From the 1 of 7 linked papers with an AI index.
Showing cs.MMShow all
2 papers · 1 filter
cs.MM2026
RetroHolmes: When Semantic Plausibility Fails Retrospective Physical Process Reasoning
Ruoxuan Zhang, Qiyun Zheng, Siyu Wu +12
The paper presents RetroHolmes, a benchmark for testing vision‑language models on retrospective physical process reasoning—inferring hidden causes from image outcomes—and shows tha…
cs.MM2024
ReCorD: Reasoning and Correcting Diffusion for HOI Generation
Jian-Yu Jiang-Lin, Kang-Yang Huang, Ling Lo +5
Diffusion models revolutionize image generation by leveraging natural language to guide the creation of multimedia content. Despite significant advancements in such generative mode…