Related papers: CoSteer: Collaborative Decoding-Time Personalizati…

Personalization is becoming indispensable for LLMs to align with individual user preferences and needs. Yet current approaches are often computationally expensive, data-intensive, susceptible to catastrophic forgetting, and prone to…

Optimization problems with both control variables and environmental variables arise in many fields. This paper introduces a framework of personalized optimization to han- dle such problems. Unlike traditional robust optimization,…

Large Language Models (LLMs) trained for average correctness often exhibit mode collapse, producing narrow decision behaviors on tasks where multiple responses may be reasonable. This limitation is particularly problematic in ordinal…

How can we enable novice users to create effective task plans for collaborative robots? Must there be a tradeoff between generalizability and ease of use? To answer these questions, we conducted a user study with the CoSTAR system, which…

This work is concerned with the finite-horizon optimal covariance steering of networked systems governed by discrete-time stochastic linear dynamics. In contrast with existing work that has only considered systems with dynamically decoupled…

Autoscaling functions provide the foundation for achieving elasticity in the modern cloud computing paradigm. It enables dynamic provisioning or de-provisioning resources for cloud software services and applications without human…

We consider the fully decentralized machine learning scenario where many users with personal datasets collaborate to learn models through local peer-to-peer exchanges, without a central coordinator. We propose to train personalized models…

Dense embedding models have become critical for modern information retrieval, particularly in RAG pipelines, but their performance often degrades when applied to specialized corpora outside their pre-training distribution. To address thi we…

In recent years, there has been a rapid development of spatio-temporal prediction techniques in response to the increasing demands of traffic management and travel planning. While advanced end-to-end models have achieved notable success in…

As large language models (LLMs) improve in their capacity to serve as personal AI assistants, their ability to output uniquely tailored, personalized responses that align with the soft preferences of their users is essential for enhancing…

In this work, we systematically study the problem of personalized text-to-image generation, where the output image is expected to portray information about specific human subjects. E.g., generating images of oneself appearing at imaginative…

Activation steering offers a computationally efficient mechanism for controlling Large Language Models (LLMs) without fine-tuning. While effectively controlling target traits (e.g., persona), coherency degradation remains a major obstacle…

In this work we present Lodestar, an integrated engine for rapid real-time control system development. Using a functional block diagram paradigm, Lodestar allows for complex multi-disciplinary control software design, while automatically…

Pre-trained Transformer-based large models have revolutionized personal virtual assistants, but their deployment in cloud environments faces challenges related to data privacy and response latency. Deploying large models closer to the data…

Large Reasoning Models (LRMs) excel at complex reasoning tasks, but their efficiency is often hampered by overly verbose outputs. Prior steering methods attempt to address this issue by applying a single, global vector to hidden…

Supporting decision-making has long been a central vision in the field of spatio-temporal intelligence. While prior work has improved the timeliness and accuracy of spatio-temporal forecasting, converting these forecasts into actionable…

Large Language Models (LLMs) excel at a wide range of tasks, but adapting them to new data, particularly for personalized applications, poses significant challenges due to resource and computational constraints. Existing methods either rely…

Tuning machine learning models at scale, especially finding the right hyperparameter values, can be difficult and time-consuming. In addition to the computational effort required, this process also requires some ancillary efforts including…

Text-to-image personalization aims to teach a pre-trained diffusion model to reason about novel, user provided concepts, embedding them into new scenes guided by natural language prompts. However, current personalization approaches struggle…

We introduce CODS (Computational Optimization in Design Space), a theoretical model that frames computational design as a constrained optimization problem over a structured, multi-dimensional design space. Unlike existing methods that rely…