Land surface temperature (LST) retrieval from remote sensing data is pivotal for analyzing climate processes and surface energy budgets. However, LST retrieval is an ill-posed inverse problem, which becomes particularly severe when only a single band is available. In this paper, we propose a deeply coupled framework integrating mechanistic modeling and machine learning to enhance the accuracy and generalizability of single-channel LST retrieval. Training samples are generated using a physically-based radiative transfer model and a global collection of 5810 atmospheric profiles. A physics-informed machine learning framework is proposed to systematically incorporate the first principles from classical physical inversion models into the learning workflow, with optimization constrained by radiative transfer equations. Global validation demonstrated a 30% reduction in root-mean-square error versus standalone methods. Under extreme humidity, the mean absolute error decreased from 4.87 K to 2.29 K (53% improvement). Continental-scale tests across five continents confirmed the superior generalizability of this model.

This paper explores uncertainty quantification (UQ) methods in the context of Kolmogorov-Arnold Networks (KANs). We apply an ensemble approach to KANs to obtain a heuristic measure of UQ, enhancing interpretability and robustness in modeling complex functions. Building on this, we introduce Conformalized-KANs, which integrate conformal prediction, a distribution-free UQ technique, with KAN ensembles to generate calibrated prediction intervals with guaranteed coverage. Extensive numerical experiments are conducted to evaluate the effectiveness of these methods, focusing particularly on the robustness and accuracy of the prediction intervals under various hyperparameter settings. We show that the conformal KAN predictions can be applied to recent extensions of KANs, including Finite Basis KANs (FBKANs) and multifideilty KANs (MFKANs). The results demonstrate the potential of our approaches to improve the reliability and applicability of KANs in scientific machine learning.

With the widespread availability of sensor data across industrial and operational systems, we frequently encounter heterogeneous time series from multiple systems. Anomaly detection is crucial for such systems to facilitate predictive maintenance. However, most existing anomaly detection methods are designed for either univariate or single-system multivariate data, making them insufficient for these complex scenarios. To address this, we introduce M$^2$AD, a framework for unsupervised anomaly detection in multivariate time series data from multiple systems. M$^2$AD employs deep models to capture expected behavior under normal conditions, using the residuals as indicators of potential anomalies. These residuals are then aggregated into a global anomaly score through a Gaussian Mixture Model and Gamma calibration. We theoretically demonstrate that this framework can effectively address heterogeneity and dependencies across sensors and systems. Empirically, M$^2$AD outperforms existing methods in extensive evaluations by 21% on average, and its effectiveness is demonstrated on a large-scale real-world case study on 130 assets in Amazon Fulfillment Centers. Our code and results are available at https://github.com/sarahmish/M2AD.

The rapid expansion of generative AI is driving unprecedented demands for high-performance computing. Training large-scale AI models now requires vast interconnected GPU clusters across multiple data centers. Multi-scale AI training and inference demand uniform, ultra-low latency, and energy-efficient links to enable massive GPUs to function as a single cohesive unit. However, traditional electrical and optical interconnects, which rely on conventional digital signal processors (DSPs) for signal distortion compensation, are increasingly unable to meet these stringent requirements. To overcome these limitations, we present an integrated neuromorphic optical signal processor (OSP) that leverages deep reservoir computing and achieves DSP-free, all-optical, real-time processing. Experimentally, our OSP achieves a 100 Gbaud PAM4 per lane, 1.6 Tbit/s data center interconnect over a 5 km optical fiber in the C-band (equivalent to over 80 km optical fiber in the O-band), far exceeding the reach of state-of-the-art DSP solutions, which are fundamentally constrained by chromatic dispersion 1 arXiv:2504.15044v1 Simultaneously, it delivers a four-orders-of-magnitude reduction in processing latency and a three-orders-of-magnitude reduction in energy consumption. Unlike DSPs, which introduce increased latency at high data rates, our OSP maintains consistent, ultra-low latency regardless of data rate scaling, making it an ideal solution for future optical interconnects. Moreover, the OSP retains full optical field information for better impairment compensation and adapts to various modulation formats, data rates, and wavelengths. Fabricated using a mature silicon photonic process, the OSP can be monolithically integrated with silicon photonic transceivers, enhancing the compactness and reliability of all-optical interconnects. This research provides a highly scalable, energy-efficient, and high-speed solution, paving the way for next-generation AI infrastructure. Keywords: Photonic neural network, optical interconnect, AI infrastructure, data center 1 Introduction The surging demand for artificial intelligence and machine learning (AI/ML), especially in generative AI, has driven unprecedented requirements for high-performance computing infrastructure.

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.