ActiveMimic: Egocentric Video Pretraining with Active Perception Paper • 2606.06194 • Published 15 days ago • 1
WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing Paper • 2603.11593 • Published Mar 12 • 25
Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue Paper • 2509.15061 • Published Sep 18, 2025 • 2 • 3
Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue Paper • 2509.15061 • Published Sep 18, 2025 • 2 • 3
Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue Paper • 2509.15061 • Published Sep 18, 2025 • 2