Papers
Research papers from arXiv and related sources
Cornserve: A Distributed Serving System for Any-to-Any Multimodal Models
Any-to-Any models are an emerging class of multimodal models that accept combinations of multimodal data (e.g., text, image, video, audio) as input and generate them as output. Serving these models...
Jae-Won Chung, Jeff J. Ma, Jisang Ahn, Yizhuo Liang, Akshay Jajoo, Myungjin Lee, Mosharaf Chowdhury
On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agents
Reinforcement learning (RL) with outcome-based rewards has achieved significant success in training large language model (LLM) agents for complex reasoning tasks. However, in active reasoning where...
Deyu Zou, Yongqiang Chen, Fan Feng, Mufei Li, Pan Li, Yu Gong, James Cheng
To Words and Beyond: Probing Large Language Models for Sentence-Level Psycholinguistic Norms of Memorability and Reading Times
Large Language Models (LLMs) have recently been shown to produce estimates of psycholinguistic norms, such as valence, arousal, or concreteness, for words and multiword expressions, that correlate ...
Thomas Hikaru Clark, Carlos Arriaga, Javier Conde, Gonzalo Martínez, Pedro Reviriego
Human-Centred LLM Privacy Audits: Findings and Frictions
Large language models (LLMs) learn statistical associations from massive training corpora and user interactions, and deployed systems can surface or infer information about individuals. Yet people ...
Dimitri Staufer, Kirsten Morehouse, David Hartmann, Bettina Berendt
Resource-Efficient Iterative LLM-Based NAS with Feedback Memory
Neural Architecture Search (NAS) automates network design, but conventional methods demand substantial computational resources. We propose a closed-loop pipeline leveraging large language models (L...
Xiaojie Gu, Dmitry Ignatov, Radu Timofte
Cascade: Composing Software-Hardware Attack Gadgets for Adversarial Threat Amplification in Compound AI Systems
Rapid progress in generative AI has given rise to Compound AI systems - pipelines comprised of multiple large language models (LLM), software tools and database systems. Compound AI systems are con...
Sarbartha Banerjee, Prateek Sahu, Anjo Vahldiek-Oberwagner, Jose Sanchez Vicarte, Mohit Tiwari
An Intent of Collaboration: On Agencies between Designers and Emerging (Intelligent) Technologies
Amidst the emergence of powerful intelligent technologies such as LLMs and text-to-image AIs that promise to enhance creative processes, designers face the challenges of remaining empowered and cre...
Pei-Ying Lin, Julie Heij, Iris Borst, Britt Joosten, Kristina Andersen, Wijnand IJsselsteijn
Decentralized Orchestration Architecture for Fluid Computing: A Secure Distributed AI Use Case
Distributed AI and IoT applications increasingly execute across heterogeneous resources spanning end devices, edge/fog infrastructure, and cloud platforms, often under different administrative doma...
Diego Cajaraville-Aboy, Ana Fernández-Vilas, Rebeca P. Díaz-Redondo, Manuel Fernández-Veiga, Pabl...
Credibility Matters: Motivations, Characteristics, and Influence Mechanisms of Crypto Key Opinion Leaders
Crypto Key Opinion Leaders (KOLs) shape Web3 narratives and retail investment behaviour. In volatile, high-risk markets, their credibility becomes a key determinant of their influence on followers....
Alexander Kropiunig, Svetlana Kremer, Bernhard Haslhofer
BTZSC: A Benchmark for Zero-Shot Text Classification Across Cross-Encoders, Embedding Models, Rerankers and LLMs
Zero-shot text classification (ZSC) offers the promise of eliminating costly task-specific annotation by matching texts directly to human-readable label descriptions. While early approaches have pr...
Ilias Aarab
ConvScale: Conversational Interviews for Scale-Aligned Measurement
Conversational interviews are commonly used to complement structured surveys by eliciting rich and contextualized responses, which are typically analyzed qualitatively. However, their potential con...
Peinuan Qin, Jingzhu Chen, Yitian Yang, Han Meng, Zicheng Zhu, Yi-Chieh Lee
Normative Common Ground Replication (NormCoRe): Replication-by-Translation for Studying Norms in Multi-agent AI
In the late 2010s, the fashion trend NormCore framed sameness as a signal of belonging, illustrating how norms emerge through collective coordination. Today, similar forms of normative coordination...
Luca Deck, Simeon Allmendinger, Lucas Müller, Niklas Kühl
CHiL(L)Grader: Calibrated Human-in-the-Loop Short-Answer Grading
Scaling educational assessment with large language models requires not just accuracy, but the ability to recognize when predictions are trustworthy. Instruction-tuned models tend to be overconfiden...
Pranav Raikote, Korbinian Randl, Ioanna Miliou, Athanasios Lakes, Panagiotis Papapetrou
PersonaTrace: Synthesizing Realistic Digital Footprints with LLM Agents
Digital footprints (records of individuals' interactions with digital systems) are essential for studying behavior, developing personalized applications, and training machine learning models. Howev...
Minjia Wang, Yunfeng Wang, Xiao Ma, Dexin Lv, Qifan Guo, Lynn Zheng, Benliang Wang, Lei Wang, Jia...
Kraken*: Architecting Generative, Semantic, and Goal-Oriented Network Management for 6G Wireless Systems
Sixth-generation (6G) wireless networks are expected to support autonomous, immersive, and mission-critical services that require not only extreme data rates and ultra-low latency but also adaptive...
Ian F. Akyildiz, Tuğçe Bilen
Prototype-Based Knowledge Guidance for Fine-Grained Structured Radiology Reporting
Structured radiology reporting promises faster, more consistent communication than free text, but automation remains difficult as models must make many fine-grained, discrete decisions about rare f...
Chantal Pellegrini, Adrian Delchev, Ege Özsoy, Nassir Navab, Matthias Keicher
Chem4DLLM: 4D Multimodal LLMs for Chemical Dynamics Understanding
Existing chemical understanding tasks primarily rely on static molecular representations, limiting their ability to model inherently dynamic phenomena such as bond breaking or conformational change...
Xinyu Li, Zhen Zhang, Qi Chen, Anton van den Hengel, Lina Yao, Javen Qinfeng Shi
Understanding LLM Behavior When Encountering User-Supplied Harmful Content in Harmless Tasks
Large Language Models (LLMs) are increasingly trained to align with human values, primarily focusing on task level, i.e., refusing to execute directly harmful tasks. However, a subtle yet crucial c...
Junjie Chu, Yiting Qu, Ye Leng, Michael Backes, Yun Shen, Savvas Zannettou, Yang Zhang
FlexRec: Adapting LLM-based Recommenders for Flexible Needs via Reinforcement Learning
Modern recommender systems must adapt to dynamic, need-specific objectives for diverse recommendation scenarios, yet most traditional recommenders are optimized for a single static target and strug...
Yijun Pan, Weikang Qiu, Qiyao Ma, Mingxuan Ju, Tong Zhao, Neil Shah, Rex Ying
Silent Speech Interfaces in the Era of Large Language Models: A Comprehensive Taxonomy and Systematic Review
Human-computer interaction has traditionally relied on the acoustic channel, a dependency that introduces systemic vulnerabilities to environmental noise, privacy constraints, and physiological spe...
Kele Xu, Yifan Wang, Ming Feng, Qisheng Xu, Wuyang Chen, Yutao Dou, Cheng Yang, Huaimin Wang