Related papers: COLIN: Planning with Continuous Linear Numeric Cha…

In recent years research in the planning community has moved increasingly toward s application of planners to realistic problems involving both time and many typ es of resources. For example, interest in planning demonstrated by the space…

Despite great recent advances achieved by deep neural networks (DNNs), they are often vulnerable to adversarial attacks. Intensive research efforts have been made to improve the robustness of DNNs; however, most empirical defenses can be…

Deploying vision foundation models typically relies on efficient adaptation strategies, whereas conventional full fine-tuning suffers from prohibitive costs and low efficiency. While delta-tuning has proven effective in boosting the…

This paper presents our approach to the quantitative modeling and analysis of highly (re)configurable systems, such as software product lines. Different combinations of the optional features of such a system give rise to combinatorially…

Large Language Models (LLMs) are typically trained to reflect a relatively uniform set of values, which limits their applicability to tasks that require understanding of nuanced human perspectives. Recent research has underscored the…

This papers deals with the constrained discounted control of piecewise deterministic Markov process (PDMPs) in general Borel spaces. The control variable acts on the jump rate and transition measure, and the goal is to minimize the total…

The simulation of power system dynamics poses a computationally expensive task. Considering the growing uncertainty of generation and demand patterns, thousands of scenarios need to be continuously assessed to ensure the safety of power…

Advanced probabilistic programming languages (PPLs) using hybrid particle filtering combine symbolic exact inference and Monte Carlo methods to improve inference performance. These systems use heuristics to partition random variables within…

Tackling complex optimization problems often relies on expert-designed heuristics, typically crafted through extensive trial and error. Recent advances demonstrate that large language models (LLMs), when integrated into well-designed…

In real-world applications, the ability to reason about incomplete knowledge, sensing, temporal notions, and numeric constraints is vital. While several AI planners are capable of dealing with some of these requirements, they are mostly…

Recently, the makespan-minimization problem of compiling a general class of quantum algorithms into near-term quantum processors has been introduced to the AI community. The research demonstrated that temporal planning is a strong approach…

In recent years, the planning community has observed that techniques for learning heuristic functions have yielded improvements in performance. One approach is to use offline learning to learn predictive models from existing heuristics in a…

Training large language models (LLMs) with increasingly long and varying sequence lengths introduces severe load imbalance challenges in large-scale data-parallel training. Recent frameworks attempt to mitigate these issues through data…

Recent improvements in large language models have opened new opportunities for accelerating and automating scientific workflows. In parallel, modern collider analyses are becoming increasingly complex and demand substantial programming and…

We propose cognitive prompting as a novel approach to guide problem-solving in large language models (LLMs) through structured, human-like cognitive operations, such as goal clarification, decomposition, filtering, abstraction, and pattern…

The success of large language models (LLMs) across diverse NLP tasks has elevated the importance of reasoning chain optimization as a critical step in aligning model behavior with task objectives. Existing reasoning chain tuning methods…

In this paper, we develop a generic methodology to encode hierarchical causality structure among observed variables into a neural network in order to improve its predictive performance. The proposed methodology, called causality-informed…

We propose a hybrid solver that fuses the dimensionality-reduction strengths of the Method of Lines (MOL) with the flexibility of Physics-Informed Neural Networks (PINNs). Instead of approximating spatial derivatives with fixed…

Recent advancements in large language models (LLMs) have significantly improved their reasoning abilities, particularly through techniques involving search and backtracking. Backtracking naturally scales test-time compute by enabling…

Neuro-symbolic artificial intelligence aims to combine neural architectures with symbolic approaches that can represent knowledge in a human-interpretable formalism. Continual learning concerns with agents that expand their knowledge over…