arXiv:2603.14198v2 Announce Type: replace-cross Abstract: Deploying trustworthy AI systems requires principled uncertainty quantification. Conformal prediction (CP) is a widely used framework for constructing prediction sets with distribution-free coverage guarantees. In many practical settings, including healthcare, finance, and mobile sensing, the calibration data required for CP are distributed across multiple clients, each with its own local […]
Cost Trade-offs in Matrix Inversion Updates for Streaming Outlier Detection
arXiv:2603.16697v1 Announce Type: cross Abstract: Outlier detection identifies data points that deviate significantly from expected patterns, revealing anomalies that may require special attention. Incorporating online learning further improves accuracy by continuously updating the model to reflect the most recent data. When employing the Christoffel function as an outlier score, online learning requires updating the inverse […]
Detecting Sentiment Steering Attacks on RAG-enabled Large Language Models
arXiv:2603.16342v1 Announce Type: cross Abstract: The proliferation of large-scale IoT networks has been both a blessing and a curse. Not only has it revolutionized the way organizations operate by increasing the efficiency of automated procedures, but it has also simplified our daily lives. However, while IoT networks have improved convenience and connectivity, they have also […]
Unifying Optimization and Dynamics to Parallelize Sequential Computation: A Guide to Parallel Newton Methods for Breaking Sequential Bottlenecks
arXiv:2603.16850v1 Announce Type: cross Abstract: Massively parallel hardware (GPUs) and long sequence data have made parallel algorithms essential for machine learning at scale. Yet dynamical systems, like recurrent neural networks and Markov chain Monte Carlo, were thought to suffer from sequential bottlenecks. Recent work showed that dynamical systems can in fact be parallelized across the […]
LLM-Guided Reinforcement Learning for Audio-Visual Speech Enhancement
arXiv:2603.13952v2 Announce Type: replace-cross Abstract: In existing Audio-Visual Speech Enhancement (AVSE) methods, objectives such as Scale-Invariant Signal-to-Noise Ratio (SI-SNR) and Mean Squared Error (MSE) are widely used; however, they often correlate poorly with perceptual quality and provide limited interpretability for optimization. This work proposes a reinforcement learning-based AVSE framework with a Large Language Model (LLM)-based […]
Hilbert: Recursively Building Formal Proofs with Informal Reasoning
arXiv:2509.22819v2 Announce Type: replace Abstract: Large Language Models (LLMs) demonstrate impressive mathematical reasoning abilities, but their solutions frequently contain errors that cannot be automatically checked. Formal theorem proving systems such as Lean 4 offer automated verification with complete accuracy, motivating recent efforts to build specialized prover LLMs that generate verifiable proofs in formal languages. However, […]
An Interpretable Machine Learning Framework for Non-Small Cell Lung Cancer Drug Response Analysis
arXiv:2603.16330v1 Announce Type: cross Abstract: Lung cancer is a condition where there is abnormal growth of malignant cells that spread in an uncontrollable fashion in the lungs. Some common treatment strategies are surgery, chemotherapy, and radiation which aren’t the best options due to the heterogeneous nature of cancer. In personalized medicine, treatments are tailored according […]
MemPO: Self-Memory Policy Optimization for Long-Horizon Agents
arXiv:2603.00680v2 Announce Type: replace Abstract: Long-horizon agents face the challenge of growing context size during interaction with environment, which degrades the performance and stability. Existing methods typically introduce the external memory module and look up the relevant information from the stored memory, which prevents the model itself from proactively managing its memory content and aligning […]
Is Seeing Believing? Evaluating Human Sensitivity to Synthetic Video
arXiv:2603.13846v2 Announce Type: replace-cross Abstract: Advances in machine learning have enabled the creation of realistic synthetic videos known as deepfakes. As deepfakes proliferate, concerns about rapid spread of disinformation and manipulation of public perception are mounting. Despite the alarming implications, our understanding of how individuals perceive synthetic media remains limited, obstructing the development of effective […]
Deformation-Invariant Neural Network and Its Applications in Distorted Image Restoration and Analysis
arXiv:2310.02641v4 Announce Type: replace-cross Abstract: Images degraded by geometric distortions pose a significant challenge to imaging and computer vision tasks such as object recognition. Deep learning-based imaging models usually fail to give accurate performance for geometrically distorted images. In this paper, we propose the deformation-invariant neural network (DINN), a framework to address the problem of […]
A Human-Centred Architecture for Large Language Models-Cognitive Assistants in Manufacturing within Quality Management Systems
arXiv:2603.16325v1 Announce Type: cross Abstract: Large Language Models-Cognitive Assistants (LLM-CAs) can enhance Quality Management Systems (QMS) in manufacturing, fostering continuous process improvement and knowledge management. However, there is no human-centred software architecture focused on QMS that enables the integration of LLM-CAs into manufacturing in the current literature. This study addresses this gap by designing a […]
Diverse AI Personas Can Mitigate the Homogenization Effect in Human-AI Collaborative Ideation
arXiv:2504.13868v2 Announce Type: replace-cross Abstract: Recent studies suggest that while generative AI (GenAI) can enhance individual creativity, it often reduces the diversity of collective outputs. A well-known example of this homogenization effect is by Doshi and Hauser (2024) who found that GenAI-generated plot ideas improved story writing creativity but led to convergence across writers’ outputs. […]