Papers
Research papers from arXiv and related sources
Evaluating Zero-Shot and One-Shot Adaptation of Small Language Models in Leader-Follower Interaction
Leader-follower interaction is an important paradigm in human-robot interaction (HRI). Yet, assigning roles in real time remains challenging for resource-constrained mobile and assistive robots. Wh...
Rafael R. Baptista, André de Lima Salgado, Ricardo V. Godoy, Marcelo Becker, Thiago Boaventura, G...
Inferential Mechanics Part 1: Causal Mechanistic Theories of Machine Learning in Chemical Biology with Implications
Machine learning techniques are now routinely encountered in research laboratories across the globe. Impressive progress has been made through ML and AI techniques with regards to large data set pr...
Ilya Balabin, Thomas M. Kaiser
A Mixture-of-Experts Model for Multimodal Emotion Recognition in Conversations
Emotion Recognition in Conversations (ERC) presents unique challenges, requiring models to capture the temporal flow of multi-turn dialogues and to effectively integrate cues from multiple modaliti...
Soumya Dutta, Smruthi Balaji, Sriram Ganapathy
PRIMA: Pre-training with Risk-integrated Image-Metadata Alignment for Medical Diagnosis via LLM
Medical diagnosis requires the effective synthesis of visual manifestations and clinical metadata. However, existing methods often treat metadata as isolated tags, failing to exploit the rich seman...
Yiqing Wang, Chunming He, Ming-Chen Lu, Mercy Pawar, Leslie Niziol, Maria Woodward, Sina Farsiu
Impacts of Aggregation on Model Diversity and Consumer Utility
Consider a marketplace of AI tools, each with slightly different strengths and weaknesses. By selecting the right model for the task at hand, a user can do better than simply committing to a single...
Kate Donahue, Manish Raghavan
PGVMS: A Prompt-Guided Unified Framework for Virtual Multiplex IHC Staining with Pathological Semantic Learning
Immunohistochemical (IHC) staining enables precise molecular profiling of protein expression, with over 200 clinically available antibody-based tests in modern pathology. However, comprehensive IHC...
Fuqiang Chen, Ranran Zhang, Wanming Hu, Deboch Eyob Abera, Yue Peng, Boyun Zheng, Yiwen Sun, Jing...
Safety First: Psychological Safety as the Key to AI Transformation
Organizations continue to invest in artificial intelligence, yet many struggle to ensure that employees adopt and engage with these tools. Drawing on research highlighting the interpersonal and lea...
Aaron Reich, Diana Wolfe, Matt Price, Alice Choe, Fergus Kidd, Hannah Wagner
Work Design and Multidimensional AI Threat as Predictors of Workplace AI Adoption and Depth of Use
Artificial intelligence tools are increasingly embedded in everyday work, yet employees' uptake varies widely even within the same organization. Drawing on sociotechnical and work design perspectiv...
Aaron Reich, Diana Wolfe, Matt Price, Alice Choe, Fergus Kidd, Hannah Wagner
CXReasonAgent: Evidence-Grounded Diagnostic Reasoning Agent for Chest X-rays
Chest X-ray plays a central role in thoracic diagnosis, and its interpretation inherently requires multi-step, evidence-grounded reasoning. However, large vision-language models (LVLMs) often gener...
Hyungyung Lee, Hangyul Yoon, Edward Choi
Discourse-Aware Dual-Track Streaming Response for Low-Latency Spoken Dialogue Systems
Achieving human-like responsiveness is a critical yet challenging goal for cascaded spoken dialogue systems. Conventional ASR-LLM-TTS pipelines follow a strictly sequential paradigm, requiring comp...
Siyuan Liu, Jiahui Xu, Feng Jiang, Kuang Wang, Zefeng Zhao, Chu-Ren Huang, Jinghang Gu, Changqing...
A Model-Free Universal AI
In general reinforcement learning, all established optimal agents, including AIXI, are model-based, explicitly maintaining and using environment models. This paper introduces Universal AI with Q-In...
Yegon Kim, Juho Lee
Agency and Architectural Limits: Why Optimization-Based Systems Cannot Be Norm-Responsive
AI systems are increasingly deployed in high-stakes contexts -- medical diagnosis, legal research, financial analysis -- under the assumption they can be governed by norms. This paper demonstrates ...
Radha Sarma
Scaling Search Relevance: Augmenting App Store Ranking with LLM-Generated Judgments
Large-scale commercial search systems optimize for relevance to drive successful sessions that help users find what they are looking for. To maximize relevance, we leverage two complementary object...
Evangelia Christakopoulou, Vivekkumar Patel, Hemanth Velaga, Sandip Gaikwad
MovieTeller: Tool-augmented Movie Synopsis with ID Consistent Progressive Abstraction
With the explosive growth of digital entertainment, automated video summarization has become indispensable for applications such as content indexing, personalized recommendation, and efficient medi...
Yizhi Li, Xiaohan Chen, Miao Jiang, Wentao Tang, Gaoang Wang
STELLAR: Storage Tuning Engine Leveraging LLM Autonomous Reasoning for High Performance Parallel File Systems
I/O performance is crucial to efficiency in data-intensive scientific computing; but tuning large-scale storage systems is complex, costly, and notoriously manpower-intensive, making it inaccessibl...
Chris Egersdoerfer, Philip Carns, Shane Snyder, Robert Ross, Dong Dai
EmbodMocap: In-the-Wild 4D Human-Scene Reconstruction for Embodied Agents
Human behaviors in the real world naturally encode rich, long-term contextual information that can be leveraged to train embodied agents for perception, understanding, and acting. However, existing...
Wenjia Wang, Liang Pan, Huaijin Pi, Yuke Lou, Xuqian Ren, Yifan Wu, Zhouyingcheng Liao, Lei Yang,...
InnerQ: Hardware-aware Tuning-free Quantization of KV Cache for Large Language Models
Reducing the hardware footprint of large language models (LLMs) during decoding is critical for efficient long-sequence generation. A key bottleneck is the key-value (KV) cache, whose size scales w...
Sayed Mohammadreza Tayaranian Hosseini, Amir Ardakani, Warren J. Gross
SC-Arena: A Natural Language Benchmark for Single-Cell Reasoning with Knowledge-Augmented Evaluation
Large language models (LLMs) are increasingly applied in scientific research, offering new capabilities for knowledge discovery and reasoning. In single-cell biology, however, evaluation practices ...
Jiahao Zhao, Feng Jiang, Shaowei Qin, Zhonghui Zhang, Junhao Liu, Guibing Guo, Hamid Alinejad-Rok...
Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models
Transformer-based large language models exhibit in-context learning, enabling adaptation to downstream tasks via few-shot prompting with demonstrations. In practice, such models are often fine-tune...
Chungpa Lee, Jy-yong Sohn, Kangwook Lee
ESAA: Event Sourcing for Autonomous Agents in LLM-Based Software Engineering
Autonomous agents based on Large Language Models (LLMs) have evolved from reactive assistants to systems capable of planning, executing actions via tools, and iterating over environment observation...
Elzo Brito dos Santos Filho