arXiv:2609.04948v1 Announce Type: cross Abstract: Multi-expert models have become the dominant paradigm for long-tailed learning, largely attributed to…
Category: AI
How a Chatbot’s Response Style Shapes a Classroom: A Multi-Agent Simulation of Students Consulting AI
arXiv:2609.05018v1 Announce Type: cross Abstract: LLM-based chatbots are increasingly used as everyday confidants. Because they are designed to maximize…
ARIA – An Agentic Framework for Autonomous Testing of Infotainment Systems
arXiv:2609.04913v1 Announce Type: cross Abstract: Automotive infotainment validation still relies on manual testing, slow, costly, and incompatible with…
Better Understanding, Better Fixes? A Study of Hallucination in LLM-based Automated Program Repair
arXiv:2609.04909v1 Announce Type: cross Abstract: Large language models (LLMs) have significantly advanced automated program repair (APR), yet existing…
MCPO: Modality-Contrastive Preference Optimization for Multimodal Chain-of-Thought Compression
arXiv:2609.04947v1 Announce Type: cross Abstract: Recently, multimodal large-scale reasoning models have demonstrated remarkable capabilities in solving…
One Diffusion Model, Two Roles: Guided Trajectory Planning and Safety-Critical Scenario Generation in Closed-Loop Simulation
arXiv:2609.04921v1 Announce Type: cross Abstract: Diffusion probabilistic models can capture the multi-modal, interaction-rich distribution of joint…
TreeFI: Value-Aware Statistical Fault Injection for Deep Neural Networks
arXiv:2609.04912v1 Announce Type: cross Abstract: Reliability evaluation of deep neural networks under hardware faults commonly relies on fault injection,…
RefactorPlatform: An Open-Source Harness for Controlled Evaluation of Repository-Scale Refactoring Agents
arXiv:2609.04898v1 Announce Type: cross Abstract: Repository-scale refactoring requires coding agents to propagate a single change across many…
Methane Detection On Board Satellites from Unorthorectified Imagery
arXiv:2609.04906v1 Announce Type: cross Abstract: As a potent greenhouse gas, methane is a major driver of climate change. Its effective mitigation relies…
Sound-based Multi-Person 3D Pose Estimation
arXiv:2609.04902v1 Announce Type: cross Abstract: Can we recover the 3D poses of multiple people using only sound? This paper presents the first attempt…