← all releases
UCSB-SURFI·Dec 8, 2025·v1.0·open source
VulnLLM-R-7B
VulnLLM-R-7B is a specialized reasoning Large Language Model (LLM) designed for software vulnerability detection. Unlike traditional static analysis tools that rely on pattern matching, VulnLLM-R-7B employs a 'Chain-of-Thought' approach to analyze program states and identify potential vulnerabilities, enhancing generalizability and preventing learning shortcuts.
LLMLLMsSecurity
overview
VulnLLM-R-7B is a specialized reasoning Large Language Model (LLM) designed for software vulnerability detection. Unlike traditional static analysis tools that rely on pattern matching, VulnLLM-R-7B employs a 'Chain-of-Thought' approach to analyze program states and identify potential vulnerabilities, enhancing generalizability and preventing learning shortcuts.
key features
- 01Reasoning-Based Detection: Generates a 'Chain-of-Thought' to analyze why a vulnerability exists.
- 02Superior Accuracy: Outperforms commercial models like Claude-3.7-Sonnet and industry-standard tools such as CodeQL and AFL++ on key benchmarks.
- 03Efficiency: Achieves state-of-the-art performance with only 7 billion parameters, making it 30 times smaller and significantly faster than general-purpose reasoning models.
- 04Broad Coverage: Trained and tested on C, C++, Python, and Java, demonstrating zero-shot generalization across these languages.
related productsbrowse all →
Protenixopen sourceProtenix is an open-source, trainable PyTorch implementation of AlphaFold 3, designed for high-accuracy biomolecular structure prediction. It aims to advance accessible and extensible research tools for the computational biology community. ([github.com](https://github.com/bytedance/Protenix?utm_source=openai))Step-Audio-R1open sourceStep-Audio-R1 is an advanced audio language model developed by StepFun AI, designed to enhance audio reasoning capabilities by grounding its reasoning in acoustic features. It introduces Modality-Grounded Reasoning Distillation (MGRD), an iterative training framework that shifts the model's reasoning from textual abstractions to acoustic properties, effectively addressing the 'inverted scaling' problem where performance degrades with longer reasoning. This model has demonstrated superior performance across various audio understanding and reasoning benchmarks, surpassing models like Gemini 2.5 Pro and achieving results comparable to Gemini 3 Pro.Z-Imageopen sourceZ-Image is an efficient image generation foundation model developed by Tongyi-MAI, designed to produce high-quality, diverse, and stylistically versatile images. It serves as a robust base for creators, researchers, and developers seeking advanced image generation capabilities.