任思宇's Projects
Curated Reinforcement Learning Resources for Natural Language Processing
A collaborative platform for reproducible research (web interface and CLI).
Diverse and Informative Commonsense Inference with Relation-Specific Gaussian Mixture Prior
数据库大作业
[AAAI 2021]Knowledge-Driven Distractor Generation for Cloze-Style Multiple Choice Questions
Personal dotfiles including zshrc/vimrc/tmux.conf
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer (IJCAI 2019)
Easy control for Key-Value Constrained Generative LLM Inference(https://arxiv.org/abs/2402.06262)
[ICLR 2024]EMO: Earth Mover Distance Optimization for Auto-Regressive Language Modeling(https://arxiv.org/abs/2310.04691)
FastFormers - highly efficient transformer models for NLU
Code for ACL 2019 paper "Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs"
[EMNLP 2023]Context Compression for Auto-regressive Transformers with Sentinel Tokens
[NAACL 2022 Findings]Specializing Pre-trained Language Models for Better Relational Reasoning via Network Pruning
Lifelong Commonsense Knowledge Acquisition
A comparison of pretraining framework for LLM
Elegant PyTorch implementation of paper Model-Agnostic Meta-Learning (MAML)
[NAACL 2022]Mobile Text-to-Image search powered by multimodal semantic representation models(e.g., OpenAI's CLIP)
A toy implementation of B-Tree
A c++ implementation of red-black tree
[ACL2023 Findgins]Pruning Pre-trained Language Models with Principled Importance and Self-regularization
Must-read Papers on pre-trained language models.
利用LSTM生成七言律诗