The data heat island effect: quantifying the impact of AI data centers in a warming world
arXiv:2603.20897v1 Announce Type: cross Abstract: The strong and continuous increase of AI-based services leads to the steady proliferation of AI…
Weakly supervised multimodal segmentation of acoustic borehole images with depth-aware cross-attention
arXiv:2603.20729v1 Announce Type: cross Abstract: Acoustic borehole images provide high-resolution borehole-wall structure, but large-scale interpretation remains difficult because dense expert…
DMMRL: Disentangled Multi-Modal Representation Learning via Variational Autoencoders for Molecular Property Prediction
arXiv:2603.21108v1 Announce Type: cross Abstract: Molecular property prediction constitutes a cornerstone of drug discovery and materials science, necessitating models capable…
Structural Sensitivity in Compressed Transformers: Error Propagation, Lyapunov Stability, and Formally Verified Bounds
arXiv:2603.20991v1 Announce Type: cross Abstract: A single matrix out of 468 in GPT-2 Small can increase perplexity by 20,000x when…
When both Grounding and not Grounding are Bad — A Partially Grounded Encoding of Planning into SAT (Extended Version)
arXiv:2603.19429v1 Announce Type: new Abstract: Classical planning problems are typically defined using lifted first-order representations, which offer compactness and generality.…
CustomTex: High-fidelity Indoor Scene Texturing via Multi-Reference Customization
arXiv:2603.19121v2 Announce Type: replace-cross Abstract: The creation of high-fidelity, customizable 3D indoor scene textures remains a significant challenge. While text-driven…
Uncertainty-aware Prototype Learning with Variational Inference for Few-shot Point Cloud Segmentation
arXiv:2603.19757v1 Announce Type: cross Abstract: Few-shot 3D semantic segmentation aims to generate accurate semantic masks for query point clouds with…
MOSS-TTSD: Text to Spoken Dialogue Generation
arXiv:2603.19739v1 Announce Type: cross Abstract: Spoken dialogue generation is crucial for applications like podcasts, dynamic commentary, and entertainment content, but…
Points-to-3D: Structure-Aware 3D Generation with Point Cloud Priors
arXiv:2603.18782v2 Announce Type: replace-cross Abstract: Recent progress in 3D generation has been driven largely by models conditioned on images or…
Computational framework to predict and shape human–machine interactions in closed-loop, co-adaptive neural interfaces
Nature Machine Intelligence, Published online: 23 March 2026; doi:10.1038/s42256-026-01194-z Madduri et al. introduce a computational framework grounded in control and…