Data imbalance persists as a pervasive challenge in regression tasks, introducing bias in model performance and undermining predictive reliability. This is particularly detrimental in applications aimed at predicting rare events that fall outside the domain of the bulk of the training data. In this study, we review the current state-of-the-art regarding sampling-based methods and cost-sensitive learning. Additionally, we propose novel approaches to mitigate model bias. To better asses the importance of data, we introduce the density-distance and density-ratio relevance functions, which effectively integrate empirical frequency of data with domain-specific preferences, offering enhanced interpretability for end-users. Furthermore, we present advanced mitigation techniques (cSMOGN and crbSMOGN), which build upon and improve existing sampling methods. In a comprehensive quantitative evaluation, we benchmark state-of-the-art methods on 10 synthetic and 42 real-world datasets, using neural networks, XGBoosting trees and Random Forest models. Our analysis reveals that while most strategies improve performance on rare samples, they often degrade it on frequent ones. We demonstrate that constructing an ensemble of models -- one trained with imbalance mitigation and another without -- can significantly reduce these negative effects. The key findings underscore the superior performance of our novel crbSMOGN sampling technique with the density-ratio relevance function for neural networks, outperforming state-of-the-art methods.

Statistical inference in physics is often based on samples from a generator (sometimes referred to as a ``forward model") that emulate experimental data and depend on parameters of the underlying theory. Modern machine learning has supercharged this workflow to enable high-dimensional and unbinned analyses to utilize much more information than ever before. We propose a general framework for describing the integration of machine learning with generators called Generator Based Inference (GBI). A well-studied special case of this setup is Simulation Based Inference (SBI) where the generator is a physics-based simulator. In this work, we examine other methods within the GBI toolkit that use data-driven methods to build the generator. In particular, we focus on resonant anomaly detection, where the generator describing the background is learned from sidebands. We show how to perform machine learning-based parameter estimation in this context with data-derived generators. This transforms the statistical outputs of anomaly detection to be directly interpretable and the performance on the LHCO community benchmark dataset establishes a new state-of-the-art for anomaly detection sensitivity.

Humanity is progressing towards automated product development, a trend that promises faster creation of better products and thus the acceleration of technological progress. However, increasing reliance on non-human agents for this process introduces many risks. This perspective aims to initiate a discussion on these risks and appropriate mitigation strategies. To this end, we outline a set of principles for safer AI-driven product development which emphasize human oversight, accountability, and explainable design, among others. The risk assessment covers both technical risks which affect product quality and safety, and sociotechnical risks which affect society. While AI-driven product development is still in its early stages, this discussion will help balance its opportunities and risks without delaying essential progress in understanding, norm-setting, and regulation.

Analog In-Memory Compute (AIMC) can improve the energy efficiency of Deep Learning by orders of magnitude. Yet analog-domain device and circuit non-idealities -- within the analog ``Tiles'' performing Matrix-Vector Multiply (MVM) operations -- can degrade neural-network task accuracy. We quantify the impact of low-level distortions and noise, and develop a mathematical model for Multiply-ACcumulate (MAC) operations mapped to analog tiles. Instantaneous-current IR-drop (the most significant circuit non-ideality), and ADC quantization effects are fully captured by this model, which can predict MVM tile-outputs both rapidly and accurately, as compared to much slower rigorous circuit simulations. A statistical model of PCM read noise at nanosecond timescales is derived from -- and matched against -- experimental measurements. We integrate these (statistical) device and (deterministic) circuit effects into a PyTorch-based framework to assess the accuracy impact on the BERT and ALBERT Transformer networks. We show that hardware-aware fine-tuning using simple Gaussian noise provides resilience against ADC quantization and PCM read noise effects, but is less effective against IR-drop. This is because IR-drop -- although deterministic -- is non-linear, is changing significantly during the time-integration window, and is ultimately dependent on all the excitations being introduced in parallel into the analog tile. The apparent inability of simple Gaussian noise applied during training to properly prepare a DNN network for IR-drop during inference implies that more complex training approaches -- incorporating advances such as the Tile-circuit model introduced here -- will be critical for resilient deployment of large neural networks onto AIMC hardware.

Post-training compression reduces the computational and memory costs of large language models (LLMs), enabling resource-efficient deployment. However, existing compression benchmarks only focus on language modeling (e.g., perplexity) and natural language understanding tasks (e.g., GLUE accuracy), ignoring the agentic capabilities - workflow, tool use/function call, long-context understanding and real-world application. We introduce the Agent Compression Benchmark (ACBench), the first comprehensive benchmark for evaluating how compression impacts LLMs' agentic abilities. ACBench spans (1) 12 tasks across 4 capabilities (e.g., WorfBench for workflow generation, Needle-in-Haystack for long-context retrieval), (2) quantization (GPTQ, AWQ) and pruning (Wanda, SparseGPT), and (3) 15 models, including small (Gemma-2B), standard (Qwen2.5 7B-32B), and distilled reasoning LLMs (DeepSeek-R1-Distill). Our experiments reveal compression tradeoffs: 4-bit quantization preserves workflow generation and tool use (1%-3% drop) but degrades real-world application accuracy by 10%-15%. We introduce ERank, Top-k Ranking Correlation and Energy to systematize analysis. ACBench provides actionable insights for optimizing LLM compression in agentic scenarios. The code can be found in https://github.com/pprp/ACBench.

The performance of Large Language Models (LLMs) is intrinsically linked to the quality of its training data. Although several studies have proposed methods for high-quality data selection, they do not consider the importance of knowledge richness in text corpora. In this paper, we propose a novel and gradient-free High-Knowledge Scorer (HKS) to select high-quality data from the dimension of knowledge, to alleviate the problem of knowledge scarcity in the pre-trained corpus. We propose a comprehensive multi-domain knowledge element pool and introduce knowledge density and coverage as metrics to assess the knowledge content of the text. Based on this, we propose a comprehensive knowledge scorer to select data with intensive knowledge, which can also be utilized for domain-specific high-knowledge data selection by restricting knowledge elements to the specific domain. We train models on a high-knowledge bilingual dataset, and experimental results demonstrate that our scorer improves the model's performance in knowledge-intensive and general comprehension tasks, and is effective in enhancing both the generic and domain-specific capabilities of the model.

Parametric differential equations of the form du/dt = f(u, x, t, p) are fundamental in science and engineering. While deep learning frameworks such as the Fourier Neural Operator (FNO) can efficiently approximate solutions, they struggle with inverse problems, sensitivity estimation (du/dp), and concept drift. We address these limitations by introducing a sensitivity-based regularization strategy, called Sensitivity-Constrained Fourier Neural Operators (SC-FNO). SC-FNO achieves high accuracy in predicting solution paths and consistently outperforms standard FNO and FNO with physics-informed regularization. It improves performance in parameter inversion tasks, scales to high-dimensional parameter spaces (tested with up to 82 parameters), and reduces both data and training requirements. These gains are achieved with a modest increase in training time (30% to 130% per epoch) and generalize across various types of differential equations and neural operators. Code and selected experiments are available at: https://github.com/AMBehroozi/SC_Neural_Operators

Powered by a large language model (LLM), a web browsing agent operates web browsers in a human-like manner and offers a highly transparent path toward automating a wide range of everyday tasks. As web agents become increasingly capable and demonstrate proficiency in general browsing tasks, a critical question emerges: Can they go beyond general browsing to robustly handle tasks that are tedious and complex, or chores that humans often avoid doing themselves? In this paper, we introduce WebChoreArena, a new fully reproducible benchmark comprising 532 carefully curated tasks designed to extend the scope of WebArena beyond general browsing to more labor-intensive and tedious tasks. WebChoreArena systematically integrates three key challenges: (i) Massive Memory tasks requiring accurate retrieval of large amounts of information in the observations, (ii) Calculation tasks demanding precise mathematical reasoning, and (iii) Long-Term Memory tasks necessitating long-term memory across multiple webpages. Built on top of the fully reproducible and widely adopted four WebArena simulation environments, WebChoreArena ensures strict reproducibility and enables fair, direct comparisons with the established WebArena benchmark, offering key insights into agent progress. Our experimental results demonstrate that as LLMs evolve, represented by GPT-4o, Claude 3.7 Sonnet, and Gemini 2.5 Pro, significant improvements in performance are observed on WebChoreArena. These findings suggest that WebChoreArena is well-suited to measure the advancement of state-of-the-art LLMs with greater clarity. Nevertheless, the results also indicate that even with Gemini 2.5 Pro, there remains substantial room for improvement compared to WebArena, highlighting the increased challenges posed by WebChoreArena.

As machine learning algorithms are shown to be an increasingly valuable tool, the demand for their access has grown accordingly. Oftentimes, it is infeasible to run inference with larger models without an accelerator, which may be unavailable in environments that have constraints such as energy consumption, security, or cost. To increase the availability of these models, we aim to improve the LLM inference speed on a CPU-only environment by modifying the cache architecture. To determine what improvements could be made, we conducted two experiments using Llama.cpp and the QWEN model: running various cache configurations and evaluating their performance, and outputting a trace of the memory footprint. Using these experiments, we investigate the memory access patterns and performance characteristics to identify potential optimizations.

Accurate localization is essential for a wide range of applications, including asset tracking, smart agriculture, and animal monitoring. While traditional localization methods, such as Global Navigation Satellite System (GNSS), Wi-Fi, and Bluetooth Low Energy (BLE), offer varying levels of accuracy and coverage, they have drawbacks regarding power consumption, infrastructure requirements, and deployment flexibility. Ultra-Wideband (UWB) is emerging as an alternative, offering centimeter-level accuracy and energy efficiency, especially suitable for medium to large field monitoring with capabilities to work indoors and outdoors. However, existing UWB localization systems require infrastructure with mains power to supply the anchors, which impedes their scalability and ease of deployment. This underscores the need for a fully battery-powered and energy-efficient localization system. This paper presents an energy-optimized, battery-operated UWB localization system that leverages Long Range Wide Area Network (LoRaWAN) for data transmission to a server backend. By employing single-sided two-way ranging (SS-TWR) in a time-slotted localization approach, the power consumption both on the anchor and the tag is reduced, while maintaining high accuracy. With a low average power consumption of 20.44 mW per anchor and 7.19 mW per tag, the system allows fully battery-powered operation for up to 25 days, achieving average accuracy of 13.96 cm with self-localizing anchors on a 600 m2 testing ground. To validate its effectiveness and ease of installation in a challenging application scenario, ten anchors and two tags were successfully deployed in a tropical zoological biome where they could be used to track Aldabra Giant Tortoises (Aldabrachelys gigantea).