Related papers: LEGO: Spatial Accelerator Generation and Optimizat…

Over the last decades, the challenges in applied regression and in predictive modeling have been changing considerably: (1) More flexible model specifications are needed as big(ger) data become available, facilitated by more powerful…

This paper shows how to build a sparse tensor algebra compiler that is agnostic to tensor formats (data layouts). We develop an interface that describes formats in terms of their capabilities and properties, and show how to build a modular…

Optimization benchmarks play a fundamental role in assessing algorithm performance; however, existing artificial benchmarks often fail to capture the diversity and irregularity of real-world problem structures, while benchmarks derived from…

We propose Intermediate Layer Optimization (ILO), a novel optimization algorithm for solving inverse problems with deep generative models. Instead of optimizing only over the initial latent code, we progressively change the input layer…

Recent advances in 3D Gaussian Splatting (3DGS) have enabled Simultaneous Localization and Mapping (SLAM) systems to build photorealistic maps. However, these maps lack the open-vocabulary semantic understanding required for advanced…

Large language models (LLMs) have recently emerged as promising tools for solving challenging robotic tasks, even in the presence of action and observation uncertainties. Recent LLM-based decision-making methods (also referred to as…

Modern large language model workloads put increasing demands on parallel compute capability and on-chip memory capacity, while also stressing fine-grained data movement and synchronization. These trends motivate exploring and designing…

This paper introduces LMFAO (Layered Multiple Functional Aggregate Optimization), an in-memory optimization and execution engine for batches of aggregates over the input database. The primary motivation for this work stems from the…

Many real-world problems, such as airfoil design, involve optimizing a black-box expensive objective function over complex structured input space (e.g., discrete space or non-Euclidean space). By mapping the complex structured input space…

We introduce LEGOMem, a modular procedural memory framework for multi-agent large language model (LLM) systems in workflow automation. LEGOMem decomposes past task trajectories into reusable memory units and flexibly allocates them across…

Molecular design based on generative models, such as variational autoencoders (VAEs), has become increasingly popular in recent years due to its efficiency for exploring high-dimensional molecular space to identify molecules with desired…

Recent advancements in generative artificial intelligence have introduced groundbreaking approaches to innovating next-generation semantic communication, which prioritizes conveying the meaning of a message rather than merely transmitting…

Humanoid robots are increasingly demanded to operate in interactive and human-surrounded environments while achieving sophisticated locomotion and manipulation tasks. To accomplish these tasks, roboticists unremittingly seek for advanced…

Dedicated tensor accelerators demonstrate the importance of linear algebra in modern applications. Such accelerators have the potential for impressive performance gains, but require programmers to rewrite code using vendor APIs - a barrier…

Designing nuclear reactor cores requires navigating large discrete design spaces governed by complex neutronic interactions. Traditional deterministic, metaheuristic, and machine-learning-assisted methods search within fixed, human-defined…

Current research on Multimodal Retrieval-Augmented Generation (MRAG) enables diverse multimodal inputs but remains limited to single-modality outputs, restricting expressive capacity and practical utility. In contrast, real-world…

This study proposes an intelligent multi-agent framework built on LLMs and VLMs and specifically tailored to robotics. The goal is to integrate the strengths of LLMs and VLMs with computational tools to automatically analyze and solve…

Generative Large Language Models (LLMs) stand as a revolutionary advancement in the modern era of artificial intelligence (AI). However, scaling down LLMs for resource-constrained hardware, such as Internet-of-Things (IoT) devices requires…

Token generation speed is critical to power the next wave of AI inference applications. GPUs significantly underperform during token generation due to synchronization overheads at kernel boundaries, utilizing only 21% of their peak memory…

Reinforcement learning (RL) post-training for Large Language Models (LLMs) is now scaling to large clusters and running for extended durations to enhance model reasoning performance. However, the scalability of existing RL frameworks is…