AQuaUI uses adaptive quadtrees to cut visual tokens in GUI-agent LMMs by up to 29.52% at inference time while retaining 99.06% of full-token accuracy on grounding and navigation benchmarks.
hub
Davies and Donald W
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
dataset 1
citation-polarity summary
verdicts
UNVERDICTED 13roles
dataset 1polarities
use dataset 1representative citing papers
CADI quantifies the preservation of relative cluster angles in low-dimensional projections using internal angles from point triples.
AFGNN detects API misuses in Java code more effectively than prior methods by representing usage as graphs and clustering learned embeddings from self-supervised training.
GPS tracking across theme parks shows visitor movement forms a continuum rather than discrete types, diverges from self-reports, and reverses feature relationships from site to site, requiring local calibration.
Token-level confidence trajectories in LLMs encode a content-agnostic geometry that separates correct and incorrect reasoning traces and supports a lightweight correctness estimator called NeuralConf.
New hardware-usage-based similarity metrics can identify matching computational kernels between proxy applications and performance suites on both CPU and GPU systems.
Vision transformers with supervised contrastive learning achieve 91% top-3 accuracy and 0.66 MCC on ground-level habitat images, matching experienced ecological experts.
Converting percentage scores to A/B/C/D grades reduces information entropy by 69 percent, makes optimal student clusters sensitive to single data points, and drops temporal diagnostic consistency from 93-96 percent to 52-96 percent.
Formal concept lattices guide staged, hierarchical concept learning in deep networks to produce more interpretable and semantically structured representations.
wSSAS is a two-phase deterministic framework that uses hierarchical text organization and SNR-based feature prioritization to improve clustering integrity, categorization accuracy, and reproducibility when applying LLMs to large review datasets.
An unsupervised-to-supervised ML pipeline on UK NDNS data discovers four dietary patterns, reproduces them with macro-F1 0.963 using a surrogate classifier, and interprets them via SHAP for potential clinical use.
Controlled personalization combining editorial curation with modest algorithmic recommendations in legacy news increases engagement, diversity, and reduces popularity bias per an A/B test.
HCP data analysis clusters individuals by social profiles into two groups where the more socially beneficial cluster scores higher on positive mental health measures and shows lower interconnectivity especially in the default mode network.
citing papers explorer
-
AQuaUI: Visual Token Reduction for GUI Agents with Adaptive Quadtrees
AQuaUI uses adaptive quadtrees to cut visual tokens in GUI-agent LMMs by up to 29.52% at inference time while retaining 99.06% of full-token accuracy on grounding and navigation benchmarks.
-
Class Angular Distortion Index for Dimensionality Reduction
CADI quantifies the preservation of relative cluster angles in low-dimensional projections using internal angles from point triples.
-
AFGNN: API Misuse Detection using Graph Neural Networks and Clustering
AFGNN detects API misuses in Java code more effectively than prior methods by representing usage as graphs and clustering learned embeddings from self-supervised training.
-
Do Waders, Swimmers, and Divers Exist? A GPS-Based Pilot Study of Site-Dependent Visitor Movement in Theme Parks
GPS tracking across theme parks shows visitor movement forms a continuum rather than discrete types, diverges from self-reports, and reverses feature relationships from site to site, requiring local calibration.
-
Confidence Geometry Reveals Trace-Level Correctness in Large Language Model Reasoning
Token-level confidence trajectories in LLMs encode a content-agnostic geometry that separates correct and incorrect reasoning traces and supports a lightweight correctness estimator called NeuralConf.
-
On Similarity of Computational Kernels in our Codes and Proxies
New hardware-usage-based similarity metrics can identify matching computational kernels between proxy applications and performance suites on both CPU and GPU systems.
-
Habitat Classification from Ground-Level Imagery Using Deep Neural Networks
Vision transformers with supervised contrastive learning achieve 91% top-3 accuracy and 0.66 MCC on ground-level habitat images, matching experienced ecological experts.
-
Data Aphasia: An Institutional Counterfactual Study of the Stability of Academic Cognition Under Letter-Grade Evaluation Systems
Converting percentage scores to A/B/C/D grades reduces information entropy by 69 percent, makes optimal student clusters sensitive to single data points, and drops temporal diagnostic consistency from 93-96 percent to 52-96 percent.
-
Formal Concept Lattices are Good Semantic Scaffolds for Concept-Based Learning
Formal concept lattices guide staged, hierarchical concept learning in deep networks to produce more interpretable and semantically structured representations.
-
Leveraging Weighted Syntactic and Semantic Context Assessment Summary (wSSAS) Towards Text Categorization Using LLMs
wSSAS is a two-phase deterministic framework that uses hierarchical text organization and SNR-based feature prioritization to improve clustering integrity, categorization accuracy, and reproducibility when applying LLMs to large review datasets.
-
An Explainable Unsupervised-to-Supervised Machine Learning Framework for Dietary Pattern Discovery Using UK National Dietary Survey Data
An unsupervised-to-supervised ML pipeline on UK NDNS data discovers four dietary patterns, reproduces them with macro-F1 0.963 using a surrogate classifier, and interprets them via SHAP for potential clinical use.
-
Controlled Personalization in Legacy Media Online Services: A Case Study in News Recommendation
Controlled personalization combining editorial curation with modest algorithmic recommendations in legacy news increases engagement, diversity, and reduces popularity bias per an A/B test.
-
Linking the "inner" and "outer" self to mental health and brain networks
HCP data analysis clusters individuals by social profiles into two groups where the more socially beneficial cluster scores higher on positive mental health measures and shows lower interconnectivity especially in the default mode network.