BoYang Zheng

bytetriper's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 2 days ago

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes

Paper • 2608.05000 • Published 4 days ago • 52

New activity in nyu-visionx/RAE-collections 4 months ago

Can you briefly introduce the newly added decB_ganv3?

1

#4 opened 4 months ago by

shy0423

upvoted a paper 4 months ago

LangFlow: Continuous Diffusion Rivals Discrete in Language Modeling

Paper • 2604.11748 • Published Apr 15 • 14

upvoted a paper 5 months ago

Beyond Language Modeling: An Exploration of Multimodal Pretraining

Paper • 2603.03276 • Published Mar 3 • 107

New activity in nyu-visionx/RAE-mae-base-p16-ViTXL-n08 5 months ago

Update weights: include latent normalization buffers for diffusers compatibility

#3 opened 5 months ago by

kashif

New activity in nyu-visionx/RAE-siglip2-base-p16-i256-ViTXL-n08 5 months ago

Update weights: include latent normalization buffers for diffusers compatibility

#4 opened 5 months ago by

kashif

New activity in nyu-visionx/RAE-dinov2-wReg-large-ViTXL-n08 5 months ago

Update weights: include latent normalization buffers for diffusers compatibility

#4 opened 5 months ago by

kashif

New activity in nyu-visionx/RAE-dinov2-wReg-small-ViTXL-n08 5 months ago

Update weights: include latent normalization buffers for diffusers compatibility

#3 opened 5 months ago by

kashif

New activity in nyu-visionx/RAE-dinov2-wReg-base-ViTXL-n08-i512 5 months ago

Update weights: include latent normalization buffers for diffusers compatibility

#3 opened 5 months ago by

kashif

New activity in nyu-visionx/RAE-dinov2-wReg-base-ViTXL-n08 5 months ago

Update weights: include latent normalization buffers for diffusers compatibility

#4 opened 5 months ago by

kashif

updated a model 5 months ago

nyu-visionx/RAE-collections

Unconditional Image Generation • Updated Mar 1 • 48

New activity in nyu-visionx/RAE-dinov2-wReg-large-ViTXL-n08 5 months ago

Add encoder_num_hidden_layers=24 to config

1

#3 opened 5 months ago by

kashif

New activity in nyu-visionx/RAE-siglip2-base-p16-i256-ViTXL-n08 5 months ago

Remap encoder keys to match SiglipVisionModel key layout

#3 opened 5 months ago by

kashif

New activity in nyu-visionx/RAE-dinov2-wReg-base-ViTXL-n08 6 months ago

Update config for diffusers AutoencoderRAE refactor

#3 opened 6 months ago by

kashif

New activity in nyu-visionx/RAE-dinov2-wReg-base-ViTXL-n08-i512 6 months ago

Update config for diffusers AutoencoderRAE refactor

#2 opened 6 months ago by

kashif

New activity in nyu-visionx/RAE-dinov2-wReg-small-ViTXL-n08 6 months ago

Update config for diffusers AutoencoderRAE refactor

#2 opened 6 months ago by

kashif

New activity in nyu-visionx/RAE-dinov2-wReg-large-ViTXL-n08 6 months ago

Update config for diffusers AutoencoderRAE refactor

#2 opened 6 months ago by

kashif

New activity in nyu-visionx/RAE-siglip2-base-p16-i256-ViTXL-n08 6 months ago

Update config for diffusers AutoencoderRAE refactor

#2 opened 6 months ago by

kashif

New activity in nyu-visionx/RAE-mae-base-p16-ViTXL-n08 6 months ago

Update config for diffusers AutoencoderRAE refactor

#2 opened 6 months ago by

kashif

updated a collection 6 months ago

RAE

Collection

Collection for Diffusion Transformers with Representation Autoencoders • 7 items • Updated Feb 22 • 15