Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation
Paper • 2610.20571 • Published • 239
Kyu Song PRO
deepkyu
AI & ML interests
Efficient model for image/video generation
Recent Activity
upvoted a paper 15 days ago
Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation upvoted a paper 16 days ago
VideoJev: System One Model for Video Understanding and Interaction upvoted a paper 20 days ago
Multi-Agent Egocentric World Model with Fine-Grained Embodied InteractionOrganizations
upvoted a paper 15 days ago
upvoted a paper 16 days ago
upvoted a paper 20 days ago
upvoted 3
papers 28 days ago
WorldAuditBench: Interactive 3D World Auditing with Multimodal Agents
Paper • 2609.40325 • Published • 95
Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents
Paper • 2609.39982 • Published • 120
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 208
published 2
datasets 28 days ago
updated 2
datasets 28 days ago
upvoted 2
papers 29 days ago
liked a
model 29 days ago
upvoted 3
papers about 2 months ago
FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlow
Paper • 2609.03563 • Published • 16
WorldReward: Reward Modeling for Camera-Conditioned World Models
Paper • 2609.03952 • Published • 25
Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM
Paper • 2609.04098 • Published • 65
updated a
Space about 2 months ago
upvoted a paper 3 months ago
upvoted 2
collections 3 months ago