Showing 1–20 of 40 results
/ Date/ Name
Dec 28, 2023Beyond PID Controllers: PPO with Neuralized PID Policy for Proton Beam Intensity Control in Mu2eNov 25, 2024Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and EfficiencySep 22, 2023On Sparse Modern Hopfield ModelSep 25, 2025Are Hallucinations Bad Estimations?Apr 22, 2025Universal Approximation with Softmax AttentionSep 26, 2025POLO: Preference-Guided Multi-Turn Reinforcement Learning for Lead OptimizationApr 7, 2026Discrete Flow Matching Policy OptimizationMay 1, 2025Fast and Low-Cost Genomic Foundation Models via Outlier RemovalApr 27, 2026Transformer Approximations from ReLUsApr 4, 2024Outlier-Efficient Hopfield Layers for Large Transformer-Based ModelsApr 5, 2024Nonparametric Modern Hopfield ModelsMay 31, 2024Mind the Inconspicuous: Revealing the Hidden Weakness in Aligned LLMs' Refusal BoundariesOct 6, 2025On Structured State-Space DualityFeb 2, 2026Cell-JEPA: Latent Representation Learning for Single-Cell TranscriptomicsJun 9, 2023Feature Programming for Multivariate Time Series PredictionApr 4, 2024BiSHop: Bi-Directional Cellular Learning for Tabular Data with Generalized Sparse Modern Hopfield ModelSep 3, 2024Differentially Private Kernel Density EstimationApr 28, 2025Attention Mechanism, Max-Affine Partition, and Universal ApproximationJun 5, 2024Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer ModelsDec 28, 2023STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction