Latest Advances on Agentic AI & AI Agents for Healthcare

Code base for Universal Sparse Autoencoders (USAEs)

[NeurIPS 2025] Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models

HypotheSAEs: hypothesizing interpretable relationships in text datasets using sparse autoencoders. https://arxiv.org/abs/2502.04382

Earth system foundation model data, training, and eval

Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models know themselves through automated interpretability.

Official code for the NeurIPS 2025 paper "egoEMOTION: Egocentric Vision and Physiological Signals for Emotion and Personality Recognition in Real-World Tasks."

Code and data for UniEgoMotion (ICCV 2025)

Open-source framework for the research and development of foundation models.

A framework that allows you to apply Sparse AutoEncoder on any models

[ICML 2025 Poster] SAE-V: Interpreting Multimodal Models for Enhanced Alignment

Training Sparse Autoencoders on Language Models

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

[ICCV 2025] Auto Interpretation Pipeline and many other functionalities for Multimodal SAE Analysis.

Code for paper: Reinforced Vision Perception with Tools

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

Graph Neural Network Library for PyTorch

This repo contains evaluation code for the paper "BLINK: Multimodal Large Language Models Can See but Not Perceive". https://arxiv.org/abs/2404.12390 [ECCV 2024]

Code that accompanies the public release of the paper Lost in Conversation (https://arxiv.org/abs/2505.06120)

Explain Before You Answer: A Survey on Compositional Visual Reasoning

Reference PyTorch implementation and models for DINOv3

Official repository for Beyond Binary Rewards: Training LMs to Reason about Their Uncertainty