Milo Banks

milobanks's activity

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

upvoted 4 papers about 13 hours ago

WorldDiT: A Unified Diffusion Architecture for World and Action Modeling

Paper • 2607.23909 • Published 7 days ago • 7

Moving Alphabet: A Controlled Study of Training Data for Text-to-Video Generation

Paper • 2607.18789 • Published 13 days ago • 2

Closing the Loop: Training-Free Revisit Consistency for Autoregressive Generative Rendering

Paper • 2607.21848 • Published 11 days ago • 9

FVAttn: Adaptive Sparse Attention with Runtime Load Balancing for Video Generation

Paper • 2607.16190 • Published 17 days ago • 9

upvoted 2 papers 1 day ago

Self Gradient Forcing: Native Long Video Extrapolation

Paper • 2607.20368 • Published 12 days ago • 35

CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents

Paper • 2607.25431 • Published 6 days ago • 103

upvoted 5 papers 2 days ago

Temporal-Distance JEPA: Plan-Aware Representation Learning for Latent World Model Predictive Control

Paper • 2607.25337 • Published 6 days ago • 5

VisualPatchWorld: Code World Models as Latent Structured Representations for Planning

Paper • 2607.25236 • Published 6 days ago • 4

Wonder: Video World Model Done Better

Paper • 2607.26037 • Published 6 days ago • 18

Parallel Decoding Distillation for Fast Image and Video Generation

Paper • 2607.26004 • Published 6 days ago • 12

ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition

Paper • 2607.25565 • Published 6 days ago • 61

upvoted 5 papers 3 days ago

FilmBench: A Film-Grade Benchmark for Cinematic Video Generation

Paper • 2607.24241 • Published 7 days ago • 6

The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation

Paper • 2607.24720 • Published 7 days ago • 25

Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification

Paper • 2607.24027 • Published 7 days ago • 35

OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation

Paper • 2607.23855 • Published 8 days ago • 26

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 7 days ago • 431

upvoted 4 papers 5 days ago

GraphVid: Interactive Graph-Controllable Video Generation

Paper • 2607.21580 • Published 11 days ago • 8

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation

Paper • 2607.21553 • Published 11 days ago • 39

Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers

Paper • 2607.21594 • Published 11 days ago • 16

AREX: Towards a Recursively Self-Improving Agent for Deep Research

Paper • 2607.21461 • Published 11 days ago • 150