Submitted by akhaliq 32 BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation · 11 authors 1
Submitted by akhaliq 18 Proactive Detection of Voice Cloning with Localized Watermarking · 6 authors 4
Submitted by akhaliq 14 OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer · 12 authors 1
Submitted by akhaliq 10 ReGAL: Refactoring Programs to Discover Generalizable Abstractions · 3 authors 2
Submitted by akhaliq 5 T3: Transparent Tracking & Triggering for Fine-grained Overlap of Compute & Collectives · 5 authors 1