Related papers: Cognify: Supercharging Gen-AI Workflows With Hiera…

Agentic systems powered by Large Language Models (LLMs) have demonstrated remarkable potential in tackling complex, long-horizon tasks. However, their efficacy is fundamentally constrained by static configurations governing agent behaviors,…

Clinical trials play an important role in cancer care and research, yet participation rates remain low. We developed MSK-MATCH (Memorial Sloan Kettering Multi-Agent Trial Coordination Hub), an AI system for automated eligibility screening…

Adaptive Retrieval-Augmented Generation aims to mitigate the interference of extraneous noise by dynamically determining the necessity of retrieving supplementary passages. However, as Large Language Models evolve with increasing robustness…

High-stakes applications rely on combining Artificial Intelligence (AI) and humans for responsive and reliable decision making. For example, content moderation in social media platforms often employs an AI-human pipeline to promptly remove…

Generative AI is transforming image synthesis, enabling the creation of high-quality, diverse, and photorealistic visuals across industries like design, media, healthcare, and autonomous systems. Advances in techniques such as…

Propelled by their remarkable capabilities to generate novel and engaging content, Generative Artificial Intelligence (GenAI) technologies are disrupting traditional workflows in many industries. While prior research has examined GenAI from…

Effectively integrating Large Language Models (LLMs) into autonomous driving requires a balance between leveraging high-level reasoning and maintaining real-time efficiency. Existing approaches either activate LLMs too frequently, causing…

Generative artificial intelligence (AI) is increasingly used to write and refactor research code, expanding computational workflows. At the same time, Green AI research has largely measured the footprint of models rather than the downstream…

Foundation models require fine-tuning to ensure their generative outputs align with intended results for specific tasks. Automating this fine-tuning process is challenging, as it typically needs human feedback that can be expensive to…

Generative AI (GenAI) systems offer opportunities to increase user productivity in many tasks, such as programming and writing. However, while they boost productivity in some studies, many others show that users are working ineffectively…

Artificial intelligence systems for scientific discovery have demonstrated remarkable potential, yet existing approaches remain largely proprietary and operate in batch-processing modes requiring hours per research cycle, precluding…

Despite the impressive performance of large language models (LLMs) in general domains, they often underperform in specialized domains. Existing approaches typically rely on data synthesis methods and yield promising results by using…

Modern AI clusters, which host diverse workloads like data pre-processing, training and inference, often store the large-volume data in cloud storage and employ caching frameworks to facilitate remote data access. To avoid code-intrusion…

The rapid growth of Retrieval-Augmented Generation (RAG) has created a proliferation of toolkits, yet a fundamental gap remains between experimental prototypes and robust, production-ready systems. We present SearchGym, a modular…

Many evolutionary algorithms (EAs) take advantage of parallel evaluation of candidates. However, if evaluation times vary significantly, many worker nodes (i.e.,\ compute clients) are idle much of the time, waiting for the next generation…

Agentic AI enables LLM to dynamically reason, plan, and interact with tools to solve complex tasks. However, agentic workflows often require many iterative reasoning steps and tool invocations, leading to significant operational expense,…

As high-performance computing and AI workloads become increasingly dependent on GPUs, maintaining high performance across rapidly evolving hardware generations has become a major challenge. Developers often spend months tuning scientific…

Training large language models (LLMs) is often constrained by GPU memory limitations. To alleviate memory pressure, activation recomputation and data compression have been proposed as two major strategies. However, both approaches have…

Recently, there emerged revived interests of designing automatic programs (e.g., using genetic/evolutionary algorithms) to optimize the structure of Convolutional Neural Networks (CNNs) for a specific task. The challenge in designing such…

We present significant extensions to diffusion-based sequence generation models, blurring the line with autoregressive language models. We introduce hyperschedules, which assign distinct noise schedules to individual token positions,…