Milo Banks

milobanks's activity

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

upvoted 5 papers 2 days ago

Measuring Language Transfer in Robot Policies: Adding Greek to a Cosmos3 Vision-Language-Action Policy

Paper • 2609.07470 • Published 9 days ago • 25

Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout

Paper • 2609.09123 • Published 8 days ago • 55

The Attention Triangle in Audio-Video Models

Paper • 2609.03586 • Published 13 days ago • 42

The Missing Temporal Link: Temporal Context Routing for Script-Driven Audio-Video Generation

Paper • 2609.02367 • Published 14 days ago • 37

SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models

Paper • 2609.02886 • Published 14 days ago • 152

upvoted a paper 5 days ago

FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience

Paper • 2609.03241 • Published 13 days ago • 98

upvoted 3 papers 12 days ago

Matrix-Game 3.5: Enhancing Real-Time Streaming Interactive World Models with Patch Memory

Paper • 2608.29910 • Published 17 days ago • 19

WebWorld: The Browser as a World Model for Self-Improving Web Code

Paper • 2608.30530 • Published 16 days ago • 10

DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution

Paper • 2608.31106 • Published 16 days ago • 101

upvoted a paper 13 days ago

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published 15 days ago • 488

upvoted 3 papers 14 days ago

Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models

Paper • 2608.25518 • Published 21 days ago • 196

PAWBench: How Far Are We from Probabilistically Aligned World Modeling?

Paper • 2608.27345 • Published 20 days ago • 146

Magpie: Real-Time World Renderer for Interactive Games

Paper • 2608.27168 • Published 20 days ago • 12

upvoted 2 papers 15 days ago

VGI-Bench: Probing Visual Intelligence in Video Generation Models

Paper • 2608.19583 • Published 21 days ago • 179

VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning

Paper • 2608.26105 • Published 21 days ago • 270

upvoted 2 papers 18 days ago

Game2World Engine: Unlocking In-the-Wild Gameplay Videos for World Model Training

Paper • 2608.24680 • Published 22 days ago • 11

Meta^n: Recursive Self-Improvement through Emergent Depth

Paper • 2608.24735 • Published 22 days ago • 15

upvoted 2 papers 19 days ago

EchoWM: Open and Enterable Omnimodal World Models

Paper • 2608.23189 • Published 23 days ago • 79

Apodex 1.1: Scaling Agentic Intelligence for Complex Work

Paper • 2608.23283 • Published 23 days ago • 207

upvoted a paper 20 days ago

Partition the Support, Reconstruct the Residual: Training-Free Sparse Attention for Video Generation and World Models

Paper • 2608.18484 • Published 28 days ago • 9