[ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling

kmeans using PyTorch

LLM papers I'm reading, mostly on inference and model compression

Fourier Controller Networks (FCNet) for Real-Time Decision-Making in Embodied Learning, ICML 2024

Autoregressive Entity Retrieval

Resume，Resume Templates，程序员简历例句，简历模版，

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

TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.

Official implementation of our LREC-COLING 2024 paper "Generative Multimodal Entity Linking".

A playbook for systematically maximizing the performance of deep learning models.

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…

Support extracting BUTD features for NLVR2 images.

Research code for ECCV 2020 paper "UNITER: UNiversal Image-TExt Representation Learning"

Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)

Simple image captioning model

Power CLI and Workflow manager for LLMs (core package)

CapDec: SOTA Zero Shot Image Captioning Using CLIP and GPT2, EMNLP 2022 (findings)

Multimodal entity linking for Tweets

🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

Some scripts and configuration files for personal use.

Entity Linker solution

A collection of resources on multimodal knowledge graph, including datasets, papers and contests.