Yixuan Su

PandaGPT. [TLLM'23] PandaGPT: One Model To Instruction-Follow Them All

SimCTG. [NeurIPS'22 Spotlight] A Contrastive Framework for Neural Text Generation

OpenAlpaca. OpenAlpaca: A Fully Open-Source Instruction-Following Model Based On OpenLLaMA

MAGIC. Language Models Can See: Plugging Visual Controls in Text Generation

Contrastive_Search_Is_What_You_Need. [TMLR'23] Contrastive Search Is What You Need For Neural Text Generation

TaCL. [NAACL'22] TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning

PlanGen. [EMNLP'21] Plan-then-Generate: Controlled Data-to-Text Generation via Planning

NAG-BERT. [EACL'21] Non-Autoregressive with Pretrained Language Model

Chinese-TaCL-BERT-NER-CWS. 基于中文TaCL-BERT的中文命名实体识别及中文分词

Contrastive_Search_versus_Contrastive_Decoding. An Empirical Study On Contrastive Search And Contrastive Decoding For Open-ended Text Generation

Few-Shot-Table-to-Text-Generation. [EMNLP'21] Few-Shot Table-to-Text Generation with Prototype Memory

HCL. [ACL'21] Dialogue Response Selection with Hierarchical Curriculum Learning

Awesome_Diffusions.

Paper_List_of_LLMs_as_Agent_and_Tool_Use.

yxuansu.github.io. My personal webpage

PyTorch-Beam-Search-Decoding. PyTorch implementation of beam search decoding for seq2seq models

Contrastive-Learning-NLP-Papers. Paper List for Contrastive Learning for Natural Language Processing

ceval. Official github repo for C-Eval, a Chinese evaluation suite for foundation models

blog. Public repo for HF blog posts

open_llama.

BERT-CH-NER. 基于BERT的中文命名实体识别

cambridge_thesis. A LaTeX document class that conforms to the Computer Laboratory's PhD thesis formatting guidelines.

hello-world. first repository

cite. Implementation for our paper "Conditional Image-Text Embedding Networks"

Awesome-LLM. Awesome-LLM: a curated list of Large Language Model

citation-file-format. 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.