Tootfinder

Information-Optimal Sensing and Control in High-Intensity Laser Experiments
A. D\"opp, C. Eberle, J. Esslinger, S. Howard, F. Irshad, J. Schroeder, N. Weisse, S. Karsch
https://arxiv.org/abs/2506.04946

Information-Optimal Sensing and Control in High-Intensity Laser Experiments
High-intensity laser systems present unique measurement and optimization challenges due to their high complexity, low repetition rates, and shot-to-shot variations. We discuss recent developments towards a unified framework based on information theory and Bayesian inference that addresses these challenges. Starting from fundamental constraints on the physical field structure, we recently demonstrated how to capture complete spatio-temporal information about individual petawatt laser pulses. Bui…

Towards Secure MLOps: Surveying Attacks, Mitigation Strategies, and Research Challenges
Raj Patel, Himanshu Tripathi, Jasper Stone, Noorbakhsh Amiri Golilarz, Sudip Mittal, Shahram Rahimi, Vini Chaudhary
https://arxiv.org/abs/2506.02032

Towards Secure MLOps: Surveying Attacks, Mitigation Strategies, and Research Challenges
The rapid adoption of machine learning (ML) technologies has driven organizations across diverse sectors to seek efficient and reliable methods to accelerate model development-to-deployment. Machine Learning Operations (MLOps) has emerged as an integrative approach addressing these requirements by unifying relevant roles and streamlining ML workflows. As the MLOps market continues to grow, securing these pipelines has become increasingly critical. However, the unified nature of MLOps ecosystem …

Transferable Modeling Strategies for Low-Resource LLM Tasks: A Prompt and Alignment-Based
Shuangquan Lyu, Yingnan Deng, Guiran Liu, Zhen Qi, Ruotong Wang
https://arxiv.org/abs/2507.00601

Transferable Modeling Strategies for Low-Resource LLM Tasks: A Prompt and Alignment-Based
This paper addresses the limited transfer and adaptation capabilities of large language models in low-resource language scenarios. It proposes a unified framework that combines a knowledge transfer module with parameter-efficient fine-tuning strategies. The method introduces knowledge alignment loss and soft prompt tuning to guide the model in effectively absorbing the structural features of target languages or tasks under minimal annotation. This enhances both generalization performance and tr…

Gated Multimodal Graph Learning for Personalized Recommendation
Sibei Liu, Yuanzhe Zhang, Xiang Li, Yunbo Liu, Chengwei Feng, Hao Yang
https://arxiv.org/abs/2506.00107

Gated Multimodal Graph Learning for Personalized Recommendation
Multimodal recommendation has emerged as a promising solution to alleviate the cold-start and sparsity problems in collaborative filtering by incorporating rich content information, such as product images and textual descriptions. However, effectively integrating heterogeneous modalities into a unified recommendation framework remains a challenge. Existing approaches often rely on fixed fusion strategies or complex architectures , which may fail to adapt to modality quality variance or introduc…

A LoD of Gaussians: Unified Training and Rendering for Ultra-Large Scale Reconstruction with External Memory
Felix Windisch, Lukas Radl, Thomas K\"ohler, Michael Steiner, Dieter Schmalstieg, Markus Steinberger
https://arxiv.org/abs/2507.01110

A LoD of Gaussians: Unified Training and Rendering for Ultra-Large Scale Reconstruction with External Memory
Gaussian Splatting has emerged as a high-performance technique for novel view synthesis, enabling real-time rendering and high-quality reconstruction of small scenes. However, scaling to larger environments has so far relied on partitioning the scene into chunks -- a strategy that introduces artifacts at chunk boundaries, complicates training across varying scales, and is poorly suited to unstructured scenarios such as city-scale flyovers combined with street-level views. Moreover, rendering re…

CrossPipe: Towards Optimal Pipeline Schedules for Cross-Datacenter Training
Tiancheng Chen, Ales Kubicek, Langwen Huang, Torsten Hoefler
https://arxiv.org/abs/2507.00217

CrossPipe: Towards Optimal Pipeline Schedules for Cross-Datacenter Training
Training large language models (LLMs) now requires resources that exceed a single datacenter, making cross-datacenter strategies increasingly crucial. We present CrossPipe, a framework designed to optimize model training across geographically distributed datacenters by explicitly modeling and mitigating the impact of network latency and limited bandwidth. It enables unified analysis and optimization incorporating both pipeline parallelism (PP) and opportunities for overlapping data parallelism …

Moduli spaces for $\Theta$-strata and non-reductive quotients
Ludvig Modin
https://arxiv.org/abs/2505.22812 https://arxiv.org/pdf/250…

Moduli spaces for $Θ$-strata and non-reductive quotients
We give a new proof of the $\hat{U}$-theorem of Bérczi, Doran, Hawes and Kirwan on the existence of geometric quotients for actions of graded unipotent groups in terms of stacks of filtrations and gradings introduced by Halpern-Leistner. Our proof works over any affine Noetherian base, in particular it simultaneously generalizes the previous results to arbitrary characteristic, actions in families and to general $Θ$-strata.

Attention Is Not Always the Answer: Optimizing Voice Activity Detection with Simple Feature Fusion
Kumud Tripathi, Chowdam Venkata Kumar, Pankaj Wasnik
https://arxiv.org/abs/2506.01365

Attention Is Not Always the Answer: Optimizing Voice Activity Detection with Simple Feature Fusion
Voice Activity Detection (VAD) plays a key role in speech processing, often utilizing hand-crafted or neural features. This study examines the effectiveness of Mel-Frequency Cepstral Coefficients (MFCCs) and pre-trained model (PTM) features, including wav2vec 2.0, HuBERT, WavLM, UniSpeech, MMS, and Whisper. We propose FusionVAD, a unified framework that combines both feature types using three fusion strategies: concatenation, addition, and cross-attention (CA). Experimental results reveal that …

Geological Everything Model 3D: A Promptable Foundation Model for Unified and Zero-Shot Subsurface Understanding
Yimin Dou, Xinming Wu, Nathan L Bangs, Harpreet Singh Sethi, Jintao Li, Hang Gao, Zhixiang Guo
https://arxiv.org/abs/2507.00419

Geological Everything Model 3D: A Promptable Foundation Model for Unified and Zero-Shot Subsurface Understanding
Understanding Earth's subsurface is critical for energy transition, natural hazard mitigation, and planetary science. Yet subsurface analysis remains fragmented, with separate models required for structural interpretation, stratigraphic analysis, geobody segmentation, and property modeling-each tightly coupled to specific data distributions and task formulations. We introduce the Geological Everything Model 3D (GEM), a unified generative architecture that reformulates all these tasks as prompt-…

FocalClick-XL: Towards Unified and High-quality Interactive Segmentation
Xi Chen, Hengshuang Zhao
https://arxiv.org/abs/2506.14686 https://

FocalClick-XL: Towards Unified and High-quality Interactive Segmentation
Interactive segmentation enables users to extract binary masks of target objects through simple interactions such as clicks, scribbles, and boxes. However, existing methods often support only limited interaction forms and struggle to capture fine details. In this paper, we revisit the classical coarse-to-fine design of FocalClick and introduce significant extensions. Inspired by its multi-stage strategy, we propose a novel pipeline, FocalClick-XL, to address these challenges simultaneously. Fol…