UltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing Paper • 2607.08646 • Published 17 days ago • 3
KronQ: LLM Quantization via Kronecker-Factored Hessian Paper • 2607.07964 • Published 18 days ago • 32
Video Generation Models are General-Purpose Vision Learners Paper • 2607.09024 • Published 16 days ago • 83
Multiplayer Interactive World Models with Representation Autoencoders Paper • 2607.05352 • Published 20 days ago • 28
Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Paper • 2607.07675 • Published 18 days ago • 64
Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling Paper • 2607.02980 • Published 23 days ago • 81
Flow-ERD: Agent-type Aware Flow Matching with Entropy-Regularized Distillation for Diverse Traffic Simulation Paper • 2607.06957 • Published 18 days ago • 12
From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models Paper • 2607.06553 • Published 17 days ago • 20
Terrain Diffusion: A Diffusion-Based Successor to Perlin Noise in Infinite, Real-Time Terrain Generation Paper • 2512.08309 • Published Dec 9, 2025 • 9
PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation Paper • 2607.02515 • Published 24 days ago • 19
Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling Paper • 2607.01642 • Published 24 days ago • 39
Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training Paper • 2607.01232 • Published 24 days ago • 7