arXiv AI
Beyond Static Visual Tokens: Structured Sequential Visual Chain-of-Thought Reasoning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Oct 27
Do MLLMs Really See It: Reinforcing Visual Attention in Multimodal LLMs
arXiv:2602.08241v2 Announce Type: replace Abstract: While chain-of-thought (CoT) reasoning has substantially improved multimodal large language models (MLLMs) on complex reasoning tasks, existing app...
arXiv AI
Aug 5
CURV: Enhancing Chart Understanding Through Curriculum Visual Grounded Reasoning
arXiv:2608. 02833v1 Announce Type: cross Abstract: Chart question answering (CQA) requires multimodal large language models (MLLMs) to integrate visual comprehension with logical reasoning, yet current models struggle with accurate visual grounding and coherent reasoning chains.
arXiv AI
Jun 3
\textsc{CR-Seg}: Attention-Guided and CoT-Enhanced Coarse-to-Refined Reasoning Segmentation
arXiv:2606. 03564v1 Announce Type: cross Abstract: Reasoning segmentation aims to segment target objects described by complex language through joint visual-textual reasoning.
arXiv AI
Aug 25
Think with Structured Grounding: Perceptual Reinforcement Learning for Chart and Visual-Tabular Understanding
arXiv:2608.22429v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) capable of thinking with images often rely on external tools for fine-grained perception. However, this relian...
arXiv AI
Oct 9
SLVR: Structured Latent Visual Reasoning via Human-like Reasoning Flows
SLVR (Structured Latent Visual Reasoning) is a training framework that blends explicit chain-of-thought with latent reasoning for multimodal large language models. It organizes reasoning into typed latent stages—planning, grounding, evidence selection, and integration—each supervised by corresponding signals such as plans, bounding boxes, visual evidence, and final rationales. Built on Qwen2.5‑VL‑7B, SLVR consistently improves performance on multimodal reasoning benchmarks, achieving significant gains on MMVP, BLINK Relation, V*, MathVista, and ChartQA.
arXiv Computer Vision
Aug 25
Boosting Knowledge-based Visual Question Answering with Structured Context Reasoning
arXiv:2608.21431v1 Announce Type: new Abstract: Knowledge-based Visual Question Answering aims to answer questions about an image by integrating external knowledge with visual and textual information...