10545 papers
This paper proposes augmenting Proximal Policy Optimization with temporal sequence models, particularly Transformers, to enable robust reinforcement learning under sensor drift and partial observability by inferring missing information from history, a claim supported by theoretical bounds on reward degradation and empirical success on MuJoCo benchmarks.
This paper introduces iAgentBench, a dynamic open-domain question answering benchmark designed to evaluate the cross-source sensemaking capabilities of information-seeking agents on high-traffic topics by requiring the integration of evidence from multiple sources rather than simple retrieval.
This paper introduces VeNRA, a neuro-symbolic financial reasoning system that replaces probabilistic text retrieval with a strictly typed Universal Fact Ledger and employs an adversarially trained Sentinel model to audit execution traces, thereby eliminating hallucinations and arithmetic errors in high-stakes financial domains.
This paper proposes a post-processing method that significantly improves the accuracy of physics-informed neural networks (PINNs) by finding the best approximation in a function space associated with the network, achieving errors four to five orders of magnitude lower than standard PINNs while enabling transfer learning and providing a metric for optimal basis function selection.
This study demonstrates that a deep regression network trained on synthetic LiDAR data can directly and accurately estimate plot-level tree volume and aboveground biomass with significantly lower error rates (2–20%) compared to traditional indirect methods using allometric models (27–85% error).
This paper proposes that memory consolidation serves a computational role beyond mere stabilization, utilizing "predictive forgetting" to compress stored representations into a form that optimizes generalization by selectively retaining information that predicts future outcomes, a process necessitated by high-capacity encoding constraints and validated through simulations across diverse neural and transformer models.
This paper addresses the computational challenges of generalizing fair top- selection to multiple protected groups while minimizing disparity from a reference function, revealing new hardness barriers for small and proposing an efficient, robust two-pronged solution that incorporates utility loss as an alternative disparity measure.
This paper introduces TREDBench and an embedding-guided synthetic data curation method to adapt the TabPFN 2.5 foundation model for engineering regression tasks, achieving superior predictive accuracy and data efficiency without requiring training on real-world engineering samples.
This paper demonstrates that increasing depth in matrix completion models intensifies coupled dynamics, which drives convergence to low-rank solutions and prevents the loss of plasticity observed in shallow networks.
This paper demonstrates that applying the SAM-Audio speech enhancement model as a preprocessing step for zero-shot ASR with Whisper consistently degrades recognition accuracy despite improving perceptual audio quality, revealing a fundamental mismatch between human-perceived signal cleanliness and machine recognition robustness.
This paper introduces "Probabilistic Dreaming," a novel enhancement to the Dreamer world model that utilizes probabilistic methods to enable parallel latent exploration and maintain distinct hypotheses for mutually exclusive futures, resulting in a 4.5% performance improvement and 28% variance reduction on the MPE SimpleTag domain.
This paper proposes a hybrid methodology combining theoretical modeling with empirical benchmarking to accurately determine the optimal allocation of Prefill-Decode disaggregated hardware resources for Large Language Model inference while satisfying throughput, SLO, and request characteristic constraints.
This paper presents a systematic benchmark study evaluating the effectiveness of pruning, quantization, and knowledge distillation in compressing neural networks for hyperspectral image classification, demonstrating that these methods can significantly reduce model size and computational costs while maintaining competitive accuracy for resource-constrained remote sensing applications.
This paper introduces "Model Medicine," a comprehensive clinical research program that treats AI models as biological-like organisms by establishing a taxonomy of subdisciplines, a behavioral genetics framework, and novel diagnostic tools like Neural MRI to systematically understand, diagnose, and treat model disorders.
This paper introduces Count Bridges, a novel stochastic bridge process for integer-valued data that enables principled generative modeling and the deconvolution of aggregated biological count measurements, such as bulk RNA-seq and spatial transcriptomics, into single-cell resolution profiles.
This paper identifies that pretraining priors undermine the effectiveness of Unlearnable Examples by enabling models to bypass their protective perturbations, and proposes BAIT, a bi-level optimization method that binds perturbations to incorrect targets to override these priors and ensure robust data unlearnability.
This paper introduces Distribution-Conditioned Transport (DCT), a flexible framework that conditions transport maps on learned distribution embeddings to enable generalization to unseen source-target pairs and semi-supervised learning, demonstrating significant performance improvements across synthetic benchmarks and diverse biological applications.
This paper proposes "Interactive Benchmarks," a unified evaluation paradigm that assesses model intelligence through active information acquisition and reasoning under budget constraints in interactive proofs and games, demonstrating that current models still have significant room for improvement in these dynamic scenarios.
This paper introduces CONE, a hybrid transformer encoder that utilizes a novel composite embedding algorithm to preserve the semantics of units and variables for complex numerical data, achieving state-of-the-art performance in numerical reasoning tasks across diverse domains.
KindSleep is a deep learning framework that integrates clinical knowledge with single-channel oximetry and patient data to accurately diagnose obstructive sleep apnea, achieving superior performance and enhanced transparency across large, diverse datasets.