Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,291 papers · 148 categories

Trend · papers per month

2.8%5.5%8.3%11.0% · May 202619922001200920182026
48 results for Latent Semantic Concepts

SEMASIA provides a large dataset of latent representations for model comparison.

problem Difficulty in comparing semantic structures across different neural network models.
method Collection of latent representations from 1700 pretrained models across various benchmarks.
result Consistent semantic organization across models and datasets.

This work shows how transformers use multi-concept word semantics for efficient in-context learning.

problem Understanding the connection between transformer-based LLMs' multi-concept semantic representation and their innovative in-context learning abilities.
method A concept-based low-noise sparse coding prompt model, leveraging advanced techniques to analyze the exponential convergence of 0-1 loss over non-convex training dynamics.
result Transformers leverage multi-concept word semantics to enable powerful and excellent out-of-distribution in-context learning.

Proposes a new VAE model with hierarchical nonparametric priors for better data representation.

problem Limited flexibility of standard VAE latent representations.
method Combines tree-structured Bayesian nonparametric priors with VAEs for joint learning of neural parameters and priors.
result Discover highly interpretable activity hierarchies and improved clustering accuracy.

Method infers domain-specific models without domain semantic descriptors.

problem Poor performance of standard supervised learning methods in unseen domains.
method Introduces latent domain vectors and neural networks for optimization.
result Inference of appropriate domain-specific models without semantic descriptors.

This work explains how linear representations in large language models arise from training objectives and gradient descent.

problem Understanding the origins of linear representations in large language models.
method A latent variable model to abstract and formalize concept dynamics, combined with analysis of the softmax cross-entropy objective and gradient descent.
result Linear representations emerge when learning from data matching the latent variable model, and this simple structure suffices to yield linear representations.

This work provides uncertainty intervals for semantic latent variables in disentangled latent spaces.

problem Challenges in providing meaningful uncertainty quantification for semantic information in disentangled latent spaces.
method Uses quantile regression to output heuristic uncertainty intervals, calibrates these intervals to contain true latent values, and propagates them through the generator.
result Reliably communicates semantically meaningful, principled, and instance-adaptive uncertainty in image super-resolution and image completion.

Enhanced ontology learning from text improves question-answering systems.

problem Improving ontology learning from unstructured text for better question-answering systems.
method Heuristically modified FP-Tree with DFA for concept extraction and frequent pattern mining for ontology learning.
result Our approach significantly improves question-answering system performance, answering 80% of questions compared to 28.4% with Text2Onto.

RCAV quantifies model sensitivity to semantic concepts, improving interpretability methods.

problem Lack of semantic interpretability in image classification models.
method RCAV calculates concept gradients and ascent steps to assess model sensitivity to semantic concepts.
result RCAV yields more accurate and robust interpretations of model behavior.

Semantic TrueLearn uses semantic graphs to improve educational recommendation systems.

problem Challenges in handling semantic and hierarchical structure in knowledge areas.
method Introduces a novel learner model that exploits semantic relatedness between knowledge components using a Wikipedia link graph.
result Achieves statistically significant improvements in predictive performance for educational engagement.

Probabilistic Latent Semantic Analysis is a novel statistical technique for the analysis of two-mode and co-occurrence data, which has applications in information retrieval and filtering, natural language processing, machine learning from text, and in related areas. Compared to standard Latent Semantic Analysis which s…

2013-01-23abs ↗pdf ↗

This work prevents variational autoencoders from collapsing by adding an auxiliary decoder.

problem Variational autoencoders can collapse into autodecoders, losing semantic information.
method Adding an auxiliary decoder to regularize the latent space.
result Auxiliary decoders increase semantic information in the latent space and reconstructions.

New method neutralizes gender bias in word embeddings without losing semantic information.

problem Gender biases in word embeddings trained on human-generated corpora.
method Latent Disentanglement and Counterfactual Generation with siamese auto-encoder and gradient reversal layer.
result Our method outperforms existing debiasing methods in preserving semantic information and neutralizing gender biases.

The paper explores how AI systems use information geometry to encode semantic structure.

problem How AI systems encode semantic structure into geometric representation spaces.
method Focuses on softmax distributions and develops dual steering method for robust concept manipulation.
result Dual steering optimally modifies target concepts while minimizing off-target changes.

Net2Vec maps filters to vectors to reveal complex concept encoding.

problem Understanding how deep neural networks encode semantic concepts.
method Net2Vec framework that maps semantic concepts to vectorial embeddings based on filter responses.
result Multiple filters are often required to code for a concept, and filters help encode multiple concepts.

We developed a caching method to speed up concept learning in complex knowledge bases.

problem Complex concept learning requires many instance retrieval calls, increasing runtime.
method Semantics-aware caching that links concepts to instances via crisp set operations.
result Our cache reduces concept retrieval and learning runtime by an order of magnitude.

New framework aligns latent representations over-the-air using intelligent metasurfaces.

problem Heterogeneous transmitter-receiver models produce misaligned latent representations in semantic communication.
method Intelligent metasurfaces (SIM) emulate supervised and zero-shot semantic aligners directly in the wave domain.
result SIMs achieve up to 90% task accuracy in high SNR regimes, robust to low SNR.

The paper improves semantic interpolation in latent spaces of implicit models.

problem Interpolating between latent points in implicit models requires careful distributional matching.
method Proposes modifying the prior code distribution to concentrate more probability mass near the origin.
result Linear interpolation paths are shortest and pass through high-density regions, improving sample quality and semantics.

Service robots learn new tasks more efficiently with ISI, improving query performance and reducing training time.

problem Incremental learning of semantic concepts in multi-relational embeddings for service robots.
method Incremental Semantic Initialization (ISI) that allows new semantic concepts to be initialized in relation to previously learned embeddings.
result ISI improves immediate query performance by 41.4% and reduces the number of epochs to approach model convergence by 78.2%.

Top2Vec finds topic vectors from documents and words without needing stop words or custom settings.

problem Topic modeling weaknesses, including needing known topics, stop words, and custom settings.
method Joint document and word semantic embedding to find topic vectors automatically.
result Top2Vec finds more informative and representative topics than probabilistic models.

The paper tests semantic importance in opaque models using betting.

problem Precise statistical guarantees for semantic concepts in black-box models.
method Formalizes global and local statistical importance via conditional independence and SKIT.
result Shows effectiveness and flexibility of the framework on various models.

This paper proposes using contextualized word representations for better concept taxonomies.

problem Current taxonomy learning systems define concepts as single words, limiting their semantic understanding.
method Defines concepts as synsets, learns density-based approximations of contextualized word representations, and measures similarity and hypernymy.
result Contextualized word representations can improve the accuracy of concept taxonomies.

The ability of the Generative Adversarial Networks (GANs) framework to learn generative models mapping from simple latent distributions to arbitrarily complex data distributions has been demonstrated empirically, with compelling results showing that the latent space of such generators captures semantic variation in the…

2016-05-31abs ↗pdf ↗

A new neural network model extends word embedding vectors with MeSH concepts for biomedical semantic similarity.

problem Eliciting semantic similarity between biomedical concepts remains challenging.
method Proposes a MeSH-gram neural network model that extends skip-gram by using MeSH descriptors.
result MeSH-gram outperforms skip-gram and is comparable to best methods but requires more computation and external resources.

Investigates latent variable models for useful generative concept representations.

problem Creating latent representations that support various concepts and attributes.
method Latent variable modeling, including latent variable models, latent representations, and latent spaces.
result Hierarchical latent representations and latent space vectors and geometry are effective for generative concept representations.

In information retrieval, a fundamental goal is to transform a document into concepts that are representative of its content. The term "representative" is in itself challenging to define, and various tasks require different granularities of concepts. In this paper, we aim to model concepts that are sparse over the voca…

2012-04-11abs ↗pdf ↗

DCR improves interpretability of concept-based models by using neural networks to build rule structures.

problem Inability of concept-based models to provide transparent decision processes.
method DCR uses neural networks to build syntactic rule structures using concept embeddings and executes these rules on concept truth degrees.
result DCR improves interpretability by up to 25% on challenging benchmarks and discovers meaningful logic rules.

Improved generalization with semantic perturbations using normalizing flows.

problem Overfitting in deep neural networks training.
method Use normalizing flows for generating semantically meaningful perturbations in latent space.
result Achieved 96.6% test accuracy on CIFAR-10 with ResNet-18, outperforming existing methods.

Unsupervised method discovers interpretable directions in GAN latent space.

problem Discovering interpretable directions in GAN latent space without supervision.
method Model-agnostic procedure to identify directions corresponding to semantic manipulations.
result Findings include directions for background removal and competitive saliency detection performance.

ML-VAE learns disentangled representations from grouped data.

problem Learning disentangled representations from grouped observations with minimal supervision.
method Multi-Level Variational Autoencoder (ML-VAE) that separates latent representation at group and observation levels.
result ML-VAE learns meaningful disentanglement of grouped data and enables manipulation of latent representation.

CADD improves generative quality by augmenting discrete diffusion with continuous latent space.

problem Loss of semantic information between denoising steps in discrete diffusion models.
method Introduces a framework that augments discrete state space with a continuous latent space, allowing for graded, informative masked tokens.
result CADD improves generative quality across text generation, image synthesis, and code modeling.

The paper tests deep music embeddings for semantic consistency.

problem Ensuring deep music embeddings capture meaningful musical semantics.
method Proposes a systematic method to test deep music representations for semantic consistency, considering both input audio space and latent deep space.
result Distance consistency between related points is maintained in both input audio space and latent deep space.

An increasing number of people are using online social networking services (SNSs), and a significant amount of information related to experiences in consumption is shared in this new media form. Text mining is an emerging technique for mining useful information from the web. We aim at discovering in particular tweets s…

2016-03-24abs ↗pdf ↗