4679 papers
This paper proposes VSOPINN, a novel framework that integrates differentiable Voronoi tessellation with Physics-Informed Neural Networks to enable end-to-end optimization of sensor placement, thereby significantly enhancing the accuracy and robustness of high-fidelity flow field reconstruction under sparse measurements and sensor failures.
SPAARS is a curriculum learning framework for offline-to-online reinforcement learning that safely improves policies by initially exploring a low-dimensional latent space to ensure sample efficiency and stability, then seamlessly transitioning to raw action space to bypass decoder-induced performance ceilings, thereby achieving superior results over state-of-the-art baselines on both robotic manipulation and locomotion tasks.
This paper introduces the Fully Convolutional Diffusion Model (FCDM), a ConvNeXt-based architecture that achieves competitive generative performance with significantly fewer computational resources and training steps than Transformer-based counterparts, demonstrating that modern convolutional designs remain a highly efficient alternative for scaling diffusion models.
This paper proposes four enhancements to the Spatial-Temporal Matching algorithm—dynamic buffering, adaptive observation probability, a redesigned temporal scoring function, and behavioral analysis—to improve the efficiency and accuracy of reconstructing GPS trajectories from sparse, low-frequency data in dense urban environments, as validated by experiments in Milan.
This paper systematically analyzes how Markov Decision Process design choices impact the sim-to-real gap in industrial process control, demonstrating through a color mixing task that physics-based dynamics models significantly outperform simplified models in achieving real-world success under strict precision constraints.
This paper proposes Nonparametric Weighting (NW) and Model-assisted Nonparametric Weighting (MNW) estimators for off-policy evaluation in contextual bandits, which achieve lower variance than traditional Inverse Probability Weighting and Doubly Robust methods while maintaining low bias by constructing weights via nonparametric models and incorporating reward predictions.
This paper introduces Variational Mixture-of-Experts Routing (VMoER), a scalable Bayesian framework that confines uncertainty quantification to the expert-selection stage of Mixture-of-Experts Transformers, achieving significant improvements in calibration, stability, and out-of-distribution detection with negligible computational overhead.
This paper introduces temporal-conditioned normalizing flows (tcNF), a novel autoregressive framework that enhances multivariate time series anomaly detection by effectively modeling temporal dependencies and uncertainty to identify low-probability events with improved accuracy and robustness.
TrainDeeploy is a novel framework that enables efficient, parameter-efficient on-device fine-tuning of both CNN and Transformer models on ultra-low-power, memory-constrained RISC-V SoCs, achieving significant reductions in memory usage and computational overhead while supporting end-to-end training at the extreme edge.
This paper demonstrates that language models can covertly acquire behavioral traits from a teacher model through "subliminal learning" on faithful paraphrases, where the student adopts the teacher's preferences even when the paraphrased content is semantically unrelated or explicitly contradicts those preferences, rendering content-based inspection ineffective.
This paper introduces Efficient Draft Adaptation (EDA), a parameter- and data-efficient framework that restores speculative decoding performance on fine-tuned target models through a decoupled architecture, data regeneration strategy, and sample selection mechanism, achieving superior acceptance lengths with significantly reduced training costs compared to full retraining.
This paper introduces BRACE, a parameter-free algorithm for multi-armed bandits with noncompliance that simultaneously optimizes recommendation welfare and treatment learning by performing certified instrumental variable inversion only when identification is strong, otherwise providing honest structural intervals to navigate the trade-offs between mediated and direct-control regimes.
This paper demonstrates that Mamba-2's state space duality can be implemented entirely using standard XLA primitives without custom kernels, achieving portable, host-synchronization-free autoregressive caching with high performance across CPU, NVIDIA GPU, and Google Cloud TPU hardware.
This paper investigates constraint-based structure learning for Markov and Bayesian networks using an unreliable oracle, demonstrating that Markov networks remain uniquely identifiable under bounded errors if vertex-wise disjoint paths are limited, whereas Bayesian networks cannot tolerate any errors for guaranteed identification, and subsequently providing algorithms for cases where unique identifiability holds.
This paper introduces a-TMFG, a scalable algorithm that overcomes the memory and computational limitations of traditional Triangulated Maximally Filtered Graphs by leveraging k-Nearest Neighbors and on-the-fly correlation estimation to construct sparse graphs from massive datasets.
This paper proposes a rigorous optimal control framework that models Transformer training as a lifted Markov decision process on probability measures, establishing the existence of globally optimal policies and providing a quantized, gradient-free training alternative that respects key architectural constraints like input independence and positional encoding.
The paper introduces Sensor-Conditioned Diffusion Policies (SCDP), a novel framework that enables robust humanoid locomotion using only onboard sensors by distilling privileged full-body knowledge through mixed-observation training and specialized denoising techniques, successfully achieving near-perfect simulation performance and real-world deployment on a G1 robot without explicit state estimation.
The paper introduces Routing without Forgetting (RwF), a transformer architecture that addresses Online Continual Learning by replacing iterative gradient-based specialization with dynamic, single-step associative retrieval of input-conditioned prompts via energy-based layers, thereby achieving superior performance on class-incremental benchmarks without explicit task identifiers.
This paper theoretically demonstrates that Adam naturally achieves local linear convergence on highly degenerate polynomials through a decoupling mechanism that amplifies the effective learning rate, significantly outperforming Gradient Descent and Momentum without requiring external schedulers.
This paper introduces a theoretically grounded parameter clipping strategy derived from Rényi Divergence minimization to stabilize training and improve the privacy-utility trade-off in nonparametric variational differential privacy models by preventing learned latent representations from drifting into high-information regions.