benchmark evaluation 1intermediate visual states 1large language models 1multimodal models 1visual reasoning 1
From the 1 of 3 linked papers with an AI index.
3 papers
cs.CV2026
See2Think: Do Multimodal Models Really Use Intermediate Visual States?
Siyu Yan, Zhuoran Yan, Haiying Xu +10
The paper presents See2Think, an evaluation framework and benchmark for testing whether multimodal large language models actually use intermediate visual states during reasoning, a…
cs.AI2026
Latent Thought Flow: Efficient Latent Reasoning in Large Language Models
Xiandong Zou, Jing Huang, Jianshu Li +1
Large Language Models (LLMs) increasingly rely on intermediate reasoning, yet explicit Chain-of-Thought (CoT) suffers from a linguistic space bottleneck: each thought must be decod…
cs.CV2025
LOVA3: Learning to Visual Question Answering, Asking and Assessment
Henry Hengyuan Zhao, Pan Zhou, Difei Gao +2
Question answering, asking, and assessment are three innate human traits crucial for understanding the world and acquiring knowledge. By enhancing these capabilities, humans can mo…