Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Beyond Static Visual Tokens: Structured Sequential Visual Chain-of-Thought Reasoning

About

Current multimodal LLMs encode images as static visual prefixes and rely on text-based reasoning, lacking goal-driven and adaptive visual access. Inspired by human visual perception-where attention is selectively and sequentially shifted from the most informative regions to secondary cues-we propose Structural Sequential Visual CoT SSV-CoT. First, a question-relevant saliency map identifies and organizes key visual regions, explicitly modeling the spatial distribution of visual importance. Second, reasoning is performed following this discriminative order, inducing a curriculum-like semantic progression from primary to secondary cues. This method is trained end-to-end, using text cot and answer supervision, without relying on region-level annotations or specialized external tools. Experiments on diverse visual reasoning benchmarks show gains, validating structured and sequential visual cognition.

Guangfu Guo, Xiaoqian Lu, Yue Feng, Mingming Sun• 2026

Related benchmarks

TaskDatasetResultRank
Visual Mathematical ReasoningMathVista
Accuracy72.2
278
Visual Mathematical ReasoningMathVision
Accuracy23.5
186
Showing 2 of 2 rows

Other info

Follow for update