{"total":24,"rows":[{"id":"2403.03507","title":"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection","created":"2024-03-06","cited_by_count":463,"area":null},{"id":"2410.07698","title":"Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures","created":"2024-10-10","cited_by_count":50,"area":null},{"id":"2408.12857","title":"Memory-Efficient LLM Training with Online Subspace Descent","created":"2024-08-23","cited_by_count":39,"area":null},{"id":"2210.03044","title":"Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask?","created":"2022-10-06","cited_by_count":38,"area":null},{"id":"2405.17991","title":"VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections","created":"2024-05-28","cited_by_count":18,"area":null},{"id":"2112.00195","title":"Efficient Online Bayesian Inference for Neural Bandits","created":"2021-12-01","cited_by_count":15,"area":null},{"id":"2409.10927","title":"Propulsion: Steering LLM with Tiny Fine-Tuning","created":"2024-09-17","cited_by_count":14,"area":null},{"id":"2405.16528","title":"LoQT: Low-Rank Adapters for Quantized Pretraining","created":"2024-05-26","cited_by_count":12,"area":null},{"id":"2211.10691","title":"Two Facets of SDE Under an Information-Theoretic Lens: Generalization of SGD via Training Trajectories and via Terminal States","created":"2022-11-19","cited_by_count":11,"area":null},{"id":"2412.19616","title":"Gradient Weight-normalized Low-rank Projection for Efficient LLM Training","created":"2024-12-27","cited_by_count":11,"area":null},{"id":"2410.08598","title":"Parameter-Efficient Fine-Tuning of Large Language Models using Semantic Knowledge Tuning","created":"2024-10-11","cited_by_count":10,"area":null},{"id":"2306.05857","title":"How Sparse Can We Prune A Deep Network: A Fundamental Limit Perspective","created":"2023-06-09","cited_by_count":9,"area":null},{"id":"2206.03483","title":"Few-Shot Learning by Dimensionality Reduction in Gradient Space","created":"2022-06-07","cited_by_count":8,"area":null},{"id":"2505.21226","title":"Why Do More Experts Fail? A Theoretical Analysis of Model Merging","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2210.05546","title":"What does a deep neural network confidently perceive? The effective dimension of high certainty class manifolds and their low confidence boundaries","created":"2022-10-11","cited_by_count":5,"area":null},{"id":"2506.11898","title":"Martingale Posterior Neural Networks for Fast Sequential Decision Making","created":"2025-06-13","cited_by_count":4,"area":null},{"id":"2312.05827","title":"Detecting Toxic Flow","created":"2023-12-10","cited_by_count":3,"area":null},{"id":"2305.14852","title":"Sparse Weight Averaging with Multiple Particles for Iterative Magnitude Pruning","created":"2023-05-24","cited_by_count":2,"area":null},{"id":"2606.17526","title":"MGUP: A Momentum-Gradient Alignment Update Policy for Stochastic Optimization","created":"2026-06-16","cited_by_count":2,"area":null},{"id":"2504.05343","title":"AROMA: Autonomous Rank-one Matrix Adaptation","created":"2025-04-06","cited_by_count":1,"area":null},{"id":"2403.05123","title":"ECToNAS: Evolutionary Cross-Topology Neural Architecture Search","created":"2024-03-08","cited_by_count":0,"area":null},{"id":"2403.15022","title":"Insights into the Lottery Ticket Hypothesis and Iterative Magnitude Pruning","created":"2024-03-22","cited_by_count":0,"area":null},{"id":"2602.06208","title":"Emergent Low-Rank Training Dynamics in MLPs with Smooth Activations","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2609.33193","title":"Apparent Compression, Real Stability: The Intrinsic Dimension of Learning a Quantum Wavefunction","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}