CrossTimeEdit: A Decade-Spanning Cross-View Dataset and Reward-Guided Editing for Historical Street-View Generation Paper • 2609.36616 • Published 17 days ago • 31
Hear the World in Stereo: Learning Dynamic Spatial Correspondence for Immersive Joint Video-Audio Generation Paper • 2609.38748 • Published 8 days ago • 66
AMLworld-Compact: Importance-Weighted Downsampling for Cost-Effective LLM Evaluation and Error Diagnosis Paper • 2610.13627 • Published 7 days ago • 13
hardikpatel/GPT2_Music_Generation_Trained Text Generation • 27.1M • Updated Apr 28, 2024 • 153 • 4
WorldGuide: Goal-Directed Video World Model for Procedural Task Execution Paper • 2610.12459 • Published 8 days ago • 20
STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization Paper • 2609.38169 • Published 17 days ago • 131
DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation Paper • 2610.03543 • Published 14 days ago • 102
Aalto-Speech-Synthesis/whisper-large-v3-Icelandic-finetuned-ct2 Automatic Speech Recognition • Updated Sep 3 • 69 • 4
Learning Functional Subspaces for Neural Network Compression Paper • 2609.40127 • Published 16 days ago • 25
ehcalabres/distilgpt2-abc-irish-music-generation Text Generation • 88.2M • Updated Sep 21, 2023 • 171 • 6
SlimWise: Decoupling Expert Pruning Across Prefill and Decode for Efficient MoE Serving Paper • 2609.34117 • Published 18 days ago • 25