Machine Learning

EPIC: Effective prompting makes LLMs generate high-quality synthetic tabular data, significantly boosting imbalanced-class classification.

Entropy-regularized diffusion policy with Q-ensembles achieves state-of-the-art offline reinforcement learning by tackling overestimation of Q-values and boosting exploration.

Small ensembles in stochastic linear bandits achieve near-optimal regret; a rigorous analysis shows that ensemble size need only scale logarithmically with horizon.

EnOF-SNN boosts spiking neural network (SNN) accuracy by enhancing output feature representation using a novel knowledge distillation method and ReLU activation, outperforming current state-of-the-art…

RDSS: a novel sample selection method for semi-supervised learning, boosts model accuracy by minimizing a-MMD, striking a balance between sample representativeness and diversity.

Deep RL agents lack robustness; this paper enhances their resilience by implementing Maximal Lyapunov Exponent regularisation in the Dreamer V3 architecture, thus improving real-world applicability.

Revolutionizing protein mutation effect prediction, this work introduces a retrieval-augmented framework achieving state-of-the-art accuracy by efficiently incorporating similar local structure inform…

Hierarchical Distance Structural Encoding (HDSE) empowers graph transformers to better capture hierarchical graph structures, leading to improved performance in graph classification and regression tas…

ESPO enhances safe RL efficiency by dynamically manipulating sample size based on reward-safety gradient conflicts, ensuring faster training and superior performance.

Prompt Gradient Alignment (PGA) enhances unsupervised domain adaptation by aligning per-objective gradients in a multi-objective optimization framework, achieving state-of-the-art results.

Boosting Bayesian deep learning’s diversity and uncertainty quantification, this study proposes hyperspherical energy minimization of CKA to generate diverse and reliable neural network ensembles and …

AlphaGateau: a novel Graph Neural Network architecture outperforms previous chess AI models by leveraging graph representations for faster training and superior generalization to different board sizes…

Train discrete EBMs efficiently with Energy Discrepancy, a novel loss function that eliminates the need for Markov Chain Monte Carlo, using diffusion processes on structured spaces.

Hopfield Boosting, a novel energy-based boosting approach, achieves state-of-the-art OOD detection by leveraging Hopfield energy to sharpen the decision boundary between in-distribution and out-of-dis…

ELCRec: a novel intent learning model for recommendation, unites behavior representation learning with end-to-end learnable clustering, achieving superior performance and scalability.

DIVA: Evolutionary task generation for robust, adaptable AI agents in complex simulators.

This study introduces a novel active learning paradigm for 3D molecular graphs, significantly improving efficiency and accuracy by leveraging geometric graph isomorphisms and distributional representa…

Discover optimal embedding dimensions for contrastive learning & k-NN using graph arboricity; achieve efficient model design & performance.

ElasTST: A novel time-series transformer enables robust forecasting across various horizons without per-horizon training, enhancing adaptability and accuracy.

Einspace: A novel neural architecture search space built from fundamental operations, enabling discovery of diverse high-performing network architectures and surpassing existing NAS methods.