Lists (2)
Stars
Fast and accurate DRAM power and energy estimation tool
The First LiDAR-Camera Multimodal Dataset for Professional Basketball MOT
[ASP-DAC 2026] Verification on Adaptation Performance for "BitROM: Weight Reload-Free CiROM Architecture Towards Billion-Parameter 1.58-bit LLM Inference"
Optimized primitives for collective multi-GPU communication
Open Overleaf/ShareLaTex projects in vscode, with full collaboration support.
It is said that, Ilya Sutskever gave John Carmack this reading list of ~ 30 research papers on deep learning.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
Let's train vision transformers (ViT) for cifar 10 / cifar 100!
A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/
The official repository for paper: BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization
[ICCV 2025] SAM4D: Segment Anything in Camera and LiDAR Streams
[ICCV 2025] Offical implementation of "AHCPTQ: Accurate and Hardware-Compatible Post-Training Quantization for Segment Anything Model"
[TIP 2025] TripleMixer: A Triple-Domain Mixing Model for Point Cloud Denoising under Adverse Weather
[CVPR 2024] PTQ4SAM: Post-Training Quantization for Segment Anything
This is a package for LiDARTag, described in paper: LiDARTag: A Real-Time Fiducial Tag System for Point Clouds
An open-source AI agent that brings the power of Gemini directly into your terminal.
📊 Benchmark multiple object trackers (MOT) in Python
HOTA (and other) evaluation metrics for Multi-Object Tracking (MOT).
Optical character recognition for Japanese text, with the main focus being Japanese manga
ROS2 の/imu /image_rawをpython上で取り扱う用のサンプルコード
MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
A unified library for object tracking featuring clean room re-implementations of leading multi-object tracking algorithms
(T-IV) Radar4Motion: 4D Imaging Radar based IMU-free Odometry with Radar Cross Section (RCS) weighted Correspondences
3D LIDAR Localization using NDT/GICP and pointcloud map in ROS 2 (Not SLAM)