Research & Education

Awesome-3D-Object-Detection-for-Autonomous-Driving is a GitHub repository that accompanies a comprehensive survey paper titled "3D Object Detection for Autonomous Driving: A Comprehensive Survey (IJCV 2023)". This resource is designed to help researchers and engineers stay updated on the latest advancements in 3D object detection techniques for autonomous driving systems. The repository categorizes methods into LiDAR-based, Camera-based, Multi-Modal, Temporal, and Label-Efficient 3D Object Detection, as well as their application in Driving Systems. It provides detailed overviews of various approaches within each category, including point-based, grid-based, anchor-based, and fusion techniques. The content is structured to offer a chronological overview and includes links to relevant papers, making it an essential reference for anyone working in this specialized domain.

GoReply is a unique platform designed for businesses focusing on Corporate Social Responsibility (CSR) and Environmental, Social, and Governance (ESG) reporting. It enables employees to engage in skill-based, paid volunteering, where consultation fees are donated to carefully vetted charities. The platform connects professionals from leading organizations with individuals seeking expert advice across various industries like Consulting, Healthcare, Finance, Tech, Marketing, and Retail & Real Estate. GoReply helps companies build sustainability reporting networks by documenting employee contributions to social responsibility, enhancing their CSR and ESG profiles. Users can monetize their expertise, reduce unsolicited contact requests, and contribute to causes they care about, while businesses can track and quantify their social impact.

Bibelanalys offers an interactive platform for exploring the Bible, designed to enhance study and comprehension through dynamic visualizations. Users can navigate scriptural content with integrated timelines that contextualize events chronologically, geographical maps that illustrate locations mentioned in the Bible, and informative popups providing additional details. The tool specifically analyzes the Gospels and the stories of the 12 disciples, utilizing the Folkbibeln 2015 translation. This makes it an ideal resource for anyone interested in a deeper, more visual understanding of biblical narratives and historical contexts.

This research tool presents a groundbreaking demonstration of how evolved cellular systems can autonomously navigate complex mazes. Crucially, this navigation occurs without any prior training or explicit fitness functions, highlighting an emergent form of intelligence in biological computation. The tool illustrates how fundamental cellular behaviors, driven by evolutionary processes, can lead to sophisticated problem-solving capabilities. This work offers significant insights into the potential for biological systems to perform complex tasks through self-organization and adaptation, challenging traditional views on engineered intelligence and providing a new perspective on the origins of problem-solving in living systems.

awesome-humanoid-robot-learning is a comprehensive GitHub repository that compiles academic papers focused on the field of humanoid robot learning. The collection is meticulously organized by the specific tasks the papers address, making it easy for researchers to find relevant work. A key differentiator of this list is its preference for papers that include real robot experiments, providing a practical and applied perspective. Additionally, papers that offer open-sourced code are highlighted with a star, encouraging reproducibility and further development within the community. This resource is invaluable for academics, researchers, and engineers looking to stay updated on the latest advancements and foundational studies in humanoid robotics and AI.

Awesome-Implicit-NeRF-Robotics is a curated repository offering a comprehensive list of research papers, code implementations, and related websites focused on Implicit Representations and Neural Radiance Fields (NeRF) within the Robotics and Reinforcement Learning (RL) domains. This resource is largely based on the survey paper "Neural Fields in Robotics: A Survey." It categorizes papers into key areas such as Object Pose Estimation, SLAM, Manipulation/RL, Object Reconstruction, Physics, and Planning/Navigation, making it an invaluable resource for academics and practitioners exploring these advanced topics. The repository is actively maintained, with regular updates on new research and workshops in the field.

Awesome-GUI-Agent is a meticulously curated list of papers, projects, and resources specifically focused on multi-modal Graphical User Interface (GUI) agents. This open-source repository serves as a valuable hub for researchers and developers aiming to build advanced digital assistants capable of interacting with computer screens. It categorizes resources into key areas such as Datasets/Benchmarks, Models/Agents, Surveys, and Projects, making it easy to navigate the vast landscape of GUI agent research. The project is actively maintained and encourages contributions, ensuring its relevance and comprehensiveness. It also features an 'Awesome-Paper-Agent' to automatically format arXiv links, streamlining the process of adding new research to the list. This resource is essential for anyone working on or interested in the development of intelligent agents that can understand and operate graphical user interfaces.

Awesome-holistic-3d is a valuable open-source resource for researchers and academics focused on holistic 3D reconstruction in computer vision. This GitHub repository compiles a comprehensive list of relevant papers, datasets, and code, categorized by scene-level and object-level reconstruction. It includes references to tutorials, workshops, and a wide array of research papers spanning from 2009 to 2020. The resource details various datasets with information on the number of scenes, rooms, frames, and annotated structures, making it an essential reference for anyone working on or studying 3D reconstruction techniques.

awesome-self-driving-car is a comprehensive, open-source curated list of resources dedicated to self-driving car technology. It serves as a valuable hub for developers, researchers, and students interested in autonomous vehicles, offering links to full-stack open-source projects like Apollo and Autoware, as well as essential libraries such as ROS, OpenCV, and TensorFlow. The list also includes academic courses from institutions like Udacity and MIT, alongside a vast collection of papers and blogs covering topics from HD mapping and simulation to localization, perception, planning, and control. Furthermore, it details various systems, hardware components, datasets, and benchmarks crucial for autonomous driving research and development.

Awesome-Referring-Image-Segmentation is a curated GitHub repository that compiles a vast collection of academic papers and datasets related to referring image segmentation. This resource is invaluable for researchers and practitioners in the computer vision domain, offering insights into traditional and interactive methods, as well as current challenges in the field. The repository is organized into sections covering datasets, challenges, traditional referring image segmentation, interactive referring image segmentation, referring video object segmentation, 3D referring segmentation, and referring image segmentation in specific domains. It is actively maintained and encourages contributions via pull requests or issue submissions, fostering a collaborative environment for advancing research in this specialized area.

Awesome-RLHF is a comprehensive, open-source repository dedicated to curating resources for Reinforcement Learning with Human Feedback (RLHF). It serves as a vital hub for researchers and practitioners, offering an up-to-date collection of research papers, associated codebases, and relevant datasets. The repository is meticulously organized by publication year, spanning from 2020 to 2025, and includes detailed explanations of RLHF concepts, advanced techniques like Inverse Reinforcement Learning and Human-in-the-Loop RL, and practical examples across various applications such as game playing, recommendation systems, and robotics. Its continuous updates ensure users have access to the latest advancements in the field.

Lidar_For_AD_references is a comprehensive, open-source repository offering a curated list of academic papers and resources focused on LiDAR point cloud processing for autonomous driving applications. This tool is invaluable for researchers and engineers working in the autonomous vehicle domain, providing references across various critical tasks. These tasks include LiDAR point cloud clustering, semantic segmentation, plane extraction, object detection and tracking, registration and localization, feature extraction, and mapping. The repository also covers topics like point cloud density and compression, simulated point clouds, and various LiDAR datasets, making it a central hub for relevant academic literature and practical resources.

PyTorch-RL offers a comprehensive PyTorch implementation of various deep reinforcement learning algorithms. This repository is designed for researchers and developers working with reinforcement learning, providing ready-to-use implementations of popular policy gradient methods such as Trust Region Policy Optimization (TRPO), Proximal Policy Optimization (PPO), and Synchronous A3C (A2C). Additionally, it includes Generative Adversarial Imitation Learning (GAIL). A key feature is its fast Fisher vector product calculation and support for multiprocessing, enabling agents to collect samples from multiple environments simultaneously for improved performance. It supports both discrete and continuous action spaces, making it versatile for different reinforcement learning tasks.

Awesome-Spatial-Intelligence-in-VLM is a comprehensive, curated list of resources dedicated to spatial intelligence within Vision Language Models (VLMs). This GitHub repository serves as a valuable index for researchers and engineers, bringing together essential methods, datasets, and benchmarks. It aims to facilitate the tracking of the latest advancements in evaluating and enhancing the spatial reasoning capabilities of multimodal models. The list is actively maintained and welcomes contributions, ensuring it remains a current and relevant resource for anyone working on spatial reasoning in VLMs. It categorizes resources into visual-based and text-based methods, as well as visual-based datasets and benchmarks, offering a structured overview of the field.

Creative Biolabs provides custom biotechnology and pharmaceutical services, focusing on the full scope of drug discovery and development. The platform offers extensive services for antibody development projects, including discovery, engineering, and custom production. Key technologies include phage display, yeast display, and single B cell sorting for binder discovery. They also provide services for antibody characterization, immunogenicity analysis, and property optimization like affinity maturation and stability improvement. Additionally, Creative Biolabs offers custom manufacturing for membrane proteins, virus-like particles, and recombinant antibodies, ensuring high-quality solutions for various research and therapeutic needs.

LIBERO is an open-source benchmarking framework designed for studying knowledge transfer in multitask and lifelong robot learning problems. It provides a procedural generation pipeline capable of creating an infinite number of manipulation tasks, alongside 130 pre-defined tasks grouped into four distinct task suites: LIBERO-Spatial, LIBERO-Object, LIBERO-Goal, and LIBERO-100. These suites are structured to facilitate research into specific types of knowledge transfer, with LIBERO-100 focusing on entangled knowledge transfer for pretraining and testing lifelong learning performance. The framework also includes five research topics, three visuomotor policy network architectures, and three lifelong learning algorithms, along with sequential finetuning and multitask learning baselines. High-quality human teleoperation demonstrations are available for all task suites.

Learnable-triangulation-pytorch is an official PyTorch implementation of the paper "Learnable Triangulation of Human Pose" (ICCV 2019, oral). This open-source project focuses on 3D human pose estimation from multiple cameras, offering two novel methods: Algebraic and Volumetric learnable triangulation. These methods significantly outperform previous state-of-the-art techniques, with the Volumetric model achieving a 2.4 times reduction in error. The repository provides code for training and evaluation, supports both single and multi-GPU setups, and includes pretrained models and configurations for the Human3.6M dataset. It is designed for researchers and engineers working on advanced computer vision tasks, particularly in human pose estimation.

MedMamba is the official code repository for "MedMamba: Vision Mamba for Medical Image Classification." This innovative tool addresses the limitations of traditional CNNs and ViTs in medical image analysis by introducing a novel hybrid basic block called SS-Conv-SSM. This block effectively integrates convolutional layers for local feature extraction with State Space Models (SSMs) to capture long-range dependencies, ensuring efficient modeling of medical images from diverse modalities. MedMamba is designed to provide fewer model parameters and a lower computational burden without sacrificing accuracy, making it suitable for real-world applications with limited computational resources. It has been extensively tested across 16 datasets, ten imaging modalities, and over 400,000 images, demonstrating competitive performance in classifying various medical images.

mega.pytorch offers an official PyTorch implementation of the "Memory Enhanced Global-Local Aggregation for Video Object Detection" (MEGA) approach, which was accepted by CVPR 2020. This repository is built upon maskrcnn_benchmark and includes training scripts to replicate results on ImageNet VID. Beyond MEGA, it also implements other video object detection algorithms like FGFA and RDN, welcoming contributions for new methods. The project aims to support further research in video object detection, providing pretrained models and detailed instructions for installation, data preparation, inference, and training.

DeepEMD offers a PyTorch implementation for few-shot image classification, based on the research paper "DeepEMD: Few-Shot Image Classification with Differentiable Earth Mover's Distance and Structured Classifiers." This tool is designed to address the challenge of learning from limited labeled data by employing the Earth Mover's Distance (EMD) as a metric for structural matching between image regions. It includes a cross-reference mechanism to mitigate issues from cluttered backgrounds and intra-class variations, and supports k-shot classification through a structured fully connected layer. DeepEMD has demonstrated significant performance improvements on benchmarks like miniImageNet, tieredImageNet, FC100, and CUB, without requiring extra training or testing data. The repository provides code for model pre-training, meta-training, and evaluation, along with options for different EMD solvers and model configurations.

F0lkl0r3.dev is a unique digital archive that brings the rich history of computing to life through oral history interviews from the Computer History Museum. This platform enriches these invaluable firsthand accounts with AI-generated context, relevant visuals, and interconnected links, creating a searchable and interlinked map of computing history. It serves as an essential resource for historians, researchers, students, and anyone with a keen interest in the evolution of technology. By making complex historical narratives more accessible and engaging, F0lkl0r3.dev allows users to explore the stories of the pioneers who shaped the digital world, understand the intricate connections between various innovations, and gain deeper insights into the foundational moments of computer science.

Emotion-LLaMA is an advanced open-source AI model designed for multimodal emotion recognition and reasoning, leveraging instruction tuning. It addresses the limitations of traditional single-modality approaches by seamlessly integrating audio, visual, and textual inputs through emotion-specific encoders. The model aligns features into a shared space and employs a modified LLaMA model, significantly enhancing both emotional recognition and reasoning capabilities. It was accepted at NIPS 2024 and has achieved top scores in various challenges, including the MER2024 Challenge. The project also includes the MERR dataset, which contains a large number of coarse-grained and fine-grained annotated samples across diverse emotional categories, enabling models to learn from varied scenarios and generalize to real-world applications.

Eagle 2.5 is a family of frontier vision-language models (VLMs) developed by NVlabs, specifically engineered for long-context multimodal learning. Unlike many existing VLMs that focus on short-context tasks, Eagle 2.5 excels at challenges like long video comprehension and high-resolution image understanding, providing a generalist framework for both. It supports up to 512 video frames and is trained jointly on image and video data, including the novel Eagle-Video-110K dataset. Key innovations include Information-First Sampling for optimal image and text retention, Progressive Mixed Post-Training for enhanced context length processing, and Diversity-Driven Data Recipe. The model also features significant efficiency and framework optimizations, such as GPU memory optimization and inference acceleration, making it suitable for advanced research and development in multimodal AI.

Lenzy AI offers a comprehensive analysis and visualization of two decades of Hacker News discussions. Utilizing clustering algorithms, the platform identifies and presents key trends, recurring patterns, and community insights from the vast dataset. This tool is designed for researchers and analysts to explore the evolution of technology conversations, pinpoint dominant themes, and understand the collective interests of the developer community over a significant period. It provides an overview of discussed topics, making it valuable for anyone interested in the historical trajectory of tech discourse on Hacker News.