arXiv:2608. 06155v1 Announce Type: cross Abstract: Conditional expectation operators (CEOs) and their associated conditional mean embeddings (CMEs) play a central role across applied mathematics and machine learning, appearing in nonparametric regression, Bayesian inverse problems, and Koopman operator theory.
By Maximiliano Hertel, Ilja Klebanov, Manuel Schaller, Karl Worthmann
arXiv:2608. 05336v1 Announce Type: cross Abstract: Molecular representations are essential for the evaluation of molecular similarity and the development of structure-property relationships.
By Jacob W. Toney, Ayleen Y. Farnood, Samir Darouich, Heather J. Kulik
arXiv:2608. 05437v1 Announce Type: cross Abstract: Supervised training of finite-element (FE) surrogate models requires reference solutions, and each reference solution is obtained by solving the system that the surrogate is intended to replace.
By Ruifeng Cao (The University of Manchester), Xidan Song (Wuhan University)
arXiv:2608. 05232v1 Announce Type: cross Abstract: The work of Tang et.
By Patrizia Kaye
arXiv:2608. 06111v1 Announce Type: cross Abstract: Positional embeddings (PE) in Transformers encode token distance and order but are largely agnostic to \textit{syntactic structure}.
By Haris Riaz, Hyungji Kim, Mihai Surdeanu
arXiv:2608. 06115v1 Announce Type: new Abstract: Predicting how a population will answer a new question is a long-standing goal.
By Pranav Dahiya
arXiv:2608. 05980v1 Announce Type: new Abstract: We investigate whether simple transformations can translate representations across heterogeneous text embedding models.
By Sid Ali Hamideche (Orange Research), Louis Adrien Dufrene (Orange Research), Quentin Lampin (Orange Research), Guillaume Larue (Orange Research)
arXiv:2608. 05960v1 Announce Type: cross Abstract: Routine CT interpretation is inherently comprehensive, capturing incidental findings across the entire scan volume.
By Maulik Chevli, Johannes Brandt, Rickmer Braren, Daniel Rueckert, Philip M\"uller
arXiv:2603. 05997v2 Announce Type: replace-cross Abstract: Irregularly sampled time series (ISTS) are widespread in real-world scenarios, exhibiting asynchronous observations on uneven time intervals across diverse variables.
By Zhi Lei, Chenxi Liu, Hao Miao, Wanghui Qiu, Bin Yang, Chenjuan Guo
arXiv:2608. 05928v1 Announce Type: new Abstract: Single-cell transcriptomes are sparse observations of coordinated biological programmes, yet most self-supervised models learn by reconstructing individual genes.
By Yuhao Wang, Zelin Zang, Yuxuan Liu, Zhen Lei, Stan Z. Li
Transformer models for high-dimensional omics analysis process thousands of genes or pathways, although only a subset requires deep computation. Mixture-of-Recursions (MoR) improves efficiency through adaptive token-choice or expert-choice routing.
While deep learning models, particularly transformer-based architectures, have shown impressive performance in time series forecasting, the application of retrieval-augmented generation (RAG) in this domain remains limited. Since RAG has proven effective in enhancing the capabilities of large language models by incorporating relevant external information, retrieving similar time series sequences as references might also improve accuracy in time series forecasting tasks.
Predicting how a population will answer a new question is a long-standing goal. Statistical methods succeed at the level of the mass but falter at the level of the individual.
Enterprise Document Intelligence [Vol. 1 #11] - When the first answer points elsewhere in the document, the pipeline loops back to fetch the linked context The post Loop Engineering for Cross-References: When RAG Answers ‘see Section 7.
By angela shi
Single-cell transcriptomes are sparse observations of coordinated biological programmes, yet most self-supervised models learn by reconstructing individual genes. Here we present BioM-JEPA, a joint-embedding predictive architecture that instead predicts aggregate representations of graph-connected gene blocks defined by protein-association and corpus-derived coexpression evidence.
Retrieval-Augmented Generation systems rely on similarity scores to retrieve relevant content, yet scores are not directly comparable across embedding models due to differing geometric properties, complicating model migration and limiting threshold reuse. We study how similarity scores can be related by learning mappings between score distributions rather than embeddings.
Sparse word embedding pipelines can avoid dense co-occurrence matrix materialization, dense factorization, and gradient training while still relying on sparse global corpus statistics. This paper studies Random Indexing (RI) vectors refined by weighted averaging on a sparse Positive Pointwise Mutual Information (PPMI) graph.
arXiv:2608. 05030v1 Announce Type: new Abstract: Football score forecasting combines a strong statistical core with a difficult contextual edge.
By Shaopeng Liang
arXiv:2608. 04378v1 Announce Type: cross Abstract: Collaborative music agents need internal representations rich enough to support both understanding and generation, yet flexible enough for a workflow where the human retains agency.
By Scott H. Hawley
arXiv:2608. 04569v1 Announce Type: cross Abstract: Hard prompt compression reduces long-context inference cost by independently scoring tokens, sentences, or chunks and retaining the highest-scoring units under a budget.
By Zhengpei Hu, Kai Li, Dapeng Fu, Xuechao Zou, Yuanhao Tang, Yue Li, Tengfei Cao, Jianqiang Huang