To bridge this crucial gap, first, this paper presents a comprehensive benchmark suite to evaluate the out-of-distribution (OOD) performance of image compression methods.

The background model is trained byperturbing aproportion ofrandomly chosen pixels,wheretheperturbation isdonebyreplacing the pixel value by a uniformly sampled random value between 0 and 255.

These disagreements raise the question: which, if any, of these dissimilarity measures should we believe?

A formal link between regression and classification has been tenuous. Even though the margin maximization term $\|w\|$ is used in support vector regression, it has at best been justified as a regularizer. We show that a regression problem with $M$ samples lying on a hyperplane has a one-to-one equivalence with a linearly separable classification task with $2M$ samples. We show that margin maximization on the equivalent classification task leads to a different regression formulation than traditionally used. Using the equivalence, we demonstrate a ``regressability'' measure, that can be used to estimate the difficulty of regressing a dataset, without needing to first learn a model for it. We use the equivalence to train neural networks to learn a linearizing map, that transforms input variables into a space where a linear regressor is adequate.

--This paper presents a framework for processing EV charging load data in order to forecast future load predictions using a Recurrent Neural Network, specifically an LSTM. The framework processes a large set of raw data from multiple locations and transforms it with normalization and feature extraction to train the LSTM. The pre-processing stage corrects for missing or incomplete values by interpolating and normalizing the measurements. This information is then fed into a Long Short-T erm Memory Model designed to capture the short-term fluctuations while also interpreting the long-term trends in the charging data. Experimental results demonstrate the model's ability to accurately predict charging demand across multiple time scales (daily, weekly, and monthly), providing valuable insights for infrastructure planning, energy management, and grid integration of EV charging facilities. The system's modular design allows for adaptation to di fferent charging locations with varying usage patterns, making it applicable across diverse deployment scenarios. I. INTRODUCTION The transition to electric vehicles (EVs) is crucial for mitigating climate change by reducing greenhouse gas emissions and reliance on fossil fuels. However, as EV adoption increases [1], the installation of numerous EV charging stations (EVCS) poses challenges to electric grids, particularly in dense communities. The increased demand for EVCS strains electric grid systems, leading to issues such as voltage drops and transformer overloads. Understanding these problems and their impacts is crucial for optimizing grid performance and ensuring sustainable EV infrastructure development. Therefore, accurately predicting EVCS load demand helps manage grid load, improve power network e fficiency, and ensure reliable customer access to charging stations.

Large audio-language models (LALMs) unify speech and text processing, but their robustness in noisy real-world settings remains underexplored. We investigate how irrelevant audio, such as silence, synthetic noise, and environmental sounds, affects text reasoning tasks where audio is unnecessary. Across three text-based benchmarks, we find that even non-informative audio reduces accuracy and increases prediction volatility; the severity of interference scales with longer durations, higher amplitudes, and elevated decoding temperatures. Silence, often assumed neutral, destabilizes outputs as strongly as synthetic noise. While larger models show greater resilience, vulnerabilities persist across all evaluated systems. We further test mitigation strategies and find that prompting shows limited effectiveness, whereas self-consistency improves stability at the cost of increased computation. Our results reveal cross-modal interference as a key robustness challenge and highlight the need for efficient fusion strategies that preserve reasoning performance in the presence of irrelevant inputs.

--The intersection of generative AI and art is a fascinating area that brings both exciting opportunities and significant challenges, especially when it comes to identifying synthetic artworks. This study takes a unique approach by examining diffusion-based generative models in the context of Indian art, specifically focusing on the distinctive style of Jamini Roy. T o explore this, we fine-tuned Stable Diffusion 3 and used techniques like ControlNet and IPAdapter to generate realistic images. This allowed us to create a new dataset that includes both real and AI-generated artworks, which is essential for a detailed analysis of what these models can produce. We employed various qualitative and quantitative methods, such as Fourier domain assessments and autocorrelation metrics, to uncover subtle differences between synthetic images and authentic pieces. A key takeaway from recent research is that existing methods for detecting deep-fakes face considerable challenges, especially when the deepfakes are of high quality and tailored to specific cultural contexts. This highlights a critical gap in current detection technologies, particularly in light of the challenges identified above, where high-quality and culturally specific deepfakes are difficult to detect. This work not only sheds light on the increasing complexity of generative models but also sets a crucial foundation for future research aimed at effective detection of synthetic art. With the rapid advancement of artificial intelligence, the realm of art generation has undergone profound transformation, utilizing various methods to create incredibly realistic and complex digital artwork.

Large Language Models (LLMs) have revolutionized various Natural Language Generation (NLG) tasks, including Argument Summarization (ArgSum), a key subfield of Argument Mining (AM). This paper investigates the integration of state-of-the-art LLMs into ArgSum, including for its evaluation. In particular, we propose a novel prompt-based evaluation scheme, and validate it through a novel human benchmark dataset. Our work makes three main contributions: (i) the integration of LLMs into existing ArgSum frameworks, (ii) the development of a new LLM-based ArgSum system, benchmarked against prior methods, and (iii) the introduction of an advanced LLM-based evaluation scheme. We demonstrate that the use of LLMs substantially improves both the generation and evaluation of argument summaries, achieving state-of-the-art results and advancing the field of ArgSum.