2 papers
cs.CV2026
Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs
Xinming Wang, Weinong Wang, Hongming Yang +13
Hybrid-thinking multimodal large language models (MLLMs) allow a single model to alternate between deliberative thinking and latency-efficient non-thinking inference. Although thes…
cs.CV2025
Vision-Language Models Do Not Understand Negation
Kumail Alhamoud, Shaden Alshammari, Yonglong Tian +4
Many practical vision-language applications require models that understand negation, e.g., when using natural language to retrieve images which contain certain objects but not othe…