Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities Paper • 2507.06261 • Published Jul 7, 2025 • 67
ObjectMate: A Recurrence Prior for Object Insertion and Subject-Driven Generation Paper • 2412.08645 • Published Dec 11, 2024 • 12
Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction Paper • 2412.04454 • Published Dec 5, 2024 • 71
AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials Paper • 2412.09605 • Published Dec 12, 2024 • 30
