works on
large language models 2data synthesis 1humanities 1humanities and social sciences 1instruction tuning 1preference alignment 1quality evaluation 1social sciences 1synthetic data generation 1

From the 2 of 53 linked papers with an AI index.

activity
20242026
collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2026

Think-as-You-See: Streaming Chain-of-Thought Reasoning for Large Vision-Language Models

Jialiang Zhang, Junlong Tong, Junyan Lin +4

Large Vision Language Models (LVLMs) exhibit strong Chain-of-Thought (CoT) capabilities, yet most existing paradigms assume full-video availability before inference, a batch-style…