A pure-Python structured memory benchmark for multi-agent LLM systems — context graph vs vector RAG vs raw history dump, five scenarios, 18 graded queries, zero API calls.
DeepSeek Harness Image2 生图插件，通过第三方 OpenAI Images 兼容接口调用 gpt-image-2，只需配置 baseURL 和 API Key。 | Image2 generation plugin for DeepSeek Harness via third-party OpenAI Images-compatible...
Official implementation of “A Turbo-Inference Strategy for Object Detection and Instance Segmentation” (CVIU 2026). A training-free framework for iterative refinement between objec...
Native Adversariality Mining (NAM) is a framework for discovering more informative and challenging synthetic samples from diffusion models, helping synthetic data better improve do...