{"total":134,"rows":[{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623,"area":null},{"id":"2403.03507","title":"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection","created":"2024-03-06","cited_by_count":463,"area":null},{"id":"2310.05915","title":"FireAct: Toward Language Agent Fine-tuning","created":"2023-10-09","cited_by_count":256,"area":"agents"},{"id":"2409.11321","title":"SOAP: Improving and Stabilizing Shampoo using Adam","created":"2024-09-17","cited_by_count":192,"area":null},{"id":"2310.10505","title":"ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models","created":"2023-10-16","cited_by_count":187,"area":"alignment"},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2407.05000","title":"LoRA-GA: Low-Rank Adaptation with Gradient Approximation","created":"2024-07-06","cited_by_count":141,"area":null},{"id":"2406.16793","title":"Adam-mini: Use Fewer Learning Rates To Gain More","created":"2024-06-24","cited_by_count":137,"area":null},{"id":"2402.16788","title":"Why Transformers Need Adam: A Hessian Perspective","created":"2024-02-26","cited_by_count":124,"area":null},{"id":"2402.03293","title":"Flora: Low-Rank Adapters Are Secretly Gradient Compressors","created":"2024-02-05","cited_by_count":108,"area":null},{"id":"2402.08562","title":"Higher Layers Need More LoRA Experts","created":"2024-02-13","cited_by_count":102,"area":"moe"},{"id":"2403.12881","title":"Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models","created":"2024-03-19","cited_by_count":100,"area":"agents"},{"id":"2405.10739","title":"Efficient Multimodal Large Language Models: A Survey","created":"2024-05-17","cited_by_count":96,"area":"mllm"},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2309.02411","title":"Delta-LoRA: Fine-Tuning High-Rank Parameters with the Delta of Low-Rank Matrices","created":"2023-09-05","cited_by_count":74,"area":null},{"id":"2405.04760","title":"Large Language Models for Cyber Security: A Systematic Literature Review","created":"2024-05-08","cited_by_count":68,"area":null},{"id":"2412.05270","title":"APOLLO: SGD-like Memory, AdamW-level Performance","created":"2024-12-06","cited_by_count":54,"area":null},{"id":"2312.15698","title":"RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair","created":"2023-12-25","cited_by_count":50,"area":null},{"id":"2411.16085","title":"Cautious Optimizers: Improving Training with One Line of Code","created":"2024-11-25","cited_by_count":47,"area":null},{"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,"area":null},{"id":"2403.16073","title":"Combining Fine-Tuning and LLM-based Agents for Intuitive Smart Contract Auditing with Justifications","created":"2024-03-24","cited_by_count":41,"area":"agents"},{"id":"2405.09055","title":"A safety realignment framework via subspace-oriented model fusion for large language models","created":"2024-05-15","cited_by_count":41,"area":"safety"},{"id":"2408.12857","title":"Memory-Efficient LLM Training with Online Subspace Descent","created":"2024-08-23","cited_by_count":39,"area":null},{"id":"2407.08296","title":"Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients","created":"2024-07-11","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":"2406.14088","title":"ReaL: Efficient RLHF Training of Large Language Models with Parameter Reallocation","created":"2024-06-20","cited_by_count":37,"area":"alignment"},{"id":"2407.13647","title":"Weak-to-Strong Reasoning","created":"2024-07-18","cited_by_count":33,"area":"lr"},{"id":"2310.10195","title":"AdaLomo: Low-memory Optimization with Adaptive Learning Rate","created":"2023-10-16","cited_by_count":31,"area":null},{"id":"2404.02827","title":"BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models","created":"2024-04-03","cited_by_count":27,"area":null},{"id":"2308.04709","title":"A Comparative Study of Open-Source Large Language Models, GPT-4 and Claude 2: Multiple-Choice Test Taking in Nephrology","created":"2023-08-09","cited_by_count":26,"area":null},{"id":"2312.15184","title":"ZO-AdaMU Optimizer: Adapting Perturbation by the Momentum and Uncertainty in Zeroth-order Optimization","created":"2023-12-23","cited_by_count":25,"area":null},{"id":"2404.13506","title":"Parameter Efficient Fine Tuning: A Comprehensive Analysis Across Applications","created":"2024-04-21","cited_by_count":25,"area":null},{"id":"2408.13233","title":"Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time","created":"2024-08-23","cited_by_count":22,"area":null},{"id":"2411.19557","title":"Initialization using Update Approximation is a Silver Bullet for Extremely Efficient Low-Rank Fine-Tuning","created":"2024-11-29","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":"2505.16270","title":"Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning","created":"2025-05-22","cited_by_count":21,"area":null},{"id":"2412.13148","title":"SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training","created":"2024-12-17","cited_by_count":20,"area":null},{"id":"2307.02053","title":"Flacuna: Unleashing the Problem Solving Power of Vicuna using FLAN Fine-Tuning","created":"2023-07-05","cited_by_count":18,"area":null},{"id":"2405.17991","title":"VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections","created":"2024-05-28","cited_by_count":18,"area":null},{"id":"2406.17660","title":"Grass: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients","created":"2024-06-25","cited_by_count":18,"area":null},{"id":"2407.01031","title":"PocketLLM: Enabling On-Device Fine-Tuning for Personalized LLMs","created":"2024-07-01","cited_by_count":18,"area":null},{"id":"2411.03707","title":"Fine-Tuning Vision-Language Model for Automated Engineering Drawing Information Extraction","created":"2024-11-06","cited_by_count":18,"area":"mllm"},{"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":"2410.17881","title":"AdaRankGrad: Adaptive Gradient-Rank and Moments for Memory-Efficient LLMs Training and Fine-Tuning","created":"2024-10-23","cited_by_count":17,"area":null},{"id":"2402.12168","title":"Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning","created":"2024-02-19","cited_by_count":16,"area":null},{"id":"2502.01586","title":"SubTrack++ : Gradient Subspace Tracking for Scalable LLM Training","created":"2025-02-03","cited_by_count":16,"area":null},{"id":"2505.11827","title":"Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning","created":"2025-05-17","cited_by_count":16,"area":"lr"},{"id":"2410.20650","title":"NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks","created":"2024-10-28","cited_by_count":14,"area":null},{"id":"2405.06275","title":"Pruning as a Domain-specific LLM Extractor","created":"2024-05-10","cited_by_count":13,"area":null},{"id":"2408.10280","title":"NoRA: Nested Low-Rank Adaptation for Efficient Fine-Tuning Large Models","created":"2024-08-18","cited_by_count":13,"area":null},{"id":"2501.13669","title":"How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization","created":"2025-01-23","cited_by_count":13,"area":null},{"id":"2401.15207","title":"HiFT: A Hierarchical Full Parameter Fine-Tuning Strategy","created":"2024-01-26","cited_by_count":12,"area":null},{"id":"2402.13482","title":"Retrieval-Augmented Data Augmentation for Low-Resource Domain Tasks","created":"2024-02-21","cited_by_count":12,"area":"rag"},{"id":"2405.16528","title":"LoQT: Low-Rank Adapters for Quantized Pretraining","created":"2024-05-26","cited_by_count":12,"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":"2410.06441","title":"Addax: Utilizing Zeroth-Order Gradients to Improve Memory Efficiency and Performance of SGD for Fine-Tuning Language Models","created":"2024-10-09","cited_by_count":11,"area":null},{"id":"2412.19616","title":"Gradient Weight-normalized Low-rank Projection for Efficient LLM Training","created":"2024-12-27","cited_by_count":11,"area":null},{"id":"2310.07147","title":"QFT: Quantized Full-parameter Tuning of LLMs with Affordable Resources","created":"2023-10-11","cited_by_count":10,"area":null},{"id":"2402.05188","title":"InCoRo: In-Context Learning for Robotics Control with Feedback Loops","created":"2024-02-07","cited_by_count":10,"area":"lr"},{"id":"2405.13025","title":"A survey on fairness of large language models in e-commerce: progress, application, and challenge","created":"2024-05-15","cited_by_count":10,"area":null},{"id":"2411.07837","title":"FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training","created":"2024-11-12","cited_by_count":10,"area":null},{"id":"2402.05868","title":"EmojiPrompt: Generative Prompt Obfuscation for Privacy-Preserving Communication with Cloud-based LLMs","created":"2024-02-08","cited_by_count":9,"area":null},{"id":"2506.04430","title":"Leveraging Coordinate Momentum in SignSGD and Muon: Memory-Optimized Zero-Order","created":"2025-06-04","cited_by_count":9,"area":null},{"id":"2509.03057","title":"Structure-Learnable Adapter Fine-Tuning for Parameter-Efficient Large Language Models","created":"2025-09-03","cited_by_count":9,"area":null},{"id":"2402.16968","title":"A Survey of Large Language Models in Cybersecurity","created":"2024-02-26","cited_by_count":8,"area":null},{"id":"2412.00071","title":"COAP: Memory-Efficient Training with Correlation-Aware Gradient Projection","created":"2024-11-26","cited_by_count":8,"area":null},{"id":"2506.17374","title":"From Drawings to Decisions: A Hybrid Vision-Language Framework for Parsing 2D Engineering Drawings into Structured Manufacturing Knowledge","created":"2025-06-20","cited_by_count":8,"area":null},{"id":"2507.02938","title":"A Large Language Model-Empowered Agent for Reliable and Robust Structural Analysis","created":"2025-06-27","cited_by_count":8,"area":"agents"},{"id":"2407.21330","title":"Performance of Recent Large Language Models for a Low-Resourced Language","created":"2024-07-31","cited_by_count":7,"area":null},{"id":"2409.01990","title":"Designing Large Foundation Models for Efficient Training and Inference: A Survey","created":"2024-09-03","cited_by_count":7,"area":null},{"id":"2409.15371","title":"MiSS: Revisiting the Trade-off in LoRA with an Efficient Shard-Sharing Structure","created":"2024-09-19","cited_by_count":7,"area":null},{"id":"2411.03820","title":"Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PC","created":"2024-11-06","cited_by_count":7,"area":"deeprl"},{"id":"2412.08587","title":"Advancing Single and Multi-task Text Classification through Large Language Model Fine-tuning","created":"2024-12-11","cited_by_count":7,"area":null},{"id":"2410.20777","title":"KD-LoRA: A Hybrid Approach to Efficient Fine-Tuning with LoRA and Knowledge Distillation","created":"2024-10-28","cited_by_count":6,"area":"distill"},{"id":"2603.13792","title":"IGU-LoRA: Adaptive Rank Allocation via Integrated Gradients and Uncertainty-Aware Scoring","created":"2026-03-14","cited_by_count":6,"area":null},{"id":"2403.09428","title":"Borrowing Treasures from Neighbors: In-Context Learning for Multimodal Learning with Missing Modalities and Data Scarcity","created":"2024-03-14","cited_by_count":5,"area":null},{"id":"2403.14683","title":"A Moral Imperative: The Need for Continual Superalignment of Large Language Models","created":"2024-03-13","cited_by_count":5,"area":"alignment"},{"id":"2407.10855","title":"Weighted Grouped Query Attention in Transformers","created":"2024-07-15","cited_by_count":5,"area":null},{"id":"2502.19571","title":"LORENZA: Enhancing Generalization in Low-Rank Gradient LLM Training via Efficient Zeroth-Order Adaptive SAM","created":"2025-02-26","cited_by_count":5,"area":null},{"id":"2504.19583","title":"Graph-Based Spectral Decomposition for Parameter Coordination in Language Model Fine-Tuning","created":"2025-04-28","cited_by_count":5,"area":null},{"id":"2506.12072","title":"TRACE: Transparent Web Reliability Assessment with Contextual Explanations","created":"2025-06-05","cited_by_count":5,"area":null},{"id":"2602.23349","title":"FlashOptim: Optimizers for Memory-Efficient Training","created":"2026-02-26","cited_by_count":5,"area":null},{"id":"2409.04833","title":"Achieving Peak Performance for Large Language Models: A Systematic Review","created":"2024-09-07","cited_by_count":4,"area":null},{"id":"2412.13243","title":"In-Context Learning Distillation for Efficient Few-Shot Fine-Tuning","created":"2024-12-17","cited_by_count":4,"area":"distill"},{"id":"2412.14426","title":"All-in-One Tuning and Structural Pruning for Domain-Specific LLMs","created":"2024-12-19","cited_by_count":4,"area":null},{"id":"2412.17107","title":"Grams: Gradient Descent with Adaptive Momentum Scaling","created":"2024-12-22","cited_by_count":4,"area":null},{"id":"2502.18424","title":"Compressing Language Models for Specialized Domains","created":"2025-02-25","cited_by_count":4,"area":null},{"id":"2507.08091","title":"Low-rank Momentum Factorization for Memory Efficient Training","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2311.15698","title":"Cerbero-7B: A Leap Forward in Language-Specific LLMs Through Enhanced Chat Corpus Generation and Evaluation","created":"2023-11-27","cited_by_count":3,"area":null},{"id":"2312.00407","title":"CoLLiE: Collaborative Training of Large Language Models in an Efficient Way","created":"2023-12-01","cited_by_count":3,"area":null},{"id":"2409.15520","title":"MobiZO: Enabling Efficient LLM Fine-Tuning at the Edge via Inference Engines","created":"2024-09-23","cited_by_count":3,"area":null},{"id":"2410.07854","title":"HeGraphAdapter: Tuning Multi-Modal Vision-Language Models with Heterogeneous Graph Adapter","created":"2024-10-10","cited_by_count":3,"area":"mllm"},{"id":"2501.02373","title":"BADTV: Unveiling Backdoor Threats in Third-Party Task Vectors","created":"2025-01-04","cited_by_count":3,"area":"safety"},{"id":"2508.15478","title":"SLM-Bench: A Comprehensive Benchmark of Small Language Models on Environmental Impacts--Extended Version","created":"2025-08-21","cited_by_count":3,"area":null},{"id":"2308.10252","title":"LMTuner: An user-friendly and highly-integrable Training Framework for fine-tuning Large Language Models","created":"2023-08-20","cited_by_count":2,"area":null},{"id":"2407.21037","title":"An Application of Large Language Models to Coding Negotiation Transcripts","created":"2024-07-18","cited_by_count":2,"area":null},{"id":"2412.02735","title":"CPP-UT-Bench: Can LLMs Write Complex Unit Tests in C++?","created":"2024-12-03","cited_by_count":2,"area":null},{"id":"2503.07399","title":"Exploring Representation Invariance in Finetuning","created":"2025-03-10","cited_by_count":2,"area":null},{"id":"2503.16071","title":"Tuning LLMs by RAG Principles: Towards LLM-native Memory","created":"2025-03-20","cited_by_count":2,"area":"rag"},{"id":"2503.23362","title":"Mixture of Routers","created":"2025-03-30","cited_by_count":2,"area":"alignment"}],"next_cursor":"100"}