LancoPKU

pkuseg-python

pkuseg多领域中文分词工具; The pkuseg toolkit for multi-domain Chinese word segmentation

label-words-are-anchors

Repository for Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

text-autoaugment

[EMNLP 2021] Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification

meProp

meProp: Sparsified Back Propagation for Accelerated Deep Learning (ICML 2017)

Prime

A simple module consistently outperforms self-attention and Transformer model on main NMT datasets with SoTA performance.

Explicit-Sparse-Transformer

code for Explicit Sparse Transformer

DynamicKD

Code for EMNLP 2021 main conference paper "Dynamic Knowledge Distillation for Pre-trained Language Models"

well-classified-examples-are-underestimated

Code for the AAAI 2022 publication "Well-classified Examples are Underestimated in Classification with Deep Neural Networks"

Embedding-Poisoning

Code for the paper "Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models" (NAACL-HLT 2021)

IAIS

[ACL 2021] Learning Relation Alignment for Calibrated Cross-modal Retrieval

codable-watermarking-for-llm

Repository for Towards Codable Watermarking for Large Language Models

agent-backdoor-attacks

Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents"

CGM

Code for IJCAI 2021 main conference paper "Long-term, Short-term and Sudden Event: Trading Volume Movement Prediction with Graph-based Multi-view Modeling"

clip-openness

[ACL 2023] Delving into the Openness of CLIP

SOS

Code for the paper "Rethinking Stealthiness of Backdoor Attack against NLP Models" (ACL-IJCNLP 2021)

RAP

Code for the paper "RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models" (EMNLP 2021)

MUKI

[Findings of EMNLP22] From Mimicking to Integrating: Knowledge Integration for Pre-Trained Language Models

Avg-Avg

[Findings of EMNLP 2022] Holistic Sentence Embeddings for Better Out-of-Distribution Detection

ChineseNER

Code for "Cross-Domain and Semi-Supervised Named Entity Recognition in Chinese Social Media: A Unified Model"

CascadeBERT

Code for CascadeBERT, Findings of EMNLP 2021

DCKD

Code and data for Distributional Correlation–Aware Knowledge Distillation for Stock Trading Volume Prediction (ECML-PKDD 22)

DAN

[Findings of EMNLP 2022] Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks

FedMNMT

[Findings of ACL 2023] Communication Efficient Federated Learning for Multilingual Machine Translation with Adapter

GKD

Attention-Augmentation

GNOME

Code of the EACL 2023 Paper: Fine-Tuning Deteriorates General Textual Out-of-Distribution Detection by Distorting Task-Agnostic Features

MR-VPC

Towards Multimodal Video Paragraph Captioning Models Robust to Missing Modality

FedGLAD

LaDiC

[NAACL 2024] LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-text Generation?

lancopku.github.io

Lanco Lab website