UniMore: Fine-Grained Supervision for Unified Understanding and Generation
cs.MM, cs.CV
Submitted: 2026-11-06
Updated: 2026-11-06
Code: https://github.com/AIFrontierLab/TorchUMM
Terminology
Sources
- Qwen2.5-VL Technical Report
- Chameleon: Mixed-Modal Early-Fusion Foundation Models
- Are We on the Right Way for Evaluating Large Vision-Language Models?
- Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
- Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation
- Emu3.5: Native Multimodal Models are World Learners
- Emerging Properties in Unified Multimodal Pretraining
- GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment
- Co-Reinforcement Learning for Unified Multimodal Understanding and Generation
- UEval: A Benchmark for Unified Multimodal Generation
- Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
- MMBench: Is Your Multi-modal Model an All-around Player?
- Steering Visual Generation in Unified Multimodal Models with Understanding Supervision
- MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
- FlexUMM: Flexible Representation Learning for Unified Multimodal Models
- Beyond Structural Unification: A Perspective and Roadmap on Unified Multimodal Models
- LatentUMM: Dual Latent Alignment for Unified Multimodal Models
- UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning
- WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation
- DOCCI: Descriptions of Connected and Contrasting Images
Related papers
- FLARE: Full-Modality Long-Video Audiovisual Retrieval Benchmark with User-Simulated Queries
- When does the head leave? Shared timing and a movement clock in 360-degree video viewing
- Augmented Hybrid TV Services. Habits, Preferences, Opinions and Expectations of Spanish Consumers
- A Survey of Generative Categories and Techniques in Multimodal Generative Models
- ControlFoley: Unified and Controllable Video-to-Audio Generation with Cross-Modal Conflict Handling
- EyeNavGS: A 6-DoF Navigation Dataset and Record-n-Replay Software for Real-World 3DGS Scenes in VR