SketchVLM: Vision language models can annotate images to explain thoughts and guide users

arXiv:2604.22875 · cs.CV, cs.AI · Submitted 2026-04-23 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-04-23

Updated: 2026-08-31

Code: https://github.com/allenai/molmo

Project page: https://sketchvlm.github.io

Terminology

• Accuracy — 45× in this paper · explained in 1 episode
• Alignment — 16× in this paper · explained in 1 episode
• Benchmark — 14× in this paper · explained in 2 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Trace — 7× in this paper · explained in 2 episodes
• Verification — 4× in this paper · explained in 2 episodes
• Consistency — 3× in this paper · explained in 3 episodes
• Grounding — 3× in this paper · explained in 3 episodes
• Reasoning Traces — 3× in this paper · explained in 3 episodes
• Brandon Collins — 2× in this paper
• Generalizability — 2× in this paper · explained in 6 episodes
• Generative AI — 2× in this paper · explained in 2 episodes
• Logan Bolton — 2× in this paper
• Model-Agnostic — 2× in this paper · explained in 2 episodes
• Multimodal Reasoning — 2× in this paper · explained in 5 episodes
• RAG — 2× in this paper · explained in 3 episodes
• Agentic System — 1× in this paper · explained in 2 episodes
• Alignment Scores — 1× in this paper · explained in 1 episode
• Anh Nguyen — 1× in this paper
• Average Precision — 1× in this paper
• Benchmarking — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Hung Nguyen — 1× in this paper
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Scaffolding — 1× in this paper · explained in 3 episodes
• Training-Free Framework — 1× in this paper · explained in 2 episodes
• Vision-Language Models (VLMs) — 1× in this paper · explained in 6 episodes

Sources

• Qwen2.5-VL Technical Report
• PHYRE: A New Benchmark for Physical Reasoning
• PaliGemma: A versatile 3B VLM for transfer
• SAM 3: Segment Anything with Concepts
• Emerging Properties in Unified Multimodal Pretraining
• ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning
• Visual Structures Helps Visual Reasoning: Addressing the Binding Problem in VLMs
• SketchMind: A Multi-Agent Cognitive Framework for Assessing Student-Drawn Scientific Sketches
• Imagine while Reasoning in Space: Multimodal Visualization-of-Thought
• GUI-GenBench: Evaluating Image Generation Models as Interactive GUI Environments
• HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs
• OpenAI GPT-5 System Card
• Bridging the Dynamic Perception Gap: Training-Free Draft Chain-of-Thought for Dynamic Multimodal Spatial Reasoning
• Teaching CLIP to Count to Ten
• OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning
• Understanding Generative AI Capabilities in Everyday Image Editing Tasks
• Chameleon: Mixed-Modal Early-Fusion Foundation Models
• Gemini: A Family of Highly Capable Multimodal Models
• Kimi K2.5: Visual Agentic Intelligence
• Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models