{"total":370,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380,"area":null},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503,"area":"diffusion"},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631,"area":"moe"},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245,"area":null},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797,"area":null},{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460,"area":null},{"id":"2110.06500","title":"Differentially Private Fine-tuning of Language Models","created":"2021-10-13","cited_by_count":400,"area":null},{"id":"2305.17333","title":"Fine-Tuning Language Models with Just Forward Passes","created":"2023-05-27","cited_by_count":345,"area":null},{"id":"2405.09673","title":"LoRA Learns Less and Forgets Less","created":"2024-05-15","cited_by_count":328,"area":null},{"id":"2310.11454","title":"VeRA: Vector-based Random Matrix Adaptation","created":"2023-10-17","cited_by_count":300,"area":null},{"id":"2205.13147","title":"Matryoshka Representation Learning","created":"2022-05-26","cited_by_count":282,"area":null},{"id":"2404.02948","title":"PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models","created":"2024-04-03","cited_by_count":269,"area":null},{"id":"2201.03514","title":"Black-Box Tuning for Language-Model-as-a-Service","created":"2022-01-10","cited_by_count":256,"area":null},{"id":"2312.03732","title":"A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA","created":"2023-11-28","cited_by_count":243,"area":null},{"id":"2209.09858","title":"Extremely Simple Activation Shaping for Out-of-Distribution Detection","created":"2022-09-20","cited_by_count":212,"area":null},{"id":"2310.16218","title":"Knowledge Editing for Large Language Models: A Survey","created":"2023-10-24","cited_by_count":194,"area":"lr"},{"id":"2203.06904","title":"Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models","created":"2022-03-14","cited_by_count":180,"area":null},{"id":"2303.15647","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","created":"2023-03-28","cited_by_count":173,"area":null},{"id":"2403.12313","title":"Improving LoRA in Privacy-preserving Federated Learning","created":"2024-03-18","cited_by_count":161,"area":null},{"id":"2210.05643","title":"A Kernel-Based View of Language Model Fine-Tuning","created":"2022-10-11","cited_by_count":121,"area":null},{"id":"2303.02861","title":"Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning","created":"2023-03-06","cited_by_count":115,"area":null},{"id":"2306.04723","title":"Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts","created":"2023-06-07","cited_by_count":112,"area":null},{"id":"2410.21228","title":"LoRA vs Full Fine-tuning: An Illusion of Equivalence","created":"2024-10-28","cited_by_count":109,"area":null},{"id":"2405.18541","title":"Low-Rank Few-Shot Adaptation of Vision-Language Models","created":"2024-05-28","cited_by_count":104,"area":"mllm"},{"id":"2406.09044","title":"MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning","created":"2024-06-13","cited_by_count":94,"area":null},{"id":"2309.15698","title":"Deep Model Fusion: A Survey","created":"2023-09-27","cited_by_count":91,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2102.10472","title":"Learning Neural Network Subspaces","created":"2021-02-20","cited_by_count":82,"area":null},{"id":"2203.16329","title":"Parameter-efficient Model Adaptation for Vision Transformers","created":"2022-03-29","cited_by_count":81,"area":null},{"id":"2410.01463","title":"Selective Aggregation for Low-Rank Adaptation in Federated Learning","created":"2024-10-02","cited_by_count":80,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2407.18242","title":"LoRA-Pro: Are Low-Rank Adapters Properly Optimized?","created":"2024-07-25","cited_by_count":77,"area":null},{"id":"2211.13609","title":"PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization","created":"2022-11-24","cited_by_count":76,"area":null},{"id":"2111.13171","title":"Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks","created":"2021-11-25","cited_by_count":70,"area":null},{"id":"2308.11584","title":"Building Emotional Support Chatbots in the Era of LLMs","created":"2023-08-17","cited_by_count":62,"area":null},{"id":"2103.05121","title":"Multiple Instance Captioning: Learning Representations from Histopathology Textbooks and Articles","created":"2021-03-08","cited_by_count":58,"area":null},{"id":"2201.05867","title":"Transferability in Deep Learning: A Survey","created":"2022-01-15","cited_by_count":57,"area":null},{"id":"2405.15471","title":"Emergence of a High-Dimensional Abstraction Phase in Language Transformers","created":"2024-05-24","cited_by_count":56,"area":null},{"id":"2503.02113","title":"Deep Learning is Not So Mysterious or Different","created":"2025-03-03","cited_by_count":56,"area":null},{"id":"2108.08842","title":"EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learning","created":"2021-08-19","cited_by_count":55,"area":null},{"id":"2312.06353","title":"Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes","created":"2023-12-11","cited_by_count":55,"area":null},{"id":"2312.17173","title":"Non-Vacuous Generalization Bounds for Large Language Models","created":"2023-12-28","cited_by_count":53,"area":null},{"id":"2105.08339","title":"DRIVE: One-bit Distributed Mean Estimation","created":"2021-05-18","cited_by_count":52,"area":null},{"id":"2106.16225","title":"Analytic Insights into Structure and Rank of Neural Network Hessian Maps","created":"2021-06-30","cited_by_count":52,"area":null},{"id":"2306.07042","title":"Transformers learn through gradual rank increase","created":"2023-06-12","cited_by_count":52,"area":null},{"id":"2202.01889","title":"Generalizing to New Physical Systems via Context-Informed Dynamics Model","created":"2022-02-01","cited_by_count":50,"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":"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":"2207.00160","title":"When Does Differentially Private Learning Not Suffer in High Dimensions?","created":"2022-07-01","cited_by_count":48,"area":null},{"id":"2406.05223","title":"CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuning","created":"2024-06-07","cited_by_count":44,"area":null},{"id":"2209.15007","title":"Understanding Collapse in Non-Contrastive Siamese Representation Learning","created":"2022-09-29","cited_by_count":42,"area":null},{"id":"2501.01765","title":"SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation","created":"2025-01-03","cited_by_count":42,"area":"safety"},{"id":"2111.12229","title":"Subspace Adversarial Training","created":"2021-11-24","cited_by_count":41,"area":null},{"id":"2410.11795","title":"Efficient Diffusion Models: A Comprehensive Survey from Principles to Practices","created":"2024-10-15","cited_by_count":41,"area":"diffusion"},{"id":"2506.08010","title":"Vision Transformers Don't Need Trained Registers","created":"2025-06-09","cited_by_count":41,"area":null},{"id":"2204.01172","title":"PERFECT: Prompt-free and Efficient Few-shot Learning with Language Models","created":"2022-04-03","cited_by_count":40,"area":null},{"id":"2207.13129","title":"LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity","created":"2022-07-26","cited_by_count":39,"area":null},{"id":"2311.05928","title":"The Shape of Learning: Anisotropy and Intrinsic Dimensions in Transformer-Based Models","created":"2023-11-10","cited_by_count":39,"area":null},{"id":"2406.01775","title":"OLoRA: Orthonormal Low-Rank Adaptation of Large Language Models","created":"2024-06-03","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":"2410.16103","title":"LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics","created":"2024-10-21","cited_by_count":38,"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":"2407.02880","title":"Knowledge Composition using Task Vectors with Learned Anisotropic Scaling","created":"2024-07-03","cited_by_count":37,"area":null},{"id":"2501.00365","title":"Low-Rank Adaptation for Foundation Models: A Comprehensive Review","created":"2024-12-31","cited_by_count":37,"area":null},{"id":"2403.16187","title":"ALoRA: Allocating Low-Rank Adaptation for Fine-tuning Large Language Models","created":"2024-03-24","cited_by_count":36,"area":null},{"id":"2405.16002","title":"Does SGD really happen in tiny subspaces?","created":"2024-05-25","cited_by_count":36,"area":null},{"id":"2408.06621","title":"Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs","created":"2024-08-13","cited_by_count":36,"area":"lr"},{"id":"2510.08396","title":"FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts","created":"2025-10-09","cited_by_count":35,"area":"moe"},{"id":"2305.15065","title":"Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning","created":"2023-05-24","cited_by_count":33,"area":null},{"id":"2206.14882","title":"LIDL: Local Intrinsic Dimension Estimation Using Approximate Likelihood","created":"2022-06-29","cited_by_count":30,"area":null},{"id":"2105.09557","title":"Power-law escape rate of SGD","created":"2021-05-20","cited_by_count":29,"area":null},{"id":"2310.02556","title":"NOLA: Compressing LoRA using Linear Combination of Random Basis","created":"2023-10-04","cited_by_count":29,"area":null},{"id":"2104.11044","title":"Analyzing Monotonic Linear Interpolation in Neural Network Loss Landscapes","created":"2021-04-22","cited_by_count":28,"area":null},{"id":"2106.16004","title":"What can linear interpolation of neural network loss landscapes tell us?","created":"2021-06-30","cited_by_count":28,"area":null},{"id":"2107.05802","title":"How many degrees of freedom do we need to train deep networks: a loss landscape perspective","created":"2021-07-13","cited_by_count":28,"area":null},{"id":"2205.07069","title":"Homogenization of SGD in high-dimensions: Exact dynamics and generalization properties","created":"2022-05-14","cited_by_count":27,"area":null},{"id":"2105.04504","title":"Deep Neural Networks as Point Estimates for Deep Gaussian Processes","created":"2021-05-10","cited_by_count":26,"area":null},{"id":"2310.09639","title":"DPZero: Private Fine-Tuning of Language Models without Backpropagation","created":"2023-10-14","cited_by_count":26,"area":null},{"id":"2310.13620","title":"Bridging Information-Theoretic and Geometric Compression in Language Models","created":"2023-10-20","cited_by_count":26,"area":null},{"id":"2406.04112","title":"Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2107.03311","title":"RoFL: Robustness of Secure Federated Learning","created":"2021-07-07","cited_by_count":25,"area":null},{"id":"2110.07867","title":"Exploring Universal Intrinsic Task Subspace via Prompt Tuning","created":"2021-10-15","cited_by_count":25,"area":null},{"id":"2407.00066","title":"Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead","created":"2024-06-17","cited_by_count":24,"area":null},{"id":"2206.07252","title":"Implicit Regularization or Implicit Conditioning? Exact Risk Trajectories of SGD in High Dimensions","created":"2022-06-15","cited_by_count":23,"area":null},{"id":"2409.02877","title":"Configurable Foundation Models: Building LLMs from a Modular Perspective","created":"2024-09-04","cited_by_count":22,"area":null},{"id":"2410.22815","title":"Towards Robust and Efficient Federated Low-Rank Adaptation with Heterogeneous Clients","created":"2024-10-30","cited_by_count":22,"area":null},{"id":"2412.09810","title":"The Complexity Dynamics of Grokking","created":"2024-12-13","cited_by_count":22,"area":null},{"id":"2312.11875","title":"Sparse is Enough in Fine-tuning Pre-trained Large Language Models","created":"2023-12-19","cited_by_count":21,"area":null},{"id":"2404.13588","title":"Machine Unlearning via Null Space Calibration","created":"2024-04-21","cited_by_count":21,"area":"safety"},{"id":"2510.13003","title":"OPLoRA: Orthogonal Projection LoRA Prevents Catastrophic Forgetting during Parameter-Efficient Fine-Tuning","created":"2025-10-14","cited_by_count":21,"area":null},{"id":"2104.13424","title":"Policy Manifold Search: Exploring the Manifold Hypothesis for Diversity-based Neuroevolution","created":"2021-04-27","cited_by_count":20,"area":null},{"id":"2311.02105","title":"Making Harmful Behaviors Unlearnable for Large Language Models","created":"2023-11-02","cited_by_count":20,"area":null},{"id":"2405.14438","title":"LoRA-Ensemble: Efficient Uncertainty Modelling for Self-Attention Networks","created":"2024-05-23","cited_by_count":20,"area":null},{"id":"2406.01355","title":"Differentially Private Fine-Tuning of Diffusion Models","created":"2024-06-03","cited_by_count":20,"area":"diffusion"},{"id":"2409.14396","title":"Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape","created":"2024-09-22","cited_by_count":20,"area":null},{"id":"2502.09376","title":"LoRA Training Provably Converges to a Low-Rank Global Minimum or It Fails Loudly (But it Probably Won't Fail)","created":"2025-02-13","cited_by_count":20,"area":null},{"id":"2305.17446","title":"Fine-tuning Happens in Tiny Subspaces: Exploring Intrinsic Task-specific Subspaces of Pre-trained Language Models","created":"2023-05-27","cited_by_count":19,"area":null},{"id":"2402.05926","title":"On the Convergence of Zeroth-Order Federated Tuning for Large Language Models","created":"2024-02-08","cited_by_count":19,"area":null},{"id":"2309.01715","title":"Prompting or Fine-tuning? A Comparative Study of Large Language Models for Taxonomy Construction","created":"2023-09-04","cited_by_count":18,"area":null},{"id":"2310.14848","title":"Zero-Knowledge Proof-based Verifiable Decentralized Machine Learning in Communication Network: A Comprehensive Survey","created":"2023-10-23","cited_by_count":18,"area":null}],"next_cursor":"100"}