2315 papers
This paper introduces Graph-GRPO, an online reinforcement learning framework that enhances Graph Flow Models through analytical transition probabilities and a localized refinement strategy, achieving state-of-the-art performance in graph generation and molecular optimization tasks.
This paper analyzes the learning dynamics of two-layer over-parameterized linear networks under label noise SGD, revealing a two-phase process where noise drives the transition from the lazy to the rich regime to improve generalization, a mechanism that also extends to Sharpness-Aware Minimization (SAM).
This paper introduces PP-LUCB, a cost-efficient algorithm that optimally combines biased LLM-generated proxy scores with selective human audits to identify the best service system configuration while providing statistically valid confidence guarantees and significantly reducing audit costs.
The paper introduces STemDist, the first dataset distillation method designed for spatio-temporal forecasting that simultaneously compresses both spatial and temporal dimensions through a hybrid cluster-level and subset-based approach, achieving significantly faster training, reduced memory usage, and lower prediction errors compared to existing methods.
This paper proposes a domain-adaptive framework featuring degradation-stage synchronized batch sampling and a cross-domain aligned fusion large autoencoder to overcome distribution mismatches and temporal dependency limitations in health indicator learning, achieving significant performance improvements on industrial datasets.
This paper proposes Weighted improved Greedy Sampling (WiGS), a reinforcement learning-based active learning framework that dynamically adapts the balance between feature-space diversity and output-space uncertainty to outperform static multiplicative methods, particularly in domains with irregular data density.
This paper introduces Generalized Gaussian Mixture Processes (GGMPs), a scalable and tractable Gaussian process-based framework that enables multimodal conditional density estimation by combining local mixture fitting, cross-input component alignment, and per-component heteroscedastic GP training to overcome the unimodal limitations of standard GP regression.
This paper identifies a coherent rank-one mean bias as the primary cause of numerical instability in low-bit LLM training and demonstrates that simply subtracting this mean restores stability and performance in FP4 quantization, offering a hardware-efficient alternative to complex spectral methods.
This paper introduces a prompt-free instance unlearning method for diffusion models that effectively removes specific, unpromptable undesired outputs—such as individual faces or culturally inaccurate depictions—while preserving the model's overall integrity through a novel approach combining image editing, timestep-aware weighting, and gradient surgery.
This paper introduces "Brenier isotonic regression," a novel multi-output regression framework that extends classical isotonic regression by enforcing cyclic monotonicity through optimal transport principles, demonstrating superior performance in probability calibration and generalized linear models.
This study introduces a multi-resolution ConvLSTM stacking ensemble framework that effectively mitigates error accumulation and enhances the accuracy of long-horizon retaining wall deformation forecasting by integrating models trained on diverse temporal input resolutions.
This paper establishes a kinetic field theory for beam-plasma collective oscillations in intermediate-energy charged-particle beams, deriving dispersion relations and critical density thresholds that are validated by a Prometheus beta-VAE analyzing particle-in-cell simulation data to confirm predicted signatures like density-tunable resonances and Friedel oscillations.
This paper introduces a physiology-informed reinforcement learning framework that utilizes low-dimensional muscle synergies as a control constraint to significantly enhance the biomechanical fidelity and generalization of predictive musculoskeletal simulations across diverse locomotion conditions.
This paper establishes the convergence of Dual Space Preconditioned Gradient Descent to an interpolating solution for overparameterized linear models using novel Bregman divergence techniques, while characterizing its implicit bias to show that isotropic preconditioners recover standard gradient descent solutions and general preconditioners yield solutions within a constant factor of the standard solution.
The paper introduces JEDI, a hierarchical model that jointly learns shared embeddings over recurrent neural network weights to robustly infer generalizable, task-specific neural dynamics from noisy, high-dimensional experimental recordings, successfully recovering underlying mechanistic structures and providing insights into motor control.
This paper introduces a universal, nearest-neighbor-based estimator for intrinsic dimensionality that achieves state-of-the-art performance through simple calculations and theoretical guarantees of convergence independent of the underlying data distribution.
The paper introduces VERI-DPO, an evidence-aware alignment framework that leverages claim verification to mine preference pairs for Direct Preference Optimization, significantly reducing unsupported claims and improving the faithfulness of clinical summarizations while maintaining informative length.
This paper introduces the tubal tensor train (TTT) decomposition, a novel tensor network model that integrates t-product algebra with the tensor train structure to achieve linear storage scaling for high-order tensors, and validates its effectiveness through efficient algorithms and applications in image/video compression, tensor completion, and hyperspectral imaging.
This paper proposes a lightweight hybrid framework for the Game of the Amazons that integrates Graph Attention Autoencoders, Stochastic Graph Genetic Algorithms, and GPT-4o-mini to overcome resource constraints, achieving decision accuracy improvements of 15%–56% over baselines and outperforming its teacher model by effectively denoising LLM outputs through structural graph reasoning.
The paper introduces IH-Challenge, a reinforcement learning dataset designed to enhance instruction hierarchy robustness in frontier LLMs, which significantly improves their ability to prioritize instructions against conflicts and adversarial attacks while maintaining helpfulness and minimizing capability regression.