arXiv:2507.01613v2 Announce Type: replace-cross Abstract: Paired comparison data, where users evaluate items in pairs, play a central role in ranking and preference learning tasks. While ordinal comparison data intuitively offer richer information than binary comparisons, this paper challenges that conventional…
arXiv:2510.09660v1 Announce Type: new Abstract: Diffusion Probabilistic Models (DPMs) have achieved strong generative performance, yet their inductive biases remain largely implicit. In this work, we aim to build inductive biases into the training and sampling of diffusion models to better…
arXiv:2510.09662v1 Announce Type: new Abstract: Electrochemical impedance spectroscopy (EIS) data is typically modeled using an equivalent circuit model (ECM), with parameters obtained by minimizing a loss function via nonlinear least squares fitting. This paper introduces two new loss functions, log-B…
arXiv:2510.09659v1 Announce Type: new Abstract: NOvA is a long-baseline neutrino oscillation experiment that detects neutrino particles from the NuMI beam at Fermilab. Before data from this experiment can be used in analyses, raw hits in the detector must be matched…
arXiv:2510.09658v1 Announce Type: new Abstract: When a new release of a foundation model is published, practitioners typically need to repeat full fine-tuning, even if the same task has already been solved in the previous version. A promising alternative is to…
arXiv:2510.09657v1 Announce Type: new Abstract: Accurate simulation of wave propagation in complex acoustic materials is crucial for applications in sound design, noise control, and material engineering. Traditional numerical solvers, such as finite element methods, are computationally expensive, especially when dealing…
arXiv:2510.09174v2 Announce Type: replace Abstract: This paper takes a closer look at Git Re-Basin, an interesting new approach to merge trained models. We propose a hierarchical model merging scheme that significantly outperforms the standard MergeMany algorithm. With our new algorithm,…
arXiv:2510.09665v1 Announce Type: new Abstract: Today’s LLM inference systems treat individual engines and queries independently for simplicity, but this causes significant resource inefficiencies. While there are proposals to avoid redundant computation by reusing KV caches across queries and to increase…
arXiv:2502.18940v2 Announce Type: replace-cross Abstract: Evaluating the pedagogical capabilities of AI-based tutoring models is critical for making guided progress in the field. Yet, we lack a reliable, easy-to-use, and simple-to-run evaluation that reflects the pedagogical abilities of models. To fill…
arXiv:2510.09666v1 Announce Type: new Abstract: Climate change is intensifying wildfire risks globally, making reliable forecasting critical for adaptation strategies. While machine learning shows promise for wildfire prediction from Earth observation data, current approaches lack uncertainty quantification essential for risk-aware decision…
