Papers
Research papers from arXiv and related sources
LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure
Large language model (LLM) serving infrastructures are undergoing a shift toward heterogeneity and disaggregation. Modern deployments increasingly integrate diverse accelerators and near-memory pro...
Jaehong Cho, Hyunmin Choi, Guseul Heo, Jongse Park
SubspaceAD: Training-Free Few-Shot Anomaly Detection via Subspace Modeling
Detecting visual anomalies in industrial inspection often requires training with only a few normal images per category. Recent few-shot methods achieve strong results employing foundation-model fea...
Camile Lendering, Erkut Akdag, Egor Bondarev
Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization
Exploration remains the key bottleneck for large language model agents trained with reinforcement learning. While prior methods exploit pretrained knowledge, they fail in environments requiring the...
Zeyuan Liu, Jeonghye Kim, Xufang Luo, Dongsheng Li, Yuqing Yang
Managing Uncertainty in LLM-based Multi-Agent System Operation
Applying LLM-based multi-agent software systems in safety-critical domains such as lifespan echocardiography introduces system-level risks that cannot be addressed by improving model accuracy alone...
Man Zhang, Tao Yue, Yihua He
Understanding Older Adults' Experiences of Support, Concerns, and Risks from Kinship-Role AI-Generated Influencers
AI-generated influencers are rapidly gaining popularity on Chinese short-video platforms, often adopting kinship-based roles such as AI grandchildren to attract older adults. Although this trend ha...
Tianqi Song, Black Sun, Jingshu Li, Han Li, Chi-Lan Yang, Yijia Xu, Yi-Chieh Lee
Obscure but Effective: Classical Chinese Jailbreak Prompt Optimization via Bio-Inspired Search
As Large Language Models (LLMs) are increasingly used, their security risks have drawn increasing attention. Existing research reveals that LLMs are highly susceptible to jailbreak attacks, with ef...
Xun Huang, Simeng Qin, Xiaoshuang Jia, Ranjie Duan, Huanqian Yan, Zhitao Zeng, Fei Yang, Yang Liu...
Modeling Expert AI Diagnostic Alignment via Immutable Inference Snapshots
Human-in-the-loop validation is essential in safety-critical clinical AI, yet the transition between initial model inference and expert correction is rarely analyzed as a structured signal. We intr...
Dimitrios P. Panagoulias, Evangelia-Aikaterini Tsichrintzi, Georgios Savvidis, Evridiki Tsoureli-...
SPM-Bench: Benchmarking Large Language Models for Scanning Probe Microscopy
As LLMs achieved breakthroughs in general reasoning, their proficiency in specialized scientific domains reveals pronounced gaps in existing benchmarks due to data contamination, insufficient compl...
Peiyao Xiao, Xiaogang Li, Chengliang Xu, Jiayi Wang, Ben Wang, Zichao Chen, Zeyu Wang, Kejun Yu, ...
ClawMobile: Rethinking Smartphone-Native Agentic Systems
Smartphones represent a uniquely challenging environment for agentic systems. Unlike cloud or desktop settings, mobile devices combine constrained execution contexts, fragmented control interfaces,...
Hongchao Du, Shangyu Wu, Qiao Li, Riwei Pan, Jinheng Li, Youcheng Sun, Chun Jason Xue
pMoE: Prompting Diverse Experts Together Wins More in Visual Adaptation
Parameter-efficient fine-tuning has demonstrated promising results across various visual adaptation tasks, such as classification and segmentation. Typically, prompt tuning techniques have harnesse...
Shentong Mo, Xufang Luo, Dongsheng Li
InfoAlign: A Human-AI Co-Creation System for Storytelling with Infographics
Storytelling infographics are a powerful medium for communicating data-driven stories through visual presentation. However, existing authoring tools lack support for maintaining story consistency a...
Jielin Feng, Xinwu Ye, Qianhui Li, Verena Ingrid Prantl, Jun-Hsiang Yao, Yuheng Zhao, Yun Wang, S...
OmniGAIA: Towards Native Omni-Modal AI Agents
Human intelligence naturally intertwines omni-modal perception -- spanning vision, audio, and language -- with complex reasoning and tool usage to interact with the world. However, current multi-mo...
Xiaoxi Li, Wenxiang Jiao, Jiarui Jin, Shijian Wang, Guanting Dong, Jiajie Jin, Hao Wang, Yinuo Wa...
They Think AI Can Do More Than It Actually Can: Practices, Challenges, & Opportunities of AI-Supported Reporting In Local Journalism
Declining newspaper revenues prompt local newsrooms to adopt automation to maintain efficiency and keep the community informed. However, current research provides a limited understanding of how loc...
Besjon Cifliku, Hendrik Heuer
Towards LLM-Empowered Knowledge Tracing via LLM-Student Hierarchical Behavior Alignment in Hyperbolic Space
Knowledge Tracing (KT) diagnoses students' concept mastery through continuous learning state monitoring in education.Existing methods primarily focus on studying behavioral sequences based on ID or...
Xingcheng Fu, Shengpeng Wang, Yisen Gao, Xianxian Li, Chunpei Li, Qingyun Sun, Dongran Yu
Effective QA-driven Annotation of Predicate-Argument Relations Across Languages
Explicit representations of predicate-argument relations form the basis of interpretable semantic analysis, supporting reasoning, generation, and evaluation. However, attaining such semantic struct...
Jonathan Davidov, Aviv Slobodkin, Shmuel Tomi Klein, Reut Tsarfaty, Ido Dagan, Ayal Klein
MEDNA-DFM: A Dual-View FiLM-MoE Model for Explainable DNA Methylation Prediction
Accurate computational identification of DNA methylation is essential for understanding epigenetic regulation. Although deep learning excels in this binary classification task, its "black-box" natu...
Yi He, Yina Cao, Jixiu Zhai, Di Wang, Junxiao Kong, Tianchi Lu
Improving Neural Argumentative Stance Classification in Controversial Topics with Emotion-Lexicon Features
Argumentation mining comprises several subtasks, among which stance classification focuses on identifying the standpoint expressed in an argumentative text toward a specific target topic. While arg...
Mohammad Yeghaneh Abkenar, Weixing Wang, Manfred Stede, Davide Picca, Mark A. Finlayson, Panagiot...
The AI Research Assistant: Promise, Peril, and a Proof of Concept
Can artificial intelligence truly contribute to creative mathematical research, or does it merely automate routine calculations while introducing risks of error? We provide empirical evidence throu...
Tan Bui-Thanh
Moral Preferences of LLMs Under Directed Contextual Influence
Moral benchmarks for LLMs typically use context-free prompts, implicitly assuming stable preferences. In deployment, however, prompts routinely include contextual signals such as user requests, cue...
Phil Blandfort, Tushar Karayil, Urja Pawar, Robert Graham, Alex McKenzie, Dmitrii Krasheninnikov
TCM-DiffRAG: Personalized Syndrome Differentiation Reasoning Method for Traditional Chinese Medicine based on Knowledge Graph and Chain of Thought
Background: Retrieval augmented generation (RAG) technology can empower large language models (LLMs) to generate more accurate, professional, and timely responses without fine tuning. However, due ...
Jianmin Li, Ying Chang, Su-Kit Tang, Yujia Liu, Yanwen Wang, Shuyuan Lin, Binkai Ou