No Image
2502.18639
Abstract and deep analysis are available in the full post.
General Research
All posts under category "General Research"
781 posts total
Sorted by date
No Image
2510.13709
Abstract and deep analysis are available in the full post.
No Image
A Multi-dimensional Semantic Surprise Framework Based on Low-Entropy Semantic Manifolds for Fine-Grained Out-of-Distribution Detection
Abstract and deep analysis are available in the full post.
Detection
Framework
AI Simulation by Digital Twins: Systematic Survey, Reference Framework, and Mapping to a Standardized Architecture
Insufficient data volume and quality are particularly pressing challenges in the adoption of modern subsymbolic AI. To alleviate these challenges, AI simulation uses virtual training environments in which AI agents can be safely and efficiently developed with simulated, synthetic data. Digital twins
Framework
System
No Image
AI ๊ธฐ๋ฐ ์์ ์ค์ ์์คํ ์ ์ํ ์๊ตฌ๊ณตํ๊ณผ ์๊ฐ ์ธ์ ๊ฒ์ฆ ํตํฉ ํ๋ ์์ํฌ
The integration of AI components, particularly Deep Neural Networks (DNNs), into safety-critical systems such as aerospace and autonomous vehicles presents fundamental challenges for assurance. The opacity of AI systems, combined with the semantic gap between high-level requirements and low-level ne
No Image
Auditing Algorithmic Bias in Transformer-Based Trading
Abstract and deep analysis are available in the full post.
No Image
AutoBackdoor: Automating Backdoor Attacks via LLM Agents
Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. However, existing methods often rely on manually crafted triggers and static data pipelines, which are rigid, labor-intensiv
BreakFun: Jailbreaking LLMs via Schema Exploitation
Abstract and deep analysis are available in the full post.
No Image
Bridging Research and Standardization: Innovations and Methodology for 6G Standard Contributions
Abstract and deep analysis are available in the full post.
Calibrating and Rotating: A Unified Framework for Weight Conditioning in PEFT
Parameter-Efficient Fine-Tuning (PEFT) methods are crucial for adapting large pre-trained models. Among these, LoRA is considered a foundational approach. Building on this, the influential DoRA method enhances performance by decomposing weight updates into magnitude and direction. However, its under
Framework
CAMNet: Leveraging Cooperative Awareness Messages for Vehicle Trajectory Prediction
Abstract and deep analysis are available in the full post.
No Image
EnergyTwin: A Multi-Agent System for Simulating and Coordinating Energy Microgrids
Microgrids are deployed to reduce purchased grid energy, limit exposure to volatile tariffs, and ensure service continuity during disturbances. This requires coordinating heterogeneous distributed energy resources across multiple time scales and under variable conditions. Among existing tools, typic
System
ESG ๋ฉํธ๋ฆญ ์ง์ ๊ทธ๋ํ ์๋ ๊ตฌ์ถ์ ์ํ ์จํจ๋ก์ง ๊ธฐ๋ฐ ํ๋ ์์ํฌ
Environmental, Social, and Governance (ESG) metric knowledge is inherently structured, connecting industries, reporting frameworks, metric categories, metrics, and calculation models through compositional dependencies, yet in practice this structure remains embedded implicitly in regulatory document
No Image
EvoXplain: When Machine Learning Models Agree on Predictions but Disagree on Why -- Measuring Mechanistic Multiplicity Across Training Runs
Machine learning models are primarily judged by predictive performance, especially in applied settings. Once a model reaches high accuracy, its explanation is often assumed to be correct and trustworthy. This assumption raises an overlooked question: when two models achieve high accuracy, do they re
Model
Learning
No Image
From FAIR to CURE: Guidelines for Computational Models of Biological Systems
Abstract and deep analysis are available in the full post.
Model
System
Language Models Can Understand Spectra: A Multimodal Model for Molecular Structure Elucidation
Abstract and deep analysis are available in the full post.
Model
No Image
LLM ํ์ต ๋ฐ์ดํฐ ์ ์๊ถ ๊ฒ์ฆ์ ์ํ ์คํ์์ค ํ๋ซํผ
The widespread use of Large Language Models (LLMs) raises critical concerns regarding the unauthorized inclusion of copyrighted content in training data. Existing detection frameworks, such as DE-COP, are computationally intensive, and largely inaccessible to independent creators. As legal scrutiny
No Image
LLMs for Automated Unit Test Generation and Assessment in Java: The AgoneTest Framework
Unit testing is an essential but resource-intensive step in software development, ensuring individual code units function correctly. This paper introduces AgoneTest, an automated evaluation framework for Large Language Model-generated (LLM) unit tests in Java. AgoneTest does not aim to propose a nov
Framework
No Image
MaskClip: Detachable Clip-on Piezoelectric Sensing of Mask Surface Vibrations for Real-time Noise-Robust Speech Input
Masks are essential in medical settings and during infectious outbreaks but significantly impair speech communication, especially in environments with background noise. Existing solutions often require substantial computational resources or compromise hygiene and comfort. We propose a novel sensing
MTQ-Eval: Multilingual Text Quality Evaluation for Language Models
Abstract and deep analysis are available in the full post.
Model
No Image
Multi-Agent Code Verification via Information Theory
LLMs generate buggy code: 29.6% of SWE-bench solved patches fail, 62% of BaxBench solutions have vulnerabilities, and existing tools only catch 65% of bugs with 35% false positives. We built CodeX-Verify, a multi-agent system that uses four specialized agents to detect different types of bugs. We pr
No Image
NOTAM-Evolve: A Knowledge-Guided Self-Evolving Optimization Framework with LLMs for NOTAM Interpretation
Accurate interpretation of Notices to Airmen (NOTAMs) is critical for aviation safety, yet their condensed and cryptic language poses significant challenges to both manual and automated processing. Existing automated systems are typically limited to shallow parsing, failing to extract the actionable
Framework
No Image
OS-R1: Agentic Operating System Kernel Tuning with Reinforcement Learning
Abstract and deep analysis are available in the full post.
Learning
System
PRiSM ๊ณผํ์ ์ถ๋ก ์ ์ํ ๋์ ๋ฉํฐ๋ชจ๋ฌ ๋ฒค์น๋งํฌ
Evaluating vision-language models (VLMs) in scientific domains like mathematics and physics poses unique challenges that go far beyond predicting final answers. These domains demand conceptual understanding, symbolic reasoning, and adherence to formal laws, requirements that most existing benchmarks
No Image
Quantifying Bounded Rationality: Formal Verification of Simon's Satisficing Through Flexible Stochastic Dominance
This paper introduces Flexible First-Order Stochastic Dominance (FFSD), a mathematically rigorous framework that formalizes Herbert Simon's concept of bounded rationality using the Lean 4 theorem prover. We develop machine-verified proofs demonstrating that FFSD bridges classical expected utility th
No Image
RAG-Driven Data Quality Governance for Enterprise ERP Systems
Enterprise ERP systems managing hundreds of thousands of employee records face critical data quality challenges when human resources departments perform decentralized manual entry across multiple languages. We present an end-to-end pipeline combining automated data cleaning with LLM-driven SQL query
System
Data
Robust and High-Fidelity 3D Gaussian Splatting: Fusing Pose Priors and Geometry Constraints for Texture-Deficient Outdoor Scenes
Abstract and deep analysis are available in the full post.
No Image
Snakes in the Plane: Controllable Gliders in a Nanomagnetic Metamaterial
Abstract and deep analysis are available in the full post.
Speeding Up MACE: Low-Precision Tricks for Equivarient Force Fields
Machine-learning force fields can deliver accurate molecular dynamics (MD) at high computational cost. For SO(3)-equivariant models such as MACE, there is little systematic evidence on whether reduced-precision arithmetic and GPU-optimized kernels can cut this cost without harming physical fidelity.
No Image
The complexity of reachability problems in strongly connected finite automata
Several reachability problems in finite automata, such as completeness of NFAs and synchronisation of total DFAs, correspond to fundamental properties of sets of nonnegative matrices. In particular, the two mentioned properties correspond to matrix mortality and ergodicity, which ask whether there e
Understanding and Mitigating Errors of LLM-Generated RTL Code
Abstract and deep analysis are available in the full post.
No Image
When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models
Large Reasoning Models (LRMs) achieve strong performance on complex multi-step reasoning, yet they still exhibit severe safety failures such as harmful content generation. Existing methods often apply coarse-grained constraints over the entire reasoning trajectories, which can undermine reasoning ca
Model
WorldScore: A Unified Evaluation Benchmark for World Generation
Abstract and deep analysis are available in the full post.
No Image
๋ฒ๋ฅ ๋ถ์ผ LLM ์ฑ๋ฅ ํฅ์์ ์ํ ๋ฌธ์ ๊ตฌ์กฐ ์ฌ๋ฐฐ์น์ ์ญํ ๊ธฐ๋ฐ ํ๋กฌํํธ ์ฐ๊ตฌ
Large Language Models (LLMs), trained on extensive datasets from the web, exhibit remarkable general reasoning skills. Despite this, they often struggle in specialized areas like law, mainly because they lack domain-specific pretraining. The legal field presents unique challenges, as legal documents
No Image
๋น๋ฐ๋ฒํธ ๊ฐ๋ ํ๊ฐ์ ์์ฑ์ ์ํ SODA ADVANCE: ๋ํ ์ธ์ด ๋ชจ๋ธ์ ์ญํ
Although passwords remain the primary defense against unauthorized access, users often tend to use passwords that are easy to remember. This behavior significantly increases security risks, also due to the fact that traditional password strength evaluation methods are often inadequate. In this discu
No Image
์์ฑ ํ๊ฐ ์ผ๊ด์ฑ์ ํ์ฉํ ๋ํ ์ธ์ด ๋ชจ๋ธ ์ ๋ ฌ ๋ฒค์น๋งํฌ
Alignment with human preferences is an important evaluation aspect of LLMs, requiring them to be helpful, honest, safe, and to precisely follow human instructions. Evaluating large language models' (LLMs) alignment typically involves directly assessing their open-ended responses, requiring human ann
ํ์ฐ ๋ชจ๋ธ์ ํ์ฉํ ๋ ธ๋ ์์ฑ ๋ถ๋ฆฌ ๋ผํฐ์ค ๋ํจ์ ๊ธฐ๋ฐ ํจ์จ์ ์์ฑ ์ ๊ทผ
Extracting individual elements from music mixtures is a valuable tool for music production and practice. While neural networks optimized to mask or transform mixture spectrograms into the individual source(s) have been the leading approach, the source overlap and correlation in music signals poses a
Irresponsible AI: big tech's influence on AI research and associated impacts
The accelerated development, deployment and adoption of artificial intelligence systems has been fuelled by the increasing involvement of big tech. This has been accompanied by increasing ethical concerns and intensified societal and environmental impacts. In this article, we review and discuss how
Placenta Accreta Spectrum Detection Using an MRI-based Hybrid CNN-Transformer Model
Placenta Accreta Spectrum (PAS) is a serious obstetric condition that can be challenging to diagnose with Magnetic Resonance Imaging (MRI) due to variability in radiologists' interpretations. To overcome this challenge, a hybrid 3D deep learning model for automated PAS detection from volumetric MRI
Model
Detection
Rectifying LLM Thought from Lens of Optimization
Recent advancements in large language models (LLMs) have been driven by their emergent reasoning capabilities, particularly through long chain-of-thought (CoT) prompting, which enables thorough exploration and deliberation. Despite these advances, long-CoT LLMs often exhibit suboptimal reasoning beh
Story2MIDI: Emotionally Aligned Music Generation from Text
In this paper, we introduce Story2MIDI, a sequence-to-sequence Transformer-based model for generating emotion-aligned music from a given piece of text. To develop this model, we construct the Story2MIDI dataset by merging existing datasets for sentiment analysis from text and emotion classification
Vision Foundry: A System for Training Foundational Vision AI Models
Self-supervised learning (SSL) leverages vast unannotated medical datasets, yet steep technical barriers limit adoption by clinical researchers. We introduce Vision Foundry, a code-free, HIPAA-compliant platform that democratizes pre-training, adaptation, and deployment of foundational vision models
Model
System
'The Dentist is an involved parent, the bartender is not': Revealing Implicit Biases in QA with Implicit BBQ
Existing benchmarks evaluating biases in large language models (LLMs) primarily rely on explicit cues, declaring protected attributes like religion, race, gender by name. However, real-world interactions often contain implicit biases, inferred subtly through names, cultural cues, or traits. This cri
A Comprehensive Framework for Automated Quality Control in the Automotive Industry
This paper presents a cutting-edge robotic inspection solution designed to automate quality control in automotive manufacturing. The system integrates a pair of collaborative robots, each equipped with a high-resolution camera-based vision system to accurately detect and localize surface and thread
Framework
A Linear Expectation Constraint for Selective Prediction and Routing with False-Discovery Control
Foundation models often generate unreliable answers, while heuristic uncertainty estimators fail to fully distinguish correct from incorrect outputs, causing users to accept erroneous answers without statistical guarantees. We address this through the lens of false discovery rate (FDR) control, ensu
A Survey of Bugs in AI-Generated Code
Developers are widely using AI code-generation models, aiming to increase productivity and efficiency. However, there are also quality concerns regarding the AI-generated code. The generated code is produced by models trained on publicly available code, which are known to contain bugs and quality is
Advancing Multimodal Teacher Sentiment Analysis:The Large-Scale T-MED Dataset & The Effective AAM-TSA Model
Teachers' emotional states are critical in educational scenarios, profoundly impacting teaching efficacy, student engagement, and learning achievements. However, existing studies often fail to accurately capture teachers' emotions due to the performative nature and overlook the critical impact of in
Analysis
Model
Data
AI/ML in 3GPP 5G Advanced -- Services and Architecture
The 3rd Generation Partnership Project (3GPP), the standards body for mobile networks, is in the final phase of Release 19 standardization and is beginning Release 20. Artificial Intelligence/ Machine Learning (AI/ML) has brought about a paradigm shift in technology and it is being adopted across in
AncientBench: Towards Comprehensive Evaluation on Excavated and Transmitted Chinese Corpora
Comprehension of ancient texts plays an important role in archaeology and understanding of Chinese history and civilization. The rapid development of large language models needs benchmarks that can evaluate their comprehension of ancient characters. Existing Chinese benchmarks are mostly targeted at
Arc Spline Approximation of Envelopes of Evolving Planar Domains
Computing the envelope of deforming planar domains is a significant and challenging problem with a wide range of potential applications. We approximate the envelope using circular arc splines, curves that balance geometric flexibility and computational simplicity. Our approach combines two concepts
< Category Statistics (Total: 5017) >
Astrophysics
658
Computer Science
1843
Condensed Matter
193
Economics
17
Electrical Engineering and Systems Science
94
General Relativity
66
General Research
781
HEP-EX
25
HEP-LAT
7
HEP-PH
79
HEP-TH
67
MATH-PH
79
Mathematics
922
NUCL-EX
6
NUCL-TH
14
Nonlinear Sciences
180
Physics
799
Quantitative Biology
307
Quantitative Finance
159
Quantum Physics
67
Statistics
234