DeLoop: Repeated Actions as Self-Supervision for Long-Horizon Agents Paper • 2610.19376 • Published 9 days ago • 18
Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation Paper • 2610.20571 • Published 9 days ago • 367
Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout Paper • 2609.09123 • Published Sep 8 • 54
AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing Paper • 2609.08936 • Published Sep 8 • 155
The Missing Temporal Link: Temporal Context Routing for Script-Driven Audio-Video Generation Paper • 2609.02367 • Published Sep 2 • 38
On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability Paper • 2608.30320 • Published Aug 31 • 62
An Empirical Study of Training Pixel-Space Text-to-Image Diffusion Models Paper • 2608.16887 • Published Aug 17 • 36