Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models Paper • 2606.25473 • Published 6 days ago • 23
SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior Paper • 2606.18322 • Published 14 days ago • 17
SCOPE Collection Model weights for SCOPE: Simulating Cross-game Operations in Playable Environments for FPS World Models • 2 items • Updated May 25 • 2
SCOPE: Simulating Cross-game Operations in Playable Environments for FPS World Models Paper • 2605.23345 • Published May 22 • 17
Incantation: Natural Language as the Action Interface for Multi-Entity Video World Models Paper • 2605.18601 • Published May 18 • 6
Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs Paper • 2605.20315 • Published May 19 • 28
LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation Paper • 2605.18739 • Published May 18 • 116
AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation Paper • 2605.13724 • Published May 13 • 105
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond Paper • 2604.22748 • Published Apr 24 • 231
Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models Paper • 2603.15557 • Published Mar 16 • 30
ViFeEdit: A Video-Free Tuner of Your Video Diffusion Transformer Paper • 2603.15478 • Published Mar 16 • 24
SpotEdit: Selective Region Editing in Diffusion Transformers Paper • 2512.22323 • Published Dec 26, 2025 • 39