Stars
Use Codex from Claude Code to review code or delegate tasks.
[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
Official implementation of “ACE: Anti-Editing Concept Erasure in Text-to-Image Models”
Unlearning on MoE
A maze environment for training and evaluating agents
LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations
Use Hawkes Process to stabilize the predicting capability of the World Model
Implements semantic equalization for DeepJSCC, addressing mismatched latent spaces between transmitter and receiver models. Evaluates linear, neural, and zero-shot equalizers for aligning heterogen…
About This repository is a curated collection of the most exciting and influential CVPR 2026 papers. 🔥 [Paper + Code + Demo]
DomainBed is a suite to test domain generalization algorithms
The repository is for safe reinforcement learning baselines.
LLM-KG4QA: Large Language Models and Knowledge Graphs for Question Answering
Code for visualizing the loss landscape of neural nets
[NeurIPS 2022] Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach -- Official Implementation
Towards Understanding Sharpness-Aware Minimization [ICML 2022]
Code for AAAI 2024 paper: CR-SAM: Curvature Regularized Sharpness-Aware Minimization
Code for ICLR 2023 Paper Better Generative Replay for Continual Federated Learning
[NeurIPS 2023] Enhancing Sharpness-Aware Optimization Through Variance Suppression
A Reproduction of GDM's Nested Learning Paper
Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch
Multi-agent demo platform for Titans (arXiv:2501.00663) — neural networks that learn to memorize at test time. 7 AI agents, native desktop UI.