SolveEdit: Benchmarking Visual Problem Solving in Generative Models

arXiv:2609.35504 · cs.CV, cs.AI · Submitted 2026-09-28 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-09-28

Updated: 2026-09-28

Code: https://github.com/WenjieShu/SolveEdit

Project page: https://wenjieshu.github.io/SolveEdit-project-page

Terminology

• Generative Model — 28× in this paper · explained in 2 episodes
• Generative Models — 27× in this paper · explained in 2 episodes
• Benchmark — 26× in this paper · explained in 2 episodes
• Benchmarking — 26× in this paper · explained in 3 episodes
• Conference on Computer Vision and Pattern Recognition — 8× in this paper
• Ablation — 7× in this paper · explained in 1 episode
• Accuracy — 7× in this paper · explained in 1 episode
• Grounding — 6× in this paper · explained in 3 episodes
• Alignment — 5× in this paper · explained in 1 episode
• Abstention — 4× in this paper · explained in 1 episode
• Diffusion Model — 4× in this paper · explained in 8 episodes
• Foundation Model — 4× in this paper · explained in 3 episodes
• Foundation Models — 4× in this paper · explained in 7 episodes
• Diffusion Models — 3× in this paper · explained in 6 episodes
• International Conference on Computer Vision — 3× in this paper
• Provenance — 3× in this paper · explained in 3 episodes
• Multimodal Reasoning — 2× in this paper · explained in 5 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Fidelity — 1× in this paper · explained in 2 episodes
• Flow Matching — 1× in this paper · explained in 7 episodes
• In Instruction-Specified — 1× in this paper
• In Rule-Dependent — 1× in this paper
• In State-Dependent — 1× in this paper
• Latent Space — 1× in this paper · explained in 7 episodes
• Nash Equilibrium — 1× in this paper · explained in 2 episodes
• Semantic Accuracy — 1× in this paper
• Trace — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Visual Grounding — 1× in this paper · explained in 2 episodes

Sources

• TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models
• BabyVision: Visual Reasoning Beyond Language
• On the Measure of Intelligence
• Emerging Properties in Unified Multimodal Pretraining
• PaLM-E: An Embodied Multimodal Language Model
• UniREditBench: A Unified Reasoning-based Image Editing Benchmark
• Prompt-to-Prompt Image Editing with Cross Attention Control
• Instruct-Imagen: Image Generation with Multi-modal Instruction
• HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing
• VideoPoet: A Large Language Model for Zero-Shot Video Generation
• HunyuanVideo: A Systematic Framework For Large Video Generative Models
• FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space
• SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations
• GIE-Bench: Towards Grounded Evaluation for Text-Guided Image Editing
• Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
• HunyuanVideo 1.5 Technical Report
• Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models
• Qwen-Image Technical Report
• MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action
• ReAct: Synergizing Reasoning and Acting in Language Models

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