Related papers: Optimizing Logical Execution Time Model for Both D…

We address the problem of learning observation models end-to-end for estimation. Robots operating in partially observable environments must infer latent states from multiple sensory inputs using observation models that capture the joint…

Large language models (LLMs) can perform reasoning computations both internally within their latent space and externally by generating explicit token sequences like chains of thought. Significant progress in enhancing reasoning abilities…

With advances in large language models (LLMs), researchers are creating new systems that can perform AI-driven analytics over large unstructured datasets. Recent work has explored executing such analytics queries using semantic operators --…

BitTorrent developers have recently introduced a new application layer congestion control algorithm based on UDP framing at transport layer and currently under definition at the IETF LEDBAT Working Group. LEDBAT is a delay-based protocol…

The expectation-maximization (EM) algorithm can compute the maximum-likelihood (ML) or maximum a posterior (MAP) point estimate of the mixture models or latent variable models such as latent Dirichlet allocation (LDA), which has been one of…

Prompt engineering is a challenging and important task due to the high sensitivity of Large Language Models (LLMs) to the given prompt and the inherent ambiguity of a textual task instruction. Automatic prompt engineering is essential to…

Large language models (LLMs) have recently been employed as agents to solve sequential decision-making tasks such as Bayesian optimization and multi-armed bandits (MAB). These works usually adopt an LLM for sequential action selection by…

Context: Just-in-Time (JIT) compilers are able to specialize the code they generate according to a continuous profiling of the running programs. This gives them an advantage when compared to Ahead-of-Time (AoT) compilers that must choose…

Recent works have demonstrated the effectiveness of adapting pre-trained language models (LMs) for forecasting time series in the low-data regime. We build upon these findings by analyzing the effective transfer from language models to time…

Modeling the dynamics of financial Limit Order Books (LOB) at the message level is challenging due to irregular event timing, rapid regime shifts, and the reactions of high-frequency traders to visible order flow. Previous LOB models…

Constructing a timeline requires identifying the chronological order of events in an article. In prior timeline construction datasets, temporal orders are typically annotated by either event-to-time anchoring or event-to-event pairwise…

The demand for stringent interactive quality-of-service has intensified in both mobile edge computing (MEC) and cloud systems, driven by the imperative to improve user experiences. As a result, the processing of computation-intensive tasks…

Temporal abstraction and efficient planning pose significant challenges in offline reinforcement learning, mainly when dealing with domains that involve temporally extended tasks and delayed sparse rewards. Existing methods typically plan…

Large Language Model (LLM) based multi-agent systems (MAS) show remarkable potential in collaborative problem-solving, yet they still face critical challenges: low communication efficiency, poor scalability, and a lack of effective…

Learning how to learn efficiently is a fundamental challenge for biological agents and a growing concern for artificial ones. To learn effectively, an agent must regulate its learning speed, balancing the benefits of rapid improvement…

There is a growing cross-disciplinary effort in the broad domain of optimization and learning with streams of data, applied to settings where traditional batch optimization techniques cannot produce solutions at time scales that match the…

Real time systems are systems in which there is a commitment for timely response by the computer to external stimuli. Real time applications have to function correctly even in presence of faults. Fault tolerance can be achieved by either…

End-to-end learning has become a widely applicable and studied problem in training predictive ML models to be aware of their impact on downstream decision-making tasks. These end-to-end models often outperform traditional methods that…

We consider the load balancing problem in large-scale heterogeneous systems with multiple dispatchers. We introduce a general framework called Local-Estimation-Driven (LED). Under this framework, each dispatcher keeps local (possibly…

Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by introducing novel…