Concept Bottleneck Models, ICML 2020

Code for the paper "Post-hoc Concept Bottleneck Models". Spotlight @ ICLR 2023

ICLR 2024: Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretations

[ICLR 23] A new framework to transform any neural networks into an interpretable concept-bottleneck-model (CBM) without needing labeled concept data

Official code for "Probabilistic Concept Bottleneck Models (ICML 2023)"

Repository for our NeurIPS 2022 paper "Concept Embedding Models", our NeurIPS 2023 paper "Learning to Receive Help", and our ICML 2025 paper "Avoiding Leakage Poisoning"

CVPR 2023: Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification

The code for the paper "Pre-trained Vision-Language Models Learn Discoverable Concepts"

NeurIPS 2024 (spotlight): A Textbook Remedy for Domain Shifts Knowledge Priors for Medical Image Analysis

(ICML 2024) Spider: A Unified Framework for Context-dependent Concept Segmentation

The official implementation of the paper **Learning Concise and Descriptive Attributes for Visual Recognition**

[ICML 24] A novel automated neuron explanation framework that can accurately describe poly-semantic concepts in deep neural networks

Implementation of the paper "Conceptual-Learning via Embedding Approximations for Reinforcing Interpretability and Transparency"

[NeurIPS 24] A new training and evaluation framework for learning interpretable deep vision models and benchmarking different interpretable concept-bottleneck-models (CBMs)

[ICLR 25] A novel framework for building intrinsically interpretable LLMs with human-understandable concepts to ensure safety, reliability, transparency, and trustworthiness.

Official repo for ICML25 paper: DCBM: Data-Efficient Visual Concept Bottleneck Models

Code for the paper: "Tree-Based Leakage Inspection and Control in Concept Bottleneck Models"

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Code repository for "Explanation Bottleneck Models" (AAAI2025 Oral)

PyTorch Explain: Interpretable Deep Learning in Python.

PyC (Pytorch Concepts) is a PyTorch-based library for training concept-based interpretable deep learning models.

CausalVLR: A Toolbox and Benchmark for Vision-Language Causal Reasoning (多模态因果推理开源框架)

Intervening in Black Box: Concept Bottleneck Model for Enhancing Human Neural Network Mutual Understanding (ICCV 2025 Accepted)