Retrieval pipelines, vector search, chunking and reranking: how models are grounded in a corpus instead of their weights.
arXiv:2605. 08442v3 Announce Type: replace-cross Abstract: Persistent memory attacks against LLM agents achieve high attack success rates against open-source models.
arXiv:2606. 24984v1 Announce Type: new Abstract: Learning representations that remain robust across centuries of variation in handwriting is a key challenge in diachronic representation learning.
arXiv:2606. 24967v1 Announce Type: new Abstract: In ill-posed inverse problems, the recovered solution depends as much on the prior as on the data, yet much of the engineering knowledge that could serve as that prior is recorded qualitatively rather than in formal mathematical form.
arXiv:2606. 25439v1 Announce Type: new Abstract: Deep learning-based models have achieved state-of-the-art performance in Time Series Forecasting (TSF), yet their evaluation remains dominated by pointwise error metrics such as Mean Squared Error (MSE), which quantify numerical accuracy but overlook structural properties of the forecast signal, including recurrent dynamics, oscillatory behavior, and phase alignment.
arXiv:2606. 24899v1 Announce Type: new Abstract: AI-assisted mathematics is often evaluated on solving predefined problems.
arXiv:2606. 25147v1 Announce Type: cross Abstract: User modeling in industrial recommender systems typically produces dense embeddings, which suffer from representational constraints inherent to fixed-dimensional vectors.
arXiv:2507. 00028v2 Announce Type: replace Abstract: The representation of urban trajectory data plays a critical role in effectively analyzing spatial movement patterns.
arXiv:2606. 24976v1 Announce Type: cross Abstract: Foundation-model agents in multi-step, open-ended environments frequently suffer from compounding errors, where early mistakes contaminate long-horizon trajectories.
arXiv:2602. 14239v3 Announce Type: replace-cross Abstract: Predicting links in sparse, continuously evolving networks is a central challenge in network science.
arXiv:2606. 24983v1 Announce Type: cross Abstract: Implicit solvent machine learning potentials (MLPs) offer a powerful route to bridging the gap between accuracy and efficiency in molecular simulations.
arXiv:2606. 24969v1 Announce Type: new Abstract: While the quadratic sequence-length bottleneck of transformers has fueled a resurgence in recurrent models, effectively capturing complex dynamics requires architectures that balance efficient training with highly expressive latent states.
arXiv:2408. 01273v3 Announce Type: replace Abstract: We propose a framework for training neural network controllers with certified robust forward invariant polytopes.
arXiv:2602. 08629v2 Announce Type: replace Abstract: Causal discovery is essential for advancing data-driven fields such as scientific AI and data analysis, yet existing approaches face significant time- and space-efficiency bottlenecks when scaling to large graphs.
arXiv:2603. 07221v2 Announce Type: replace Abstract: Margin-based learning, exemplified by linear and kernel methods, is one of the few classical settings where generalization guarantees are independent of the number of parameters.
arXiv:2606. 24948v1 Announce Type: new Abstract: Knowledge graph embedding (KGE) models predict single-hop links well but have no mechanism for zero-shot compositional queries: multi-hop questions whose relation chains never appeared during training.
arXiv:2606. 25770v1 Announce Type: new Abstract: Data scarcity is a major bottleneck in medical Multiple Instance Learning (MIL), especially for rare diseases or expensive modalities.
The neutral, or floating, tone of Mandarin Chinese is a tone with an enigmatic set of properties. It has been described as a reduced tone, or as a tone that sometimes is lexically fixed but that can also be toneless.
Enterprise Document Intelligence [Vol. 1 #7B] - Retrieval is filtering on structured tables: keywords first, TOC second, embeddings last The post Anchor Detection for RAG: Parallel Detectors, Then One LLM Call at the End appeared first on Towards Data Science .
Enterprise Document Intelligence [Vol. 1 #7B] - Retrieval is filtering on structured tables: keywords first, TOC second, embeddings last The post Finding the right anchors for RAG: keyword, embedding, and TOC signals in parallel appeared first on Towards Data Science .
LLM-based text embedders have substantially improved retrieval and semantic representation quality, but their deployment remains costly: large backbone models slow down embedding inference, while high-dimensional full-precision embeddings impose substantial storage and bandwidth overhead on large-scale indexes. In this paper, we present BITEMBED, an extreme low-bit framework for LLM-based text embedding that jointly targets encoding efficiency and vector storage.