OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents
Paper • 2606.02031 • Published • 12
Stoney Kang
sikang99
AI & ML interests
Remote Control based on Vision
Recent Activity
upvoted a paper about 2 hours ago
OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents upvoted a paper about 2 hours ago
K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts upvoted a paper about 2 hours ago
NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle SimulationOrganizations
upvoted 4
papers about 2 hours ago
K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts
Paper • 2606.02404 • Published • 50
NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation
Paper • 2606.03159 • Published • 7
PlatonicNav: Unveiling Semantic Correspondence in Navigation with Platonic Topological Maps
Paper • 2606.01788 • Published • 7
upvoted 4
papers 1 day ago
ESPO: Early-Stopping Proximal Policy Optimization
Paper • 2605.29860 • Published • 15
SurGe: Improved Surface Geometry in Point Maps
Paper • 2605.31577 • Published • 4
VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies
Paper • 2605.30011 • Published • 8
Count Anything
Paper • 2605.30846 • Published • 8
upvoted 4
papers 2 days ago
Task-Focused Memorization for Multimodal Agents
Paper • 2605.31075 • Published • 29
WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction
Paper • 2605.29341 • Published • 14
DynaFLIP: Rethinking Robotics Perception via Tri-Modal-Dynamics Guided Representation
Paper • 2605.30350 • Published • 10
VLM3: Vision Language Models Are Native 3D Learners
Paper • 2605.30561 • Published • 20
upvoted 3
papers 4 days ago
PANDO: Efficient Multimodal AI Agents via Online Skill Distillation
Paper • 2605.24785 • Published • 9
When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems
Paper • 2605.30102 • Published • 13
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
Paper • 2605.29801 • Published • 139
upvoted 3
papers 5 days ago
Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments
Paper • 2605.30280 • Published • 132
minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models
Paper • 2605.30263 • Published • 54
AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation
Paper • 2605.28655 • Published • 11
upvoted 2
papers 6 days ago