Search: “research”

Fine-Tuning Pre-Trained Code Models for AI-Generated Code Detection

arXiv:2605.01596v1 Announce Type: new Abstract: This paper describes the system submitted by team extbf{Archaeology} to SemEval-2026 Task~13 on AI-generated code detection. The shared task consists of

Floating-Point Networks with Automatic Differentiation Can Represent Almost All Floating-Point Functions and Their Gradients

DGX agent

arXiv:2605.01702v1 Announce Type: new Abstract: Theoretical studies show that for any differentiable function on a compact domain, there exists a neural network that approximates both the function val

researcharxiv-cs-lg

5 May 2026

Focus and Dilution: The Multi-stage Learning Process of Attention

arXiv:2605.01199v1 Announce Type: new Abstract: Transformer-based models have achieved remarkable success across a wide range of domains, yet our understanding of their training dynamics remains limit

Foundation Model Guided Dual-Branch Co-Adaptation for Source-Free EEG Decoding

arXiv:2605.00857v1 Announce Type: cross Abstract: Source-free domain adaptation (SFDA) provides a practical solution to cross-subject EEG decoding by adapting source-pretrained models to unlabeled tar

From Characterization To Construction: Generative Quantum Circuit Synthesis from Gate Set Tomography Data

arXiv:2605.01367v1 Announce Type: cross Abstract: High-fidelity circuit execution on noisy intermediate-scale quantum devices is bottlenecked by compilation pipelines that disregard complex, correlate

From Cortical Synchronous Rhythm to Brain Inspired Learning Mechanism: An Oscillatory Spiking Neural Network with Time-Delayed Coordination

arXiv:2605.01656v1 Announce Type: cross Abstract: Human cognition emerges from coordinated spiking dynamics in distributed neural circuits, where information is encoded via both firing rates and preci

From Flat Facts to Sharp Hallucinations: Detecting Stubborn Errors via Gradient Sensitivity

arXiv:2605.00939v1 Announce Type: new Abstract: Traditional hallucination detection fails on 'Stubborn Hallucinations' -- errors where LLMs are confidently wrong. We propose a geometric solution: Embe

From Packets to Patterns: Interpreting Encrypted Network Traffic as Longitudinal Behavioral Signals

arXiv:2605.01616v1 Announce Type: new Abstract: Human behavior is difficult to observe continuously at scale, yet it leaves measurable traces in everyday device use. We test whether encrypted smartpho

From Spherical to Gaussian: A Comparative Analysis of Point Cloud Cropping Strategies in Large-Scale 3D Environments

arXiv:2605.02098v1 Announce Type: new Abstract: Large-scale 3D point clouds can consist of billions of points. Even after downsampling, these point clouds are too large for modern 3D neural networks.

FunFuzz: An LLM-Powered Evolutionary Fuzzing Framework

arXiv:2605.02789v1 Announce Type: cross Abstract: Modern fuzzers increasingly use Large Language Models (LLMs) to generate structured inputs, but LLM-driven fuzzing is sensitive to prompt initializati

Fuzzy Fingerprinting Encoder Pre-trained Language Models for Emotion Recognition in Conversations: Human Assessment and Validity Study

arXiv:2605.02665v1 Announce Type: new Abstract: In Emotion Recognition in Conversations (ERC), model decisions should align with nuanced human perception and ideally provide insights on the classifica

Gaussian Approximation and Multiplier Bootstrap for Stochastic Gradient Descent

arXiv:2502.06719v3 Announce Type: replace-cross Abstract: In this paper, we establish the non-asymptotic validity of the multiplier bootstrap procedure for constructing the confidence sets using the S

GEASS: Training-Free Caption Steering for Hallucination Mitigation in Vision-Language Models

arXiv:2605.01733v1 Announce Type: new Abstract: Vision-Language Models (VLMs) excel at grounded reasoning but remain prone to object hallucination. Recent work treats self-generated captions as a unif

Generative Interfaces for Language Models

arXiv:2508.19227v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly seen as assistants, copilots, and consultants, capable of supporting a wide range of tasks through nat

GEODE: Angle-Adaptive OOD Detection with Universal Scorer Compatibility

arXiv:2605.01063v1 Announce Type: cross Abstract: Outlier Exposure (OE) is among the strongest training-based OOD detectors on standard benchmarks but exhibits scorer-dependent tradeoffs (e.g., strong

Global-Local Feature Decoding with Adapter-Guided SAMv2 for Salient Object Detection

arXiv:2605.02616v1 Announce Type: new Abstract: Salient Object Detection (SOD) remains an essential yet underexplored task in the era of large-scale vision models. Although foundation models like SAM

Gradient Boosted Risk Scores

arXiv:2605.02593v1 Announce Type: new Abstract: Risk scores are an interpretable and actionable class of machine learning models with applications in medicine, insurance, and risk management. Unlike m

Gradient-Discrepancy Acquisition for Pool-Based Active Learning

arXiv:2605.02609v1 Announce Type: new Abstract: The effectiveness of active learning hinges on the choice of the acquisition criterion by which a learning algorithm selects potentially informative dat

Graph-Augmented Topological Internalization with Dual-Stream Classifiers for Medical Report Generation

arXiv:2605.02376v1 Announce Type: new Abstract: Automated medical report generation, MRG, holds substantial value for alleviating radiologist workload and enhancing diagnostic efficiency. However, mai

GraphSculptor: Sculpting Pre-training Coreset for Graph Self-supervised Learning

arXiv:2605.01310v1 Announce Type: new Abstract: Graph self-supervised learning typically relies on large-scale unlabeled datasets, heavily inflating computational costs. However, empirical evidence su

GRAVITY: Architecture-Agnostic Structured Anchoring for Long-Horizon Conversational Memory

arXiv:2605.01688v1 Announce Type: new Abstract: Long-horizon conversational agents rely on memory systems with increasingly sophisticated retrieval mechanisms. However, retrieved fragments are typical

GSDeformer: Direct, Real-time and Extensible Cage-based Deformation for 3D Gaussian Splatting

arXiv:2405.15491v4 Announce Type: replace Abstract: We present GSDeformer, a method that enables cage-based deformation on 3D Gaussian Splatting (3DGS). Our approach bridges cage-based deformation and

Hallucination Detection in LLMs with Topological Divergence on Attention Graphs

arXiv:2504.10063v4 Announce Type: replace Abstract: Hallucination, i.e., generating factually incorrect content, remains a critical challenge for large language models (LLMs). We introduce TOHA, a TOp

Harnessing Reasoning Trajectories for Hallucination Detection via Answer-agreement Representation Shaping

arXiv:2601.17467v2 Announce Type: replace Abstract: Large reasoning models (LRMs) often generate long, seemingly coherent reasoning traces yet still produce incorrect answers, making hallucination det

Heavy-Tailed Principal Component Analysis

arXiv:2603.11308v2 Announce Type: replace Abstract: Principal Component Analysis (PCA) is a cornerstone of dimensionality reduction, yet its classical formulation relies critically on second-order mom

HELIX: Hybrid Encoding with Learnable Identity and Cross-dimensional Synthesis for Time Series Imputation

arXiv:2605.02278v1 Announce Type: new Abstract: Time series imputation benefits from leveraging cross-feature correlations, yet existing attention-based methods re-discover feature relationships at ea

Hey, That's My Data! Token-Only Dataset Inference in Large Language Models

arXiv:2506.06057v2 Announce Type: replace Abstract: Large Language Models (LLMs) rely on massive training datasets, often including proprietary data, which raises concerns about unauthorized usage and

HiFi-Mamba: Dual-Stream W-Laplacian Enhanced Mamba for High-Fidelity MRI Reconstruction

arXiv:2508.09179v3 Announce Type: replace-cross Abstract: Reconstructing high-fidelity MR images from undersampled k-space data remains a challenging problem in MRI. While Mamba variants for vision ta

High-Quality Spatial Reconstruction and Orthoimage Generation Using Efficient 2D Gaussian Splatting

arXiv:2503.19703v3 Announce Type: replace Abstract: Highly accurate geometric precision and dense image features characterize True Digital Orthophoto Maps (TDOMs), which are in great demand for applic

High-Speed, Scalable Sensor Readout for Dexterous Robotic Hands via Shift-Register Multiplexing

arXiv:2605.01434v1 Announce Type: new Abstract: Dexterous robotic hands require high-speed multimodal sensing across many degrees of freedom, yet existing readout architectures often impose trade-offs

researcharxiv-cs-ro

Higher-Order Flexible Configurations of Planar Parallel Manipulators Constructed by Averaging

arXiv:2605.02434v1 Announce Type: new Abstract: This paper investigates singular configurations of planar 3-RPR parallel manipulators, which result from applying the averaging technique to solution pa

researcharxiv-cs-ro

How Good is Your Wikipedia? Auditing Data Quality for Low-resource and Multilingual NLP

arXiv:2411.05527v3 Announce Type: replace Abstract: Wikipedia's perceived high quality and broad language coverage have established it as a fundamental resource in NLP. However, in recent years, such

How Label Imbalance Shapes Geometry: A General Spectral Analysis of Multi-Label Neural Collapse

arXiv:2605.01897v1 Announce Type: new Abstract: This work investigates the phenomenon of Neural Collapse (NC) in multi-label classification, extending its conceptual framework from multi-class learnin

How Prompts Move Language Model Behavior: Frames, Salience, and Construal as Semantic Control

arXiv:2512.12688v3 Announce Type: replace-cross Abstract: Prompt engineering is widely used to shape large language model behavior, yet it is often treated as a practical heuristic rather than as a fo

HyMem: Hybrid Memory Architecture with Dynamic Retrieval Scheduling

arXiv:2602.13933v2 Announce Type: replace Abstract: Large language model (LLM) agents demonstrate strong performance in short-text contexts but often underperform in extended dialogues due to ineffici

researcharxiv-cs-ai

IMPACT-HOI: Supervisory Control for Onset-Anchored Partial HOI Event Construction

arXiv:2605.01666v1 Announce Type: new Abstract: We present IMPACT-HOI, a mixed-initiative framework for annotating egocentric procedural video by constructing structured event graphs for Human-Object

IMPACT-Scribe: Interactive Temporal Action Segmentation with Boundary Scribbles and Query Planning

arXiv:2605.01668v1 Announce Type: new Abstract: Dense temporal annotation of procedural activity videos is vital for action understanding and embodied intelligence but remains labor-intensive due to r

Improving Factuality in LLMs via Inference-Time Knowledge Graph Construction

arXiv:2509.03540v3 Announce Type: replace Abstract: Large Language Models (LLMs) often struggle with producing factually consistent answers due to limitations in their parametric memory. Retrieval-Aug

Improving Imbalanced Multi-Label Chest X-Ray Diagnosis via CBAM-Enhanced CNN Backbones

arXiv:2605.02328v1 Announce Type: new Abstract: Chest radiography is a widely used imaging modality for thoracic disease diagnosis, yet its conventional interpretation remains time-consuming and heavi

Improving LLM Code Generation via Requirement-Aware Curriculum Reinforcement Learning

arXiv:2605.00433v1 Announce Type: cross Abstract: Code generation, which aims to automatically generate source code from given programming requirements, has the potential to substantially improve soft

researcharxiv-cs-ai

InfiltrNet: Dual-Branch CNN-Transformer Architecture for Brain Tumor Infiltration Risk Prediction

arXiv:2605.02230v1 Announce Type: new Abstract: Gliomas are aggressive brain tumors that infiltrate surrounding tissue beyond the visible tumor margins observed on Magnetic Resonance Imaging (MRI). Pr

InfoLaw: Information Scaling Laws for Large Language Models with Quality-Weighted Mixture Data and Repetition

arXiv:2605.02364v1 Announce Type: new Abstract: Upweighting high-quality data in LLM pretraining often improves performance, but in datalimited regimes, especially under overtraining, stronger upweigh

Interlaced R2D2 DNN Series for Scalable Non-Cartesian MRI with Sensitivity Self-calibration

arXiv:2503.09559v3 Announce Type: replace-cross Abstract: We introduce interlaced R2D2 (iR2D2), a DNN series paradigm for scalable image reconstruction from accelerated non-Cartesian k-space acquisiti

Interpretable Difficulty-Aware Knowledge Tracing in Tutor-Student Dialogues

arXiv:2605.01097v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have led to the development of AI-powered tutoring systems that provide interactive support via dialogue

KANs need curvature: penalties for compositional smoothness

arXiv:2605.02190v1 Announce Type: new Abstract: Kolmogorov-Arnold networks (KANs) offer a potent combination of accuracy and interpretability, thanks to their compositions of learnable univariate acti

Kernel Treatment Effects with Adaptively Collected Data

arXiv:2510.10245v2 Announce Type: replace-cross Abstract: Adaptive experiments improve efficiency by adjusting treatment assignments based on past outcomes, but this adaptivity breaks the i.i.d. assum

Kinematic Kitbashing

arXiv:2510.13048v2 Announce Type: replace Abstract: We introduce Kinematic Kitbashing, an optimization framework that synthesizes articulated 3D objects by assembling reusable parts conditioned on an

researcharxiv-cs-ro

Large margin classifier with graph-based adaptive regularization

arXiv:2605.02027v1 Announce Type: new Abstract: This paper introduces the use of per-class regularization hyperparameters in Gabriel graph-based binary classifiers. We demonstrate how the quality inde