DreamForge-World 0.1 Preview: A Low-Compute Real-Time Controllable World Model Paper • 2606.30292 • Published 7 days ago • 14
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 12 days ago • 25
UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating Paper • 2606.21661 • Published 17 days ago • 28
LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing Paper • 2606.26740 • Published 11 days ago • 81
BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding Paper • 2606.31315 • Published 6 days ago • 73
AVTok: 1D Unified Tokenization for Holistic Audio-Video Generation Paper • 2606.30811 • Published 7 days ago • 7
MemLearner: Learning to Query Context memory for Video World Models Paper • 2606.31734 • Published 6 days ago • 23
SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History Paper • 2606.08671 • Published 13 days ago • 29
Learning Transferable Dynamics Priors from Action to World Modeling Paper • 2606.29501 • Published 8 days ago • 4
Trimming the Long-Tail of Visual World Modeling Evaluation Paper • 2606.24256 • Published 13 days ago • 41
MemoBench: Benchmarking World Modeling in Dynamically Changing Environments Paper • 2606.27537 • Published 11 days ago • 6
PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation Paper • 2606.28128 • Published 10 days ago • 50
Thinking While Speaking: Inference-Time Knowledge Transfer for Responsive and Intelligent Conversational Voice Agents Paper • 2511.07397 • Published 5 days ago • 10
PhysiFormer: Learning to Simulate Mechanics in World Space Paper • 2606.27364 • Published 11 days ago • 11
The Verification Horizon: No Silver Bullet for Coding Agent Rewards Paper • 2606.26300 • Published 12 days ago • 47
MVTrack4Gen: Multi-View Point Tracking as Geometric Supervision for 4D Video Generation Paper • 2606.26087 • Published 12 days ago • 35
DomainShuttle: Freeform Open Domain Subject-driven Text-to-video Generation Paper • 2606.26058 • Published 12 days ago • 67
RL-Index: Reinforcement Learning for Retrieval Index Reasoning Paper • 2606.16316 • Published 21 days ago • 6
Holo-World: Unified Camera, Object and Weather Control for Video World Model Paper • 2606.20083 • Published 18 days ago • 11
LooseControlVideo: Directorial Video Control using Spatial Blocking Paper • 2606.19495 • Published 19 days ago • 9