论文检索

Ruihua Han, Shuai Wang, Shuaijun Wang, Zeqing Zhang, Jianjun Chen, Shijie Lin, Chengyang Li, Chengzhong Xu, Yonina C. Eldar, Qi Hao 等

Navigating a nonholonomic robot in a cluttered, unknown environment requires accurate perception and precise motion control for real-time collision avoidance. This article presents neural proximal alternating-minimization network (NeuPAN): a real-time, highly accurate, map-free, easy-to-deploy, and environment-invariant robot motion planner. Leveraging a tightly coupled perception-to-control framework, NeuPAN has two key innovations compared to existing approaches: first, it directly maps raw point cloud data to a latent distance feature space for collision-free motion generation, avoiding error propagation from the perception to control pipeline; second, it is interpretable from an end-to-end model-based learning perspective. The crux of NeuPAN is solving an end-to-end mathematical model with numerous point-level constraints using a plug-and-play proximal alternating-minimization network, incorporating neurons in the loop. This allows NeuPAN to generate real-time, physically interpretable motions. It seamlessly integrates data and knowledge engines, and its network parameters can be fine-tuned via back propagation. We evaluate NeuPAN on a ground mobile robot, a wheel-legged robot, and an autonomous vehicle, in extensive simulated and real-world environments. Results demonstrate that NeuPAN outperforms existing baselines in terms of accuracy, efficiency, robustness, and generalization capabilities across various environments, including the cluttered sandbox, office, corridor, and parking lot. We show that NeuPAN works well in unknown and unstructured environments with arbitrarily shaped objects, transforming impassable paths into passable ones.

Martin Gebser, Enrico Giunchiglia, Marco Maratea, Marco Mochi

Stable models of logic programs have been studied and characterized in relation with other formalisms by many researchers. As already argued in previous papers, such characterizations are interesting for diverse reasons, including theoretical investigations and the possibility of leading to new algorithms for computing stable models of logic programs. At the theoretical level, complexity and expressiveness comparisons have brought about fundamental insights. Beyond that, practical implementations of the developed reductions enable the use of existing solvers for other logical formalisms to compute stable models. In this paper, we first provide a simple characterization of stable models that can be viewed as a proof-theoretic counterpart of the standard model-theoretic definition. We further show how it can be naturally encoded in difference logic. Such an encoding, compared to the existing reductions to classical logics, does not require Boolean variables. Then, we implement our novel translation to a Satisfiability Modulo Theories (SMT) formula. We finally compare our approach, employing the SMT solver yices, to the translation-based ASP solver lp2diff and to clingo on domains from the “Basic Decision” track of the 2017 Answer Set Programming competition. The results show that our approach is competitive to and often better than lp2diff, and that it can also be faster than clingo on non-tight domains.

Marcos V. Ferreira, Matheus Souza, Tatiane N. Rios, Islame F. C. Fernandes, Jorge Nery, João Gama, Albert Bifet, Ricardo A. Rios

Efficient public transportation management is essential for the development of large urban centers, providing several benefits such as comprehensive coverage of population mobility, reduction of transport costs, better control of traffic congestion, and significant reduction of environmental impact limiting gas emissions and pollution. Realizing these benefits requires a deeply understanding the population and transit patterns and the adoption of approaches to model multiple relations and characteristics efficiently. This work addresses these challenges by providing a novel dataset that includes various public transportation components from three different systems: regular buses, subway, and BRT (Bus Rapid Transit). Our dataset comprises daily information from about 700,000 passengers in Salvador, one of Brazil’s largest cities, and local public transportation data with approximately 2,000 vehicles operating across nearly 400 lines, connecting almost 3,000 stops and stations. With data collected from March 2024 to March 2025 at a frequency lower than one minute, SUNT stands as one of the largest, most comprehensive, and openly available urban datasets in the literature.

Fu Feng, Jing Wang, Xu Yang, Xin Geng

Biological intelligence has driven significant progress in artificial intelligence (AI), but a critical gap remains: biological systems inherit innate abilities from genes, with brains initialized by blueprints refined over 3.5 billion years of evolution, while machines rely heavily on inefficient, data-driven learning from scratch. This gap arises from the lack of a genetic mechanism in machines to transfer and accumulate inheritable knowledge across generations. To bridge this gap, we propose learngenes, network fragments that act as inheritable 'genes' for machines. Unlike conventional knowledge transfer methods, learngenes enable efficient and universal knowledge transfer by selectively encapsulating task-agnostic knowledge. To facilitate the transfer and accumulation of task-agnostic knowledge across generations, we introduce Genetic Reinforcement Learning (GRL), a framework that simulates the learning and evolution of organisms in intelligent agents following Lamarckian principles. Through GRL, we identify learngenes as network fragments within agents' policy networks, equipping newborn agents with innate abilities for rapid adaptation to novel tasks. We demonstrate the advantages of learngene-based knowledge transfer over evolution-based search and traditional pre-trained models, and show how learngenes evolve through the accumulation of task-agnostic knowledge. Overall, this work establishes a novel paradigm for knowledge transfer and model initialization in AI, offering new possibilities for more adaptive, efficient, and scalable learning systems.

Mourad El Hamri, Younès Bennani, Issam Falih

Domain adaptation arises as an important problem in statistical learning theory, arising when the data-generating processes differ between the training and test samples, respectively called source and target domains. Recent theoretical advances have demonstrated that the success of domain adaptation algorithms heavily relies on their ability to minimize the divergence between the probability distributions of the source and target domains. However, minimizing this divergence cannot be achieved independently of other key ingredients, such as the source risk or the combined error of the ideal joint hypothesis. The trade-off between these terms is often ensured through algorithmic solutions that remain implicit and are not directly reflected by the theoretical guarantees. To get to the bottom of this issue, we propose in this paper a new theoretical framework for domain adaptation through hierarchical optimal transport. This framework provides more explicit generalization bounds and enables us to consider the natural hierarchical organization of samples in both domains into structures, i.e. classes or clusters. Additionally, we provide a new divergence measure between the source and target domains called Hierarchical Wasserstein distance that indicates under mild assumptions, which structures need to be aligned to achieve successful adaptation.

Nayana Dasgupta, Mirco Musolesi

Solving the problem of cooperation is fundamentally important for the creation and maintenance of functional societies. Problems of cooperation are omnipresent within human society, with examples ranging from navigating busy road junctions to negotiating treaties. As the use of AI becomes more pervasive throughout society, the need for socially intelligent agents capable of navigating these complex cooperative dilemmas is becoming increasingly evident. Direct punishment is a ubiquitous social mechanism that has been shown to foster the emergence of cooperation in both humans and non-humans. In the natural world, direct punishment is often strongly coupled with partner selection and reputation and used in conjunction with third-party punishment. The interactions between these mechanisms could potentially enhance the emergence of cooperation within populations. However, no previous work has evaluated the learning dynamics and outcomes emerging from multi-agent reinforcement learning populations that combine these mechanisms. This paper addresses this gap. It presents a comprehensive analysis and evaluation of the behaviors and learning dynamics associated with direct punishment, third-party punishment, partner selection, and reputation. Finally, we discuss the implications of using these mechanisms on the design of cooperative AI systems.

Jing Chen, Bo Li, Yingkai Li

In this paper we design information elicitation mechanisms for Bayesian auctions. While in Bayesian mechanism design the distributions of the players’ private types are often assumed to be common knowledge, information elicitation considers the situation where the players know the distributions better than the decision maker. To weaken the information assumption in Bayesian auctions, we consider an information structure where the knowledge about the distributions is arbitrarily scattered among the players. In such an unstructured information setting, we design mechanisms for unit-demand auctions and additive auctions that aggregate the players’ knowledge, generating revenue that are constant approximations to the optimal Bayesian mechanisms with a common prior. Our mechanisms are 2-step dominant-strategy truthful, and the approximation ratios improve gracefully with the amount of knowledge the players collectively have.

Jatin Chaudhary, Dipak Nidhi, Jukka Heikkonen, Harri Merisaari, Rajeev Kumar Kanth

This paper presents a theoretically grounded optimization framework for neural network training that integrates an Exponentially Decaying Learning Rate with Lyapunov-based stability analysis. We develop a dynamic learning rate algorithm and prove that it induces connected and stable descent paths through the loss landscape by maintaining the connectivity of super-level sets Sλ = {θ ∈ ℝn : ℒ(θ) ≥ λ}. Under the condition that the Lyapunov function V(θ) = ℒ(θ) satisfies Δ V(θ) ⋅ Δ ℒ(θ) ≥ 0, we establish that these super-level sets are not only connected but also equiconnected across epochs, providing uniform topological stability. We further derive convergence guarantees using a second-order Taylor expansion and demonstrate that our exponentially scheduled learning rate with gradient-based modulation leads to a monotonic decrease in loss. The proposed algorithm incorporates this schedule into a stability-aware update mechanism that adapts step sizes based on both curvature and energy-level geometry. This work formalizes the role of topological structure in convergence dynamics and introduces a provably stable optimization algorithm for high-dimensional, non-convex neural networks.

João Carvalho, An Thai Le, Piotr Kicki, Dorothea Koert, Jan Peters

The performance of optimization-based robot motion planning algorithms is highly dependent on the initial solutions, commonly obtained by running a sampling-based planner to obtain a collision-free path. However, these methods can be slow in high-dimensional and complex scenes and produce nonsmooth solutions. Given previously solved path-planning problems, it is highly desirable to learn their distribution and use it as a prior for new similar problems. Several works propose utilizing this prior to bootstrap the motion planning problem, either by sampling initial solutions from it, or using its distribution in a maximum-a-posterior formulation for trajectory optimization. In this work, we introduce motion planning diffusion (MPD), an algorithm that learns trajectory distribution priors with diffusion models. These generative models have shown increasing success in encoding multimodal data and have desirable properties for gradient-based motion planning, such as cost guidance. Given a motion planning problem, we construct a cost function and sample from the posterior distribution using the learned prior combined with the cost function gradients during the denoising process. Instead of learning the prior on all trajectory waypoints, we propose learning a lower dimensional representation of a trajectory using linear motion primitives, particularly B-spline curves. This parametrization guarantees that the generated trajectory is smooth, can be interpolated at higher frequencies, and needs fewer parameters than a dense waypoint representation. We demonstrate the results of our method ranging from simple 2-D to more complex tasks using a 7-DOF robot arm manipulator. In addition to learning from simulated data, we also use human demonstrations on a real-world pick-and-place task. The experiment results show that diffusion models are strong priors for encoding multimodal trajectory distributions for optimization-based motion planning.

Christian Brommer, Alessandro Fornasier, Jan Steinbrener, Stephan Weiss

We present a method for the unattended gray-box identification of sensor models commonly used by localization algorithms in the field of robotics. The objective is to determine the most likely sensor model for a time series of unknown measurement data, given an extendable catalog of predefined sensor models. Sensor model definitions may require states for rigid-body calibrations and dedicated reference frames to replicate a measurement based on the robot’s localization state. A health metric is introduced, which verifies the outcome of the selection process in order to detect false positives and facilitate reliable decision-making. In the second stage, an initial guess for identified calibration states is generated, and the necessity of sensor world reference frames is evaluated. The identified sensor model with its parameter information is then used to parameterize and initialize a state estimation application, thus ensuring a more accurate and robust integration of new sensor elements. This method is helpful for inexperienced users who want to identify the source and type of a measurement, sensor calibrations, or sensor reference frames. It will also be important in the field of modular multiagent scenarios and modularized robotic platforms that are augmented by sensor modalities during runtime. Overall, this work aims to provide a simplified integration of sensor modalities to downstream applications and circumvent common pitfalls in the usage and development of localization approaches.

Rahul Bordoloi, Clémence Réda, Orell Trautmann, Saptarshi Bej, Olaf Wolkenhauer

The more extensive access to time-series data, especially for biomedical purposes, raises new methodological challenges, particularly regarding missing values. Functional linear discriminant analysis (FLDA) extends Linear Discriminant Analysis (LDA)-mediated multiclass classification and dimension reduction to data in the form of fragmented observations of a univariate function. For large multivariate and partially-observed data, there are two challenges: (i) statistical dependencies between different components of a multivariate function and (ii) heterogeneous sampling times with missing features. We here develop a multivariate version of FLDA, called MUDRA, to tackle these challenges and describe a computationally efficient expectation/conditional-maximisation (ECM) algorithm to infer its parameters without any tensor inversions. We assess its predictive power on the “Articulary Words” dataset and show its improvement over the state-of-the-art, especially in the case of missing data. This advancement in dimension reduction of multivariate functional data holds promise for enhancing classification accuracy in scenarios like partially observed short multivariate time series analysis.

Amanjot Bhullar, Michael Czomko, R. Ayesha Ali, Douglas L. Welch

Artificial neural networks are popular for computer vision as they often give state-of-the-art performance, but are difficult to interpret because of their complexity. This black box modeling is especially troubling when the application concerns human well-being such as in medical image analysis or autonomous driving. In this work, we propose a technique called routing path visualization for capsule networks, which reveals how much of each region in an image is routed to each capsule. In turn, this technique can be used to interpret the entity that a given capsule detects, and speculate how the network makes a prediction. We demonstrate our new visualization technique on several real world datasets. Experimental results suggest that routing path visualization can precisely localize the predicted class from an image, even though the capsule networks are trained using just images and their respective class labels, without additional information defining the location of the class in the image.

Jovana Aleksic, Miguel García-Remesal

Many mainstream machine learning approaches, such as neural networks, are not well suited to work with imbalanced data. Yet, this problem is frequently present in many real-world data sets. Collection methods are imperfect, and often not able to capture enough data in a specific range of the target variable. Furthermore, in certain tasks data is inherently imbalanced with many more normal events than edge cases. This problem is well studied within the classification context. However, only several methods have been proposed to deal with regression tasks. In addition, the proposed methods often not yield good performance with high-dimensional data, while imbalanced high-dimensional regression has scarcely been explored. In this paper we present a selective under-sampling (SUS) algorithm for dealing with imbalanced regression and its iterative version SUSiter. We assessed this method on 15 regression data sets from different imbalanced domains, 5 synthetic high-dimensional imbalanced data sets and 2 more complex imbalanced age estimation image data sets. Our results suggest that SUS and SUSiter typically outperform other state-of-the-art techniques like SMOGN, or random under-sampling, when used with neural networks as learners.

Sara A. Al-Emadi, Yin Yang, Ferda Ofli

Deep learning models are designed based on the i.i.d. assumption; consequently, they experience a significant performance drop due to the distribution shifts when deployed in real environments. Domain Generalisation (DG) aims to bridge the distribution shift between the source and target domains by improving the generalisability of the model to Out-Of-Distribution (OOD) data. This challenge is prominent in satellite imagery classification due to the scarcity of data from underrepresented regions such as Africa and Oceania. In this paper, we address the limitations of existing datasets in capturing distribution shifts caused by geospatial differences between geographic regions by constructing a new, large-scale dataset called Domain Shift across Geographic Regions (DSGR). This dataset aims to help researchers better understand the impact of distribution shifts on satellite imagery classification. Furthermore, we perform rigorous experiments on DSGR to investigate and benchmark the robustness of existing DG techniques under single- and multi-source domain settings and the role of foundation models in enhancing the DG techniques. Our evaluations reveal that recent DG techniques have a comparable, yet weak, performance on DSGR. However, when combined with a foundation model like CLIP, ERM (introduced in 1999) achieves highly competitive results, surpassing even recent state-of-the-art DG solutions in enhancing the generalisability of deep learning models across different geographic regions. Our dataset and code are available at https://github.com/RWGAI/DSGR.

Ursula Addison

An autonomous agent deployed to operate over extended horizons in uncertain environments will encounter situations for which it was not designed. A class of these situations involves an invalidation of agent goals and limited guidance in establishing a new set of goals to pursue. An agent will benefit from some mechanism that will allow it to pursue new goals under these circumstances such that the goals are broadly useful in its environment and take advantage of its existing skills while aligning with societal norms. We propose augmenting a goal reasoning agent, i.e., an agent that can deliberate on and self-select its goals, with a motivation system that can be used to both constrain and motivate agent behavior. A human-like motivation system coupled with a goal-self concordant selection technique allows the approach to be framed as an optimization problem in which the agent selects goals that have high utility while simultaneously in harmony with its motivations. Over the agent’s operational lifespan its motivation system adjusts incrementally to more closely reflect the reality of its goal reasoning and goal pursuit experiences. Experiments performed with an ablation testing technique comparing the average utility of goals achieved in the presence and absence of a motivation system suggest that the motivated version of the system leads to pursuing more useful goals than the baseline.

Ben Zhou

Large Language Models (LLMs) have advanced rapidly and raised the bar for what AI is expected to do. However, accompanied with such progress is a stronger consensus that these models consistently fail in out-of-distribution reasoning, especially on tasks that require abstraction, transfer, or long-horizon planning. While acceptable for most consumer use, these issues prevent AI from being safely deployed in high-stakes settings (e.g., healthcare), where stakeholders cannot trust AI models that exhibit uncontrollable and unpredictable failures. In this talk, I will discuss our work and insights on how to make LLM reasoning controllable and trustworthy, by 1) understanding the mechanisms of LLM reasoning and predicting when LLM will fail; 2) improving model reasoning and generalization based on such insights; and 3) moving towards trustworthy AI applications through such improvements, and identifying new problems to form a healthy positive-feedback loop.

Wenxuan Zhang

Large language models (LLMs) have advanced rapidly, yet their development remains disproportionately focused on a few high-resource languages, leaving fundamental scientific and societal questions about multilingual capability, safety, and equity unresolved. This talk examines multilingual LLMs as a lens for understanding these challenges. I will first discuss observations from large-scale evaluations with real-world natural data, which reveal substantial performance gaps and highlight the need to treat multilingualism as a multidimensional construct. I then turn to safety, presenting work that uncovers multilingual jailbreak vulnerabilities and introduces frameworks for achieving more consistent cross-lingual alignment. Building on analyses of language-specific internal mechanisms, I will outline new strategies for enhancing multilingual systems and describe open-source efforts such as the SeaLLMs and Babel projects that aim to broaden linguistic and cultural inclusivity. Finally, I will discuss emerging directions beyond language, including recent findings on abstract thought in LLMs, which point toward the development of models that are not only multilingual but genuinely multicultural and contextually grounded.

Weitong Zhang

In this New Faculty Highlights, I begin with the reward free exploration that learns broad state and skill coverage with intrinsic rewards and remains robust under misspecification during efficient finetuning; guided generation methods that preserve the prior policy and mitigate reward hacking; and AI for science and healthcare, including practical RL for autonomous laboratories and automatic diagnosis. Building on impacts evidenced by publications, adoption, and awards. My future work will pursue imitation learning and contextual multi task RL that connect behavioral cloning with interactive policies without explicit reward design; personalized and multi-tasked offline to online adaptation with in-context demonstrations. In parallel, I am broadening the impact of AI for science and healthcare through existing collaborations. I will close with a talk that surveys these results and outlines an agenda for reinforcement learning without explicit rewards.

Chenyu You

Artificial intelligence is rapidly transforming biomedical imaging, from tumor segmentation to multimodal diagnosis, but reliable deployment in hospitals remains a pressing challenge. Models often struggle with limited labeled data, fail to generalize across scanners and institutions, and lack theoretical guarantees needed for safety-critical decisions. In this talk, I will present our research on overcoming these challenges. I will discuss label-efficient and class-imbalanced learning methods that make effective use of large-scale unlabeled data, theoretical frameworks that embed statistical principles into deep learning for stability and reliability, and medical foundation models that provide universal anatomical priors with lightweight refinement for diverse clinical settings. Together, these advances move biomedical AI beyond benchmark performance toward systems that are robust, generalizable, and clinically actionable.

Jaehong Yoon

Our world is constantly evolving, and human beings continuously enhance their knowledge by learning from their experiences throughout life. Despite significant advancements in embodied AI, current agents struggle to operate reliably, robustly, and continually in complex, real-world multimodal environments due to complex problems that span large and diverse domains, especially when faced with out-of-distribution (OOD) scenarios they have not previously encountered. Our goal is to develop a multimodal, embodied AI system that continually enhances its capabilities and skills through safe and robust interactions with an ever-changing, multimodal world. This is enabled by a novel, adaptively expandable memory architecture that integrates both long- and short-term information across multiple modalities. The system selectively decides what to store and learn, filtering out adversarial or low-quality inputs to prevent negative transfer and distractions, while improving overall efficiency and effectiveness.