A curated list of resources for activation engineering

支持大麦网，淘票票、缤玩岛等多个平台，演唱会演出抢票脚本

A lightweight macOS literature manager built in native Swift.

一个基于 Vue 3 + Express 的网盘资源搜索与转存工具。

Sparse Linear Concept Embeddings

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

CB2M extend bottlenecks with a two-fold memory to automatically detect model mistakes and generalize human interventions.

A comprehensive survey of Concept Bottleneck Models (CBM)

A collection of research materials on explainable AI/ML

Implementation of PatchSAE as presented in "Sparse autoencoders reveal selective remapping of visual concepts during adaptation"

Source code for paper "Improving Continual Learning Performance and Efficiency with Auxiliary Classifiers" from ICML 2025

[NeurIPS 2025] VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learning

A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.

🌈Bilibili_video_download-B站视频下载

Semi-supervised Concept Bottleneck Models (SSCBM)

A cross-platform, instant-rendering desktop Markdown editor 一个跨平台的、即时渲染桌面端 Markdown 编辑器

Lumina Robotics Talent Call | Lumina社区具身智能招贤榜 | A list for Embodied AI / Robotics Jobs (PhD, RA, intern, etc

学术双语简历模板，涵盖教育背景、论文发表、项目经历、竞赛经历和个人陈述等关键部分，可适用于申请研究生项目、学术职位或相关行业岗位。

[CVPR 2025] Official implementation of the paper "Show and Tell: Visually Explainable Deep Neural Nets via Spatially-Aware Concept Bottleneck Models" (by Benou and Riklin-Raviv): https://arxiv.org/…

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

This is the official implementation of the Coarse-to-Fine Concept Bottleneck Models paper, NeurIPS 2024.

中文LaTeX简历模板

SSiT: Saliency-guided Self-supervised Image Transformer for Diabetic Retinopathy Grading

Papers and Public Datasets for Diabetic Retinopathy Detection

Next.js Blog Template for ladder theme

Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models

The codes for 'Progressive cross-primitive consistency for open-world compositional zero-shot learning'