We introduce a multiple criteria Bayesian preference learning framework incorporating behavioral cues for decision aiding. The framework integrates pairwise comparisons, response time, and attention duration to deepen insights into decision-making processes. The approach employs an additive value function model and utilizes a Bayesian framework to derive the posterior distribution of potential ranking models by defining the likelihood of observed preference data and specifying a prior on the preference structure. This distribution highlights each model's ability to reconstruct Decision-Makers' holistic pairwise comparisons. By leveraging both response time as a proxy for cognitive effort and alternative discriminability as well as attention duration as an indicator of criterion importance, the proposed model surpasses traditional methods by uncovering richer behavioral patterns. We report the results of a laboratory experiment on mobile phone contract selection involving 30 real subjects using a dedicated application with time-, eye-, and mouse-tracking components. We validate the novel method's ability to reconstruct complete preferences. The detailed ablation studies reveal time- and attention-related behavioral patterns, confirming that integrating comprehensive data leads to developing models that better align with the DM's actual preferences.

The small sample imbalance (S&I) problem is a major challenge in machine learning and data analysis. It is characterized by a small number of samples and an imbalanced class distribution, which leads to poor model performance. In addition, indistinct inter-class feature distributions further complicate classification tasks. Existing methods often rely on algorithmic heuristics without sufficiently analyzing the underlying data characteristics. We argue that a detailed analysis from the data perspective is essential before developing an appropriate solution. Therefore, this paper proposes a systematic analytical framework for the S\&I problem. We first summarize imbalance metrics and complexity analysis methods, highlighting the need for interpretable benchmarks to characterize S&I problems. Second, we review recent solutions for conventional, complexity-based, and extreme S&I problems, revealing methodological differences in handling various data distributions. Our summary finds that resampling remains a widely adopted solution. However, we conduct experiments on binary and multiclass datasets, revealing that classifier performance differences significantly exceed the improvements achieved through resampling. Finally, this paper highlights open questions and discusses future trends.

Machine learning (ML)-based planners have recently gained significant attention. They offer advantages over traditional optimization-based planning algorithms. These advantages include fewer manually selected parameters and faster development. Within ML-based planning, imitation learning (IL) is a common algorithm. It primarily learns driving policies directly from supervised trajectory data. While IL has demonstrated strong performance on many open-loop benchmarks, it remains challenging to determine if the learned policy truly understands fundamental driving principles, rather than simply extrapolating from the ego-vehicle's initial state. Several studies have identified this limitation and proposed algorithms to address it. However, these methods often use original datasets for evaluation. In these datasets, future trajectories are heavily dependent on initial conditions. Furthermore, IL often overfits to the most common scenarios. It struggles to generalize to rare or unseen situations. To address these challenges, this work proposes: 1) a novel closed-loop simulator supporting both imitation and reinforcement learning, 2) a causal benchmark derived from the Waymo Open Dataset to rigorously assess the impact of the copycat problem, and 3) a novel framework integrating imitation learning and reinforcement learning to overcome the limitations of purely imitative approaches. The code for this work will be released soon.

Published as a workshop paper at "Tackling Climate Change with Machine Learning", ICLR 2025 Accurate ocean modeling and coastal hazard prediction depend on high-resolution bathymetric data; yet, current worldwide datasets are too coarse for exact numerical simulations. While recent deep learning advances have improved earth observation data resolution, existing methods struggle with the unique challenges of producing detailed ocean floor maps, especially in maintaining physical structure consistency and quantifying uncertainties. This work presents a novel uncertainty-aware mechanism using spatial blocks to efficiently capture local bathymetric complexity based on block-based conformal prediction. Compared to conventional techniques, experimental results over several ocean regions show notable increases in both reconstruction quality and uncertainty estimation reliability. This framework increases the reliability of bathymetric reconstructions by preserving structural integrity while offering spatially adaptive uncertainty estimates, so opening the path for more solid climate modeling and coastal hazard assessment.Figure 1: Learning Enhanced Structural Representations with Block-Based Uncertainties 1 Simple diffusion equations to complex Navier-Stokes equations used in computational fluid dynamics (CFD) span these physical models, all of which depend on thorough bathymetric data to properly forecast tsunami propagation, storm surges, and the effects of sea level rise on coastal communities. The GEBCO project (General Bathymetric Chart of the Oceans), fuses multibeam sonar, satellite altimetry, and shipborne soundings, yet filling in sub-kilometer details globally would take on the order of two centuries at current survey rates Mayer et al. (2018). Enhancement is further complicated by three interrelated factors: (1) heterogeneous data sources with distinct error characteristics and regional resolution gaps; (2) the need to preserve sharp morphological boundaries, such as ridges, canyons, and trenches, that are critical for physical simulations; and (3) spatially varying data quality arising from different acquisition techniques (direct soundings vs. altimetry) that induce nonuniform uncertainty patterns.

--Large language model (LLM) pruning with fixed N:M structured sparsity significantly limits the expressivity of the sparse model, yielding sub-optimal performance. On the contrary, support for more than one N:M pattern to provide sparse representational freedom yields a costly overhead in the hardware. T o mitigate these challenges for LLMs, we first present a f lexible l ayer-wise o utlier-density-a ware N:M sparsity (FLOW) selection method. FLOW enables the identification of optimal layer-wise N and M values (from a given range) by simultaneously accounting for the presence and distribution of outliers, allowing a higher degree of representational freedom. T o deploy the sparse models with such N:M flexibility, we then present a flex ible low overhead, digital c ompute-i n-m emory architecture (FlexCiM). FlexCiM enables support for diverse sparsity patterns by partitioning a digital CiM (DCiM) macro into smaller sub-macros which are adaptively aggregated and disaggregated through distribution and merging mechanisms for different values of N and M. Extensive experiments on both transformer-based and recurrence-based state space foundation models (SSMs) demonstrate FLOW to outperform existing alternatives with an accuracy improvement of up to 36%, while FlexCiM delivers up to 1.75 lower inference latency and 1.5 lower energy consumption compared to existing sparse accelerators. To reduce the colossal size of large language models (LLMs) and enable their efficient deployment on resource-constrained devices, post-training pruning has emerged as an effective model compression method [9], [33], [37]. It reduces the memory footprint of the pre-trained LLMs by removing ineffectual model parameters, at the granularity of individual weights ( unstructured) or blocks of weights ( structured), and storing sparse tensors in a compressed format (CSR/CSC) [14]. Notably, model pruning may yield compute acceleration via skipping ineffectual computations associated with the zero-valued weight/activation. However, traditional weight pruning often requires fine-tuning, which becomes exceedingly compute-heavy for LLMs. Furthermore, this often requires the model to yield structured pruned weights, which can cause a high accuracy drop compared to the models pruned via an unstructured approach.

Large models such as Large Language Models (LLMs) and Vision Language Models (VLMs) have transformed artificial intelligence, powering applications in natural language processing, computer vision, and multimodal learning. However, fully fine-tuning these models remains expensive, requiring extensive computational resources, memory, and task-specific data. Parameter-Efficient Fine-Tuning (PEFT) has emerged as a promising solution that allows adapting large models to downstream tasks by updating only a small portion of parameters. This survey presents a comprehensive overview of PEFT techniques, focusing on their motivations, design principles, and effectiveness. We begin by analyzing the resource and accessibility challenges posed by traditional fine-tuning and highlight key issues, such as overfitting, catastrophic forgetting, and parameter inefficiency. We then introduce a structured taxonomy of PEFT methods -- grouped into additive, selective, reparameterized, hybrid, and unified frameworks -- and systematically compare their mechanisms and trade-offs. Beyond taxonomy, we explore the impact of PEFT across diverse domains, including language, vision, and generative modeling, showing how these techniques offer strong performance with lower resource costs. We also discuss important open challenges in scalability, interpretability, and robustness, and suggest future directions such as federated learning, domain adaptation, and theoretical grounding. Our goal is to provide a unified understanding of PEFT and its growing role in enabling practical, efficient, and sustainable use of large models.

The undergoing energy transition is causing behavioral changes in electricity use, e.g. with self-consumption of local generation, or flexibility services for demand control. To better understand these changes and the challenges they induce, accessing individual smart meter data is crucial. Yet this is personal data under the European GDPR. A widespread use of such data requires thus to create synthetic realistic and privacy-preserving samples. This paper introduces a new synthetic load curve dataset generated by conditional latent diffusion. We also provide the contracted power, time-of-use plan and local temperature used for generation. Fidelity, utility and privacy of the dataset are thoroughly evaluated, demonstrating its good quality and thereby supporting its interest for energy modeling applications.

Conducting data analysis typically involves authoring code to transform, visualize, analyze, and interpret data. Large language models (LLMs) are now capable of generating such code for simple, routine analyses. LLMs promise to democratize data science by enabling those with limited programming expertise to conduct data analyses, including in scientific research, business, and policymaking. However, analysts in many real-world settings must often exercise fine-grained control over specific analysis steps, verify intermediate results explicitly, and iteratively refine their analytical approaches. Such tasks present barriers to building robust and reproducible analyses using LLMs alone or even in conjunction with existing authoring tools (e.g., computational notebooks). This paper introduces Flowco, a new mixed-initiative system to address these challenges. Flowco leverages a visual dataflow programming model and integrates LLMs into every phase of the authoring process. A user study suggests that Flowco supports analysts, particularly those with less programming experience, in quickly authoring, debugging, and refining data analyses.

Battery degradation is a major challenge in electric vehicles (EV) and energy storage systems (ESS). However, most degradation investigations focus mainly on estimating the state of charge (SOC), which fails to accurately interpret the cells' internal degradation mechanisms. Differential capacity analysis (DCA) focuses on the rate of change of cell voltage about the change in cell capacity, under various charge/discharge rates. This paper developed a battery cell degradation testing model that used two types of lithium-ions (Li-ion) battery cells, namely lithium nickel cobalt aluminium oxides (LiNiCoAlO2) and lithium iron phosphate (LiFePO4), to evaluate internal degradation during loading conditions. The proposed battery degradation model contains distinct charge rates (DCR) of 0.2C, 0.5C, 1C, and 1.5C, as well as discharge rates (DDR) of 0.5C, 0.9C, 1.3C, and 1.6C to analyze the internal health and performance of battery cells during slow, moderate, and fast loading conditions. Besides, this research proposed a model that incorporates the Extended Kalman Filter (EKF), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM) networks to validate experimental data. The proposed model yields excellent modelling results based on mean squared error (MSE), and root mean squared error (RMSE), with errors of less than 0.001% at DCR and DDR. The peak identification technique (PIM) has been utilized to investigate battery health based on the number of peaks, peak position, peak height, peak area, and peak width. At last, the PIM method has discovered that the cell aged gradually under normal loading rates but deteriorated rapidly under fast loading conditions. Overall, LiFePO4 batteries perform more robustly and consistently than (LiNiCoAlO2) cells under varying loading conditions.

As our information environments become ever more powered by artificial intelligence (AI), the phenomenon of trust in a human's interactions with this intelligence is becoming increasingly pertinent. For example, in the not too distant future, there will be teams of humans and intelligent robots involved in dealing with the repercussions of high-risk disaster situations such as hurricanes, earthquakes, or nuclear accidents. Even in such conditions of high uncertainty, humans and intelligent machines will need to engage in shared decision making, and trust is fundamental to the effectiveness of these interactions. A key challenge in modeling the dynamics of this trust is to provide a means to incorporate sensitivity to fluctuations in human trust judgments. In this article, we explore the ability of Quantum Random Walk models to model the dynamics of trust in human-AI interactions, and to integrate a sensitivity to fluctuations in participant trust judgments based on the nature of the interaction with the AI. We found that using empirical parameters to inform the use of different Hamiltonians can provide a promising means to model the evolution of trust in Human-AI interactions.