{"list":"other","total":60,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"2305.13245","title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","created":"2023-05-22","cited_by_count":1346},{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713},{"id":"1803.09050","title":"Learning to Reweight Examples for Robust Deep Learning","created":"2018-03-24","cited_by_count":675},{"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":"1806.04910","title":"Bilevel Programming for Hyperparameter Optimization and Meta-Learning","created":"2018-06-13","cited_by_count":405},{"id":"2305.10429","title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining","created":"2023-05-17","cited_by_count":399},{"id":"1805.08136","title":"Meta-learning with differentiable closed-form solvers","created":"2018-05-21","cited_by_count":397},{"id":"1802.02246","title":"Approximation Methods for Bilevel Programming","created":"2018-02-06","cited_by_count":236},{"id":"2010.07962","title":"Bilevel Optimization: Convergence Analysis and Enhanced Design","created":"2020-10-15","cited_by_count":222},{"id":"2307.05695","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","created":"2023-07-11","cited_by_count":204},{"id":"1810.10667","title":"Truncated Back-propagation for Bilevel Optimization","created":"2018-10-25","cited_by_count":190},{"id":"2007.05170","title":"A Two-Timescale Framework for Bilevel Optimization: Complexity Analysis and Application to Actor-Critic","created":"2020-07-10","cited_by_count":144},{"id":"1911.03809","title":"Meta Label Correction for Noisy Label Learning","created":"2019-11-10","cited_by_count":108},{"id":"2102.07367","title":"A Near-Optimal Algorithm for Stochastic Bilevel Optimization via Double-Momentum","created":"2021-02-15","cited_by_count":106},{"id":"2106.04692","title":"Provably Faster Algorithms for Bilevel Optimization","created":"2021-06-08","cited_by_count":106},{"id":"2301.10945","title":"A Fully First-Order Method for Stochastic Bilevel Optimization","created":"2023-01-26","cited_by_count":100},{"id":"2201.13409","title":"A framework for bilevel optimization that enables stochastic and global variance reduction algorithms","created":"2022-01-31","cited_by_count":99},{"id":"2410.07471","title":"SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection","created":"2024-10-09","cited_by_count":64},{"id":"2111.14580","title":"Amortized Implicit Differentiation for Stochastic Bilevel Optimization","created":"2021-11-29","cited_by_count":63},{"id":"2205.02215","title":"FedNest: Federated Bilevel, Minimax, and Compositional Optimization","created":"2022-05-04","cited_by_count":60},{"id":"2412.05270","title":"APOLLO: SGD-like Memory, AdamW-level Performance","created":"2024-12-06","cited_by_count":54},{"id":"1812.01094","title":"A Single Time-Scale Stochastic Approximation Method for Nested Stochastic Optimization","created":"2018-12-03","cited_by_count":53},{"id":"2112.04660","title":"A Fully Single Loop Algorithm for Bilevel Optimization without Hessian Inverse","created":"2021-12-09","cited_by_count":53},{"id":"2309.01753","title":"On Penalty Methods for Nonconvex Bilevel Optimization and First-Order Stochastic Approximation","created":"2023-09-04","cited_by_count":51},{"id":"2112.03459","title":"A Novel Convergence Analysis for Algorithms of the Adam Family","created":"2021-12-07","cited_by_count":50},{"id":"2406.02214","title":"SLTrain: a sparse plus low-rank approach for parameter and memory efficient pretraining","created":"2024-06-04","cited_by_count":45},{"id":"2406.19976","title":"ScaleBiO: Scalable Bilevel Optimization for LLM Data Reweighting","created":"2024-06-28","cited_by_count":37},{"id":"1905.10874","title":"RSN: Randomized Subspace Newton","created":"2019-05-26","cited_by_count":34},{"id":"2410.11289","title":"Subspace Optimization for Large Language Models with Convergence Guarantees","created":"2024-10-15","cited_by_count":34},{"id":"1911.03432","title":"Penalty Method for Inversion-Free Deep Bilevel Optimization","created":"2019-11-08","cited_by_count":33},{"id":"2206.10870","title":"Decentralized Gossip-Based Stochastic Bilevel Optimization over Communication Networks","created":"2022-06-22","cited_by_count":32},{"id":"2306.12067","title":"Optimal Algorithms for Stochastic Bilevel Optimization under Relaxed Smoothness Conditions","created":"2023-06-21","cited_by_count":31},{"id":"2502.10940","title":"CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation","created":"2025-02-16","cited_by_count":28},{"id":"2106.13781","title":"Tighter Analysis of Alternating Stochastic Gradient Method for Stochastic Nested Problems","created":"2021-06-25","cited_by_count":22},{"id":"2210.12839","title":"Decentralized Stochastic Bilevel Optimization with Improved per-Iteration Complexity","created":"2022-10-23","cited_by_count":21},{"id":"2302.06810","title":"Learning from Noisy Labels with Decoupled Meta Label Purifier","created":"2023-02-14","cited_by_count":21},{"id":"2405.17991","title":"VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections","created":"2024-05-28","cited_by_count":18},{"id":"2502.07222","title":"A Memory Efficient Randomized Subspace Optimization Method for Training Large Language Models","created":"2025-02-11","cited_by_count":16},{"id":"2401.09587","title":"Bilevel Optimization under Unbounded Smoothness: A New Algorithm and Convergence Analysis","created":"2024-01-17","cited_by_count":15},{"id":"2305.19442","title":"SimFBO: Towards Simple, Flexible and Communication-efficient Federated Bilevel Learning","created":"2023-05-30","cited_by_count":14},{"id":"2407.17823","title":"Optimal Hessian/Jacobian-Free Nonconvex-PL Bilevel Optimization","created":"2024-07-25","cited_by_count":11},{"id":"2302.06701","title":"Communication-Efficient Federated Bilevel Optimization with Local and Global Lower Level Problems","created":"2023-02-13","cited_by_count":8},{"id":"2412.00071","title":"COAP: Memory-Efficient Training with Correlation-Aware Gradient Projection","created":"2024-11-26","cited_by_count":8},{"id":"2502.05790","title":"Breaking the Frozen Subspace: Importance Sampling for Low-Rank Optimization in LLM Pretraining","created":"2025-02-09","cited_by_count":7},{"id":"2509.18993","title":"CR-Net: Scaling Parameter-Efficient Training with Cross-Layer Low-Rank Structure","created":"2025-09-23","cited_by_count":7},{"id":"2405.18777","title":"SPABA: A Single-Loop and Probabilistic Stochastic Bilevel Algorithm Achieving Optimal Sample Complexity","created":"2024-05-29","cited_by_count":6},{"id":"2402.03167","title":"Decentralized Bilevel Optimization: A Perspective from Transient Iteration Complexity","created":"2024-02-05","cited_by_count":5},{"id":"2410.05140","title":"Tuning-Free Bilevel Optimization: New Algorithms and Convergence Analysis","created":"2024-10-07","cited_by_count":5},{"id":"2502.03604","title":"Bilevel ZOFO: Efficient LLM Fine-Tuning and Meta-Training","created":"2025-02-05","cited_by_count":5},{"id":"2404.03331","title":"LancBiO: dynamic Lanczos-aided bilevel optimization via Krylov subspace","created":"2024-04-04","cited_by_count":4},{"id":"2411.14166","title":"SPARKLE: A Unified Single-Loop Primal-Dual Framework for Decentralized Bilevel Optimization","created":"2024-11-21","cited_by_count":3},{"id":"2405.18858","title":"Distributed Bilevel Optimization with Communication Compression","created":"2024-05-29","cited_by_count":2}],"next_cursor":null}