The world’s cultural heritage faces mounting peril from escalating conflicts and natural disasters, jeopardizing ancient sites and artifacts worldwide. Wars, earthquakes, and floods pose existential threats, imperiling invaluable pieces of history. Urgent action is needed to protect these sites. Artificial intelligence (AI) presents a potent solution, providing sophisticated tools to document, analyze, and safeguard cultural… →

Managing, analyzing, and extracting data from large volumes of documents is a crucial yet challenging task. Traditionally, this has required expensive proprietary software solutions. Introducing Open Contracts, a free and open-source platform designed to democratize document analytics. Open Contracts is a fully open-source, AI-powered document analytics tool licensed under Apache-2. This platform empowers users to… →

Product insights & monitoring, testing, end-to-end analytics, and errors are four of the most difficult LLMs to monitor and test. Teams mostly waste weeks of dev time building internal tools to solve these problems. Most product analytics efforts have concentrated on numerical metrics like CTR and conversion rates. This information is critical, yet it is… →

Few-shot Generative Domain Adaptation (GDA) is a machine learning and domain adaptation concept that addresses the challenge of adapting a model trained on a source domain to perform well on a target domain, using only a few examples from the target domain. Such a technique is particularly useful when obtaining a large amount of labeled… →

Traditional protein design, often relying on physics-based methods like Rosetta, faces challenges in creating functional proteins with complex structures due to the need for parametric and symmetric restraints. Recent advances in deep learning, particularly with tools like AlphaFold2, have transformed protein design by enabling accurate prediction and exploration of vast sequence spaces. This has led… →

Developers often face challenges when working on large coding projects. These challenges include getting stuck on unfamiliar technologies, managing extensive backlogs, and spending much time on repetitive tasks. Traditional methods and tools may need more to handle these issues effectively, leading to delays and frustration. There are some existing solutions aimed at improving developers’ productivity… →

Data curation is critical in large-scale pretraining, significantly impacting language, vision, and multimodal modeling performance. Well-curated datasets can achieve strong performance with less data, but current pipelines often rely on manual curation, which is costly and hard to scale. Model-based data curation, leveraging training model features to select high-quality data, offers potential improvements in scaling… →

Advances in hardware and software have enabled AI integration into low-power IoT devices, such as ultra-low-power microcontrollers. However, deploying complex ANNs on these devices requires techniques like quantization and pruning to meet their constraints. Additionally, edge AI models can face errors due to shifts in data distribution between training and operational environments. Furthermore, many applications… →