Skip to content
View fireae's full-sized avatar

Block or report fireae

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Starred repositories

Showing results
Jupyter Notebook 135 34 Updated Oct 1, 2025

Covers pre-training data, Tokenizer, Transformer, MoE,distributed training, Scaling Laws, inference & alignment .6 progressive code assignments for full-stack LLM learning | 涵盖预训练数据、分词器、Transformer…

Jupyter Notebook 3,032 298 Updated Nov 20, 2026

[ACL'26 Oral] AgentOCR is a token-efficient framework that compresses multi-turn agent history by rendering it into images and adopting RL-driven self-compression

Python 51 2 Updated Mar 1, 2026
Jupyter Notebook 993 165 Updated Jul 10, 2024

Type-safe, extensible, and high-performance background processing library for Rust

Rust 1,509 101 Updated Nov 20, 2026
Python 272 34 Updated May 26, 2025

Eagle: Frontier Vision-Language Models with Data-Centric Strategies

Python 3,861 375 Updated Nov 7, 2026

A full model customization repo for Liquid Foundation Models

Python 248 47 Updated Nov 21, 2026

BoT-SORT: Robust Associations Multi-Pedestrian Tracking

Jupyter Notebook 1,584 499 Updated Aug 8, 2024

RTMPose series (RTMPose, DWPose, RTMO, RTMW) without mmcv, mmpose, mmdet etc.

Python 705 103 Updated Nov 7, 2026

[ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box

Python 6,823 1,156 Updated Jun 19, 2024

A Chinese probabilistic decision model: one forward pass, straight to candidate probabilities

Python 87 14 Updated Nov 12, 2026

Document scanning app

C++ 2,676 153 Updated Nov 20, 2026

[AAAI2026] X-SAM: From Segment Anything to Any Segmentation

Python 397 17 Updated Jul 14, 2026

WiLoR: End-to-end 3D hand localization and reconstruction in-the-wild

Python 746 80 Updated Apr 7, 2026

Includes the code for training and testing the CountGD model from the paper CountGD: Multi-Modal Open-World Counting.

Python 338 40 Updated Jun 25, 2025

Official PyTorch implementation of "Multi-modal Queried Object Detection in the Wild" (accepted by NeurIPS 2023)

Python 348 17 Updated Feb 23, 2024

Code for OPUS: A Simple yet Effective Unified Framework for Open-Vocabulary Detection

Python 19 2 Updated Sep 4, 2026

Multimodal Reference Visual Grounding (will have more updates)

Python 9 2 Updated Apr 26, 2026

[IROS 2025] NIDS-Net: A unified framework for novel instance detection and segmentation

Python 80 9 Updated May 12, 2025
Python 38 2 Updated Jan 2, 2025

SOTA Re-identification Methods and Toolbox

Python 4,011 881 Updated Jul 30, 2024

1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracy

Python 1,909 197 Updated Nov 4, 2026

Document image dewarping library using a cubic sheet model

Python 254 25 Updated Nov 16, 2026

Improving and Evaluating Hand-Object Interaction Detection

Python 221 14 Updated Jun 29, 2026

VideoJev: System One Model for Video Understanding and Interaction

Python 317 12 Updated Oct 18, 2026

OFDBox 是一个 Rust 实现的 OFD 版式文档工具箱,实现了标准GB/T 33190—2016。

Rust 3 1 Updated Oct 29, 2026

对招股书的财务勾稽关系校验,包含跨表勾稽、表内勾稽、文表勾稽多种校验,校验后在pdf文档中自动高亮显示。

Python 18 4 Updated Jul 28, 2023

2022阿里天池真实场景篡改图像检测挑战赛-冠军方案(1/1149)

Python 202 29 Updated Oct 26, 2022

GGUF quantizations of Xiaomi-OCR-0 (0.8B document-parsing VLM) for llama.cpp, with reproducible scripts and measured accuracy/speed/memory

Shell 2 Updated Oct 2, 2026
Next