Tag
GLIDE is an open-source Python library that unifies state-of-the-art Prediction-Powered Inference methods for debiased evaluation of generative AI and agentic systems, enabling annotation savings with valid uncertainty estimates.
LELA is an LLM-based entity linking framework that combines zero-shot NER and entity disambiguation into an end-to-end Python library, validated across diverse settings.
A library called teich converts agent traces into supervised fine-tuning (SFT) datasets, simplifying dataset preparation for AI training.
This paper introduces projection agents for graph combinatorial optimization using reinforcement learning and graph neural networks, operating in a continuous action embedding space to improve generalization and scalability, and releases the LaGCO-RL library.
dLLM is an open-source Python library that allows converting any autoregressive language model into a diffusion language model with minimal compute, unifying training and evaluation.
The author shares benchmark results for memweave, a Python library for agent memory, achieving 98% Recall@5 on LongMemEval-S using only local embeddings without LLM calls. The post details the methodology and compares performance against mempalace, highlighting stable retrieval across different question types.
ExLlamaV3 has released a series of major updates including Gemma 4 support, improved caching efficiency, and the new DFlash technology for significantly faster inference speeds across various model categories.
A Python library for calculating ephemerides and spectral data, hosted on PyPI.
nature-skills is a scientific visualization tool based on matplotlib. It features built-in Nature-style templates, supports various chart types, and outputs editable SVG format, aiming to streamline the figure creation process for scientific papers.
A Python library that scrapes websites while bypassing bot protections like Cloudflare and Akamai by rotating fingerprints, mimicking browser headers, and automatically handling CAPTCHAs. It uses Headless Chromium, Playwright, proxy rotation, and is fully open-source.
Sentence Transformers v5.4 introduces support for multimodal embedding and reranking, allowing users to encode and compare text, images, audio, and video using a unified API.
OpenAI releases GABRIEL, an open-source toolkit that uses GPT to convert unstructured qualitative data (text, images) into quantitative measurements for social scientists and economists. The tool enables researchers to analyze large-scale qualitative datasets more efficiently by automating repetitive labeling tasks while preserving the richness of human data.
OpenAI open-sources mujoco-py, a high-performance Python library for robotic simulation using the MuJoCo engine, featuring ~40x speedup with headless GPU rendering and VR interaction support.
Browser Use is an AI agent tool that automates web browser tasks like form filling and data extraction by mimicking human interactions.
A minimal Python library for drawing customized maps from OpenStreetMap, utilizing osmnx, matplotlib, shapely, and vsketch for geographic visualization.
andrewyng/aisuite is a lightweight Python library providing a unified Chat Completions API across multiple LLM providers and an Agents API with tools. It also includes OpenCoworker, a desktop AI agent for everyday tasks.