KronQ: LLM Quantization via Kronecker-Factored Hessian Paper • 2607.07964 • Published 6 days ago • 17
Video Generation Models are General-Purpose Vision Learners Paper • 2607.09024 • Published 4 days ago • 47
Multiplayer Interactive World Models with Representation Autoencoders Paper • 2607.05352 • Published 8 days ago • 24
Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Paper • 2607.07675 • Published 6 days ago • 62
Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling Paper • 2607.02980 • Published 11 days ago • 73
Flow-ERD: Agent-type Aware Flow Matching with Entropy-Regularized Distillation for Diverse Traffic Simulation Paper • 2607.06957 • Published 6 days ago • 5
From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models Paper • 2607.06553 • Published 5 days ago • 10
Terrain Diffusion: A Diffusion-Based Successor to Perlin Noise in Infinite, Real-Time Terrain Generation Paper • 2512.08309 • Published Dec 9, 2025 • 8
PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation Paper • 2607.02515 • Published 12 days ago • 16
Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling Paper • 2607.01642 • Published 12 days ago • 37
Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training Paper • 2607.01232 • Published 12 days ago • 6
Loop, Think, & Generalize: Implicit Reasoning in Recurrent-Depth Transformers Paper • 2604.07822 • Published Apr 9 • 2
ReFreeKV: Towards Threshold-Free KV Cache Compression Paper • 2502.16886 • Published 18 days ago • 48