SmartFreeEdit: Mask-Free Spatial-Aware Image Editing with Complex Instruction Understanding Paper • 2504.12704 • Published Apr 17, 2025
TeleEgo: Benchmarking Egocentric AI Assistants in the Wild Paper • 2510.23981 • Published Oct 28, 2025
Gestura: A LVLM-Powered System Bridging Motion and Semantics for Real-Time Free-Form Gesture Understanding Paper • 2510.21814 • Published Oct 21, 2025
STMI: Segmentation-Guided Token Modulation with Cross-Modal Hypergraph Interaction for Multi-Modal Object Re-Identification Paper • 2603.00695 • Published Feb 28 • 3
From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company Paper • 2604.22446 • Published Apr 24 • 124