Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation Paper • 2503.16430 • Published 10 days ago • 34
When Less is Enough: Adaptive Token Reduction for Efficient Image Representation Paper • 2503.16660 • Published 10 days ago • 70
SampleMix: A Sample-wise Pre-training Data Mixing Strategey by Coordinating Data Quality and Diversity Paper • 2503.01506 • Published 28 days ago • 9
DiffRhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion Paper • 2503.01183 • Published 28 days ago • 26
Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs Paper • 2503.01743 • Published 27 days ago • 79