MemHint combines LLM classification of custom memory functions with Z3 path validation to augment CodeQL and Infer, detecting 52 memory leaks (49 confirmed) across 3.4M LOC versus 19 and 3 by vanilla tools.
Research on overfitting of deep learning
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
Text Encoded Extrusions (TEE) lets LLMs generate and edit manifold 3D meshes by learning sequences of face extrusions from decomposed quadrilateral meshes.
GLUE orchestrates frozen pre-trained generative models into a system-level design generator that enforces feasibility, performance, and diversity, with data-driven and data-free variants benchmarked on UAV design.
Implicit neural fields enable joint optimization of manufacturing layers and toolpaths with explicit collision avoidance in a single differentiable pipeline for multi-axis processes.
Continuous trajectory representations of lithium-ion battery aging enable consistent knee-point detection and early remaining useful life predictions that remain robust across heterogeneous datasets.
Implicit neural representations enable stable, resolution-independent reconstruction of continuous environmental fields from sparse and irregular ecological data.
A review comparing three consciousness theories and outlining an adversarial collaboration to test their predictions through integrated multi-site experiments.
Z-Score Filtered SAM retains only high absolute Z-score gradient components per layer during the ascent step and reports higher test accuracy than standard SAM on CIFAR and Tiny-ImageNet benchmarks.
citing papers explorer
-
Finding Memory Leaks in C/C++ Programs via Neuro-Symbolic Augmented Static Analysis
MemHint combines LLM classification of custom memory functions with Z3 path validation to augment CodeQL and Infer, detecting 52 memory leaks (49 confirmed) across 3.4M LOC versus 19 and 3 by vanilla tools.
-
Learning to Build Shapes by Extrusion
Text Encoded Extrusions (TEE) lets LLMs generate and edit manifold 3D meshes by learning sequences of face extrusions from decomposed quadrilateral meshes.
-
GLUE: Coordinating Pre-Trained Generative Models for System-Level Design
GLUE orchestrates frozen pre-trained generative models into a system-level design generator that enforces feasibility, performance, and diversity, with data-driven and data-free variants benchmarked on UAV design.
-
Implicit Neural Field-Based Process Planning for Multi-Axis Manufacturing: Direct Control over Collision Avoidance and Toolpath Geometry
Implicit neural fields enable joint optimization of manufacturing layers and toolpaths with explicit collision avoidance in a single differentiable pipeline for multi-axis processes.
-
Continuous ageing trajectory representations for knee-aware lifetime prediction of lithium-ion batteries across heterogeneous dataset
Continuous trajectory representations of lithium-ion battery aging enable consistent knee-point detection and early remaining useful life predictions that remain robust across heterogeneous datasets.
-
Implicit neural representations as a coordinate-based framework for continuous environmental field reconstruction from sparse ecological observations
Implicit neural representations enable stable, resolution-independent reconstruction of continuous environmental fields from sparse and irregular ecological data.
-
Integrated information and predictive processing theories of consciousness: An adversarial collaborative review
A review comparing three consciousness theories and outlining an adversarial collaboration to test their predictions through integrated multi-site experiments.
-
Sharpness-Aware Minimization with Z-Score Gradient Filtering
Z-Score Filtered SAM retains only high absolute Z-score gradient components per layer during the ascent step and reports higher test accuracy than standard SAM on CIFAR and Tiny-ImageNet benchmarks.