Milo Banks

milobanks's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 6 days ago

Bellman Policy Optimization

Paper • 2609.15987 • Published 18 days ago • 49

upvoted 2 papers 8 days ago

WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory

Paper • 2609.24984 • Published 11 days ago • 157

GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay

Paper • 2609.25001 • Published 11 days ago • 131

upvoted 4 papers 9 days ago

GAVEL: Graph World Models for Verified and Efficient Long-Horizon LLM Task Planning

Paper • 2609.19315 • Published 16 days ago • 5

OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue

Paper • 2609.21465 • Published 14 days ago • 150

OmniVBench: A Benchmark and Large-Scale Dataset for Omni Reference-to-Video Generation

Paper • 2609.22069 • Published 14 days ago • 37

From Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention

Paper • 2609.21788 • Published 14 days ago • 13

upvoted 4 papers 10 days ago

JEPA-Anything: Learning Predictive Models across Different Worlds

Paper • 2609.20800 • Published 15 days ago • 75

Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation

Paper • 2609.20744 • Published 15 days ago • 53

Can MiniMax-H3 Reason About the Physical World? An Evaluation of Omni-Modal Generative Model

Paper • 2609.18323 • Published 16 days ago • 133

Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling

Paper • 2609.19499 • Published 16 days ago • 37

upvoted 2 papers 11 days ago

VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention

Paper • 2609.15810 • Published 18 days ago • 51

Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Control

Paper • 2609.17909 • Published 17 days ago • 47

upvoted 5 papers 12 days ago

SyncWorld: Visual Calibration Enables World Models as Zero-Shot Simulators

Paper • 2609.09155 • Published 24 days ago • 17

AgenticGen: Reward-Guided Agentic Video Generation for Advertising

Paper • 2609.09187 • Published Aug 31 • 14

Programmable World Model

Paper • 2609.10540 • Published 23 days ago • 115

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published Aug 29 • 486

Training Specialist Models without Reasoning Trajectories for Domain Expert Distillation

Paper • 2609.13770 • Published 20 days ago • 9

upvoted 2 papers 14 days ago

PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control

Paper • 2609.17521 • Published 17 days ago • 10

AI for Games in the Foundation Model Era

Paper • 2609.16679 • Published 17 days ago • 146