HAMNO introduces adaptive gating between local and global operators in a hierarchical setup, with PI-HAMNO adding PDE residual constraints, demonstrating better performance on Allen-Cahn, Cahn-Hilliard, and Swift-Hohenberg equations.
hub Canonical reference
Interpretability in mapping weeds and crops from drone images
Canonical reference. 75% of citing Pith papers cite this work as background.
27
Pith papers citing it
34
external citations · external index
Background
75% of classified citations
hub tools
citation-role summary
background 7
baseline 1
citation-polarity summary
representative citing papers
A taxonomy of SNN training algorithms is presented with the release of NeuroTrain, an open benchmarking framework for reproducible comparisons across datasets and architectures.
EVENT5Ws is a new large-scale, manually verified open-domain event extraction dataset that benchmarks LLMs and demonstrates cross-context generalization.
The saturation index S(K)=erank(pooled within-class covariance)/K tracks when few-shot labels become redundant for fixed linear probes, with within-task median Spearman ρ≈0.81 on 17 binary tasks.
A large-scale benchmark of 17 WHAR models across 30 datasets finds predictive performance has plateaued while efficiency favors compact neural models and random forests on the Pareto frontier.
A survey of on-device learning in TinyML organized by distribution change regimes, highlighting influences on applications, hardware, and solutions plus a gap between benchmarks and deployments.
Large-scale listening study of 35,532 judgments finds human accuracy on real audio fell from 72.7% to 64.1% since 2021 while fake detection remained stable, indicating a skepticism shift toward genuine speech.
Wearable accelerometry, EDA, and temperature data from 9 students with profound autism, processed with fine-tuned foundation models, enables prediction of challenging behavior episodes up to 10 minutes in advance at AUC-ROC 0.78 in actual classroom sessions.
ReLU networks' division of input space into convex polytopal regions permits direct extraction of causal rules that exactly match the original network's linear behavior in each region.
GCD-FGL mitigates neighborhood absorption and global semantic inconsistency in federated generalized category discovery, delivering +4.86 average HRScore gain over baselines on five graph datasets.
Fusing chart visualizations with raw time series improves or maintains classification accuracy on UCR datasets when the visuals add non-redundant information.
QTyBERT matches or exceeds BERT-based log anomaly detection effectiveness while reducing embedding generation time to near static word embedding levels.
Bash-Commenter applies CPT, SFT, and Syntax-Aware Preference Optimization (SAPO) via AST atomic operations to LLaMA-3.1-8B, reporting higher BLEU-4/METEOR/ROUGE-L scores than baselines on single-line and multi-line Bash comment generation tasks.
PTMC is a proposed Monte Carlo estimator that generates market-outcome distributions by simulating continuous double-auction interactions among persona-conditioned neural-policy bots whose heterogeneity is drawn from a learned distribution.
Contrastive FUSE learns node embeddings from partial pairwise supervision and structural signals alone by optimizing a spectral contrastive objective with a lightweight modularity approximation, yielding competitive performance and runtime gains on citation and co-purchase graphs.
MODEE is a multimodal system that integrates graphs with LLM embeddings to outperform prior open-domain event extraction methods on large datasets.
A simulated pipeline combining CNN wildfire detection, Bayesian confidence updates, and reconfigurable satellite scheduling automates wildfire monitoring, but it is not validated on real satellite images.
Assumed density filtering and smoothing for neural network surrogate models is enabled by analytic computation of output moments, yielding more accurate state estimates and improved LQR performance on stochastic Lorenz and Wiener systems.
Dual-stream EEG decoder separates identity and orientation to support 3D reconstruction from neural signals via circular regression and conditioned diffusion.
Short-term synaptic plasticity in a PFC-inspired reservoir model preserves goal-conditioned dynamics under noise, keeping multistep action selection robust where fixed-connectivity versions fail.
A symmetry-aware padding method for crystal structure encoding improves reconstruction accuracy by 5.3% on proton conductor data and yields 63.5% more novel stable materials on the perov-5 dataset compared to baseline.
CTiKG pipeline improves named entity recognition by 3-4% and relation extraction by up to 8% on DNRTI-AUG-STIX2 and other CTI benchmarks by adding context-aware hybrid NLP and ontology knowledge.
Literature on system prompts for AI shows fragmented and contradictory claims that complicate policy efforts to use them as reliable governance mechanisms.
Tiny NeRV models using capacity scaling, frequency-aware distillation, and low-precision quantization achieve favorable quality-efficiency trade-offs with far fewer parameters and lower computational costs than standard NeRV.
citing papers explorer
-
HAMNO: A Hierarchical Adaptive Multi-scale Neural Operator with Physics-Informed Learning for Dynamical Systems
HAMNO introduces adaptive gating between local and global operators in a hierarchical setup, with PI-HAMNO adding PDE residual constraints, demonstrating better performance on Allen-Cahn, Cahn-Hilliard, and Swift-Hohenberg equations.
-
NeuroTrain: Surveying Local Learning Rules for Spiking Neural Networks with an Open Benchmarking Framework
A taxonomy of SNN training algorithms is presented with the release of NeuroTrain, an open benchmarking framework for reproducible comparisons across datasets and architectures.
-
EVENT5Ws: A Large Dataset for Open-Domain Event Extraction from Documents
EVENT5Ws is a new large-scale, manually verified open-domain event extraction dataset that benchmarks LLMs and demonstrates cross-context generalization.
-
The Geometry of Saturation: Effective Rank Predicts When Labels Stop Helping in Few-Shot Classification
The saturation index S(K)=erank(pooled within-class covariance)/K tracks when few-shot labels become redundant for fixed linear probes, with within-task median Spearman ρ≈0.81 on 17 binary tasks.
-
WHAR Arena: Benchmarking the State of the Art in Efficient Wearable Human Activity Recognition
A large-scale benchmark of 17 WHAR models across 30 datasets finds predictive performance has plateaued while efficiency favors compact neural models and random forests on the Pareto frontier.
-
What changes after deployment? A survey on On-device Learning in TinyML
A survey of on-device learning in TinyML organized by distribution change regimes, highlighting influences on applications, hardware, and solutions plus a gap between benchmarks and deployments.
-
Eroding Trust in Real Speech: A Large-Scale Study of Human Audio Deepfake Perception
Large-scale listening study of 35,532 judgments finds human accuracy on real audio fell from 72.7% to 64.1% since 2021 while fake detection remained stable, indicating a skepticism shift toward genuine speech.
-
Prediction of Challenging Behaviors Associated with Profound Autism in a Classroom Setting Using Wearable Sensors
Wearable accelerometry, EDA, and temperature data from 9 students with profound autism, processed with fine-tuned foundation models, enables prediction of challenging behavior episodes up to 10 minutes in advance at AUC-ROC 0.78 in actual classroom sessions.
-
Causal Explanations from the Geometric Properties of ReLU Neural Networks
ReLU networks' division of input space into convex polytopal regions permits direct extraction of causal rules that exactly match the original network's linear behavior in each region.
-
Generalized Category Discovery in Federated Graph Learning
GCD-FGL mitigates neighborhood absorption and global semantic inconsistency in federated generalized category discovery, delivering +4.86 average HRScore gain over baselines on five graph datasets.
-
VTBench: A Multimodal Framework for Time-Series Classification with Chart-Based Representations
Fusing chart visualizations with raw time series improves or maintains classification accuracy on UCR datasets when the visuals add non-redundant information.
-
A Comparative Study of Semantic Log Representations for Software Log-based Anomaly Detection
QTyBERT matches or exceeds BERT-based log anomaly detection effectiveness while reducing embedding generation time to near static word embedding levels.
-
Bash-Commenter: Leveraging Syntax-Aware Preference Optimization to Reinforce Large Language Model for Bash Code Comment Generation
Bash-Commenter applies CPT, SFT, and Syntax-Aware Preference Optimization (SAPO) via AST atomic operations to LLaMA-3.1-8B, reporting higher BLEU-4/METEOR/ROUGE-L scores than baselines on single-line and multi-line Bash comment generation tasks.
-
Persona-Trained Monte Carlo: Estimating Market-Outcome Distributions via Swarms of Persona-Conditioned Neural Policy Bots in a Limit Order Book
PTMC is a proposed Monte Carlo estimator that generates market-outcome distributions by simulating continuous double-auction interactions among persona-conditioned neural-policy bots whose heterogeneity is drawn from a learned distribution.
-
Fast and Featureless Node Representation Learning with Partial Pairwise Supervision
Contrastive FUSE learns node embeddings from partial pairwise supervision and structural signals alone by optimizing a spectral contrastive objective with a lightweight modularity approximation, yielding competitive performance and runtime gains on citation and co-purchase graphs.
-
A Multimodal Text- and Graph-Based Approach for Open-Domain Event Extraction from Documents
MODEE is a multimodal system that integrates graphs with LLM embeddings to outperform prior open-domain event extraction methods on large datasets.
-
Automating the Wildfire Detection and Scheduling Pipeline with Maneuverable Earth Observation Satellites
A simulated pipeline combining CNN wildfire detection, Bayesian confidence updates, and reconfigurable satellite scheduling automates wildfire monitoring, but it is not validated on real satellite images.
-
Assumed Density Filtering and Smoothing with Neural Network Surrogate Models
Assumed density filtering and smoothing for neural network surrogate models is enabled by analytic computation of output moments, yielding more accurate state estimates and improved LQR performance on stochastic Lorenz and Wiener systems.
-
Dual-Stream EEG Decoding for 3D Visual Perception
Dual-stream EEG decoder separates identity and orientation to support 3D reconstruction from neural signals via circular regression and conditioned diffusion.
-
Short-Term Synaptic Plasticity Stabilizes Goal-Conditioned Dynamics in a PFC-Inspired Reservoir Model for Multistep Goal-Directed Action Planning
Short-term synaptic plasticity in a PFC-inspired reservoir model preserves goal-conditioned dynamics under noise, keeping multistep action selection robust where fixed-connectivity versions fail.
-
A Padding Method for Enhanced Encoding of Inorganic Structures with Varying Chemical Compositions
A symmetry-aware padding method for crystal structure encoding improves reconstruction accuracy by 5.3% on proton conductor data and yields 63.5% more novel stable materials on the perov-5 dataset compared to baseline.
-
Context-aware Entity-Relation Extraction for Threat Intelligence Knowledge Graphs
CTiKG pipeline improves named entity recognition by 3-4% and relation extraction by up to 8% on DNRTI-AUG-STIX2 and other CTI benchmarks by adding context-aware hybrid NLP and ontology knowledge.
-
Prompt Governance? On Governing Technologies Governed by Natural Language
Literature on system prompts for AI shows fragmented and contradictory claims that complicate policy efforts to use them as reliable governance mechanisms.
-
TinyNeRV: Compact Neural Video Representations via Capacity Scaling, Distillation, and Low-Precision Inference
Tiny NeRV models using capacity scaling, frequency-aware distillation, and low-precision quantization achieve favorable quality-efficiency trade-offs with far fewer parameters and lower computational costs than standard NeRV.
-
Search-Based Software Engineering and AI Foundation Models: Current Landscape and Future Roadmap
A research roadmap analyzing the current state of search-based software engineering with foundation models, outlining challenges and directions across three integration aspects.
-
Explainable Artificial Intelligence Techniques for Interpretation of Food Models: a Review
A survey proposing a taxonomy of XAI techniques for food quality research organized by data types and explanation methods.
-
Visual Hand Gesture Recognition with Deep Learning: A Comprehensive Review of Methods, Datasets, Challenges and Future Research Directions
A literature review that categorizes deep learning approaches for visual hand gesture recognition, summarizes state-of-the-art methods across tasks, reviews datasets and metrics, and identifies challenges and future directions.