eryx
Follow
Starred repositories
MetaSpatial leverages reinforcement learning to enhance 3D spatial reasoning in vision-language models (VLMs), enabling more structured, realistic, and adaptive scene generation for applications in…
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
SpatialLM: Large Language Model for Spatial Understanding
Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
LightSeq: A High Performance Library for Sequence Processing and Generation
This repo contains the code for "VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks" [ICLR25]
Retrieval and Retrieval-augmented LLMs
The ultimate LLM/AI application development framework in Golang.
MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval
MOT using deepsort and yolov3 with pytorch
Open3D: A Modern Library for 3D Data Processing
Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"
We write your reusable computer vision tools. 💜
A full attention mechanism and transformer in pure go.
Simple Online Realtime Tracking with a Deep Association Metric
Event-driven network library for multi-threaded Linux server in C++11
Go implementation of the SentencePiece tokenizer
A bidirectional pipeline parallelism algorithm for computation-communication overlap in V3/R1 training.
Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
Fast and memory-efficient exact attention
An open-source, cross-platform terminal for seamless workflows
[CVPR 2025] Magma: A Foundation Model for Multimodal AI Agents
Witness the aha moment of VLM with less than $3.
Perforator is a cluster-wide continuous profiling tool designed for large data centers
A vanilla JavaScript remake of bootstrap-datepicker for Bulma and other CSS frameworks