# Zero-shot generalization

A language model fine-tuned based on Qwen3-1.7B, which improves mathematical reasoning ability through reinforcement learning technology

SAM-HQ is an enhanced version of the Segment Anything Model (SAM), capable of generating higher-quality object masks, especially suitable for handling objects with complex structures.

SAM-HQ is an enhanced version of the Segment Anything Model (SAM), capable of generating higher-quality object masks from input prompts such as points or boxes.

TextFlux is a high-fidelity multilingual scene text synthesis model based on an OCR-free diffusion transformer. It uses FLUX.1-Fill-dev as the base model and focuses on the scene text synthesis task.

SAM-HQ is an enhanced version of Segment Anything Model, generating higher-quality object masks through input prompts like points or boxes

RobustSAM is a model for robust segmentation on degraded images, improved upon SAM to enhance segmentation performance on low-quality images.

AISAK-Detect is the core object detection component of the AISAK-Visual system, employing a convolutional backbone Transformer architecture for efficient and accurate object recognition in images.

Whisper is an advanced automatic speech recognition (ASR) and speech translation model proposed by OpenAI, trained on over 5 million hours of labeled data, with strong cross-dataset and cross-domain generalization capabilities.

ABSA model fine-tuned from Llama-2-7b, excels at identifying aspects in text and analyzing sentiment