wovepaper — the arXiv observatory

The paper introduces ArtifactGuide, a structured scoring rubric for software artifact evaluation, and ArtifactCopilot, an LLM‑based agent that follows this rubric to automatically…

#artifact evaluation#automated review#llm agents#software engineering

cs.AI2020

Analogous Process Structure Induction for Sub-event Sequence Prediction

Hongming Zhang, Muhao Chen, Haoyu Wang +2

cs.CR2023

Abusing the Ethereum Smart Contract Verification Services for Fun and Profit

Pengxiang Ma, Ningyu He, Yuhua Huang +2

stat.ML2019

Nearest-Neighbor Neural Networks for Geostatistics

Haoyu Wang, Yawen Guan, Brian J Reich

nucl-ex2025

Tomographic beta-gamma spectroscopy of nuclear beta decay

PandaX Collaboration, Zhe Yuan, Zihao Bo +111

cs.CR2021

Towards A First Step to Understand Flash Loan and Its Applications in DeFi Ecosystem

Dabao Wang, Siwei Wu, Ziling Lin +5

cs.RO2026

ExToken: Structured Exploration for Efficient Vision-Language-Action Reinforcement Fine-tuning

Yilun Kong, Yunpeng Qing, Guozheng Ma +4

The paper proposes ExToken, a framework that conditions vision‑language‑action policies on discrete behavioral tokens derived from offline demonstrations to promote diverse, struct…

#reinforcement learning#vision-language-action#exploration#behavioral tokens

cs.AI2026

Chat2Scenic: An Iterative RAG-Based Framework for Scenario Generation in Autonomous Driving

Yuan Gao, Wenting Miao, Mattia Piccinini +3

Chat2Scenic is an interactive, retrieval‑augmented framework that uses large language models to generate executable scenario scripts in a domain‑specific language for testing auton…

#scenario generation#retrieval-augmented generation#autonomous driving simulation#regulatory compliance

eess.AS2026

A Polarization-Decomposed Method for Simulating Inhomogeneous Birefringence in Laser-Interferometric Gravitational-Wave Detectors

Haoyu Wang, Yuta Michimura, Keiko Kokeyama +9

eess.SP2024

LLM$\times$MapReduce-V2: Entropy-Driven Convolutional Test-Time Scaling for Generating Long-Form Articles from Extremely Long Resources

Haoyu Wang, Yujia Fu, Zhu Zhang +8

cs.SE2026

Publications (497)

DeepPayload: Black-box Backdoor Attack on Deep Learning Models through Neural Payload Injection

Beyond Fidelity: Explaining Vulnerability Localization of Learning-based Detectors

Towards Lightweight Speaker Verification via Adaptive Neural Network Quantization

Towards Direct Latent-Space Synthesis for Parallel Branches in LLM-Agent Workflows

MV-VTON: Multi-View Virtual Try-On with Diffusion Models

Unveiling the Landscape of LLM Deployment in the Wild: An Empirical Study

Quantitative Universality for the Largest Eigenvalue of Sample Covariance Matrices

EVLA: An Electro-Aware Multimodal Assistant for Physically-Grounded Driving Reasoning and Control

Continual Alignment for SAM: Rethinking Foundation Models for Medical Image Segmentation in Continual Learning

Slow light silicon modulator beyond 110 GHz bandwidth

CHAMP: Characterizing Undesired App Behaviors from User Comments based on Market Policies

Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions

Measurement of solar $pp$ neutrino flux with the new PandaX-4T data

GPT-4o System Card

Remeasuring the Arbitrage and Sandwich Attacks of Maximal Extractable Value in Ethereum

CanCal: Towards Real-time and Lightweight Ransomware Detection and Response in Industrial Environments

CFinBench: A Comprehensive Chinese Financial Benchmark for Large Language Models

Word-Level Emotional Expression Control in Zero-Shot Text-to-Speech Synthesis

Test of Nuclear Decay Rate Variation due to an Antineutrino Flux

AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents

Representation Interventions Enable Lifelong Knowledge Memory Control in LLMs

When Specifications Meet Reality: Uncovering API Inconsistencies in Ethereum Infrastructure

Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency

A Temporal Reasoning Benchmarking Framework for LRMs via Difficulty-controlled and Dynamic Test Generation

Pitfalls in Language Models for Code Intelligence: A Taxonomy and Survey

Large Language Models for Software Engineering: A Systematic Literature Review

Software Engineering for OpenHarmony: A Research Roadmap

Structure-Aware RAG: Structured Retrieval Augmented Generation from Noisy Data for Conversational Agents

Are Large Language Models Really Robust to Word-Level Perturbations?

Dating with Scambots: Understanding the Ecosystem of Fraudulent Dating Applications

Energy-Efficient Computation with DVFS using Deep Reinforcement Learning for Multi-Task Systems in Edge Computing

"Your AI, My Shell": Demystifying Prompt Injection Attacks on Agentic AI Coding Editors

Enhancing Multimodal In-Context Learning via Inductive-Deductive Reasoning

An Empirical Study on Deployment Faults of Deep Learning Based Mobile Applications

GRASP: Guided Region-Aware Sparse Prompting for Adapting MLLMs to Remote Sensing

On the (In)Security of LLM App Stores

RIO-CPD: A Riemannian Geometric Method for Correlation-aware Online Change Point Detection

VoiceWukong: Benchmarking Deepfake Voice Detection

Lifelong Safety Alignment for Language Models

iLibScope: Reliable Third-Party Library Detection for iOS Mobile Apps

LLM$\times$MapReduce: Simplified Long-Sequence Processing using Large Language Models

HalluCXR: Benchmarking and Mitigating Hallucinations in Medical Vision-Language Models for Chest Radiograph Interpretation

Orbital Magneto-Nonlinear Anomalous Hall Effect in Kagome Magnet Fe$_3$Sn$_2$

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation

Fine-tuning an ECG Foundation Model to Predict Coronary CT Angiography Outcomes

SAM-Med2D

Extracting or Guessing? Improving Faithfulness of Event Temporal Relation Extraction

A Comprehensive Study on Challenges in Deploying Deep Learning Based Software

Optimal Smoothed Analysis and Quantitative Universality for the Smallest Singular Value of Random Matrices

Comparing SNNs and RNNs on Neuromorphic Vision Datasets: Similarities and Differences

The fate of reentrant localization phenomenon in the one-dimensional dimerized quasiperiodic chain with long-range hopping

ExACT: An End-to-End Autonomous Excavator System Using Action Chunking With Transformers

GeneralVLA-2: Geometry-Aware Reconstruction and Governed Memory for Robot Planning

CLIR: Liveness-Driven and Structure-Aware Fuzzing for the Cranelift Compiler

The Solar Close Observations and Proximity Experiments (SCOPE) mission

Rethinking Noise-Robust Training for Frozen Vision Foundation Models: A Cross-Dataset Benchmark with a Case Study of Small-Loss Failure

Assessing the Feasibility of Web-Request Prediction Models on Mobile Platforms

Dual-view X-ray Detection: Can AI Detect Prohibited Items from Dual-view X-ray Images like Humans?

Generate Then Correct: Single Shot Global Correction for Aspect Sentiment Quad Prediction

Safety Reasoning with Guidelines

SegBook: A Simple Baseline and Cookbook for Volumetric Medical Image Segmentation

Beyond the Scope: Security Testing of Permission Management in Team Workspace

Directed Greybox Fuzzing via Large Language Model

Agent-Based Software Artifact Evaluation

Analogous Process Structure Induction for Sub-event Sequence Prediction

Abusing the Ethereum Smart Contract Verification Services for Fun and Profit

Nearest-Neighbor Neural Networks for Geostatistics

Tomographic beta-gamma spectroscopy of nuclear beta decay

Towards A First Step to Understand Flash Loan and Its Applications in DeFi Ecosystem

ExToken: Structured Exploration for Efficient Vision-Language-Action Reinforcement Fine-tuning

Chat2Scenic: An Iterative RAG-Based Framework for Scenario Generation in Autonomous Driving

Efficient Emotion and Speaker Adaptation in LLM-Based TTS via Characteristic-Specific Partial Fine-Tuning

Arm-Constrained Curriculum Learning for Loco-Manipulation of the Wheel-Legged Robot

Unveiling Large Language Model Supply Chain: Structure, Domain, and Vulnerabilities

BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filtering

A Polarization-Decomposed Method for Simulating Inhomogeneous Birefringence in Laser-Interferometric Gravitational-Wave Detectors

Non-Reciprocal Reconfigurable Intelligent Surfaces

A Big Step Forward? A User-Centric Examination of iOS App Privacy Report and Enhancements

Ultrabroadband Integrated Photonics Empowering Full-Spectrum Adaptive Wireless Communications