Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation
Paper • 2610.20571 • Published • 343
John
kklibbe0992
AI & ML interests
None yet
Recent Activity
upvoted a paper 2 days ago
Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation upvoted a paper 2 days ago
Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents upvoted a paper 2 days ago
Player-1: Learning to Play from Synthetic ExperienceOrganizations
None yet
upvoted 4
papers 2 days ago
Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents
Paper • 2610.20344 • Published • 106
Player-1: Learning to Play from Synthetic Experience
Paper • 2610.20584 • Published • 335
Speculative Forcing for Efficient Autoregressive Video Generation
Paper • 2610.22347 • Published • 77
upvoted 8
papers 9 days ago
UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation
Paper • 2610.09823 • Published • 196
GRACE: Generation-aware latent compression for efficient video generation
Paper • 2610.10524 • Published • 90
Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness
Paper • 2610.08621 • Published • 98
nanoMuse: An Open-Source Personal Agent for Every Device You Own
Paper • 2610.08699 • Published • 116
Long-WAM: Scaling the Context of World-Action Models
Paper • 2610.10528 • Published • 113
STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization
Paper • 2609.38169 • Published • 133
SanSi: A Looped Typed Decision Model for System 1.5 Thinking
Paper • 2610.07730 • Published • 20
Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction
Paper • 2610.12299 • Published • 70
upvoted 6
papers 15 days ago
Orca: The World is in Your Mind
Paper • 2606.30534 • Published • 514
Atria Dawn: The Dawn of Agentic Superintelligence
Paper • 2609.15818 • Published • 423
Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation
Paper • 2609.11638 • Published • 660
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 564
InterEvolve: Test-Time Evolution of Reward Programs for Humanoid Loco-Manipulation
Paper • 2610.02196 • Published • 63
World Observer: Joint Actor-Observer Generation for Persistent World Modeling
Paper • 2610.02162 • Published • 91