Related papers: Compass: Optimizing Compound AI Workflows for Dyna…
Autonomous driving requires reasoning about interactions with surrounding traffic. A prevailing approach is large-scale imitation learning on expert driving datasets, aimed at generalizing across diverse real-world scenarios. For online…
Direct Preference Optimization (DPO) has become a standard framework for safety alignment, but its reliance on pairwise preference updates makes training sensitive to imperfect supervision. Existing robust DPO methods often address this…
Manipulation in confined and cluttered environments remains a significant challenge due to partial observability and complex configuration spaces. Effective manipulation in such environments requires an intelligent exploration strategy to…
Faced with the challenges of big data, modern cloud database management systems are designed to efficiently store, organize, and retrieve data, supporting optimal performance, scalability, and reliability for complex data processing and…
Foundation models have reshaped AI by unifying fragmented architectures into scalable backbones with multimodal reasoning and contextual adaptation. In parallel, the long-standing notion of AI agents, defined by the sensing-decision-action…
In a conventional supervised learning setting, a machine learning model has access to examples of all object classes that are desired to be recognized during the inference stage. This results in a fixed model that lacks the flexibility to…
Algorithm configuration methods optimize the performance of a parameterized heuristic algorithm on a given distribution of problem instances. Recent work introduced an algorithm configuration procedure ("Structured Procrastination") that…
Robot motion planning involves computing a sequence of valid robot configurations that take the robot from its initial state to a goal state. Solving a motion planning problem optimally using analytical methods is proven to be PSPACE-Hard.…
Emerging artificial intelligence (AI) and machine learning (ML) workloads present new challenges of managing the collective communication used in distributed training across hundreds or even thousands of GPUs. This paper presents STrack, a…
Cloud computing has established itself as the support for the vast majority of emerging technologies, mainly due to the characteristic of elasticity it offers. Auto-scalers are the systems that enable this elasticity by acquiring and…
Approaches to continual learning aim to successfully learn a set of related tasks that arrive in an online manner. Recently, several frameworks have been developed which enable deep learning to be deployed in this learning scenario. A key…
Problem Definition: Managing inpatient flow in large hospital systems is challenging due to the complexity of assigning randomly arriving patients -- either waiting for primary units or being overflowed to alternative units. Current…
We introduce KAPSO, a modular framework for autonomous program synthesis and optimization. Given a natural language goal and an evaluation method, KAPSO iteratively performs ideation, code synthesis and editing, execution, evaluation, and…
Finding good configurations for a software system is often challenging since the number of configuration options can be large. Software engineers often make poor choices about configuration or, even worse, they usually use a sub-optimal…
The increasingly complicated and diverse applications have distinct network performance demands, e.g., some desire high throughput while others require low latency. Traditional congestion controls (CC) have no perception of these demands.…
AI systems are being deployed to support human decision making in high-stakes domains. In many cases, the human and AI form a team, in which the human makes decisions after reviewing the AI's inferences. A successful partnership requires…
A machine learning configuration refers to a combination of preprocessor, learner, and hyperparameters. Given a set of configurations and a large dataset randomly split into training and testing set, we study how to efficiently select the…
Autonomous vehicle (AV) stacks are typically built in a modular fashion, with explicit components performing detection, tracking, prediction, planning, control, etc. While modularity improves reusability, interpretability, and…
AI-generated content has progressed from monolithic models to modular workflows, especially on platforms like ComfyUI, allowing users to customize complex creative pipelines. However, the large number of components in ComfyUI and the…
Platooning connected and autonomous vehicles (CAVs) can improve traffic and fuel efficiency. However, scalable platooning operations require junction-level coordination, which has not been well studied. In this paper, we study the…