arXiv:2505.17338v3 Announce Type: replace Abstract: Photorealistic volumetric rendering of CT scans greatly benefits clinical workflows, yet neural approaches such as Neural Radiance Fields (NeRF) and 3D…
arXiv:2604.20219v2 Announce Type: replace-cross Abstract: Depth is widely viewed as a central contributor to the success of deep neural networks, whereas standard neural network approximation theory…
arXiv:2606.24465v1 Announce Type: cross Abstract: We study the problem of estimating the arrival times of vertices in a uniform random recursive tree from its unlabeled structure.…
arXiv:2606.24014v1 Announce Type: new Abstract: As AI systems are deployed across increasingly diverse and high-stakes settings, model alignment must generalize beyond the tasks and domains seen…
arXiv:2606.04883v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used in workflows for generating formal proofs in Lean. These workflows often decompose problems into…
arXiv:2606.23948v1 Announce Type: new Abstract: Self-supervised and supervised speech models are increasingly used to investigate which linguistic information their internal representations encode, and at what level…
arXiv:2606.23758v1 Announce Type: new Abstract: Domain generalization learns from multiple source domains to generalize to unseen target domains. However, it often neglects the realistic case of…
arXiv:2606.23888v1 Announce Type: cross Abstract: While Vision-Language Models (VLMs) show great promise in volumetric medical report generation, they frequently suffer from visual hallucinations and a lack…
arXiv:2606.23950v1 Announce Type: new Abstract: Subject-driven image generation faces an "Identity-Diversity Paradox", where strong identity preservation often leads to rigid and low-diversity outputs. We propose a…
arXiv:2605.02701v2 Announce Type: replace-cross Abstract: We propose a robust gradient estimator based on per-sample gradient clipping and analyze its properties both theoretically and empirically. We show…
arXiv:2410.11116v4 Announce Type: replace-cross Abstract: In this paper, we establish a novel connection between the metric entropy growth and the embeddability of function spaces into reproducing…
arXiv:2606.24010v1 Announce Type: new Abstract: Multi-agent systems are widely used in safety-critical applications that require coordinated behavior under strict safety constraints. Existing approaches face a fundamental…
arXiv:2409.11363v2 Announce Type: replace Abstract: AI agents have the potential to aid users on a variety of consequential tasks, including conducting scientific research. To spur the…
arXiv:2606.24192v1 Announce Type: cross Abstract: Unlearning has emerged as a key technique to mitigate harmful content generation in diffusion models. However, existing methods often remove not…
arXiv:2606.23767v1 Announce Type: new Abstract: Headline accuracies on the Tuebingen cause-effect pairs are routinely compared across papers even though each is measured under its authors' own…
arXiv:2606.24874v1 Announce Type: new Abstract: Sparse voxel representation has emerged as a scalable foundation for image-to-3D Gaussian Splatting (3DGS) generation, yet current methods struggle to preserve…
arXiv:2603.19957v2 Announce Type: replace Abstract: Pathology reports are structured, multi-granular documents encoding diagnostic conclusions, histological grades, and ancillary test results across one or more anatomical sites;…
arXiv:2503.17300v5 Announce Type: replace-cross Abstract: We propose a variational tail bound for norms of random vectors and matrices under moment assumptions on their one-dimensional marginals. A…
arXiv:2307.13127v3 Announce Type: replace Abstract: Data used to train predictive models via empirical risk minimization (ERM) often contain sensitive personal information. While differential privacy (DP) provides…
arXiv:2606.23991v1 Announce Type: new Abstract: What is an agent? What constitutes agency? With the rise of Large Language Model (LLM) systems marketed as ``coding agents'', ``AI…
arXiv:2606.24133v1 Announce Type: cross Abstract: The composition of training data, governed by the diversity of sources and their mixing strategy, is a cornerstone of Large Language…
arXiv:2606.23959v1 Announce Type: new Abstract: Because mathematics is highly abstract, a single statement can take very different forms depending on what subfield it is framed in.…
arXiv:2606.23757v1 Announce Type: new Abstract: Extracting interpretable governing equations from sparse, noisy chemical time-series data remains difficult because discrete reaction topology and continuous kinetic parameters are…
arXiv:2606.22424v2 Announce Type: replace Abstract: Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to follow natural-language instructions in unseen scenes. While Large Models (LMs) have advanced…