Related papers: CoSteer: Collaborative Decoding-Time Personalizati…
Spatiotemporal learning has become a pivotal technique to enable urban intelligence. Traditional spatiotemporal models mostly focus on a specific task by assuming a same distribution between training and testing sets. However, given that…
Correlated time series (CTS) forecasting plays an essential role in many cyber-physical systems, where multiple sensors emit time series that capture interconnected processes. Solutions based on deep learning that deliver state-of-the-art…
Dialogue State Tracking (DST), a key component of task-oriented conversation systems, represents user intentions by determining the values of pre-defined slots in an ongoing dialogue. Existing approaches use hand-crafted templates and…
Large Transformer models achieved the state-of-the-art status for Natural Language Understanding tasks and are increasingly becoming the baseline model architecture for modeling source code. Transformers are usually pre-trained on large…
Most existing trackers based on discriminative correlation filters (DCF) try to introduce predefined regularization term to improve the learning of target objects, e.g., by suppressing background learning or by restricting change rate of…
How can we enable users to create effective, perception-driven task plans for collaborative robots? We conducted a 35-person user study with the Behavior Tree-based CoSTAR system to determine which strategies for end user creation of…
Modern large multicore systems often run multiple workloads that share CPUs under schedulers such as Linux CFS. To keep CPUs busy, these schedulers load-balance runnable work, causing each workload to execute on many cores. This weakens…
Although robotic manipulators are used in an ever-growing range of applications, robot manufacturers typically follow a ``one-fits-all'' philosophy, employing identical manipulators in various settings. This often leads to suboptimal…
In this paper we develop a sequential convex programming (SCP) framework for free-final-time covariance steering of nonlinear stochastic differential equations (SDEs) subject to both additive and multiplicative diffusion. We cast the…
We explore AI-driven distributed-systems policy design by combining stochastic code generation from large language models (LLMs) with deterministic verification in a domain-specific simulator. Using a Function-as-a-Service runtime (Bauplan)…
Federated efficient fine-tuning has emerged as an approach that leverages distributed data and computational resources across nodes to address the challenges of large-scale fine-tuning and privacy preservation. The Low-Rank Adaptation…
Activation-based control steers large language models (LLMs) by intervening on their internal representations during inference, and has emerged as an effective paradigm for controlling behaviors such as persona and style. However, existing…
Biologically inspired auditory models play an important role in developing effective audio representations that can be tightly integrated into speech and audio processing systems. Current computational models of the cochlea are typically…
The advancement in deep learning and internet-of-things have led to diverse human sensing applications. However, distinct patterns in human sensing, influenced by various factors or contexts, challenge the generic neural network model's…
Tuning parallel file system in High-Performance Computing (HPC) systems remains challenging due to the complex I/O paths, diverse I/O patterns, and dynamic system conditions. While existing autotuning frameworks have shown promising results…
The next point-of-interest (POI) recommendation task aims to predict the users' immediate next destinations based on their preferences and historical check-ins, holding significant value in location-based services. Recently, large language…
Models pre-trained on large-scale datasets are often fine-tuned to support newer tasks and datasets that arrive over time. This process necessitates storing copies of the model over time for each task that the pre-trained model is…
Model steering represents a powerful technique that dynamically aligns large language models (LLMs) with human preferences during inference. However, conventional model-steering methods rely heavily on externally annotated data, not only…
Personalized search is a problem where models benefit from learning user preferences from per-user historical interaction data. The inferred preferences enable personalized ranking models to improve the relevance of documents for users.…
Many applications of machine learning, such as human health research, involve processing private or sensitive information. Privacy concerns may impose significant hurdles to collaboration in scenarios where there are multiple sites holding…