Video-As-Prompt: Unified Semantic Control for Video Generation Paper • 2510.20888 • Published 5 days ago • 39
Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training Paper • 2510.12586 • Published 14 days ago • 107
Cache-to-Cache: Direct Semantic Communication Between Large Language Models Paper • 2510.03215 • Published 25 days ago • 93
Efficient Multi-modal Large Language Models via Progressive Consistency Distillation Paper • 2510.00515 • Published 28 days ago • 39
LongCodeZip: Compress Long Context for Code Language Models Paper • 2510.00446 • Published 28 days ago • 107
Seedream 4.0: Toward Next-generation Multimodal Image Generation Paper • 2509.20427 • Published Sep 24 • 75
EmbeddingGemma: Powerful and Lightweight Text Representations Paper • 2509.20354 • Published Sep 24 • 39
MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe Paper • 2509.18154 • Published Sep 16 • 48
view article Article From Zero to GPU: A Guide to Building and Scaling Production-Ready CUDA Kernels Aug 18 • 83