费政聪

FluxMusic. Text-to-Music Generation with Rectified Flow Transformers

DiT-MoE. Scaling Diffusion Transformers with Mixture of Experts

MLE-LLaMA. Multi-language Enhanced LLaMA

Visual-LLaMA. Open LLaMA Eyes to See the World

DiS. Scalable Diffusion Models with State Space Backbone

Diffusion-RWKV. Scaling RWKV-Like Architectures for Diffusion Models

CogvideX-Interpolation. Keyframe Interpolation with CogvideoX

Dimba. Transformer-Mamba Diffusion Models

IEA. Image Editing Anything

Video-Stable-Diffusion. Generate consistent videos with stable diffusion models

Ingredients. Blending Custom Photos with Video Diffusion Transformers

Gradient-Free-Textual-Inversion. Gradient-Free Textual Inversion for Personalized Text-to-Image Generation

Video-In-Context. Video Diffusion Transformers are In-Context Learners

Stable-Edit. Text-based real image editing with stable diffusion models

Perceiver-Music-Generation. music generation with perceiver-ar model

Vespa. Video Diffusion State Space Models

DeeCap. Dynamic Early Exit for Image Captioning

Visual-ChatGLM. Open ChatGLM Eyes to See the World

Matrix-Analysis-and-Application. References and coding homework in matrix analysis and application course in UCAS

PNAIC. Partially Non-Autoregressive Image Captioning

Image-Caption-Pytorch. Pytorch implementation for image caption baseline model

AIO. All In One: General Multimodal Large Language Model

Future-Caption. Efficient modeling of future context for image captioning

UAIC. Uncertainty-away image caption generation

Meta-Ensemble. Meta-Ensemble Parameter Learning

CLIP-MAE. When clip meet mae and beyond

Cleaned-Webvid. Use strategy to achieve clean webvid-10m dataset

Latent-Dynamics. Exploring latent dynamics for visual storytelling

MaskGMT. Masked generative music transformer

Dialogue-System. Multi-modal dialogue system

arXiv-MM. Multimodal dataset for arXiv

Visual-MOSS. Makes MOSS model understand visual information

LQMA. Language Quantized Masked AutoEncoders

Diverse-Image-Caption. Promoting Coherence and Diversity in Image Captioning

MoE-MLLM. Mixture-of-Experts for Multimodal Large Language Models

Union. Unifying Language-Image Pre-training via Single-Tower Transformer

DiffuCap. Controllable Image Captioning with Diffusion Model

MAIC. Memory augmented image captioning

DSC. descriptive synthetic captions in dalle3

feizc.

Chinese-Image-Caption. An image captioner with Chinese language

AAT. Attention-Aligned Transformer for Image Captioning

SAIC. Semi-Autoregressive Image Captioning

DiT. Efficient Vision Transformers with Dynamic Token Routing

ACSG. Actor-Critic Sequence Generation for Relative Difference Captioning