{"total":147,"rows":[{"id":"2212.10450","title":"Is GPT-3 a Good Data Annotator?","created":"2022-12-20","cited_by_count":208,"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":"2110.07577","title":"UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning","created":"2021-10-14","cited_by_count":162,"area":null},{"id":"2306.10900","title":"MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators","created":"2023-06-19","cited_by_count":145,"area":null},{"id":"2211.15583","title":"On the Effectiveness of Parameter-Efficient Fine-Tuning","created":"2022-11-28","cited_by_count":141,"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":"2309.09510","title":"Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech","created":"2023-09-18","cited_by_count":101,"area":null},{"id":"2303.10868","title":"Retrieving Multimodal Information for Augmented Generation: A Survey","created":"2023-03-20","cited_by_count":85,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2404.00925","title":"LLMs are Good Sign Language Translators","created":"2024-04-01","cited_by_count":77,"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":"2202.07962","title":"Revisiting Parameter-Efficient Tuning: Are We Really There Yet?","created":"2022-02-16","cited_by_count":76,"area":null},{"id":"2405.03644","title":"When LLMs Meet Cybersecurity: A Systematic Literature Review","created":"2024-05-06","cited_by_count":71,"area":null},{"id":"2203.06311","title":"ELLE: Efficient Lifelong Pre-training for Emerging Data","created":"2022-03-12","cited_by_count":70,"area":null},{"id":"2110.01518","title":"Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics","created":"2021-10-04","cited_by_count":67,"area":null},{"id":"2410.21747","title":"MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding","created":"2024-10-29","cited_by_count":59,"area":null},{"id":"2306.04344","title":"ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation","created":"2023-06-07","cited_by_count":58,"area":null},{"id":"2301.13741","title":"UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers","created":"2023-01-31","cited_by_count":54,"area":null},{"id":"2502.10708","title":"Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Survey","created":"2025-02-15","cited_by_count":51,"area":null},{"id":"2307.16867","title":"Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancy","created":"2023-07-31","cited_by_count":44,"area":null},{"id":"2204.04497","title":"IDPG: An Instance-Dependent Prompt Generation Method","created":"2022-04-09","cited_by_count":43,"area":null},{"id":"2210.05497","title":"Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models","created":"2022-10-11","cited_by_count":42,"area":null},{"id":"2309.15701","title":"HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models","created":"2023-09-27","cited_by_count":42,"area":null},{"id":"2402.11890","title":"Revisiting Knowledge Distillation for Autoregressive Language Models","created":"2024-02-19","cited_by_count":42,"area":"distill"},{"id":"2304.14999","title":"Empirical Analysis of the Strengths and Weaknesses of PEFT Techniques for LLMs","created":"2023-04-28","cited_by_count":38,"area":null},{"id":"2108.02340","title":"Robust Transfer Learning with Pretrained Language Models through Adapters","created":"2021-08-05","cited_by_count":35,"area":null},{"id":"2203.03131","title":"Input-Tuning: Adapting Unfamiliar Inputs to Frozen Pretrained Models","created":"2022-03-07","cited_by_count":34,"area":null},{"id":"2211.15613","title":"Frustratingly Easy Label Projection for Cross-lingual Transfer","created":"2022-11-28","cited_by_count":33,"area":null},{"id":"2311.11501","title":"MultiLoRA: Democratizing LoRA for Better Multi-Task Learning","created":"2023-11-20","cited_by_count":32,"area":null},{"id":"2211.14228","title":"GPT-3-driven pedagogical agents for training children's curious question-asking skills","created":"2022-11-25","cited_by_count":29,"area":null},{"id":"2210.06175","title":"Exploring Efficient-tuning Methods in Self-supervised Speech Models","created":"2022-10-10","cited_by_count":26,"area":null},{"id":"2211.03154","title":"On the Domain Adaptation and Generalization of Pretrained Language Models: A Survey","created":"2022-11-06","cited_by_count":23,"area":null},{"id":"2308.10172","title":"VLN-PETL: Parameter-Efficient Transfer Learning for Vision-and-Language Navigation","created":"2023-08-20","cited_by_count":23,"area":null},{"id":"2406.05130","title":"An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models","created":"2024-06-07","cited_by_count":22,"area":"mllm"},{"id":"2406.10777","title":"RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuning","created":"2024-06-16","cited_by_count":21,"area":null},{"id":"2211.08682","title":"Parameter-Efficient Tuning on Layer Normalization for Pre-trained Language Models","created":"2022-11-16","cited_by_count":19,"area":null},{"id":"2311.07603","title":"PECoP: Parameter Efficient Continual Pretraining for Action Quality Assessment","created":"2023-11-11","cited_by_count":19,"area":null},{"id":"2206.07382","title":"Sparse Structure Search for Parameter-Efficient Tuning","created":"2022-06-15","cited_by_count":17,"area":null},{"id":"2402.13137","title":"The Hidden Space of Transformer Language Adapters","created":"2024-02-20","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":"2205.02170","title":"Efficient Few-Shot Fine-Tuning for Opinion Summarization","created":"2022-05-04","cited_by_count":16,"area":null},{"id":"2303.15822","title":"One Adapter for All Programming Languages? Adapter Tuning for Code Search and Summarization","created":"2023-03-28","cited_by_count":16,"area":null},{"id":"2409.16434","title":"Lessons and Insights from a Unifying Study of Parameter-Efficient Fine-Tuning (PEFT) in Visual Recognition","created":"2024-09-24","cited_by_count":16,"area":null},{"id":"2403.13269","title":"AFLoRA: Adaptive Freezing of Low Rank Adaptation in Parameter Efficient Fine-Tuning of Large Models","created":"2024-03-20","cited_by_count":15,"area":null},{"id":"2407.01406","title":"Adapting Multilingual LLMs to Low-Resource Languages with Knowledge Graphs via Adapters","created":"2024-07-01","cited_by_count":15,"area":null},{"id":"2111.00667","title":"Unsupervised Domain Adaptation with Adapter","created":"2021-11-01","cited_by_count":14,"area":null},{"id":"2311.14030","title":"PrivateLoRA For Efficient Privacy Preserving LLM","created":"2023-11-23","cited_by_count":14,"area":null},{"id":"2111.10962","title":"Enhancing Multilingual Language Model with Massive Multilingual Knowledge Triples","created":"2021-11-22","cited_by_count":13,"area":null},{"id":"2205.01549","title":"Adaptable Adapters","created":"2022-05-03","cited_by_count":13,"area":null},{"id":"2212.01282","title":"CHAPTER: Exploiting Convolutional Neural Network Adapters for Self-supervised Speech Models","created":"2022-12-01","cited_by_count":13,"area":null},{"id":"2302.03194","title":"UDApter -- Efficient Domain Adaptation Using Adapters","created":"2023-02-07","cited_by_count":13,"area":null},{"id":"2405.17258","title":"$\\textit{Trans-LoRA}$: towards data-free Transferable Parameter Efficient Finetuning","created":"2024-05-27","cited_by_count":13,"area":null},{"id":"2411.16746","title":"LoBAM: LoRA-Based Backdoor Attack on Model Merging","created":"2024-11-23","cited_by_count":12,"area":null},{"id":"2306.00168","title":"Measuring the Robustness of NLP Models to Domain Shifts","created":"2023-05-31","cited_by_count":11,"area":null},{"id":"2306.11648","title":"Harnessing the Power of Adversarial Prompting and Large Language Models for Robust Hypothesis Generation in Astronomy","created":"2023-06-20","cited_by_count":11,"area":"safety"},{"id":"2411.15231","title":"IterIS: Iterative Inference-Solving Alignment for LoRA Merging","created":"2024-11-21","cited_by_count":11,"area":null},{"id":"2501.02191","title":"On LLM-Enhanced Mixed-Type Data Imputation with High-Order Message Passing","created":"2025-01-04","cited_by_count":11,"area":null},{"id":"2310.16393","title":"ZGUL: Zero-shot Generalization to Unseen Languages using Multi-source Ensembling of Language Adapters","created":"2023-10-25","cited_by_count":10,"area":null},{"id":"2306.15742","title":"Differentially Private Video Activity Recognition","created":"2023-06-27","cited_by_count":9,"area":null},{"id":"2308.07282","title":"Comparison between parameter-efficient techniques and full fine-tuning: A case study on multilingual news article classification","created":"2023-08-14","cited_by_count":9,"area":null},{"id":"2108.08103","title":"AdapterHub Playground: Simple and Flexible Few-Shot Learning with Adapters","created":"2021-08-18","cited_by_count":8,"area":null},{"id":"2301.12140","title":"Multilingual Sentence Transformer as A Multilingual Word Aligner","created":"2023-01-28","cited_by_count":8,"area":null},{"id":"2302.04618","title":"Robust Question Answering against Distribution Shifts with Test-Time Adaptation: An Empirical Study","created":"2023-02-09","cited_by_count":8,"area":null},{"id":"2305.14453","title":"On Robustness of Finetuned Transformer-based NLP Models","created":"2023-05-23","cited_by_count":8,"area":null},{"id":"2305.15275","title":"Self-Evolution Learning for Discriminative Language Model Pretraining","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2505.21795","title":"SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot Segmentation","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2201.00016","title":"TransLog: A Unified Transformer-based Framework for Log Anomaly Detection","created":"2021-12-31","cited_by_count":7,"area":null},{"id":"2402.15059","title":"ColBERT-XM: A Modular Multi-Vector Representation Model for Zero-Shot Multilingual Information Retrieval","created":"2024-02-23","cited_by_count":7,"area":null},{"id":"2409.20247","title":"Resource Allocation for Stable LLM Training in Mobile Edge Computing","created":"2024-09-30","cited_by_count":7,"area":null},{"id":"2110.14943","title":"Semi-Siamese Bi-encoder Neural Ranking Model Using Lightweight Fine-Tuning","created":"2021-10-28","cited_by_count":6,"area":null},{"id":"2305.12717","title":"TADA: Efficient Task-Agnostic Domain Adaptation for Transformers","created":"2023-05-22","cited_by_count":6,"area":null},{"id":"2307.03104","title":"Efficient Domain Adaptation of Sentence Embeddings Using Adapters","created":"2023-07-06","cited_by_count":6,"area":null},{"id":"2402.00149","title":"The Impact of Language Adapters in Cross-Lingual Transfer for NLU","created":"2024-01-31","cited_by_count":6,"area":null},{"id":"2408.13891","title":"SpeechCaps: Advancing Instruction-Based Universal Speech Models with Multi-Talker Speaking Style Captioning","created":"2024-08-25","cited_by_count":6,"area":null},{"id":"2410.23111","title":"Exploring Gradient Subspaces: Addressing and Overcoming LoRA's Limitations in Federated Fine-Tuning of Large Language Models","created":"2024-10-30","cited_by_count":6,"area":null},{"id":"2411.00873","title":"CleaR: Towards Robust and Generalized Parameter-Efficient Fine-Tuning for Noisy Label Learning","created":"2024-10-31","cited_by_count":6,"area":null},{"id":"2210.06425","title":"MiniALBERT: Model Distillation via Parameter-Efficient Recursive Transformers","created":"2022-10-12","cited_by_count":5,"area":null},{"id":"2212.10929","title":"SPT: Semi-Parametric Prompt Tuning for Multitask Prompted Learning","created":"2022-12-21","cited_by_count":5,"area":null},{"id":"2303.01239","title":"MixPHM: Redundancy-Aware Parameter-Efficient Tuning for Low-Resource Visual Question Answering","created":"2023-03-02","cited_by_count":5,"area":"mllm"},{"id":"2303.09421","title":"SheffieldVeraAI at SemEval-2023 Task 3: Mono and multilingual approaches for news genre, topic and persuasion technique classification","created":"2023-03-16","cited_by_count":5,"area":null},{"id":"2305.14576","title":"Parameter-Efficient Language Model Tuning with Active Learning in Low-Resource Settings","created":"2023-05-23","cited_by_count":5,"area":null},{"id":"2312.15614","title":"A Comprehensive Evaluation of Parameter-Efficient Fine-Tuning on Software Engineering Tasks","created":"2023-12-25","cited_by_count":5,"area":null},{"id":"2312.16222","title":"Segment Any Events via Weighted Adaptation of Pivotal Tokens","created":"2023-12-24","cited_by_count":5,"area":null},{"id":"2404.18322","title":"BlockLLM: Multi-tenant Finer-grained Serving for Large Language Models","created":"2024-04-28","cited_by_count":5,"area":"inference"},{"id":"2203.02652","title":"Unfreeze with Care: Space-Efficient Fine-Tuning of Semantic Parsing Models","created":"2022-03-05","cited_by_count":4,"area":null},{"id":"2212.10448","title":"Parameter-efficient Zero-shot Transfer for Cross-Language Dense Retrieval with Adapters","created":"2022-12-20","cited_by_count":4,"area":null},{"id":"2411.00029","title":"Preserving Pre-trained Representation Space: On Effectiveness of Prefix-tuning for Large Multi-modal Models","created":"2024-10-29","cited_by_count":4,"area":"mllm"},{"id":"2503.07979","title":"Achieving More with Less: Additive Prompt Tuning for Rehearsal-Free Class-Incremental Learning","created":"2025-03-11","cited_by_count":4,"area":null},{"id":"2503.22982","title":"PartialLoading: User Scheduling and Bandwidth Allocation for Parameter-sharing Edge Inference","created":"2025-03-29","cited_by_count":4,"area":null},{"id":"2509.09097","title":"DP-FedLoRA: Privacy-Enhanced Federated Fine-Tuning for On-Device Large Language Models","created":"2025-09-11","cited_by_count":4,"area":null},{"id":"2210.13673","title":"Evaluating Parameter Efficient Learning for Generation","created":"2022-10-25","cited_by_count":3,"area":null},{"id":"2210.14304","title":"Learning Better Intent Representations for Financial Open Intent Classification","created":"2022-10-25","cited_by_count":3,"area":null},{"id":"2210.14469","title":"Inducer-tuning: Connecting Prefix-tuning and Adapter-tuning","created":"2022-10-26","cited_by_count":3,"area":null},{"id":"2211.08794","title":"Towards Robust Low-Resource Fine-Tuning with Multi-View Compressed Representations","created":"2022-11-16","cited_by_count":3,"area":null},{"id":"2211.11363","title":"AF Adapter: Continual Pretraining for Building Chinese Biomedical Language Model","created":"2022-11-21","cited_by_count":3,"area":null},{"id":"2303.16985","title":"Adapting to the Low-Resource Double-Bind: Investigating Low-Compute Methods on Low-Resource African Languages","created":"2023-03-29","cited_by_count":3,"area":null},{"id":"2405.00293","title":"MoPEFT: A Mixture-of-PEFTs for the Segment Anything Model","created":"2024-05-01","cited_by_count":3,"area":"moe"},{"id":"2501.06271","title":"Large Language Models for Bioinformatics","created":"2025-01-10","cited_by_count":3,"area":null},{"id":"2502.10140","title":"Small Models, Big Impact: Efficient Corpus and Graph-Based Adaptation of Small Multilingual Language Models for Low-Resource Languages","created":"2025-02-14","cited_by_count":3,"area":null},{"id":"2209.00820","title":"Structural Bias for Aspect Sentiment Triplet Extraction","created":"2022-09-02","cited_by_count":2,"area":null}],"next_cursor":"100"}