OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents
Paper • 2606.02031 • Published • 9
Börje Karlsson
tellarin
AI & ML interests
Machine Learning Systems, Mobile Sensing, Knowledge Mining, Digital Entertainment
Recent Activity
upvoted a paper about 7 hours ago
OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents upvoted a paper about 9 hours ago
Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration? upvoted a paper about 9 hours ago
Joint Agent Memory and Exploration Learning via Novelty SignalsOrganizations
upvoted a paper about 7 hours ago
upvoted 9
papers about 9 hours ago
Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?
Paper • 2606.01247 • Published • 18
Joint Agent Memory and Exploration Learning via Novelty Signals
Paper • 2606.01528 • Published • 11
SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories
Paper • 2606.01311 • Published • 20
Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?
Paper • 2605.30557 • Published • 7
Task-Focused Memorization for Multimodal Agents
Paper • 2605.31075 • Published • 25
PhoneWorld: Scaling Phone-Use Agent Environments
Paper • 2605.29486 • Published • 3
WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction
Paper • 2605.29341 • Published • 12
Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning
Paper • 2605.28424 • Published • 28
Why Far Looks Up: Probing Spatial Representation in Vision-Language Models
Paper • 2605.30161 • Published • 56
upvoted 4
papers 29 days ago
Map2World: Segment Map Conditioned Text to 3D World Generation
Paper • 2605.00781 • Published • 25
Co-Director: Agentic Generative Video Storytelling
Paper • 2604.24842 • Published • 16
RADIO-ViPE: Online Tightly Coupled Multi-Modal Fusion for Open-Vocabulary Semantic SLAM in Dynamic Environments
Paper • 2604.26067 • Published • 74
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
Paper • 2604.22748 • Published • 227
upvoted a paper about 1 month ago
upvoted 4
papers 3 months ago
VGGT-Det: Mining VGGT Internal Priors for Sensor-Geometry-Free Multi-View Indoor 3D Object Detection
Paper • 2603.00912 • Published • 40
RANGER: A Monocular Zero-Shot Semantic Navigation Framework through Contextual Adaptation
Paper • 2512.24212 • Published • 3
SWITCH: Benchmarking Modeling and Handling of Tangible Interfaces in Long-horizon Embodied Scenarios
Paper • 2511.17649 • Published • 4
Does Your Reasoning Model Implicitly Know When to Stop Thinking?
Paper • 2602.08354 • Published • 266
upvoted a paper 4 months ago