Google DeepMind research reveals a fundamental architectural limitation in Retrieval-Augmented Generation (RAG) systems related to fixed-size embeddings. The research demonstrates that retrieval performance degrades as database size increases, with theoretical limits based on embedding dimensionality. They introduce the LIMIT benchmark to empirically test these limitations and suggest alternatives like cross-encoders, multi-vector models, and sparse models.
An Apple study shows that large language models (LLMs) can improve performance by using a checklist-based reinforcement learning scheme, similar to a simple productivity trick of checking one's work.
A new study by MIT CSAIL researchers maps the challenges of AI in software development, identifying bottlenecks and highlighting research directions to move the field forward, aiming to allow humans to focus on high-level design while automating routine tasks.
DeepMind introduces Ithaca, a deep neural network that can restore damaged ancient Greek inscriptions, identify their original location, and help establish their creation date, collaborating with historians to advance understanding of ancient history.
Introducing Aeneas, the first AI model for contextualizing ancient inscriptions, designed to help historians better interpret, attribute, and restore fragmentary texts. It reasons across thousands of Latin inscriptions, retrieving textual and contextual parallels to aid in historical research.
A detailed comparison of the architectures of recent large language models (LLMs) including DeepSeek-V3, OLMo 2, Gemma 3, Mistral Small 3.1, Llama 4, Qwen3, SmolLM3, and Kimi 2, focusing on key design choices and their impact on performance and efficiency.
This book covers foundational topics within computer vision, with an image processing and machine learning perspective. It aims to build the reader’s intuition through visualizations and is intended for undergraduate and graduate students, as well as experienced practitioners.
AI Nexus is a platform for collaboration, knowledge exchange, and groundbreaking discourse in AI. It features upcoming AI events, speaker series, and faculty contributions to the global AI community. The site also provides information on MBZUAI programs and opportunities for collaboration.
Running GenAI models is easy. Scaling them to thousands of users, not so much. This guide details avenues for scaling AI workloads from proofs of concept to production-ready deployments, covering API integration, on-prem deployment considerations, hardware requirements, and tools like vLLM and Nvidia NIMs.
PaperCoder is a multi-agent LLM system that transforms scientific papers into code repositories through a three-stage pipeline: planning, analysis, and code generation. It aims to create faithful, high-quality implementations.
