Submitted by yuchenlin 35 Stronger Models are NOT Stronger Teachers for Instruction Tuning · 5 authors 2
Submitted by akhaliq 30 JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation · 14 authors 3
Submitted by Hooman 11 Wavelet Latent Diffusion (Wala): Billion-Parameter 3D Generative Model with Compact Wavelet Encodings · 8 authors 2