ChronoVision: Temporal Reasoning via Latent State Reconstruction Paper • 2608.05631 • Published 1 day ago • 24
OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models Paper • 2608.03812 • Published 4 days ago • 25
SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Paper • 2608.02023 • Published 5 days ago • 152
Meshy T2: Fast Native Mesh Generation with Flow Matching Paper • 2607.28675 • Published 11 days ago • 53