WorldStream: Streaming Interactive 3D Worlds with Hierarchical Planning and Persistent State
Paper • 2610.28827 • Published • 11
xiaoxiao ma
krennic
·
AI & ML interests
None yet
Recent Activity
submitted a paper about 22 hours ago
WorldStream: Streaming Interactive 3D Worlds with Hierarchical Planning and Persistent State authored a paper about 24 hours ago
WorldStream: Streaming Interactive 3D Worlds with Hierarchical Planning and Persistent State authored a paper about 24 hours ago
VideoAWR: Reinforcing Video Flow Models with Decoupled-Timestep Advantage-Weighted RectificationOrganizations
None yet
submitted a
paper to Daily Papers about 22 hours ago
authored 16
papers about 24 hours ago
WorldStream: Streaming Interactive 3D Worlds with Hierarchical Planning and Persistent State
Paper • 2610.28827 • Published • 11
VideoAWR: Reinforcing Video Flow Models with Decoupled-Timestep Advantage-Weighted Rectification
Paper • 2610.13338 • Published • 1
GraftOOD: Grafting Out-of-Distribution Exemplars into Advantage-Weighted Rectification for Video Reward Optimization
Paper • 2610.13470 • Published • 1
ExeWorldBench: Benchmarking Code-Based Executable 3D World Modeling
Paper • 2610.15166 • Published • 85
CapField-OPD: Learning Continuous Capability Fields via Joint-Anchored Multi-Teacher On-Policy Distillation for Flow Models
Paper • 2609.34658 • Published
Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds
Paper • 2608.23383 • Published • 19
EchoWM: Open and Enterable Omnimodal World Models
Paper • 2608.23189 • Published • 83
STAR: Scale-wise Text-conditioned AutoRegressive image generation
Paper • 2406.10797 • Published
Poly-OPD: Heterogeneous Multi-Teacher On-Policy Distillation for Capability-Selectable Flow Models
Paper • 2608.04349 • Published • 13
Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging
Paper • 2608.03316 • Published • 26
VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System
Paper • 2607.27380 • Published • 60
FlowAWR: Online Adaptive Flow Reinforcement via Advantage-Weighted Rectification
Paper • 2606.30376 • Published • 2
Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutions
Paper • 2606.09150 • Published
SCOPE: Structured Decomposition and Conditional Skill Orchestration for Complex Image Generation
Paper • 2605.08043 • Published • 10
HQ-CLIP: Leveraging Large Vision-Language Models to Create High-Quality Image-Text Datasets and CLIP Models
Paper • 2507.22431 • Published • 1
Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation
Paper • 2312.04265 • Published • 2
upvoted a paper 1 day ago
upvoted a paper 8 days ago
liked a
dataset 8 days ago