{"total":19,"rows":[{"id":"2308.13111","title":"Bayesian Low-rank Adaptation for Large Language Models","created":"2023-08-24","cited_by_count":115,"area":null},{"id":"2406.11675","title":"BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models","created":"2024-06-17","cited_by_count":50,"area":null},{"id":"2402.12264","title":"Uncertainty quantification in fine-tuned LLMs using LoRA ensembles","created":"2024-02-19","cited_by_count":37,"area":null},{"id":"2305.12766","title":"Understanding Emergent In-Context Learning from a Kernel Regression Perspective","created":"2023-05-22","cited_by_count":24,"area":null},{"id":"2405.03425","title":"Gaussian Stochastic Weight Averaging for Bayesian Low-Rank Adaptation of Large Language Models","created":"2024-05-06","cited_by_count":20,"area":null},{"id":"2502.20525","title":"Revisiting Kernel Attention with Correlated Gaussian Process Representation","created":"2025-02-27","cited_by_count":10,"area":null},{"id":"2406.13762","title":"Unveiling the Hidden Structure of Self-Attention via Kernel Principal Component Analysis","created":"2024-06-19","cited_by_count":7,"area":null},{"id":"2406.13770","title":"Elliptical Attention","created":"2024-06-19","cited_by_count":7,"area":null},{"id":"2402.01476","title":"Self-Attention through Kernel-Eigen Pair Sparse Variational Gaussian Processes","created":"2024-02-02","cited_by_count":5,"area":null},{"id":"2602.02952","title":"UAT-LITE: Inference-Time Uncertainty-Aware Attention for Pretrained Transformers","created":"2026-02-03","cited_by_count":4,"area":null},{"id":"2408.09629","title":"A Strategy to Combine 1stGen Transformers and Open LLMs for Automatic Text Classification","created":"2024-08-19","cited_by_count":3,"area":null},{"id":"2602.11175","title":"Barriers to Discrete Reasoning with Transformers: A Survey Across Depth, Exactness, and Bandwidth","created":"2026-01-19","cited_by_count":3,"area":null},{"id":"2506.17968","title":"h-calibration: Rethinking Classifier Recalibration with Probabilistic Error-Bounded Objective","created":"2025-06-22","cited_by_count":2,"area":null},{"id":"2507.12780","title":"Compact Vision Transformer by Reduction of Kernel Complexity","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2511.21566","title":"A decoupled alignment kernel for peptide membrane permeability predictions","created":"2025-11-26","cited_by_count":0,"area":null},{"id":"2602.08920","title":"Diffusion-Inspired Reconfiguration of Transformers for Uncertainty Calibration","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2602.11863","title":"In-Context Function Learning in Large Language Models","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2605.18832","title":"Precision Tracked Transformer via Kalman Filtering, Kriging and Process Noise","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.24330","title":"Interdomain Attention: Beyond Token-Level Key-Value Memory","created":"2026-05-23","cited_by_count":0,"area":null}],"next_cursor":null}