Name: Yixuan Su
Type: User
Company: Cohere, University of Cambridge
Bio: Research Scientist at Cohere and Ph.D. student at the Language Technology Lab of the University of Cambridge.
Twitter: yixuan_su
Location: London, UK
Blog: https://yxuansu.github.io/
Yixuan Su's Projects
Awesome-LLM: a curated list of Large Language Model
基于BERT的中文命名实体识别
Public repo for HF blog posts
A LaTeX document class that conforms to the Computer Laboratory's PhD thesis formatting guidelines.
Official github repo for C-Eval, a Chinese evaluation suite for foundation models
基于中文TaCL-BERT的中文命名实体识别及中文分词
The Citation File Format lets you provide citation metadata for software or datasets in plaintext files that are easy to read by both humans and machines.
Implementation for our paper "Conditional Image-Text Embedding Networks"
Paper List for Contrastive Learning for Natural Language Processing
[TMLR'23] Contrastive Search Is What You Need For Neural Text Generation
An Empirical Study On Contrastive Search And Contrastive Decoding For Open-ended Text Generation
Companion repo for "Evaluating Verifiability in Generative Search Engines".
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
[EMNLP'21] Few-Shot Table-to-Text Generation with Prototype Memory
Folder / directory structure options and naming conventions for software projects
[ACL'21] Dialogue Response Selection with Hierarchical Curriculum Learning
first repository
my personal website
Language Models Can See: Plugging Visual Controls in Text Generation
Markdown - you can mark up titles, lists, tables, etc., in a much cleaner, readable and accurate way if you do it with HTML.
MiniGPT-4: Enhancing Vision-language Understanding with Advanced Large Language Models
Source code for end-to-end dialogue model from the MultiWOZ paper (Budzianowski et al. 2018, EMNLP)
Unified MultiWOZ evaluation scripts for the context-to-response task.
[EACL'21] Non-Autoregressive with Pretrained Language Model
Tracking the progress in non-autoregressive generation (translation, transcription, etc.)
OpenAlpaca: A Fully Open-Source Instruction-Following Model Based On OpenLLaMA
[TLLM'23] PandaGPT: One Model To Instruction-Follow Them All