Qiangyu Yan, Wenshuo Li +4
The thinking-while-speaking paradigm aims to make AI communication more human. A key challenge is maintaining fluent speech while performing deep reasoning. Our method, InterRS, ta…
cs.CV2026
Multimodal Latent Reasoning via Hierarchical Visual Cues Injection
Yiming Zhang, Qiangyu Yan, Borui Jiang +1
The advancement of multimodal large language models (MLLMs) has enabled impressive perception capabilities. However, their reasoning process often remains a "fast thinking" paradig…