arXiv:2603.14764v2 Announce Type: replace-cross Abstract: Geometric data augmentation is widely used in segmentation pipelines and typically assumes that polygon annotations represent simply connected regions. However, in structured domains such as architectural floorplan analysis, ring-type regions are often encoded as a single cyclic polygon chain connecting outer and inner boundaries. During augmentation, clipping operations may remove […]
FedSDWC: Federated Synergistic Dual-Representation Weak Causal Learning for OOD
arXiv:2511.09036v2 Announce Type: replace-cross Abstract: Amid growing demands for data privacy and advances in computational infrastructure, federated learning (FL) has emerged as a prominent distributed learning paradigm. Nevertheless, differences in data distribution (such as covariate and semantic shifts) severely affect its reliability in real-world deployments. To address this issue, we propose FedSDWC, a causal inference […]
Automated identification of Ichneumonoidea wasps via YOLO-based deep learning: Integrating HiresCam for Explainable AI
arXiv:2603.16351v1 Announce Type: cross Abstract: Accurate taxonomic identification of parasitoid wasps within the superfamily Ichneumonoidea is essential for biodiversity assessment, ecological monitoring, and biological control programs. However, morphological similarity, small body size, and fine-grained interspecific variation make manual identification labor-intensive and expertise-dependent. This study proposes a deep learning-based framework for the automated identification of Ichneumonoidea […]
High-Fidelity Compression of Seismic Velocity Models via SIREN Auto-Decoders
arXiv:2603.14284v2 Announce Type: replace-cross Abstract: Implicit Neural Representations (INRs) have emerged as a powerful paradigm for representing continuous signals independently of grid resolution. In this paper, we propose a high-fidelity neural compression framework based on a SIREN (Sinusoidal Representation Networks) auto-decoder to represent multi-structural seismic velocity models from the OpenFWI benchmark. Our method compresses each […]
Explainable machine learning workflows for radio astronomical data processing
arXiv:2603.16350v1 Announce Type: cross Abstract: Radio astronomy relies heavily on efficient and accurate processing pipelines to deliver science ready data. With the increasing data flow of modern radio telescopes, manual configuration of such data processing pipelines is infeasible. Machine learning (ML) is already emerging as a viable solution for automating data processing pipelines. However, almost […]
Understanding Cell Fate Decisions with Temporal Attention
arXiv:2603.16562v1 Announce Type: cross Abstract: Understanding non-genetic determinants of cell fate is critical for developing and improving cancer therapies, as genetically identical cells can exhibit divergent outcomes under the same treatment conditions. In this work, we present a deep learning approach for cell fate prediction from raw long-term live-cell recordings of cancer cell populations under […]
Efficient Federated Conformal Prediction with Group-Conditional Guarantees
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, […]