6992 papers
This paper provides a comprehensive theoretical and empirical analysis of unsupervised reinforcement learning with verifiable rewards (URLVR), revealing that intrinsic reward methods are fundamentally limited by a confidence-correctness alignment ceiling that causes model collapse, while suggesting that external rewards grounded in computational asymmetries may offer a scalable alternative.
This paper characterizes and upgrades a hybrid quantum-classical graph neural network for charged particle track reconstruction in high-luminosity LHC environments, demonstrating improved training convergence and behavior through the integration of parametrized quantum circuits.
This paper introduces Momentum SVGD-EM, an accelerated algorithm for Maximum Marginal Likelihood Estimation that integrates Nesterov momentum into both parameter updates and probability measure optimization via Stein variational gradient descent, demonstrating consistently faster convergence across diverse low- and high-dimensional tasks.
This paper employs an AI-guided evolutionary search framework to identify a new worst-case distribution that establishes a lower bound of 2.0749 for the approximation ratio of the Random-Offerer mechanism in bilateral trade, surpassing previous conjectures and known counterexamples.
This paper introduces Structural Causal Bottleneck Models (SCBMs), a novel framework that assumes causal effects between high-dimensional variables depend only on low-dimensional summary statistics, offering a flexible and estimable approach for task-specific dimension reduction and improved effect estimation in low-sample transfer learning settings.
This paper introduces Trilobyte, a byte-level tokenization schema that enables tractable lossless compression of full-fidelity (up to 24-bit) audio using autoregressive language models, demonstrating that while these models outperform FLAC at lower bit depths, their compression gains diminish as bit depth increases.
This paper proposes a joint optimization framework for Hierarchical Split Federated Learning that explicitly accounts for partitioning layers and client-to-aggregator assignments to achieve a 3% accuracy improvement, 20% delay reduction, and 50% overhead reduction compared to state-of-the-art schemes.
The paper proposes Agentic Critical Training (ACT), a reinforcement learning paradigm that enhances large language model agents by rewarding their ability to autonomously judge the quality of actions among alternatives, thereby fostering genuine self-reflection and outperforming traditional imitation learning and knowledge distillation methods across various benchmarks.
This paper introduces Impermanent, a live benchmark that evaluates time-series forecasting models on continuously updated GitHub activity data to assess their robustness against temporal shifts and distributional changes, addressing the limitations of static evaluation protocols that risk data contamination and inflated performance claims.
This paper proposes a mixed-frequency modeling approach to overcome the information loss inherent in temporal aggregation, demonstrating its effectiveness in predicting CAD/USD exchange rates and addressing the Meese and Rogoff puzzle.
This paper proposes an interpretable framework that leverages a concept-based graph convolutional neural network to incorporate medical prior knowledge, thereby providing clinicians with transparent, cognition-aligned explanations for fetal ultrasound scan plane detection.
This paper presents a neural network-based correlation model demonstrating similar trends between COVID-19 and Dengue cases, which is extended into an LSTM framework to predict Dengue infections in regions with insufficient data by leveraging COVID-19 statistics and external factors.
This paper proposes a scalable and robust Graph Neural Network (GNN) framework operating on augmented factor graphs to achieve fast, accurate linear state estimation in power systems using PMU data, effectively mitigating the impact of measurement failures while maintaining linear computational complexity.
This paper introduces Ancestral GFlowNet (AGFN), a diversity-seeking reinforcement learning algorithm that enables distributional inference over ancestral graphs by iteratively refining its policy through Bayesian aggregation of both ex-ante and uncertain ex-post expert feedback, ultimately converging to the true causal structure even when expert responses are noisy or conflicting.
This paper introduces a unified framework for learning unknown objects from arbitrary linear samples using general nonlinear model classes, establishing near-optimal generalization bounds based on the model's variation and complexity while recovering and extending existing results in areas like compressed sensing and matrix sketching.
This paper derives model-agnostic theoretical lower-bounds for the energy-to-solution metric of ideal neuromorphic learning-in-memory optimizers by analyzing their out-of-equilibrium thermodynamics, demonstrating how matching memory dynamics to optimization processes can overcome energy bottlenecks associated with memory writes and consolidation in large-scale AI workloads.
This paper proposes a pose-aware in-context visual learning (PA-ICVL) framework that enhances Vision-Language Models' ability to detect semantic structural visual hallucinations in non-photorealistic cartoon images by integrating pose information alongside RGB data, achieving significant performance improvements over RGB-only baselines.
BInD is a knowledge-guided diffusion model that co-generates molecules and their interactions with target proteins to achieve balanced multi-objective optimization in structure-based drug design, outperforming existing methods across key criteria like binding affinity, molecular properties, and local geometry.
This paper proposes a novel two-stage active learning pipeline for automatic speech recognition that combines unsupervised x-vector clustering with a supervised Bayesian batch selection method to efficiently identify diverse and informative samples, thereby significantly reducing labeling effort while improving model performance across various test conditions.
This paper provides a comprehensive review and formal specification of Predictive Coding Networks (PCNs), highlighting their biological plausibility, computational efficiency through inference learning, and versatility as a probabilistic framework that extends beyond traditional backpropagation-based neural networks.