LaTtE-Flow: Layerwise Timestep-Expert Flow-based Transformer Paper • 2506.06952 • Published 9 days ago • 10 • 2
LaTtE-Flow: Layerwise Timestep-Expert Flow-based Transformer Paper • 2506.06952 • Published 9 days ago • 10
LaTtE-Flow: Layerwise Timestep-Expert Flow-based Transformer Paper • 2506.06952 • Published 9 days ago • 10
AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning Paper • 2505.16400 • Published 26 days ago • 31
BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset Paper • 2505.09568 • Published May 14 • 94
zhiyang1/vlm_dc-ae-f32c32-in-1.0-diffusers-768_patch-2_epoch-64-0_group-7_5e4_residual_attn Updated May 7
zhiyang1/vlm_dc-vae-f32c32-sana-1.1-768_epoch-64-0_group-14_no-self-attn-lora_residual_attn Updated May 6
zhiyang1/vlm_dc-ae-f32c32-in-1.0-diffusers-768_patch-2_epoch-64-0_group-7_5e4_residual_attn Updated May 7
zhiyang1/vlm_dc-vae-f32c32-sana-1.1-768_epoch-64-0_group-14_no-self-attn-lora_residual_attn Updated May 6