-
Flowing from Words to Pixels: A Framework for Cross-Modality Evolution
Paper • 2412.15213 • Published • 25 -
No More Adam: Learning Rate Scaling at Initialization is All You Need
Paper • 2412.11768 • Published • 41 -
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference
Paper • 2412.13663 • Published • 103 -
Autoregressive Video Generation without Vector Quantization
Paper • 2412.14169 • Published • 13
Collections
Discover the best community collections!
Collections including paper arxiv:2412.15322
-
GenEx: Generating an Explorable World
Paper • 2412.09624 • Published • 84 -
IamCreateAI/Ruyi-Mini-7B
Image-to-Video • Updated • 12.8k • 458 -
Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation
Paper • 2412.06016 • Published • 20 -
Byte Latent Transformer: Patches Scale Better Than Tokens
Paper • 2412.09871 • Published • 74
-
SoundCTM: Uniting Score-based and Consistency Models for Text-to-Sound Generation
Paper • 2405.18503 • Published • 9 -
DITTO-2: Distilled Diffusion Inference-Time T-Optimization for Music Generation
Paper • 2405.20289 • Published • 10 -
LiveSpeech: Low-Latency Zero-shot Text-to-Speech via Autoregressive Modeling of Audio Discrete Codes
Paper • 2406.02897 • Published • 13 -
Audio Mamba: Bidirectional State Space Model for Audio Representation Learning
Paper • 2406.03344 • Published • 18