LLM-based security code review is vulnerable to framing bias, with a novel iterative refinement attack achieving 100% success in reintroducing vulnerabilities across real projects.
Canonical reference
Title resolution pending
Canonical reference. 80% of citing Pith papers cite this work as background.
17
Pith papers citing it
Background
80% of classified citations
citation-role summary
background 5
citation-polarity summary
roles
background 5representative citing papers
Presents the ev-CIVIL dataset and benchmark showing that event-based cameras can support real-time detection of cracks and spalling in civil infrastructure under challenging lighting.
NESA presents a neuro-symbolic framework that decomposes static analyses into policy-defined sub-problems solved by parsers and LLMs to enable compilation-free customizable analysis with reduced hallucinations.
ML4AVD research remains locked into binary function-level classification of C/C++ vulnerabilities because twelve pain points in the pipeline reinforce each other through feedback loops.
VLMs fail to identify visual preconditions or apply physical laws in kinematic physics tasks, as shown by new FACT diagnostics and NICE calibration methods evaluated on six state-of-the-art models.
CAHAL introduces a physics-informed mixture-of-experts super-resolution network for clinical MRI that conditions on resolution and anisotropy and uses edge-penalised, Fourier, and segmentation-guided losses to reduce hallucinations compared with prior generative methods.
A PRISMA-based survey of 158 computational works on toxic meme detection introduces a new toxicity taxonomy and a framework linking target, intent, and conveyance tactics while noting trends in LLMs and cross-modal methods.
Clockless FPGA circuits produce autonomous spiking neuron networks that achieve competitive audio classification accuracy with significantly lower power than conventional digital implementations.
Fisher vector encoding integrated into CNN-ViT hybrids outperforms benchmarks on MedMNIST datasets and matches literature results on other medical image sets.
The authors present a Python library and discrete variational framework for training neural networks to solve PDEs like Stokes equations with a robust loss function tied to the true discrete error.
RedShell fine-tunes LLMs on enhanced malicious PowerShell data to produce syntactically valid offensive code for pentesting, reporting over 90% validity, strong semantic match to references, and better edit-distance similarity than prior methods plus functional execution success.
A novel MPI-based construction method for spiking neural networks on multi-GPU clusters is introduced, with scaling demonstrated on two cortical models using point-to-point and collective communication.
Stronger physics priors in neural networks for spatio-temporal shear flow forecasting yield substantially lower training carbon footprints than weak or no priors, though inference savings are less consistent.
Mujica-MyGo decomposes multi-turn RAG interactions via multi-agent workflows and applies minimalist policy gradient optimization to improve performance on QA benchmarks while avoiding long-context problems.
SNNs deployed on Loihi 2 achieve real-time object detection with the lowest dynamic energy per inference and recover 87-100% of ANN accuracy via distillation-aware training.
Spin wave-based physical reservoir computing achieves 85.8% speaker classification accuracy without cochleagram preprocessing.
MSEA uses a master-slave encoder architecture on patent specifications and claims, enhanced with pointer networks and repetition suppression, to generate better summaries as measured by small ROUGE score gains.
citing papers explorer
-
Measuring and Exploiting Contextual Bias in LLM-Assisted Security Code Review
LLM-based security code review is vulnerable to framing bias, with a novel iterative refinement attack achieving 100% success in reintroducing vulnerabilities across real projects.
-
Event-based Civil Infrastructure Visual Defect Detection: ev-CIVIL Dataset and Benchmark
Presents the ev-CIVIL dataset and benchmark showing that event-based cameras can support real-time detection of cracks and spalling in civil infrastructure under challenging lighting.
-
NESA: Relational Neuro-Symbolic Static Program Analysis
NESA presents a neuro-symbolic framework that decomposes static analyses into policy-defined sub-problems solved by parsers and LLMs to enable compilation-free customizable analysis with reduced hallucinations.
-
Direction for Detection: A Survey of Automated Vulnerability Detection and all of its Pain Points
ML4AVD research remains locked into binary function-level classification of C/C++ vulnerabilities because twelve pain points in the pipeline reinforce each other through feedback loops.
-
NICE FACT: Diagnosing and Calibrating VLMs in Quantitative Reasoning for Kinematic Physics
VLMs fail to identify visual preconditions or apply physical laws in kinematic physics tasks, as shown by new FACT diagnostics and NICE calibration methods evaluated on six state-of-the-art models.
-
CAHAL: Clinically Applicable resolution enHAncement for Low-resolution MRI scans
CAHAL introduces a physics-informed mixture-of-experts super-resolution network for clinical MRI that conditions on resolution and anisotropy and uses edge-penalised, Fourier, and segmentation-guided losses to reduce hallucinations compared with prior generative methods.
-
Toxic Memes: A Survey of Computational Perspectives on the Detection and Explanation of Meme Toxicities
A PRISMA-based survey of 158 computational works on toxic meme detection introduces a new toxicity taxonomy and a framework linking target, intent, and conveyance tactics while noting trends in LLMs and cross-modal methods.
-
Scalable neuromorphic computing from autonomous spiking dynamics in a clockless reconfigurable chip
Clockless FPGA circuits produce autonomous spiking neuron networks that achieve competitive audio classification accuracy with significantly lower power than conventional digital implementations.
-
Deep neural networks with Fisher vector encoding for medical image classification
Fisher vector encoding integrated into CNN-ViT hybrids outperforms benchmarks on MedMNIST datasets and matches literature results on other medical image sets.
-
Python library supporting Discrete Variational Formulations and training solutions with Collocation-based Robust Variational Physics Informed Neural Networks (DVF-CRVPINN)
The authors present a Python library and discrete variational framework for training neural networks to solve PDEs like Stokes equations with a robust loss function tied to the true discrete error.
-
Towards Automated Pentesting with Large Language Models
RedShell fine-tunes LLMs on enhanced malicious PowerShell data to produce syntactically valid offensive code for pentesting, reporting over 90% validity, strong semantic match to references, and better edit-distance similarity than prior methods plus functional execution success.
-
Scalable Construction of Spiking Neural Networks using up to thousands of GPUs
A novel MPI-based construction method for spiking neural networks on multi-GPU clusters is introduced, with scaling demonstrated on two cortical models using point-to-point and collective communication.
-
Physics Priors Offer Useful Accuracy-Carbon Trade-Offs in Spatio-Temporal Forecasting
Stronger physics priors in neural networks for spatio-temporal shear flow forecasting yield substantially lower training carbon footprints than weak or no priors, though inference savings are less consistent.
-
Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning
Mujica-MyGo decomposes multi-turn RAG interactions via multi-agent workflows and applies minimalist policy gradient optimization to improve performance on QA benchmarks while avoiding long-context problems.
-
Real-Time Frame- and Event-based Object Detection with Spiking Neural Networks on Edge Neuromorphic Hardware: Design, Deployment and Benchmark
SNNs deployed on Loihi 2 achieve real-time object detection with the lowest dynamic energy per inference and recover 87-100% of ANN accuracy via distillation-aware training.
-
Spoken Digit Recognition and Speaker Classification by Nonlinear Interfered Spin Wave-Based Physical Reservoir Computing
Spin wave-based physical reservoir computing achieves 85.8% speaker classification accuracy without cochleagram preprocessing.
-
The Master-Slave Encoder Model for Improving Patent Text Summarization: A New Approach to Combining Specifications and Claims
MSEA uses a master-slave encoder architecture on patent specifications and claims, enhanced with pointer networks and repetition suppression, to generate better summaries as measured by small ROUGE score gains.