lenitokore/affine-5DG8LCSRxSGECEfnBveT6TFoKBhKDTbtAJjkpNXTmLciBR2x 33B • Updated about 5 hours ago • 1
Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration Paper • 2605.17423 • Published 17 days ago • 33
EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation Paper • 2605.23271 • Published 12 days ago • 79
HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation Paper • 2604.28196 • Published Apr 30 • 72
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model Paper • 2604.20796 • Published Apr 22 • 242
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published Apr 8 • 326
TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders Paper • 2604.07340 • Published Apr 8 • 17