Current World Models Lack a Persistent State Core
Paper • 2606.20545 • Published • 16
Milo Banks
milobanks
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
Current World Models Lack a Persistent State CoreOrganizations
None yet
upvoted 3
papers 1 day ago
upvoted 4
papers 2 days ago
World Value Models for Robotic Manipulation
Paper • 2606.24742 • Published • 6
Critique of Agent Model
Paper • 2606.23991 • Published • 20
Qwen-AgentWorld: Language World Models for General Agents
Paper • 2606.24597 • Published • 136
AOHP: An Open-Source OS-Level Agent Harness for Personalized, Efficient and Secure Interaction
Paper • 2606.23449 • Published • 30
upvoted 4
papers 3 days ago
Go-with-the-Track: Video Compositing and Motion Control with Point Tracking
Paper • 2606.20891 • Published • 3
World Action Models: A Survey
Paper • 2606.20781 • Published • 54
DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams
Paper • 2606.21337 • Published • 73
Grouped Query Experts: Mixture-of-Experts on GQA Self-Attention
Paper • 2606.20945 • Published • 75
upvoted 4
papers 6 days ago
PAIWorld: A 3D-Consistent World Foundation Model for Robotic Manipulation
Paper • 2606.18375 • Published • 11
Physics-IQ Verified
Paper • 2606.18943 • Published • 5
MaineCoon: Pursuing A Real-Time Audio-Visual Social World Model
Paper • 2606.17800 • Published • 13
Kairos: A Native World Model Stack for Physical AI
Paper • 2606.16533 • Published • 38
upvoted 5
papers 7 days ago
BadWorld: Adversarial Attacks on World Models
Paper • 2606.16519 • Published • 18
OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data
Paper • 2606.13432 • Published • 112
Avatar V: Scaling Video-Reference Avatar Video Generation
Paper • 2606.13872 • Published • 9
Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation
Paper • 2606.17030 • Published • 30
PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory
Paper • 2606.16449 • Published • 5