Diagnosing the Reference Gap: What Visual Scaffolds Can and Cannot Fix in Multimodal Reasoning Paper • 2610.39419 • Published 18 days ago • 19
OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use Paper • 2610.22200 • Published Oct 15 • 72
MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environments Paper • 2610.20939 • Published Oct 14 • 43
MobilePA-Bench: Benchmarking Mobile Planner Agents on Complex Real-World Tasks Paper • 2608.23035 • Published Aug 24 • 40
On the Generalization Capacities of MLLMs for Spatial Intelligence Paper • 2603.06704 • Published Mar 5
Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents Paper • 2607.28227 • Published Jul 30 • 108
RoboSVG: A Unified Framework for Interactive SVG Generation with Multi-modal Guidance Paper • 2510.22684 • Published Oct 26, 2025
GP3: A 3D Geometry-Aware Policy with Multi-View Images for Robotic Manipulation Paper • 2509.15733 • Published Sep 19, 2025
Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Mining Paper • 2401.08407 • Published Jan 16, 2024
MMRel: A Relation Understanding Dataset and Benchmark in the MLLM Era Paper • 2406.09121 • Published Jun 13, 2024 • 1
Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization Paper • 2607.14614 • Published Jul 16 • 12
Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents Paper • 2607.28227 • Published Jul 30 • 108 • 7
Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents Paper • 2607.28227 • Published Jul 30 • 108
Scaling Language-Centric Omnimodal Representation Learning Paper • 2510.11693 • Published Oct 13, 2025 • 62