Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders (CVPR 2025)

👀 | MobileGaze: Real-Time Gaze Estimation models using ResNet 18/34/50, MobileNet v2 and MobileOne s0-s4 | In PyTorch >> ONNX

[ECCV 2024] 3DGazeNet: Generalizing Gaze Estimation with Weak-Supervision from Synthetic Views

The official PyTorch implementation of L2CS-Net for gaze estimation and tracking

Pytorch code for experiments on Linear Transformers

The official implementation of ECCV'24 paper "To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now". This work introduces one fast and e…

A pytorch quantization backend for optimum

The simplest, fastest repository for training/finetuning medium-sized GPTs.

[NeurIPS23 (Spotlight)] "Model Sparsity Can Simplify Machine Unlearning" by Jinghan Jia*, Jiancheng Liu*, Parikshit Ram, Yuguang Yao, Gaowen Liu, Yang Liu, Pranay Sharma, Sijia Liu

Google Brain AutoML

[ICLR 2019] "ALISTA: Analytic Weights Are As Good As Learned Weights in LISTA", by Jialin Liu*, Xiaohan Chen*, Zhangyang Wang and Wotao Yin.

GTAR l2l generator unlearning project

An official implementation of "Catastrophic Failure of LLM Unlearning via Quantization" (ICLR 2025)

[CVPR 2024] "MACE: Mass Concept Erasure in Diffusion Models" (Official Implementation)

✨✨Latest Advances on Multimodal Large Language Models

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Implementation for the paper "Compositional Attention Networks for Machine Reasoning" (Hudson and Manning, ICLR 2018)

Accelerating the development of large multimodal models (LMMs) with one-click evaluation module - lmms-eval.

Open-L2O: A Comprehensive and Reproducible Benchmark for Learning to Optimize Algorithms

Code for "Discovering Symbolic Models from Deep Learning with Inductive Biases"

High-Performance Symbolic Regression in Python and Julia

A resource repository for machine unlearning in large language models

Ada-LISTA: Learned Solvers Adaptive to Varying Models

Differentiable architecture search for convolutional and recurrent networks

Pytorch version of NIPS'16 "Learning to learn by gradient descent by gradient descent"