youngsheen

USTC

Pinned Repositories

DiGIT
[NeurIPS 2024] Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective
Language:Python40 4 02
Janus
Janus-Series: Unified Multimodal Understanding and Generation Models
Language:Python1k 20 1845
lingua
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
Language:Python4.2k 29 30216
VAR
[NeurIPS 2024 Oral][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!
Language:Python4.3k 116 82315
torchtune
PyTorch native finetuning library
Language:Python4.3k 47 692430
DiGIT
Language:Python00
GPST
[ACL 2024] Generative Pre-Trained Speech Language Model with Efficient Hierarchical Transformer
Language:Python37 2 02
Open-VideoPoet
00
SimVQ
SimVQ: Addressing Representation Collapse in Vector Quantized Models with One Linear Layer
Language:Python103 2 44
youngsheen.github.io
AcadHomepage: A Modern and Responsive Academic Personal Homepage
Language:SCSS00

youngsheen's Repositories

youngsheen/SimVQ
SimVQ: Addressing Representation Collapse in Vector Quantized Models with One Linear Layer
Language:Python103 2 44
youngsheen/GPST
[ACL 2024] Generative Pre-Trained Speech Language Model with Efficient Hierarchical Transformer
Language:Python37 2 02
youngsheen/DiGIT
Language:Python00
youngsheen/Open-VideoPoet
00
youngsheen/youngsheen.github.io
AcadHomepage: A Modern and Responsive Academic Personal Homepage
Language:SCSS00