Weixin-Liang

LLM-widespread-adoption-impact. Python

Mixture-of-Transformers. Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models. TMLR 2025.

Large-Scale-Selection-for-LLMs. AISTATS 2025: Efficient and Asymptotically Unbiased Constrained Decoding for Large Language Models

STP. The official implementation of "Self-play LLM Theorem Provers with Iterative Conjecturing and Proving"

PCL-lite. [ICML 2025] Adaptive Self-improvement LLM Agentic System for ML Library Development

Mixture-of-Mamba. Python

ActSort-public. ActSort is an active learning accelerated cell sorter tool for calcium imaging.

Moon-Shape-ICML-2023. Jupyter Notebook

Mapping-the-Increasing-Use-of-LLMs-in-Scientific-Papers. Jupyter Notebook

AI-model-card-analysis-HuggingFace. Jupyter Notebook

HuggingFace-Dataset-Card-Analysis. Navigating Dataset Documentations in AI: A Large-Scale Analysis of Dataset Cards on HuggingFace (ICLR 2024)

opendataval. OpenDataVal: a Unified Benchmark for Data Valuation in Python (NeurIPS 2023)

LLM-scientific-feedback. Can large language models provide useful feedback on research papers? A large-scale empirical analysis.

opendataval.github.io. opendataval documentation

ChatGPT-Detector-Bias. Python

langchain. The agent engineering platform.

Modality-Gap. Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning

contextualized-topic-models. A python package to run contextualized topic modeling. CTMs combine contextualized embeddings (e.g., BERT) with topic models to get coherent topics. Published at EACL and ACL 2021 (Bianchi et al.).

vision-language-models-are-bows. Experiments and data for the paper "When and why vision-language models behave like bags-of-words, and what to do about it?" Oral @ ICLR 2023

debug-mistakes-cce. Meaningfully debugging model mistakes with conceptual counterfactual explanations. ICML 2022

fast_dist_shapley. Efficient Computation and Analysis of Distributional Shapley Values (AISTATS 2021)

wdro_local_perturbation. Principled learning method for Wasserstein distributionally robust optimization with local perturbations (ICML 2020)

beta_shapley. Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning (AISTATS 2022 Oral)

MetaShift. MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflicts (ICLR 2022)

data-centric-AI-perspective. Jupyter Notebook

NeuralGroupTesting. Neural Group Testing to Accelerate Deep Learning (ISIT 2021)

dcbench. A benchmark of data-centric tasks from across the machine learning lifecycle.

eLife-peer-review-random-external-factors-study. How random is the review outcome? A systematic study of the impact of external factors on eLife peer review

HERALD. HERALD: An Annotation Efficient Method to Train User Engagement Predictors in Dialogs (ACL 2021)

GraphVQA. GraphVQA: Language-Guided Graph Neural Networks for Scene Graph Question Answering

bwmapdb. Brood War Map Database

Coding-Interview-101. Coding interview tips

LRTA_Perturbed_Dataset. This repository contains the perturbed datasets presented in the paper- LRTA: A Transparent Neural-Symbolic Reasoning Framework with Modular Supervision for Visual Question Answering (NeurIPS 2020)

detr. End-to-End Object Detection with Transformers

ZhuSanJiao. C

OsOOS_without_memory. isolation

dialog_evaluation_CMADE. Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation (ACL 2020)

ATMSeer. Visual Exploration of Automated Machine Learning with ATMSeer

T3. [EMNLP 2020] "T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack" by Boxin Wang, Hengzhi Pei, Boyuan Pan, Qian Chen, Shuohang Wang, Bo Li

MOSS-End-to-End-Dialog-System-Framework-with-Modular-Supervision. https://arxiv.org/abs/1909.05528

TorchFly. A PyTorch Deep Learning Kit

ZSJ_OS_Private. This repository was private before. Since the course has ended, I made it public.

ZSJ_OS_Private. This repository was private before. Since the course has ended, I made it public.

zjuthesis. Zhejiang University Graduation Thesis LaTeX Template

InvisiSpec-1.0. Gem5 implementation of "InvisiSpec", a defense mechanism of speculative execution attacks on cache hierarchy.