6886 papers
This paper presents a novel explainable condition monitoring methodology that utilizes probabilistic anomaly detection on healthy data alone, incorporating Bayesian uncertainty quantification and interpretability tools to effectively detect and anticipate faults in safety-critical systems like helicopter transmissions.
This paper proposes SAGAD, a scalable and adaptive graph anomaly detection framework that mitigates homophily disparity through adaptive fusion and frequency preference guidance while achieving linear complexity for efficient large-scale training.
The paper introduces DARC, a retraining-free, inference-time method that mitigates the brittleness of standard preference alignment by framing response selection as a distributionally robust, risk-sensitive decision-making process to explicitly manage annotator disagreement and tail risk without compromising average quality.
The paper introduces Eventax, a JAX-based framework that resolves the trade-off between gradient bias and model flexibility in spiking neural networks by combining differentiable ODE solvers with event-based spike handling to enable exact gradient training for arbitrary neuron models.
This paper introduces Control Classifier-Free Guidance (CFG), a training-free method that optimizes generative quality by dynamically adjusting guidance strength through an exponential decay function derived from a rigorous theoretical analysis of score discrepancy in diffusion processes.
This paper critiques the current metric-centric evaluation paradigm in long-term time series forecasting, arguing that an overreliance on aggregate error metrics like MSE and MAE misaligns with real-world objectives, and proposes a multi-dimensional framework prioritizing structural coherence and decision-level relevance to advance meaningful forecasting progress.
This paper proposes ALS-IRLS, a novel outlier-robust algorithm that integrates an innovation-level adaptive thresholding mechanism with an IRLS-based Huber cost function to significantly improve the accuracy of noise covariance estimation and state filtering in the presence of measurement outliers compared to conventional methods.
The paper proposes TIER, a novel framework for Text-Rich Networks that constructs an implicit hierarchical taxonomy through similarity-guided contrastive learning and LLM refinement, then integrates this structure into node representations via a cophenetic correlation-based regularization loss to achieve superior, interpretable modeling of hierarchical semantics.
The paper introduces Covenant-72B, a 72-billion-parameter language model successfully pre-trained on 1.1 trillion tokens through the largest permissionless, globally distributed collaboration to date, demonstrating that open, blockchain-supported participation can achieve performance competitive with centralized training at unprecedented scale.
This paper demonstrates that performing reasoning in a continuous latent space via the CODI framework significantly outperforms standard explicit reasoning in multilingual settings, particularly for low-resource and zero-shot scenarios, while achieving substantial compression of reasoning traces.
The paper proposes ALOOD, a novel approach that leverages vision-language model representations to align LiDAR object features with language embeddings, thereby enabling zero-shot out-of-distribution object detection for safer autonomous driving.
AutoAdapt is a novel end-to-end automated framework that leverages a multi-agent debating system and an LLM-based surrogate optimizer to efficiently and reliably adapt large language models to specialized domains, achieving significant accuracy improvements over existing baselines while minimizing manual intervention and computational costs.
SERQ is a saliency-aware low-rank error reconstruction method that enables efficient and accurate 4-bit LLM inference by employing a single low-rank compensation matrix and offline operations to mitigate quantization errors from both weights and activations without incurring significant latency overhead.
This paper proposes a novel solution framework combining Real Options Analysis with a Transformer-based Proximal Policy Optimization algorithm to optimize sequential service region expansion under capacity constraints and stochastic spillover effects, demonstrating superior convergence and option value compared to existing deep reinforcement learning methods.
This paper critiques the reliance of current tabular foundation model benchmarks on point-estimate metrics like MSE, advocating instead for the adoption of proper scoring rules such as CRPS to evaluate probabilistic forecasts and the use of finetuning or promptable strategies to align model inductive biases with distributional regression goals.
This paper extends the adaptive aggregation method of AsyncFedED by exploring alternative distance metrics to better capture gradient staleness in asynchronous federated learning, demonstrating that specific metrics improve convergence, accuracy, and stability under heterogeneous and non-IID conditions.
This paper introduces a Wiener Chaos Expansion-based neural operator enhanced with feature-wise linear modulation (FiLM) that efficiently and accurately solves singular stochastic partial differential equations, such as the dynamic and models, without requiring renormalization factors.
This paper investigates the continuation-triggered jailbreak phenomenon in large language models, revealing through mechanistic interpretability analysis that its root cause lies in the inherent competition between the model's intrinsic continuation drive and its safety alignment defenses, while also identifying distinct behavioral patterns in safety-critical attention heads across different architectures.
This paper introduces Fibration Policy Optimization (FiberPO), a unified framework that bridges trust-region theory and compositional algebraic structures to enable principled, multi-scale stability control in large language model training through the novel Aggregational Policy Censoring Objective and Fiber Bundle Gating mechanism.
This paper proposes a neural process-based decision support system that forecasts patient vital sign trajectories to probabilistically predict readiness for switching from intravenous to oral antibiotics, thereby outperforming random selection and historical decision-learning approaches in identifying eligible patients across US and UK datasets.