[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

[ECCV 2024] Official PyTorch implementation of TC-CLIP "Leveraging Temporal Contextualization for Video Action Recognition"

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

[NeurIPS2024] Attractor memory for long-term time series forecasting: A chaos perspective

A carefully curated collection of high-quality libraries, projects, tutorials, research papers, and other essential resources focused on Physics-Informed Machine Learning (PIML) and Physics-Informe…

Code for Retrieval-Augmented Perception （ICML 2025)

Code to reproduce the experiments of "Rethinking Experience Replay: a Bag of Tricks for Continual Learning"

RetroDFM-R: Reasoning-Driven Retrosynthesis Prediction with Large Language Models via Reinforcement Learning

Retrosynthesis reaction prediction using Transformer sequence to sequence models and SMILES based data augmentation

Official code repository of "VideoCAD: A Dataset and Model for Learning Long‑Horizon 3D CAD UI Interactions from Video" @ NeurIPS 2025

[KDD2024] Class-incremental Learning for Time Series: Benchmark and Evaluation

Saliency-driven Experience Replay for Continual Learning (NeurIPS2024)

Awesome Incremental Learning

This is the Pytorch implementation of LwF

The official source code for "RAG-Enhanced Collaborative LLM Agents for Drug Discovery"

The offical source code for [2024 NeurIPS] "Retrieval-Retro: Retrieval-based Inorganic Retrosynthesis with Expert Knowledge"

[CVPR 2025] Boosting Domain Incremental Learning: Selecting the Optimal Parameters is All You Need

Generative modeling of molecular dynamics trajectories

[ICLR 2025] PIG: Physics-Informed Gaussians as Adaptive Parametric Mesh Representations

A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.

Implementation of Physics-Informed Diffusion Models (ICLR 2025)

Ceph is a distributed object, block, and file storage platform

dbt enables data analysts and engineers to transform their data using the same practices that software engineers use to build applications.

Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

Implemention of the Decision-Pretrained Transformer (DPT) from the paper Supervised Pretraining Can Learn In-Context Reinforcement Learning.

Minimal implementation of Decision Transformer: Reinforcement Learning via Sequence Modeling in PyTorch for mujoco control tasks in OpenAI gym