[AAAI2026] TextShield-R1: Reinforced Reasoning for Tampered Text Detection

[ECCV 2026] Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods

Hybrid Marlin+CUTLASS NVFP4 kernel plugin for vLLM on sm_120 — +95% prefill at same decode (Qwen3.6-27B, RTX PRO 6000)

[JAMA] "Complete AI-Enabled Echocardiography Interpretation with Multitask Deep Learning" by Gregory Holste, Evangelos K. Oikonomou, Márton Tokodi, Attila Kovács, Zhangyang Wang, & Rohan Khera

RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink

[CVPR 2026] Official data synthesis code of the paper "What’s Wrong with Synthetic Data for Scene Text Recognition? A Strong Synthetic Engine with Diverse Simulations and Self-Evolution".

Efficient Universal Perception Encoder: a single on-device vision encoder with versatile representations that match or exceed specialized experts across multiple task domains.

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

This repo contains a curated list of research papers and resources focusing on Handwritten Text Generation (HTG)

A Toolkit to Help Optimize Large Onnx Model

The code contains updated files to sucessfully compile Minkowski engine to latest cuda and pytorch versions

Table Transformer (TATR) is a deep learning model for extracting tables from unstructured documents (PDFs and images). This is also the official repository for the PubTables-1M dataset and GriTS ev…

One-shot handwritten text synthesis with Vision Transformers for English and Vietnamese.

Muon is an optimizer for hidden layers in neural networks

Official PyTorch Implementation of "WordStylist: Styled Verbatim Handwritten Text Generation with Latent Diffusion Models" - ICDAR 2023

SignboardLayout: Towards Understanding the Logical Layout of Scene Text in Signboard Images

Code for generating synthetic MRZ images

Official Code for ECCV 2024 paper — One-Shot Diffusion Mimicker for Handwritten Text Generation

Official PyTorch implementation for "Zero-Shot Styled Text Image Generation, but Make It Autoregressive" (CVPR25)

MambaSTR: Scene Text Recognition with Masked State Space Model

[WIP] Resources for AI engineers. Also contains supporting materials for the book AI Engineering (Chip Huyen, 2025)