Explore projects

A naive determinant-based implementation of CI method for teaching

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Ongoing research training transformer language models at scale, including: BERT & GPT-2

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)

[CVPR 2022] Neural Shape Mating: Self-Supervised Object Assembly with Adversarial Shape Priors

Implementation of the Transformer variant proposed in "Transformer Quality in Linear Time"

[ICCV 2023] HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generation

PyTorch implementation of Representation Learning with Contrastive Predictive Coding by Van den Oord et al. (2018)