Related papers: Relay: A New IR for Machine Learning Frameworks

Large language models (LLMs) are transforming society, powering applications from smartphone assistants to autonomous driving. Yet cloud-based LLM services alone cannot serve a growing class of applications, including those operating under…

As AI moves beyond text, large language models (LLMs) increasingly power vision, audio, and document understanding; however, their high inference costs hinder real-time, scalable deployment. Conversely, smaller open-source models offer cost…

Reinforcement learning (RL) post-training has proven effective at unlocking reasoning, self-reflection, and tool-use capabilities in large language models. As models extend to omni-modal inputs and agentic multi-turn workflows, RL training…

Linear recurrent neural networks (LRNNs) provide a structured approach to sequence modeling that bridges classical linear dynamical systems and modern deep learning, offering both expressive power and theoretical guarantees on stability and…

The rapid advancement of multimodal large language models has demonstrated impressive capabilities, yet nearly all operate in an offline paradigm, hindering real-time interactivity. Addressing this gap, we introduce the Real-tIme Video…

The rapid progress in machine learning (ML) has brought forth many large language models (LLMs) that excel in various tasks and areas. These LLMs come with different abilities and costs in terms of computation or pricing. Since the demand…

In this work, we propose Retentive Network (RetNet) as a foundation architecture for large language models, simultaneously achieving training parallelism, low-cost inference, and good performance. We theoretically derive the connection…

Machine Reading at Scale (MRS) is a challenging task in which a system is given an input query and is asked to produce a precise output by "reading" information from a large knowledge base. The task has gained popularity with its natural…

Inspired by the general Vision-and-Language Navigation (VLN) task, aerial VLN has attracted widespread attention, owing to its significant practical value in applications such as logistics delivery and urban inspection. However, existing…

Reinforcement learning (RL) has demonstrated strong potential in training large language models (LLMs) capable of complex reasoning for real-world problem solving. More recently, RL has been leveraged to create sophisticated LLM-based…

Structured prediction tasks, like machine translation, involve learning functions that map structured inputs to structured outputs. Recurrent Neural Networks (RNNs) have historically been a popular choice for such tasks, including in…

Deep reinforcement learning has been extensively studied in decision-making processes and has demonstrated superior performance over conventional approaches in various fields, including radar resource management (RRM). However, a notable…

Imitation learning often needs a large demonstration set in order to handle the full range of situations that an agent might find itself in during deployment. However, collecting expert demonstrations can be expensive. Recent work in…

A novel language system has given rise to promising alternatives to standard formal and processor network models of computation. An interstring linked with a abstract machine environment, shares sub-expressions, transfers data, and…

Reconfigurable intelligent surfaces (RIS) have drawn considerable attention recently due to their controllable scattering elements that are able to direct electromagnetic waves into desirable directions. Although RISs share some…

Modern systems evolve in unpredictable environments and have to continuously adapt their behavior to changing conditions. The "DReAM" (Dynamic Reconfigurable Architecture Modeling) framework, has been designed for modeling reconfigurable…

Information retrieval (IR) plays a crucial role in locating relevant resources from vast amounts of data, and its applications have evolved from traditional knowledge bases to modern retrieval models (RMs). The emergence of large language…

Our goal is to create an interactive natural language interface that efficiently and reliably learns from users to complete tasks in simulated robotics settings. We introduce a neural semantic parsing system that learns new high-level…

Machine learning systems are often deployed for making critical decisions like credit lending, hiring, etc. While making decisions, such systems often encode the user's demographic information (like gender, age) in their intermediate…

The rise in capability and ubiquity of generative artificial intelligence (AI) technologies has enabled its application to the field of Socially Interactive Agents (SIAs). Despite rising interest in modern AI-powered components used for…