{"list":"other","total":60,"rows":[{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"2003.01690","title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","created":"2020-03-03","cited_by_count":1451},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"1802.03268","title":"Efficient Neural Architecture Search via Parameter Sharing","created":"2018-02-09","cited_by_count":837},{"id":"2306.01116","title":"The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only","created":"2023-06-01","cited_by_count":763},{"id":"2001.03994","title":"Fast is better than free: Revisiting adversarial training","created":"2020-01-12","cited_by_count":727},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"id":"2309.05463","title":"Textbooks Are All You Need II: phi-1.5 technical report","created":"2023-09-11","cited_by_count":565},{"id":"1909.04630","title":"Meta-Learning with Implicit Gradients","created":"2019-09-10","cited_by_count":525},{"id":"2403.03507","title":"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection","created":"2024-03-06","cited_by_count":463},{"id":"2006.02903","title":"A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions","created":"2020-06-01","cited_by_count":254},{"id":"1812.04754","title":"Gradient Descent Happens in a Tiny Subspace","created":"2018-12-12","cited_by_count":217},{"id":"2306.07280","title":"Controlling Text-to-Image Diffusion by Orthogonal Finetuning","created":"2023-06-12","cited_by_count":208},{"id":"2307.05695","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","created":"2023-07-11","cited_by_count":204},{"id":"2301.12314","title":"Progressive Prompts: Continual Learning for Language Models","created":"2023-01-29","cited_by_count":197},{"id":"2311.03285","title":"S-LoRA: Serving Thousands of Concurrent LoRA Adapters","created":"2023-11-06","cited_by_count":152},{"id":"2108.06098","title":"FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learning","created":"2021-08-13","cited_by_count":141},{"id":"2212.10650","title":"KronA: Parameter Efficient Tuning with Kronecker Adapter","created":"2022-12-20","cited_by_count":133},{"id":"2311.06243","title":"Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization","created":"2023-11-10","cited_by_count":114},{"id":"2010.11635","title":"Continual Learning in Low-rank Orthogonal Subspaces","created":"2020-10-22","cited_by_count":99},{"id":"2401.04151","title":"Chain of LoRA: Efficient Fine-tuning of Language Models via Residual Learning","created":"2024-01-08","cited_by_count":82},{"id":"1509.03025","title":"Fast low-rank estimation by projected gradient descent: General statistical and algorithmic guarantees","created":"2015-09-10","cited_by_count":70},{"id":"2307.13770","title":"E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning","created":"2023-07-25","cited_by_count":70},{"id":"2311.09578","title":"Tied-Lora: Enhancing parameter efficiency of LoRA with weight tying","created":"2023-11-16","cited_by_count":65},{"id":"2305.03937","title":"Residual Prompt Tuning: Improving Prompt Tuning with Residual Reparameterization","created":"2023-05-06","cited_by_count":64},{"id":"2309.01507","title":"Memory Efficient Optimizers with 4-bit States","created":"2023-09-04","cited_by_count":54},{"id":"2405.18653","title":"Recent Advances of Foundation Language Models-based Continual Learning: A Survey","created":"2024-05-28","cited_by_count":46},{"id":"2205.06166","title":"Dynamic Prefix-Tuning for Generative Template-based Event Extraction","created":"2022-05-12","cited_by_count":35},{"id":"2311.11501","title":"MultiLoRA: Democratizing LoRA for Better Multi-Task Learning","created":"2023-11-20","cited_by_count":32},{"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},{"id":"1611.10349","title":"Non-Convex Projected Gradient Descent for Generalized Low-Rank Tensor Regression","created":"2016-11-30","cited_by_count":23},{"id":"1812.06081","title":"A Neural Multi-Task Learning Framework to Jointly Model Medical Named Entity Recognition and Normalization","created":"2018-12-14","cited_by_count":20},{"id":"2312.10868","title":"From Google Gemini to OpenAI Q* (Q-Star): A Survey of Reshaping the Generative Artificial Intelligence (AI) Research Landscape","created":"2023-12-18","cited_by_count":18},{"id":"2402.18039","title":"ResLoRA: Identity Residual Mapping in Low-Rank Adaption","created":"2024-02-28","cited_by_count":18},{"id":"2007.04146","title":"Few-Shot One-Class Classification via Meta-Learning","created":"2020-07-08","cited_by_count":17},{"id":"2409.10927","title":"Propulsion: Steering LLM with Tiny Fine-Tuning","created":"2024-09-17","cited_by_count":14},{"id":"1907.00409","title":"Evaluating Language Model Finetuning Techniques for Low-resource Languages","created":"2019-06-30","cited_by_count":12},{"id":"2303.02909","title":"Dynamic Prompting: A Unified Framework for Prompt Tuning","created":"2023-03-06","cited_by_count":12},{"id":"2402.15080","title":"Infusing Hierarchical Guidance into Prompt Tuning: A Parameter-Efficient Framework for Multi-level Implicit Discourse Relation Recognition","created":"2024-02-23","cited_by_count":11},{"id":"2402.01643","title":"L-TUNING: Synchronized Label Tuning for Prompt and Prefix in LLMs","created":"2023-12-21","cited_by_count":4},{"id":"2403.02704","title":"Projected Gradient Descent Algorithm for Low-Rank Matrix Estimation","created":"2024-03-05","cited_by_count":4},{"id":"2408.11856","title":"Dynamic Adaptive Optimization for Effective Sentiment Analysis Fine-Tuning on Large Language Models","created":"2024-08-15","cited_by_count":2},{"id":"2211.16634","title":"SPARTAN: Sparse Hierarchical Memory for Parameter-Efficient Transformers","created":"2022-11-29","cited_by_count":1}],"next_cursor":null}