SILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generation Paper • 2610.02201 • Published 3 days ago • 27
One Editor, Many Edits: A Unified Training-Free Framework for Diverse Video Editing Paper • 2609.04190 • Published Sep 3 • 7
Best of Both Worlds: Multimodal Reasoning and Generation via Unified Discrete Flow Matching Paper • 2602.12221 • Published Feb 12 • 6
HalluSegBench: Counterfactual Visual Reasoning for Segmentation Hallucination Evaluation Paper • 2506.21546 • Published Jun 26, 2025 • 2