{"total":93,"rows":[{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915,"area":null},{"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":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463,"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":"2402.05162","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","created":"2024-02-07","cited_by_count":231,"area":"alignment"},{"id":"2312.12148","title":"Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment","created":"2023-12-19","cited_by_count":230,"area":null},{"id":"2111.09839","title":"Training Neural Networks with Fixed Sparse Masks","created":"2021-11-18","cited_by_count":214,"area":null},{"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":"2107.00910","title":"Learned Token Pruning for Transformers","created":"2021-07-02","cited_by_count":139,"area":"inference"},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2402.05862","title":"Let Your Graph Do the Talking: Encoding Structured Data for LLMs","created":"2024-02-08","cited_by_count":118,"area":null},{"id":"2305.12182","title":"Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages","created":"2023-05-20","cited_by_count":116,"area":null},{"id":"2311.11696","title":"Sparse Low-rank Adaptation of Pre-trained Language Models","created":"2023-11-20","cited_by_count":96,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2310.18547","title":"Punica: Multi-Tenant LoRA Serving","created":"2023-10-28","cited_by_count":83,"area":null},{"id":"2303.08566","title":"Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning","created":"2023-03-15","cited_by_count":74,"area":null},{"id":"2301.01821","title":"Parameter-Efficient Fine-Tuning Design Spaces","created":"2023-01-04","cited_by_count":67,"area":null},{"id":"2104.03514","title":"Low-Complexity Probing via Finding Subnetworks","created":"2021-04-08","cited_by_count":64,"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":"2109.03630","title":"Discrete and Soft Prompting for Multilingual Models","created":"2021-09-08","cited_by_count":49,"area":null},{"id":"2301.12132","title":"AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuning","created":"2023-01-28","cited_by_count":49,"area":null},{"id":"2410.19878","title":"Parameter-Efficient Fine-Tuning in Large Models: A Survey of Methodologies","created":"2024-10-24","cited_by_count":47,"area":null},{"id":"2110.06366","title":"Time Masking for Temporal Language Models","created":"2021-10-12","cited_by_count":46,"area":null},{"id":"2501.13787","title":"Parameter-Efficient Fine-Tuning for Foundation Models","created":"2025-01-23","cited_by_count":45,"area":null},{"id":"2312.10136","title":"Gradient-based Parameter Selection for Efficient Fine-Tuning","created":"2023-12-15","cited_by_count":40,"area":null},{"id":"2402.15179","title":"Advancing Parameter Efficiency in Fine-tuning via Representation Editing","created":"2024-02-23","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":"2203.08055","title":"Modular and Parameter-Efficient Multimodal Fusion with Prompting","created":"2022-03-15","cited_by_count":35,"area":null},{"id":"2106.02205","title":"Enabling Lightweight Fine-tuning for Pre-trained Language Model Compression based on Matrix Product Operators","created":"2021-06-04","cited_by_count":29,"area":null},{"id":"2408.10441","title":"Goldfish: Monolingual Language Models for 350 Languages","created":"2024-08-19","cited_by_count":29,"area":null},{"id":"2205.11005","title":"Parameter-Efficient Sparsity for Large Language Models Fine-Tuning","created":"2022-05-23","cited_by_count":27,"area":null},{"id":"2407.19200","title":"On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs","created":"2024-07-27","cited_by_count":25,"area":"mechinterp"},{"id":"2404.11677","title":"Cross-Problem Learning for Solving Vehicle Routing Problems","created":"2024-04-17","cited_by_count":24,"area":null},{"id":"2410.17875","title":"Understanding Layer Significance in LLM Alignment","created":"2024-10-23","cited_by_count":19,"area":"alignment"},{"id":"2205.15171","title":"Modular and On-demand Bias Mitigation with Attribute-Removal Subnetworks","created":"2022-05-30","cited_by_count":18,"area":null},{"id":"2206.07382","title":"Sparse Structure Search for Parameter-Efficient Tuning","created":"2022-06-15","cited_by_count":17,"area":null},{"id":"2309.14763","title":"ConPET: Continual Parameter-Efficient Tuning for Large Language Models","created":"2023-09-26","cited_by_count":17,"area":null},{"id":"2405.02596","title":"Random Masking Finds Winning Tickets for Parameter Efficient Fine-tuning","created":"2024-05-04","cited_by_count":17,"area":null},{"id":"2406.13175","title":"Sparse High Rank Adapters","created":"2024-06-19","cited_by_count":17,"area":null},{"id":"2210.16079","title":"Debiasing Masks: A New Framework for Shortcut Mitigation in NLU","created":"2022-10-28","cited_by_count":16,"area":null},{"id":"2310.03084","title":"Discovering Knowledge-Critical Subnetworks in Pretrained Language Models","created":"2023-10-04","cited_by_count":16,"area":null},{"id":"2104.07155","title":"Disentangling Representations of Text by Masking Transformers","created":"2021-04-14","cited_by_count":15,"area":null},{"id":"2207.03509","title":"Meta-Learning the Difference: Preparing Large Language Models for Efficient Adaptation","created":"2022-07-07","cited_by_count":14,"area":null},{"id":"2302.06354","title":"Less is More: Selective Layer Finetuning with SubTuning","created":"2023-02-13","cited_by_count":14,"area":null},{"id":"2303.12267","title":"AUTO: Adaptive Outlier Optimization for Test-Time OOD Detection","created":"2023-03-22","cited_by_count":13,"area":null},{"id":"2305.12785","title":"MacLaSa: Multi-Aspect Controllable Text Generation via Efficient Sampling from Compact Latent Space","created":"2023-05-22","cited_by_count":12,"area":null},{"id":"2312.02515","title":"mLoRA: Fine-Tuning LoRA Adapters via Highly-Efficient Pipeline Parallelism in Multiple GPUs","created":"2023-12-05","cited_by_count":12,"area":null},{"id":"2504.13822","title":"Parameter-Efficient Continual Fine-Tuning: A Survey","created":"2025-04-18","cited_by_count":11,"area":null},{"id":"2204.11218","title":"Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training","created":"2022-04-24","cited_by_count":10,"area":null},{"id":"2411.01800","title":"Expanding Sparse Tuning for Low Memory Usage","created":"2024-11-04","cited_by_count":10,"area":null},{"id":"2112.07522","title":"LMTurk: Few-Shot Learners as Crowdsourcing Workers in a Language-Model-as-a-Service Framework","created":"2021-12-14","cited_by_count":9,"area":null},{"id":"2502.01033","title":"PARA: Parameter-Efficient Fine-tuning with Prompt Aware Representation Adjustment","created":"2025-02-03","cited_by_count":9,"area":null},{"id":"2303.09663","title":"Efficient Computation Sharing for Multi-Task Visual Scene Understanding","created":"2023-03-16","cited_by_count":8,"area":null},{"id":"2401.16457","title":"Effective Controllable Bias Mitigation for Classification and Retrieval using Gate Adapters","created":"2024-01-29","cited_by_count":8,"area":null},{"id":"2409.17834","title":"PEDRO: Parameter-Efficient Fine-tuning with Prompt DEpenDent Representation MOdification","created":"2024-09-26","cited_by_count":8,"area":null},{"id":"2103.01819","title":"The Rediscovery Hypothesis: Language Models Need to Meet Linguistics","created":"2021-03-02","cited_by_count":7,"area":null},{"id":"2105.14636","title":"LEAP: Learnable Pruning for Transformer-based Models","created":"2021-05-30","cited_by_count":7,"area":null},{"id":"2205.11833","title":"Diverse Lottery Tickets Boost Ensemble from a Single Pretrained Model","created":"2022-05-24","cited_by_count":7,"area":null},{"id":"2210.04382","title":"Parameter-Efficient Tuning with Special Token Adaptation","created":"2022-10-10","cited_by_count":7,"area":null},{"id":"2210.05211","title":"A Win-win Deal: Towards Sparse and Robust Pre-trained Language Models","created":"2022-10-11","cited_by_count":7,"area":null},{"id":"2211.01522","title":"Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing","created":"2022-11-02","cited_by_count":7,"area":null},{"id":"2307.15049","title":"Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-trained Vision-Language Models","created":"2023-07-27","cited_by_count":7,"area":"mllm"},{"id":"2105.14940","title":"Do Multilingual Neural Machine Translation Models Contain Language Pair Specific Attention Heads?","created":"2021-05-31","cited_by_count":6,"area":null},{"id":"2205.13359","title":"Feature Forgetting in Continual Representation Learning","created":"2022-05-26","cited_by_count":6,"area":null},{"id":"2407.01320","title":"Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning","created":"2024-07-01","cited_by_count":6,"area":null},{"id":"2503.03920","title":"Personalized Federated Fine-tuning for Heterogeneous Data: An Automatic Rank Learning Approach via Two-Level LoRA","created":"2025-03-05","cited_by_count":6,"area":null},{"id":"2402.18331","title":"FineDiffusion: Scaling up Diffusion Models for Fine-grained Image Generation with 10,000 Classes","created":"2024-02-28","cited_by_count":5,"area":"diffusion"},{"id":"2407.16712","title":"Rapid Switching and Multi-Adapter Fusion via Sparse High Rank Adapters","created":"2024-07-22","cited_by_count":5,"area":null},{"id":"2406.06441","title":"Interpretability of Language Models via Task Spaces","created":"2024-06-10","cited_by_count":4,"area":"mechinterp"},{"id":"2210.13673","title":"Evaluating Parameter Efficient Learning for Generation","created":"2022-10-25","cited_by_count":3,"area":null},{"id":"2305.08285","title":"Parameter-Efficient Fine-Tuning with Layer Pruning on Free-Text Sequence-to-Sequence Modeling","created":"2023-05-15","cited_by_count":3,"area":null},{"id":"2411.17426","title":"CLOVER: Cross-Layer Orthogonal Vectors Pruning and Fine-Tuning","created":"2024-11-26","cited_by_count":3,"area":null},{"id":"2204.04596","title":"Parameter-Efficient Tuning by Manipulating Hidden States of Pretrained Language Models For Classification Tasks","created":"2022-04-10","cited_by_count":2,"area":null},{"id":"2311.17299","title":"Federated Fine-Tuning of Foundation Models via Probabilistic Masking","created":"2023-11-29","cited_by_count":2,"area":null},{"id":"2507.19887","title":"CLoRA: Parameter-Efficient Continual Learning with Low-Rank Adaptation","created":"2025-07-26","cited_by_count":2,"area":null},{"id":"2110.07331","title":"Plug-Tagger: A Pluggable Sequence Labeling Framework Using Language Models","created":"2021-10-14","cited_by_count":1,"area":null},{"id":"2211.16634","title":"SPARTAN: Sparse Hierarchical Memory for Parameter-Efficient Transformers","created":"2022-11-29","cited_by_count":1,"area":null},{"id":"2405.18203","title":"IAPT: Instruction-Aware Prompt Tuning for Large Language Models","created":"2024-05-28","cited_by_count":1,"area":null},{"id":"2510.24037","title":"Kernelized Sparse Fine-Tuning with Bi-level Parameter Competition for Vision Models","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2604.09088","title":"Memory-Efficient Transfer Learning with Fading Side Networks via Masked Dual Path Distillation","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2210.14558","title":"Compressing And Debiasing Vision-Language Pre-Trained Models for Visual Question Answering","created":"2022-10-26","cited_by_count":0,"area":"mllm"},{"id":"2307.10098","title":"Gradient Sparsification For Masked Fine-Tuning of Transformers","created":"2023-07-19","cited_by_count":0,"area":null},{"id":"2310.05115","title":"Breaking Down Word Semantics from Pre-trained Language Models through Layer-wise Dimension Selection","created":"2023-10-08","cited_by_count":0,"area":null},{"id":"2403.08484","title":"Targeted Efficient Fine-tuning: Optimizing Parameter Updates with Data-Driven Sample Selection","created":"2024-03-13","cited_by_count":0,"area":null},{"id":"2506.03674","title":"Out-of-Distribution Graph Models Merging","created":"2025-06-04","cited_by_count":0,"area":null},{"id":"2508.16191","title":"GEM: A Scale-Aware and Distribution-Sensitive Sparse Fine-Tuning Framework for Effective Downstream Adaptation","created":"2025-08-22","cited_by_count":0,"area":null},{"id":"2512.19219","title":"Selective LoRA for Visual Tokens and Attention Heads","created":"2025-12-22","cited_by_count":0,"area":"mllm"},{"id":"2602.14767","title":"SAILS: Segment Anything with Incrementally Learned Semantics for Task-Invariant and Training-Free Continual Learning","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2603.05582","title":"Bias In, Bias Out? Finding Unbiased Subnetworks in Vanilla Models","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2606.10196","title":"Fisher-Guided Progressive Parameter Selection for Adaptive Fine-Tuning","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2608.25370","title":"CRAMER: Control via Request-Aware Masking for Editing Recommenders","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.19985","title":"Past, Future, All at Once: Mitigating Stability-Plasticity Dilemma via Post-hoc JANUS Rectification","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.10550","title":"Diffu-LoRA: A Novel Low-Rank Adaptation for Personalized Diffusion Models","created":"2026-09-24","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}