论文检索

Daniele Meli, Alberto Castellini, Alessandro Farinelli

Partially Observable Markov Decision Processes (POMDPs) are a powerful framework for planning under uncertainty. They allow to model state uncertainty as a belief probability distribution. Approximate solvers based on Monte Carlo sampling show great success to relax the computational demand and perform online planning. However, scaling to complex realistic domains with many actions and long planning horizons is still a major challenge, and a key point to achieve good performance is guiding the action-selection process with domain-dependent policy heuristics which are tailored for the specific application domain. We propose to learn high-quality heuristics from POMDP traces of executions generated by any solver. We convert the belief-action pairs to a logical semantics, and exploit data- and time-efficient Inductive Logic Programming (ILP) to generate interpretable belief-based policy specifications, which are then used as online heuristics. We evaluate thoroughly our methodology on two notoriously challenging POMDP problems, involving large action spaces and long planning horizons, namely, rocksample and pocman. Considering different state-of-the-art online POMDP solvers, including POMCP, DESPOT and AdaOPS, we show that learned heuristics expressed in Answer Set Programming (ASP) yield performance superior to neural networks and similar to optimal handcrafted task-specific heuristics within lower computational time. Moreover, they well generalize to more challenging scenarios not experienced in the training phase (e.g., increasing rocks and grid size in rocksample, incrementing the size of the map and the aggressivity of ghosts in pocman).

Roberto Martín-Martín

Artificial Intelligence (AI) has revolutionized fields like computer vision and natural language processing, yet its impact on robotics remains limited by challenges in long-horizon decision-making and complex physical interactions. My research pioneers robot learning algorithms that exploit (predict, perceive, plan, and reason about) physical interaction as a core component of artificial intelligence, pushing beyond passive solutions in domains such as perception, navigation, and manipulation. By leveraging techniques in imitation learning and hierarchical reinforcement learning, my work empowers robots to learn from human demonstrations, navigate interactively in real-world environments, and gather information through purposeful interactions. In my talk, I will explain how these advances are critical for robots to become useful helpers in human environments, opening the door to the next generation of household robots. I will present several AI algorithmic innovations to integrate physical interactions in computation procedures and outline the path toward developing continually learning robots capable of operating autonomously in unstructured human environments, enhancing their utility as adaptable and intelligent assistants.

Yunzhu Li

Humans have a strong intuitive understanding of the physical world. Through observations and interactions with the environment, we build mental models that predict how the world would change if we applied a specific action (i.e., intuitive physics). My research draws on these human insights to develop model-based RL agents that learn from their interactions and build predictive models that generalize widely across a range of objects made with different materials. The core idea behind my research is to introduce novel representations and integrate structural priors into learning systems to model dynamics at different levels of abstraction. I will discuss how such structures can make model-based planning algorithms more effective, helping robots accomplish complex manipulation tasks (e.g., manipulating an object pile, shaping deformable foam into a target configuration, and making a dumpling from dough using various tools).

Manling Li

While Large Language Models excel in language processing, Large Agent Models are designed to interact with the environment. This transition poses significant challenges in understanding lower-level visual details, and long-horizon reasoning for effective goal interpretation and decision-making. Despite the impressive performance of LLMs/VLMs on various benchmarks, these models perceive images as bags of words (semantic concepts). In detail, they use semantic understanding as a shortcut but lack the ability to recognize geometric structures or solve spatial problems such as mazes. To interact with the physical world, we focus on two dimensions: (1) From high-level semantic to low-level geometric understanding: We introduce a low-level visual description language that serves as geometric tokens, allowing the abstraction of multimodal low-level geometric structures. (2) From fast-thinking to slow-thinking: We propose to quantify long-horizon reasoning by incorporating Markov Decision Process (MDP) based decision-making. The key difference between language models and agent models lies in their decision-making capabilities. This fundamental difference necessitates a shift in how we approach the development of large agent models, focusing on both geometric understanding and long-term planning to create more capable embodied AI agents.

Vivek Gupta

Artificial intelligence has made remarkable progress in reasoning over complex, structured, multimodal, and multilingual data, addressing critical challenges in domains such as finance and healthcare. This abstract underscores key advancements in tabular reasoning, temporal analysis, and structured multimodal reasoning. Key contributions include the development of TempTabQA, a benchmark for temporal question answering, along with novel methods for enhancing temporal reasoning in large language models (LLMs). Additionally, a framework for evaluating mathematical reasoning in financial documents has been introduced, establishing robust techniques for interpreting time-sensitive and quantitative data. Building on these foundations, we have developed hybrid SQL-text adaptive reasoning models (H-STAR) and knowledge-aware reasoning techniques for semi-structured tables (MMTabQA), enabling precise and efficient handling of complex queries. In the vision-language domain, our contributions include advancements in spatial reasoning for geographic data (MAPWise), methods to improve robustness in chart interpretation (FlowVQA), and evaluations of LLMs’ ability to understand visual data, such as charts. Furthermore, we have addressed challenges in multilingual and cross-modal robustness through innovations such as multilingual table synchronization (InfoSync), concurrent robustness evaluations across languages and modalities, and numerical reasoning in tabular data. Our work aims to enhance reasoning on dynamically evolving data using hybrid LLM-SQL queries, symbolic query generation, and multi-table retrieval techniques. We also plan to tackle challenges in interpreting hierarchical table structures, analyzing multiple complex chart types, and exploring diverse map types, while advancing real-world multimodal data analysis. Additionally, we plan to improve table generation in both closed/open-book scenarios and refine evaluation frameworks for structured tasks. These advancements demonstrate the potential of AI in tackling complex, multimodal data and delivering impactful real-world solutions.

Ruohan Gao

The future of Artificial Intelligence demands a paradigm shift towards multisensory perception—to systems that can digest ongoing multisensory observations, that can discover structure in unlabeled raw sensory data, and that can intelligently fuse useful information from different sensory modalities for decision making. While we humans perceive the world by looking, listening, touching, smelling, and tasting, traditional form of machine intelligence mostly focuses on a single sensory modality, particularly vision. Therefore, my research, which I call multisensory machine intelligence, aims to empower machines to emulate and enhance human capabilities in seeing, hearing, and feeling, ultimately enabling them to comprehensively perceive, understand, and interact with the multisensory world. In my AAAI-25 new faculty highlight talk, I will present my research that studies two important aspects of the multisensory world: 1) multisensory objects, and 2) multisensory space. In both aspects, I will talk about how we design systems to reliably capture multisensory data from real-world objects and space, how we effectively model them with differentiable simulation algorithms that build a unified multisensory representation to virtualize real objects, and how we explore creative cross-modal/multi-modal applications with sight, sound, and touch in vision, graphics, and robotics. In the end, I will briefly conclude with my future plans.

Pat Langley

In this paper, I review approaches for acquiring hierarchical knowledge to improve the effectiveness of planning systems. First I note some benefits of such hierarchical content and the advantages of learning over manual construction. After this, I consider alternative paradigms for encoding and acquiring plan expertise before turning to hierarchical task networks. I specify the inputs to HTN learners and three subproblems they must address: identifying hierarchical structure, unifying method heads, and finding method conditions. Finally, I pose seven challenges the community should pursue so that techniques for learning HTNs can reach their full potential.

Mohan Sridharan

Robots are increasingly being used in different application domains due to rapid advancements in hardware and computational methods. However, state of the art methods for many problems in robotics are based on deep networks and similar data-driven models. These methods and models are resource-hungry and opaque, and they are known to provide arbitrary decisions in previously unseen situations, whereas practical robot application domains require transparent, multi-step, multi-level decision-making and ad hoc collaboration under resource constraints and open world uncertainty. In this talk, I argue that for widespread use of robots, we need to revisit principles such as refinement and adaptive satisficing, which can be traced back to the early pioneers of AI. We also need to make these principles the foundation of the architectures we develop for robots, with modern data-driven methods being just another tool in our toolbox. I then illustrate the potential benefits of this approach in the context of fundamental problems in robotics such as visual scene understanding, planning, changing-contact manipulation, and multiagent/human-agent collaboration.

Tingsong Xiao, Zelin Xu, Wenchong He, Zhengkun Xiao, Yupu Zhang, Zibo Liu, Shigang Chen, My T. Thai, Jiang Bian, Parisa Rashidi 等

Adverse clinical events related to unsafe care are among the top ten causes of death in the U.S. Accurate modeling and prediction of clinical events from electronic health records (EHRs) play a crucial role in patient safety enhancement. An example is modeling de facto care pathways that characterize common step-by-step plans for treatment or care. However, clinical event data pose several unique challenges, including the irregularity of time intervals between consecutive events, the existence of cycles, periodicity, multi-scale event interactions, and the high computational costs associated with long event sequences. Existing neural temporal point processes (TPPs) methods do not effectively capture the multi-scale nature of event interactions, which is common in many real-world clinical applications. To address these issues, we propose the cross-temporal-scale transformer (XTSFormer), specifically designed for irregularly timed event data. Our model consists of two vital components: a novel Feature-based Cycle-aware Time Positional Encoding (FCPE) that adeptly captures the cyclical nature of time, and a hierarchical multi-scale temporal attention mechanism, where different temporal scales are determined by a bottom-up clustering approach. Extensive experiments on several real-world EHR datasets show that our XTSFormer outperforms multiple baseline methods.

Isabelle Tingzon, Utku Can Ozturk, Ivan Dotu

Improving global school connectivity is critical for ensuring inclusive and equitable quality education. To reliably estimate the cost of connecting schools, governments and connectivity providers require complete and accurate school location data – a resource that is often scarce in many low- and middle-income countries. To address this challenge, we propose a cost-effective, scalable approach to locating schools in high-resolution satellite images using weakly supervised deep learning techniques. Our best models, which combine vision transformers and convolutional neural networks, achieve AUPRC values above 0.96 across 10 pilot African countries. Leveraging explainable AI techniques, our approach can approximate the precise geographical coordinates of the school locations using only low-cost, classification-level annotations. To demonstrate the scalability of our method, we generate nationwide maps of school location predictions in African countries and present a detailed analysis of our results, using Senegal as our case study. Finally, we demonstrate the immediate usability of our work by introducing an interactive web mapping tool to streamline human-in-the-loop model validation efforts by government partners. This work successfully showcases the real-world utility of deep learning and satellite images for planning regional infrastructure and accelerating universal school connectivity.

Minhyuk Song, Sungwon Han, Seungeon Lee, Donghyun Ahn, Jihee Kim, Meeyoung Cha

Recent studies on the urban heat island phenomenon reveal how rapid urbanization intensifies temperature disparities in urban cores, highlighting the need for sustainable urban planning solutions. Analyzing the problems caused by these effects requires high-resolution climate data; however, physical weather stations often lack sufficient regional coverage and resolution. Proposals for alternative methods have attempted to bridge this gap, but they fall short in capturing regional characteristics adequately or necessitate obtaining difficult-to-get input data. This research proposes to use satellite data, where the visual spectrum provides rich information about the degree of human development and is easy to obtain, to measure urban air temperature. Our model, UrbanHeat, uses multi-resolution satellite imagery and employs land surface temperature and global climate data as proxy labels to predict air temperature at a granular scale. The results show that the model provides predictions at a much finer scale while showing superior performance in measuring ordinal relationships between points by capturing both local and broad land cover details of the region. Our case studies demonstrate how predictions at high resolution can help protect vulnerable populations from extreme heat (e.g., elders or developing countries) and contribute to sustainable urban development worldwide.

Jinlin Li, Xintong Li, Xiao Zhou

As global populations age rapidly, incorporating age-specific considerations into urban planning has become essential to addressing the urgent demand for age-friendly built environments and ensuring sustainable urban development. However, current practices often overlook these considerations, resulting in inadequate and unevenly distributed elderly services in cities. There is a pressing need for equitable and optimized urban renewal strategies to support effective age-friendly planning. To address this challenge, we propose a novel framework, Fairness-driven Age-friendly community Planning via Conditional Diffusion generation (FAP-CD). FAP-CD leverages a conditioned graph denoising diffusion probabilistic model to learn the joint probability distribution of aging facilities and their spatial relationships at a fine-grained regional level. Our framework generates optimized facility distributions by iteratively refining noisy graphs, conditioned on the needs of the elderly during the diffusion process. Key innovations include a demand-fairness pre-training module that integrates community demand features and facility characteristics using an attention mechanism and min-max optimization, ensuring equitable service distribution across regions. Additionally, a discrete graph structure captures walkable accessibility within regional road networks, guiding model sampling. To enhance information integration, we design a graph denoising network with an attribute augmentation module and a hybrid graph message aggregation module, combining local and global node and edge information. Empirical results across multiple metrics demonstrate the effectiveness of FAP-CD in balancing age-friendly needs with regional equity, achieving an average improvement of 41% over competitive baseline models.

Marc Grimson, Zhongdi Qu, Yue Mao, Aaron M Ferber, Felipe Siqueira Pacheco, Sebastian Heilpern, Hector Angarita, Alexander Flecker, Carla P Gomes

Addressing global sustainability challenges as outlined by the United Nations (UN) Sustainable Development Goals (SDGs) often requires navigating many potentially conflicting societal objectives simultaneously. For instance, increasing hydropower production enhances renewable energy supply but may adversely impact people and nature. Understanding these trade-offs is crucial, and the Pareto frontier - the set of solutions that cannot be improved with respect to one objective without negatively affecting another - is a valuable framework. Strategic hydropower planning concerns finding energy portfolios that achieve decarbonization targets, while balancing energy production with socioeconomic and environmental impacts. Previous work has considered exact and approximate algorithms for Pareto optimization for tree-structured networks, such as rivers, for hydropower planning. However, such approaches do not account for bounding constraints, such as realistic energy production targets, critical in real-world applications. Herein, we propose a novel approach for constraint-aware Pareto optimization for tree-structured networks, incorporating objective bounds to ensure more realistic and robust solution outcomes. We apply our constraint-aware Pareto approach to the strategic planning of hydropower expansion, considering energy bounds to adhere to the UN's net zero by 2050 decarbonization targets, in the Magdalena River basin, home to more than 80% of Colombia’s population. Our analysis demonstrates how lower and upper bounds can significantly modify the unconstrained Pareto frontier, revealing that feasible Pareto solutions can be dominated by infeasible solutions, and thus may be ignored by constraint-agnostic solvers. Our results highlight the importance of considering real-world constraints in multi-objective problems such as optimizing hydropower expansion to meet both energy and sustainability goals.

Zixuan Feng, Qing Ye, Weijun Xie, Qiushi Chen

The soaring drug overdose crisis in the United States has claimed more than half a million lives in the past decade and remains a major public health threat. The ability to predict drug overdose deaths at the county level can help local communities develop action plans in response to emerging changes. Applying off-the-shelf machine learning algorithms for prediction can be challenging due to the heterogeneous risk profiles of the counties and suppressed data in common publicly available data sources. To fill these gaps, we develop a cluster-aware supervised learning (CASL) framework to enhance the prediction of county-level drug overdose deaths. This CASL model simultaneously clusters counties into groups based on geographical and socioeconomic characteristics and minimizes the loss function that accounts for suppressed values and cluster-specific regularization. Our computational study uses real-world data from 2010 to 2021, focusing on the ten states most severely impacted by the drug overdose crisis. The results demonstrate that our proposed CASL framework significantly outperforms state-of-the-art methods by achieving a superior balance in prediction accuracy for both unsuppressed and suppressed observations. The proposed model also identifies different clusters of counties, capturing heterogeneous patterns of overdose mortality among counties of diverse characteristics.

Paul Röttger, Fabio Pernisi, Bertie Vidgen, Dirk Hovy

The last two years have seen a rapid growth in concerns around the safety of large language models (LLMs). Researchers and practitioners have met these concerns by creating an abundance of datasets for evaluating and improving LLM safety. However, much of this work has happened in parallel, and with very different goals in mind, ranging from the mitigation of near-term risks around bias and toxic content generation to the assessment of longer-term catastrophic risk potential. This makes it difficult for researchers and practitioners to find the most relevant datasets for their use case, and to identify gaps in dataset coverage that future work may fill. To remedy these issues, we conduct a first systematic review of open datasets for evaluating and improving LLM safety. We review 144 datasets, which we identified through an iterative and community-driven process over the course of several months. We highlight patterns and trends, such as a trend towards fully synthetic datasets, as well as gaps in dataset coverage, such as a clear lack of non-English and naturalistic datasets. We also examine how LLM safety datasets are used in practice -- in LLM release publications and popular LLM benchmarks -- finding that current evaluation practices are highly idiosyncratic and make use of only a small fraction of available datasets. Our contributions are based on SafetyPrompts.com, a living catalogue of open datasets for LLM safety, which we plan to update continuously as the field of LLM safety develops.

Saaduddin Mahmud, Mason Nakamura, Shlomo Zilberstein

The advent of large language models (LLMs) has sparked significant interest in using natural language for preference learning. However, existing methods often suffer from high computational burdens, taxing human supervision, and lack of interpretability. To address these issues, we introduce MAPLE, a framework for large language model-guided Bayesian active preference learning. MAPLE leverages LLMs to model the distribution over preference functions, conditioning it on both natural language feedback and conventional preference learning feedback, such as pairwise trajectory rankings. MAPLE employs active learning to systematically reduce uncertainty in this distribution and incorporates a language-conditioned active query selection mechanism to identify informative and easy-to-answer queries, thus reducing the burden on humans. We evaluate MAPLE's sample efficiency and preference inference quality across two benchmarks, including a real-world vehicle route planning benchmark using OpenStreetMap data. Our results demonstrate that MAPLE accelerates the learning process and effectively improves humans' ability to answer queries.

Jingyang Zhao, Mingyu Xiao, Junqiang Peng, Ziliang Xiong

In the Clustered TSP (CTSP), we are given an edge-weighted graph satisfying the triangle inequality property, and a family of pairwise disjoint vertex groups. The goal is to find a minimum weight tour that includes all vertices, ensuring that the vertices within each group appear consecutively on the tour. The subgroup planning problem (SGPP) is an extension of CTSP by relaxing some triangle inequality requirements on edge weights. CTSP and SGPP have plentiful applications in AI and robotics. In this paper, we design three improved approximation algorithms for SGPP and CTSP. First, we propose a polynomial-time 2.167-approximation algorithm for SGPP, improving the previous ratio of 3 (IJCAI 2017). Second, we give an FPT 2.072-approximation algorithm for SGPP parameterized by the maximum group size, improving the previous ratio of 2.5 (IJCAI 2017). Third, we prove an FPT (β

Jinghan Zhang, Xiting Wang, Weijieying Ren, Lu Jiang, Dongjie Wang, Kunpeng Liu

Large Language Models (LLMs) gain substantial reasoning and decision-making capabilities from thought structures. However, existing methods such as Tree of Thought and Retrieval Augmented Thoughts often fall short in complex tasks due to the limitations of insufficient local retrieval of factual knowledge and inadequate global selection of strategies. These limitations make it challenging for these methods to balance factual accuracy and comprehensive logical optimization effectively. To address these limitations, we introduce the Retrieval Augmented Thought Tree (RATT), a novel thought structure that considers both overall logical soundness and factual correctness at each step of the thinking process. Specifically, at every point of a thought branch, RATT performs planning and lookahead to explore and evaluate multiple potential reasoning steps, and integrate the fact-checking ability of Retrieval-Augmented Generation (RAG) with LLM's ability to assess overall strategy. Through this combination of factual knowledge and strategic feasibility, the RATT adjusts and integrates the thought tree structure to search for the most promising branches within the search space. This thought structure significantly enhances the model's coherence in logical inference and efficiency in decision-making, and thus increases the limit of the capacity of LLM to generate reliable inferences and decisions based on thought structures. A broad range of experiments on different types of tasks showcases that the RATT structure significantly outperforms existing methods in factual correctness and logical coherence.

Elisa Tosello, Alessandro Valentini, Andrea Micheli

Integrating metric time into Task And Motion Planning (TAMP) is challenging, especially with simultaneous object motion. Existing work focuses on classical and numeric TAMP, not considering deadlines, motions overlapping in time, and other temporal constraints. In this paper, we fill this gap by formalizing Temporal Task and Motion Planning (TTAMP) for multi-object navigation. We propose a novel interleaved planning technique for this problem, which leverages incremental Satisfiability Modulo Theory to ensure efficient reasoning on deadlines and action duration coupled with a motion planner supporting simultaneous object motion. Geometric data on encountered obstacles prunes unreachable symbolic regions, while temporal bounds limit the geometric search space. For multiple moving objects, our algorithm contextualizes the conflicts learned from the motion planner on overlapping actions so that entire classes of temporal plans are pruned from the search space of the task planner, ensuring the eventual termination of the interplay. We provide a comprehensive benchmark suite and demonstrate the effectiveness of our solver in leveraging these scenarios.

Simon Ståhlberg, Blai Bonet, Hector Geffner

GNN-based approaches for learning general policies across planning domains are limited by the expressive power of C2, namely; first-order logic with two variables and counting. This limitation can be overcomed by transitioning to k-GNNs, for k=3, wherein object embeddings are substituted with triplet embeddings. Yet, while 3-GNNs have the expressive power of C3, unlike 1- and 2-GNNs that are confined to C2, they require quartic time for message exchange and cubic space to store embeddings, rendering them infeasible. In this work, we introduce a parameterized version R-GNN[t] (with parameter t) of Relational GNNs. Unlike GNNs, that are designed to perform computation on graphs, Relational GNNs are designed to do computation on relational structures. When t=infty, R-GNN[t] approximates 3-GNNs over graphs, but using only quadratic space for embeddings. For lower values of t, such as t=1 and t=2, R-GNN[t] achieves a weaker approximation by exchanging fewer messages, yet interestingly, often yield the expressivity required in several planning domains. Furthermore, the new R-GNN[t] architecture is the original R-GNN architecture with a suitable transformation applied to the inputs only. Experimental results illustrate the clear performance gains of R-GNN[1] over the plain R-GNNs, and also over Edge Transformers that also approximate 3-GNNs.