UniWorld @ ECCV 2026

UniWorld Workshop @ ECCV2026

Universal Representations for Perception, Reasoning, and World Modeling

Important Dates Deadlines 23:59 AoE

  1. July 1, 2026July 8, 2026 Archival Submission Deadline
  2. Non-archival Submission Deadline
  3. July 20, 2026Aug 3, 2026 Archival Notification
  4. Non-archival Notification
  5. Camera-ready
  6. Workshop Date
Upload Final Revision on OpenReview

For all accepted papers

Author Information

Requirements differ by track. Registration applies to archival papers; final-revision instructions apply to both archival and non-archival papers.

Archival papers only · ECCV policy

Complete a Full Registration

According to the official ECCV registration policy, each accepted archival paper must be covered by a Full Registration completed by one of its listed authors. One Full Registration may cover up to two papers.

Registration deadline
View ECCV registration information

Archival + non-archival · UniWorld instructions

Upload the Final Revision

Authors of both archival and non-archival accepted papers should upload a final revision through OpenReview. Please follow these requirements:

  • The main paper and supplementary material should be uploaded separately.
  • The camera-ready paper may be up to 15 pages, excluding references.
  • Acknowledgements must be included within the 15-page limit.
Final-revision deadline
Upload final revision on OpenReview

Overview

Computer vision is shifting from task-specific pipelines to general-purpose multimodal foundation models. Yet current systems remain fragmented: perception models recognize, generative models synthesize, and reasoning often occurs mainly in language space. This separation limits scalability, transferability, and holistic scene understanding.

Recent progress in multimodal large models, neural scene representations, video foundation models, and embodied world models suggests these directions are converging. UniWorld targets this moment by promoting universal representations that unify perception, reasoning, generation, and interaction within a coherent framework.

Despite rapid advances, core challenges remain: designing architectures for heterogeneous data, mitigating task interference, enabling compositional reasoning, and achieving robust generalization across domains. By bringing together researchers across foundation models, multimodal learning, and world modeling, UniWorld aims to catalyze principled approaches toward generalizable visual intelligence.

Call For Papers

Core topics

  1. Scalable visual foundation representations
  2. Vision-language and beyond multimodality
  3. Unified generation + understanding paradigms
  4. Universal 3D/4D scene modeling
  5. World modeling and embodied intelligence
  6. Transfer, continual learning, generalization
  7. Emerging trends and open challenges

Submission Guidelines

  1. Submit your paper via OpenReview. Submissions must follow the ECCV 2026 Submission Policy.
  2. Submission tracks Archival: accepted papers will be included in the ECCV proceedings. Non-archival: accepted papers will not be included in the proceedings, so we welcome submissions that have been accepted by or are under review at other venues.
  3. Prepare submissions using the ECCV 2026 Author Kit for LaTeX. Note: For the supplementary material, please append it directly to the main PDF submission.
  4. Papers submitted to the workshop will be reviewed in a double-blind process. All accepted papers will be presented in a poster session.
  • Paper LengthMaximum 14 pages, excluding references and supplementary material
View UniWorld on OpenReview

Schedule

Time Session Topic / Details
08:45-09:00WelcomeOpening remarks
09:00-09:40Invited Speaker 1TBC
09:40-10:20Invited Speaker 2TBC
10:20-10:40Coffee Break + Posters-
10:40-11:20Invited Speaker 3TBC
11:20-12:00Invited Speaker 4TBC
12:00-13:00Lunch + Posters-
13:00-13:40Invited Speaker 5TBC
13:40-14:20Invited Speaker 6TBC
14:20-14:40Coffee Break + Posters-
14:40-15:20Invited Speaker 7TBC
15:20-16:00Invited Speaker 8TBC
16:00-16:50Contributed Oral Papers5 x 10-minute presentations
16:50-17:10Awards + Closing + Social-

Invited Speakers (Confirmed)

Organizers

Advisory Board

UniWorld @ ECCV 2026

Accepted Papers

33 papers have been accepted. All accepted papers will be presented during the workshop poster session.

  1. Three Necessary Principles for Self-Supervised Visual Representation Learning
  2. A Further Leap on the Battle Against Dataset Bias to Improve Generative Self-supervised Learning from Multi-source Data
  3. Slots, Transitions, Loops: Learning Composable World Models for ARC
  4. AquaVision3D: Physically-Consistent Medium Modelling for Underwater Gaussian Splatting
  5. BRo-JEPA: Learning Modular Transformations in Latent Space
  6. Self-Routed Tensor Adapters for Parameter-Efficient Universal Visual Adaptation
  7. From Static Perception to Physical Grounding: A Survey of Visual Reasoning in Physical AI
  8. Field-Operator World Models: Learning Transferable Scene Dynamics as Operators over Moving Primitives
  9. Representation Forcing for Bottleneck-Free Unified Multimodal Models
  10. UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity
  11. Why Does RLVR Shrink the Reasoning Boundary? A Two-Mode Theory of Pass@$k$ Inversion and a Per-Problem Fix
  12. DVA-CLIP: Zero-Feature Denoising and Vision-Side Attention Adaptation for Anomaly Detection
  13. Grounded-Dreamer: Robot Learning from World Model Synthetic Data with Physical Grounding
  14. Not All Redundant Tokens Are Alike: Analyzing Visual Token Pruning through Token Roles
  15. Orbis 2: A Hierarchical World Model for Driving
  16. DoCoG: Mask-based Multi-Type Grounded Chain-of-Thought for Document QA
  17. What Moves? Context-Aware Localized Latent Actions
  18. Seeing or Knowing? Visual Context Sensitivity in Multimodal Large Language Models
  19. Rethinking the Backbone in Model-Inversion-Based Exemplar-Free Continual Learning
  20. CHIMERA: Adaptive Cache Injection and Semantic Anchor Prompting for Zero-shot Image Morphing with Morphing-oriented Metrics
  21. DINOcular: Self-Supervised Visuospatial Representations
  22. Pseudo-Hilbert Masking for I-JEPA Pre-training
  23. SAM3-WM: World Models on Segmentation Features enable Mask-Guided Planning
  24. Persistent Robot World Models: Stabilizing Multi-Step Rollouts via Reinforcement Learning
  25. ReSink: Stop Words to Improve Training-Free Referring Segmentation
  26. EgoControl: Controllable Egocentric Video Generation via 3D Full-Body Poses
  27. Prospective Geometric Anchoring for Stable and Controllable Long-Horizon Driving World Models
  28. Vero: An Open RL Recipe for General Visual Reasoning
  29. Revisiting Cross-View Completion: Self-Supervised Pre-Training via Reconstruction Error Comparison
  30. Large-scale Pre-training for Grounded Video Caption Generation
  31. Vulnerability to Multimodal Jailbreak and Prompt Injection Attacks under Activation Quantization
  32. Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction
  33. Unified Video Dense Prediction from Disjoint Data