UI-UG 2: Advancing Mobile UI Understanding and Generation with Fine-Grained Supervision and Reinforcement Learning
cs.CV, cs.AI, cs.HC
Submitted: 2026-10-31
Updated: 2026-10-31
Code: https://github.com/ultralytics/ultralytics
Project page: https://www.anthropic.com/news/claude-sonnet-4-5
Terminology
Sources
- Qwen3-VL Technical Report
- WebSRC: A Dataset for Web-Based Structural Reading Comprehension
- UI-Venus Technical Report: Building High-performance UI Agents with RFT
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
- LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
- Sketch2Code: Transformation of Sketches to UI in Real-time Using Deep Neural Network
- Ferret-UI 2: Mastering Universal User Interface Understanding Across Platforms
- Visual-RFT: Visual Reinforcement Fine-Tuning
- OmniParser for Pure Vision Based GUI Agent
- UI-TARS: Pioneering Automated GUI Interaction with Native Agents
- Do Understanding and Generation Fight? A Diagnostic Study of DPO for Unified Multimodal Models
- VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model
- Kimi K2.5: Visual Agentic Intelligence
- Automatically Generating UI Code from Screenshot: A Divide-and-Conquer-Based Approach
- Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology
- OS-ATLAS: A Foundation Action Model for Generalist GUI Agents
- UI-UG: A Unified MLLM for UI Understanding and Generation
- Mobile-Agent-v3: Fundamental Agents for GUI Automation
- R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs