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.

168,742 papers · 148 categories

Trend · papers per month

2.5%5.1%7.6%10.1% · Apr 202019922001200920172026
48 results for knowledge awareness

Paper introduces CoD for few-shot task-aware knowledge distillation using counterfactual explanations.

problem Lack of data for task-aware distillation in resource-constrained scenarios.
method Counterfactual-explanation-infused Distillation CoD for few-shot task-aware knowledge distillation.
result CoD achieves superior performance with significantly fewer samples than baseline methods.

CAKD framework optimizes knowledge transfer by focusing on influential components of distillation.

problem Balancing and optimizing knowledge transfer in distillation models.
method Decouple KL divergence into BCD, SCD, and WCD; prioritize influential components.
result CAKD framework consistently outperforms baseline across diverse models and datasets.

Online news recommender systems aim to address the information explosion of news and make personalized recommendation for users. In general, news language is highly condensed, full of knowledge entities and common sense. However, existing methods are unaware of such external knowledge and cannot fully discover latent k…

2018-01-25abs ↗pdf ↗

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.

TXtract extracts structured knowledge from thousands of product categories.

problem Extracting structured knowledge from diverse product categories in e-commerce.
method TXtract uses a taxonomy-aware model with category conditional self-attention and multi-task learning.
result TXtract outperforms state-of-the-art approaches by up to 10% in F1 and 15% in coverage across all categories.

RKD improves clustering in semi-supervised learning with limited labels.

problem Improving clustering accuracy in semi-supervised learning with few labeled examples.
method RKD as spectral clustering on a teacher model's graph, with clustering error quantification.
result RKD provably leads to low clustering error in semi-supervised classification problems.

RKT model improves knowledge tracing by considering exercise relations and student forget behavior.

problem Traditional KT models fail to consider both exercise relations and student forget behavior.
method RKT model uses relation-aware self-attention to incorporate exercise relations and student forget behavior.
result RKT model outperforms state-of-the-art KT methods on real-world datasets.

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 study shows data-oblivious attacks can outperform data-aware ones.

problem Comparing effectiveness of data-oblivious and data-aware poisoning attacks.
method Theoretical study of feature selection with LASSO, focusing on separation between full-information and oblivious attackers.
result Data-oblivious attacks can achieve the same results as full-information attacks for feature selection with LASSO.

The notion of expense in Bayesian optimisation generally refers to the uniformly expensive cost of function evaluations over the whole search space. However, in some scenarios, the cost of evaluation for black-box objective functions is non-uniform since different inputs from search space may incur different costs for …

2019-09-09abs ↗pdf ↗

Study examines flaws in probing LLMs' knowledge and introduces a new method.

problem Flaws in existing methods for probing the veracity of LLMs' internal knowledge.
method sAwMIL (Sparse-Aware Multiple-Instance Learning) combining multiple-instance learning with conformal prediction.
result LLMs encode a third type of signal distinct from true and false.

SANS uses graph structure to find meaningful negatives for entity and relation embeddings.

problem Finding hard negatives for entity and relation embeddings in knowledge graphs.
method Structure Aware Negative Sampling (SANS) that selects negatives from a node's k-hop neighborhood.
result SANS finds semantically meaningful negatives and is competitive with state-of-the-art approaches.

New method defends RL agents from poisoning attacks without MDP knowledge.

problem Poisoning attacks on RL systems can cause learning failures.
method Generic poisoning framework for online RL, Vulnerability-Aware Adversarial Critic Poison (VA2C-P).
result Successfully prevents RL agents from learning good policies or converging to target policies.

Optimizes function networks by selectively evaluating parts of the network, reducing costs.

problem Optimizing expensive function networks where full evaluations are costly.
method Knowledge gradient acquisition function for cost-aware partial evaluations.
result Outperforms existing BOFN methods and benchmarks across various problems.

KGRL uses reinforcement learning with knowledge graphs for better interactive recommendation.

problem Achieving responsiveness and accuracy in dynamic user-item interactions.
method KGRL combines reinforcement learning and knowledge graphs, using a local knowledge network and attention mechanism.
result KGRL outperforms state-of-the-art methods in simulated and real-world environments.

Active learning from demonstration allows a robot to query a human for specific types of input to achieve efficient learning. Existing work has explored a variety of active query strategies; however, to our knowledge, none of these strategies directly minimize the performance risk of the policy the robot is learning. U…

2019-01-08abs ↗pdf ↗

We integrate camera pose correlations into deep models using Gaussian processes.

problem Lack of inter-frame reasoning in deep neural networks.
method Derive a principled framework combining camera pose information with deep models using a novel view kernel.
result Soft-prior knowledge aids pose-related vision tasks like novel view synthesis.

Survey on ML advances for personalized prediction considering entity characteristics.

problem Sub-optimal performance in personalized prediction due to heterogeneity in data across entities.
method Organized current literature on entity-aware modeling based on characteristics availability and training data amount.
result Recent innovations in uncertainty quantification, fairness, and knowledge-guided machine learning can improve entity-aware modeling.

Humans can learn in a continuous manner. Old rarely utilized knowledge can be overwritten by new incoming information while important, frequently used knowledge is prevented from being erased. In artificial learning systems, lifelong learning so far has focused mainly on accumulating knowledge over tasks and overcoming…

2017-11-27abs ↗pdf ↗

Learning product representations that reflect complementary relationship plays a central role in e-commerce recommender system. In the absence of the product relationships graph, which existing methods rely on, there is a need to detect the complementary relationships directly from noisy and sparse customer purchase ac…

2019-03-16abs ↗pdf ↗

AI agent learns to handle unknown unknown states in reinforcement learning.

problem Handling unexpected, previously unseen states in reinforcement learning.
method Proposes EMDP-GA model with NIVE approach to expand value functions.
result Asymptotically consistent regret and comparable computational complexity.

Framework uses physics knowledge to improve spatiotemporal prediction with limited data.

problem Challenges in modeling physical systems with limited real-world data.
method Physics-aware meta-learning with auxiliary tasks, incorporating PDE-independent spatial and temporal modules.
result Framework outperforms in spatiotemporal prediction tasks with limited data.

Robust STAP with coprime arrays reduces clutter using sparse modeling.

problem Limited performance due to training samples support in practical applications.
method Two-stage approach: 1) RD virtual snapshot, 2) RD sparse measurement modeling with OMP-like recovery.
result Robust to prior knowledge errors, good clutter suppression performance.

LangDA improves domain adaptation for semantic segmentation by learning context-aware scene descriptions.

problem Improving domain adaptation for semantic segmentation with dense prediction tasks.
method LangDA learns contextual relationships between objects via VLM-generated scene descriptions and aligns image features with text representation.
result LangDA sets new state-of-the-art across three DASS benchmarks, outperforming existing methods.

Hybrid framework injects TSLM insights into GRLM for robust time-series reasoning.

problem Lack of domain-specific knowledge in large language models for time-series reasoning.
method Hybrid knowledge-injection framework combining RLVR for efficient knowledge transfer.
result Consistently outperforms existing models by 7.9%-26.1% on multivariate time-series benchmarks.

Zero-Shot Learning (ZSL) aims at classifying unlabeled objects by leveraging auxiliary knowledge, such as semantic representations. A limitation of previous approaches is that only intrinsic properties of objects, e.g. their visual appearance, are taken into account while their context, e.g. the surrounding objects in …

2019-04-24abs ↗pdf ↗

Paper proposes a method to estimate scientific parameters in hybrid models without relying on model architecture.

problem Estimating unknown parameters in hybrid models combining machine learning and scientific models.
method Sharpness-aware minimization adapted for hybrid modeling, focusing on model simplicity.
result Demonstrates effectiveness of SAM-based hybrid model learning for scientific parameter estimation.

UBMF tackles fault diagnosis in imbalanced industrial data with enhanced accuracy and adaptability.

problem Fault diagnosis challenges in imbalanced industrial data.
method Integrates four key modules: data perturbation, cross-task feature extraction, uncertainty-based filtering, and Bayesian meta-knowledge integration.
result Achieves an average improvement of 42.22% across ten diagnostic tasks.

This paper improves context-aware recommender systems by selecting and incorporating relevant low-dimensional contextual information.

problem Generating accurate recommendations is not enough; contextual information can cause issues like battery drain and privacy.
method Developed a feature-selection algorithm based on genetic algorithms to reduce context dimensions while maintaining explainability.
result The approach improves accuracy and transparency in recommendations, outperforming state-of-the-art models.

Reduced order modeling of energetic materials using physics-aware neural networks.

problem Simulating complex spatiotemporal dynamics in energetic materials.
method Physics-aware recurrent convolutions (PARC) combined with latent space projection to accelerate model training and inference.
result Significant decrease in training and inference time with comparable accuracy.

Work proposes CLAIRE to achieve counterfactual fairness from observational data without causal models.

problem Achieving counterfactual fairness from observational data without prior causal models.
method Proposes CLAIRE, a representation learning framework based on counterfactual data augmentation and an invariant penalty.
result CLAIRE effectively mitigates biases from the sensitive attribute and improves counterfactual fairness and prediction performance.

FinReflectKG builds a comprehensive financial knowledge graph from SEC filings, improving extraction quality.

problem Lack of large-scale, open-source financial knowledge graph datasets.
method Intelligent document parsing, table-aware chunking, schema-guided iterative extraction, reflection-driven feedback loop.
result Reflection-agent-based mode achieves best balance of efficiency, accuracy, and reliability.