As large language models (LLMs) become increasingly embedded in real-world applications—especially in Chinese-speaking regions—ensuring their safety has never been more…
Qwen-Image: Generate and Edit Images with Perfect Text—Even in Chinese 6339
If you’ve ever struggled to generate marketing visuals with legible multilingual text—or tried to edit a product image only to…
HunyuanImage-3.0: The Largest Open-Source Multimodal Image Generator with Native Reasoning and MoE Architecture 2562
HunyuanImage-3.0 is a groundbreaking open-source image generation model developed by Tencent. Unlike traditional diffusion-based approaches, it builds a native multimodal…
AI-Scientist-v2: Automate End-to-End Scientific Discovery with Agentic Tree Search 1866
In an era where AI is reshaping how knowledge is created, AI-Scientist-v2 emerges as a breakthrough system that autonomously conducts…
WizardCoder: Open-Source Code LLM That Outperforms ChatGPT and Gemini in Code Generation 9472
WizardCoder is a state-of-the-art open-source Code Large Language Model (Code LLM) that delivers exceptional performance on code generation tasks—often surpassing…
FinRobot: Build Finance-Specific AI Agents That Analyze, Forecast, and Generate Reports—Without Starting from Scratch 4779
In today’s fast-moving financial landscape, professionals and developers alike are eager to harness the power of large language models (LLMs).…
DB-GPT-Hub: Fine-Tune LLMs for Accurate Text-to-SQL Without Breaking the Bank 1945
If you’ve ever tried building a natural language interface to a relational database, you know the real bottleneck isn’t the…
MedSegDiff: Accurate Medical Image Segmentation Using Diffusion Models and Vision Transformers 1335
Medical image segmentation—the process of delineating organs, tumors, or tissues in scans like MRI or dermoscopic images—is a foundational task…
mPLUG-DocOwl: High-Accuracy, OCR-Free Document Understanding for Enterprise and Research Workflows 2261
In today’s data-driven world, extracting structured, actionable insights from digital documents—such as invoices, reports, scientific papers, or web pages—is a…
OpenHands: Empower AI Agents to Code, Debug, and Ship Like Human Developers 65759
In today’s fast-paced software landscape, developers are under constant pressure to write, test, debug, and deploy code faster than ever—often…