OmniTaskonomy: When Does Visual Generation Improve Visual Understanding?

arXiv:2609.38079 · cs.CV · Submitted 2026-09-29 · Read on arXiv

cs.CV

Submitted: 2026-09-29

Updated: 2026-09-29

Project page: https://omni-taskonomy.github.io

Terminology

• Benchmark — 50× in this paper · explained in 2 episodes
• Alignment — 47× in this paper · explained in 1 episode
• Accuracy — 17× in this paper · explained in 1 episode
• Transformer — 11× in this paper · explained in 2 episodes
• In European Conference on Computer Vision — 5× in this paper
• Conference on Computer Vision and Pattern Recognition — 4× in this paper
• Core — 3× in this paper · explained in 2 episodes
• Fidelity — 3× in this paper · explained in 2 episodes
• Verification — 3× in this paper · explained in 2 episodes
• Benchmarking — 2× in this paper · explained in 3 episodes
• Commentary — 2× in this paper · explained in 2 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Foundation Models — 2× in this paper · explained in 7 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• Instruction Tuning — 2× in this paper · explained in 2 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Affordance — 1× in this paper · explained in 1 episode
• Annotator Agreement — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Gradient Flow — 1× in this paper · explained in 2 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Hybrid Architectures — 1× in this paper · explained in 3 episodes
• Joint Attention — 1× in this paper · explained in 2 episodes
• Multimodal Learning — 1× in this paper · explained in 2 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Transfer Learning — 1× in this paper · explained in 10 episodes
• Transferability — 1× in this paper · explained in 4 episodes
• Two-stage training — 1× in this paper · explained in 2 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• Cosmos 3: Omnimodal World Models for Physical AI
• UniHetero: Could Generation Enhance Understanding for Vision-Language-Model at Large Data Scale?
• BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset
• BLIP3o-NEXT: Next Frontier of Native Image Generation
• Emerging Properties in Unified Multimodal Pretraining
• SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
• Image Generators are Generalist Vision Learners
• Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes
• UniEval: Unified Holistic Evaluation for Unified Multimodal Understanding and Generation
• Modeling Context Between Objects for Referring Expression Understanding
• Does Understanding Inform Generation in Unified Multimodal Models? From Analysis to Path Forward
• Transfer between Modalities with MetaQueries
• Chameleon: Mixed-Modal Early-Fusion Foundation Models
• Quantifying the Gap between Understanding and Generation within Unified Multimodal Models
• Beyond Accuracy: Benchmarking Cross-Task Consistency in Unified Multimodal Models
• VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agents
• UniG2U-Bench: Do Unified Models Advance Multimodal Understanding?
• Cross-Task Generalization Between Understanding and Generation in Unified Vision-Language Models: A Controlled Study
• Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning

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