{"total":128,"rows":[{"id":"2405.09673","title":"LoRA Learns Less and Forgets Less","created":"2024-05-15","cited_by_count":328,"area":null},{"id":"2406.12031","title":"Large Scale Transfer Learning for Tabular Data via Language Modeling","created":"2024-06-17","cited_by_count":76,"area":null},{"id":"2507.09404","title":"Scaling Laws for Optimal Data Mixtures","created":"2025-07-12","cited_by_count":52,"area":null},{"id":"2410.11905","title":"A Scalable Communication Protocol for Networks of Large Language Models","created":"2024-10-14","cited_by_count":45,"area":null},{"id":"2505.24034","title":"LlamaRL: A Distributed Asynchronous Reinforcement Learning Framework for Efficient Large-scale LLM Training","created":"2025-05-29","cited_by_count":42,"area":null},{"id":"2406.01375","title":"D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models","created":"2024-06-03","cited_by_count":41,"area":null},{"id":"2409.19913","title":"Scaling Optimal LR Across Token Horizons","created":"2024-09-30","cited_by_count":40,"area":null},{"id":"2502.01968","title":"Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning","created":"2025-02-04","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":"2502.06042","title":"Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection","created":"2025-02-09","cited_by_count":35,"area":null},{"id":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2410.10877","title":"Improving Data Efficiency via Curating LLM-Driven Rating Systems","created":"2024-10-09","cited_by_count":29,"area":null},{"id":"2403.16443","title":"CodeS: Natural Language to Code Repository via Multi-Layer Sketch","created":"2024-03-25","cited_by_count":28,"area":null},{"id":"2411.05282","title":"MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization","created":"2024-11-08","cited_by_count":28,"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":"2410.11840","title":"A Hitchhiker's Guide to Scaling Law Estimation","created":"2024-10-15","cited_by_count":27,"area":null},{"id":"2507.21919","title":"Training language models to be warm and empathetic makes them less reliable and more sycophantic","created":"2025-07-29","cited_by_count":21,"area":null},{"id":"2407.05040","title":"Code Less, Align More: Efficient LLM Fine-tuning for Code Generation with Data Pruning","created":"2024-07-06","cited_by_count":20,"area":null},{"id":"2502.06857","title":"Gemstones: A Model Suite for Multi-Faceted Scaling Laws","created":"2025-02-07","cited_by_count":20,"area":null},{"id":"2405.07518","title":"SambaNova SN40L: Scaling the AI Memory Wall with Dataflow and Composition of Experts","created":"2024-05-13","cited_by_count":18,"area":null},{"id":"2410.09432","title":"FedEx-LoRA: Exact Aggregation for Federated and Efficient Fine-Tuning of Foundation Models","created":"2024-10-12","cited_by_count":18,"area":null},{"id":"2404.14122","title":"Fine-Tuning Large Language Models to Translate: Will a Touch of Noisy Data in Misaligned Languages Suffice?","created":"2024-04-22","cited_by_count":17,"area":null},{"id":"2407.02118","title":"Breaking Language Barriers: Cross-Lingual Continual Pre-Training at Scale","created":"2024-07-02","cited_by_count":15,"area":null},{"id":"2502.07184","title":"Refine Knowledge of Large Language Models via Adaptive Contrastive Learning","created":"2025-02-11","cited_by_count":15,"area":null},{"id":"2502.20273","title":"How Much is Enough? The Diminishing Returns of Tokenization Training Data","created":"2025-02-27","cited_by_count":15,"area":null},{"id":"2405.20441","title":"SECURE: Benchmarking Large Language Models for Cybersecurity","created":"2024-05-30","cited_by_count":14,"area":null},{"id":"2505.03793","title":"LENSLLM: Unveiling Fine-Tuning Dynamics for LLM Selection","created":"2025-05-01","cited_by_count":14,"area":null},{"id":"2408.12780","title":"Quality or Quantity? On Data Scale and Diversity in Adapting Large Language Models for Low-Resource Translation","created":"2024-08-23","cited_by_count":13,"area":null},{"id":"2409.03668","title":"A Fused Large Language Model for Predicting Startup Success","created":"2024-09-05","cited_by_count":13,"area":null},{"id":"2410.21331","title":"Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness","created":"2024-10-27","cited_by_count":13,"area":null},{"id":"2412.13582","title":"EvoWiki: Evaluating LLMs on Evolving Knowledge","created":"2024-12-18","cited_by_count":13,"area":null},{"id":"2410.16208","title":"Compute-Constrained Data Selection","created":"2024-10-21","cited_by_count":12,"area":null},{"id":"2411.02142","title":"Training Compute-Optimal Protein Language Models","created":"2024-11-04","cited_by_count":12,"area":null},{"id":"2506.13045","title":"Continual Learning for Generative AI: From LLMs to MLLMs and Beyond","created":"2025-06-16","cited_by_count":12,"area":null},{"id":"2507.05195","title":"Train-before-Test Harmonizes Language Model Rankings","created":"2025-07-07","cited_by_count":12,"area":null},{"id":"2508.11953","title":"Data Mixing Optimization for Supervised Fine-Tuning of Large Language Models","created":"2025-08-16","cited_by_count":12,"area":null},{"id":"2408.08343","title":"API-guided Dataset Synthesis to Finetune Large Code Models","created":"2024-08-15","cited_by_count":11,"area":null},{"id":"2410.01296","title":"Speculative Coreset Selection for Task-Specific Fine-tuning","created":"2024-10-02","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":"2510.19546","title":"Conditions for Catastrophic Forgetting in Multilingual Translation","created":"2025-10-22","cited_by_count":10,"area":null},{"id":"2408.16947","title":"An Empirical Study of Scaling Laws for Transfer","created":"2024-08-30","cited_by_count":9,"area":null},{"id":"2410.04717","title":"$\\textbf{Only-IF}$:Revealing the Decisive Effect of Instruction Diversity on Generalization","created":"2024-10-07","cited_by_count":8,"area":null},{"id":"2504.13938","title":"Never Start from Scratch: Expediting On-Device LLM Personalization via Explainable Model Selection","created":"2025-04-15","cited_by_count":8,"area":null},{"id":"2602.19961","title":"Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval","created":"2026-02-23","cited_by_count":8,"area":null},{"id":"2411.00412","title":"Adapting While Learning: Grounding LLMs for Scientific Problems with Intelligent Tool Usage Adaptation","created":"2024-11-01","cited_by_count":7,"area":null},{"id":"2504.12491","title":"Can Pre-training Indicators Reliably Predict Fine-tuning Outcomes of LLMs?","created":"2025-04-16","cited_by_count":7,"area":null},{"id":"2602.22617","title":"Semantic Tube Prediction: Beating LLM Data Efficiency with JEPA","created":"2026-02-26","cited_by_count":7,"area":null},{"id":"2406.11753","title":"A Semantic-Aware Layer-Freezing Approach to Computation-Efficient Fine-Tuning of Language Models","created":"2024-06-17","cited_by_count":6,"area":null},{"id":"2407.18990","title":"Stay Tuned: An Empirical Study of the Impact of Hyperparameters on LLM Tuning in Real-World Applications","created":"2024-07-25","cited_by_count":6,"area":null},{"id":"2509.25522","title":"Understanding Generative Recommendation with Semantic IDs from a Model-scaling View","created":"2025-09-29","cited_by_count":6,"area":null},{"id":"2510.10023","title":"Skill-Targeted Adaptive Training","created":"2025-10-11","cited_by_count":6,"area":null},{"id":"2411.14055","title":"DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization","created":"2024-11-21","cited_by_count":5,"area":null},{"id":"2502.09690","title":"Trust at Your Own Peril: A Mixed Methods Exploration of the Ability of Large Language Models to Generate Expert-Like Systems Engineering Artifacts and a Characterization of Failure Modes","created":"2025-02-13","cited_by_count":5,"area":null},{"id":"2502.12051","title":"How to Upscale Neural Networks with Scaling Law? A Survey and Practical Guidelines","created":"2025-02-17","cited_by_count":5,"area":null},{"id":"2504.12687","title":"Data-efficient LLM Fine-tuning for Code Generation","created":"2025-04-17","cited_by_count":5,"area":null},{"id":"2505.00985","title":"Position: Enough of Scaling LLMs! Lets Focus on Downscaling","created":"2025-05-02","cited_by_count":5,"area":null},{"id":"2403.09167","title":"Dial-insight: Fine-tuning Large Language Models with High-Quality Domain-Specific Data Preventing Capability Collapse","created":"2024-03-14","cited_by_count":4,"area":null},{"id":"2406.04165","title":"Repurposing Language Models into Embedding Models: Finding the Compute-Optimal Recipe","created":"2024-06-06","cited_by_count":4,"area":null},{"id":"2406.11187","title":"Save It All: Enabling Full Parameter Tuning for Federated Large Language Models via Cycle Block Gradient Descent","created":"2024-06-17","cited_by_count":4,"area":null},{"id":"2407.19299","title":"The Impact of LoRA Adapters on LLMs for Clinical Text Classification Under Computational and Data Constraints","created":"2024-07-27","cited_by_count":4,"area":null},{"id":"2411.09539","title":"Fine-tuning Large Language Models with Limited Data: A Survey and Practical Guide","created":"2024-11-14","cited_by_count":4,"area":null},{"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":"2505.12512","title":"Scalable Strategies for Continual Learning with Replay","created":"2025-05-18","cited_by_count":4,"area":null},{"id":"2506.10378","title":"Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning","created":"2025-06-12","cited_by_count":4,"area":null},{"id":"2507.03648","title":"Disentangling the Roles of Representation and Selection in Data Pruning","created":"2025-07-04","cited_by_count":4,"area":null},{"id":"2509.24196","title":"Chat to Chip: Large Language Model Based Design of Arbitrarily Shaped Metasurfaces","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2510.26622","title":"Encoder-Decoder or Decoder-Only? Revisiting Encoder-Decoder Large Language Model","created":"2025-10-30","cited_by_count":4,"area":null},{"id":"2511.00382","title":"Efficiency vs. Alignment: Investigating Safety and Fairness Risks in Parameter-Efficient Fine-Tuning of LLMs","created":"2025-11-01","cited_by_count":4,"area":null},{"id":"2605.25704","title":"PowLU: An Activation Function for Stable Pre-Training of LLMs","created":"2026-05-25","cited_by_count":4,"area":null},{"id":"2409.02370","title":"Do Large Language Models Possess Sensitive to Sentiment?","created":"2024-09-04","cited_by_count":3,"area":null},{"id":"2411.06506","title":"CULL-MT: Compression Using Language and Layer pruning for Machine Translation","created":"2024-11-10","cited_by_count":3,"area":null},{"id":"2407.19775","title":"Model Agnostic Hybrid Sharding For Heterogeneous Distributed Inference","created":"2024-07-29","cited_by_count":2,"area":null},{"id":"2408.02044","title":"Fine-tuning multilingual language models in Twitter/X sentiment analysis: a study on Eastern-European V4 languages","created":"2024-08-04","cited_by_count":2,"area":null},{"id":"2410.13215","title":"Balancing Label Quantity and Quality for Scalable Elicitation","created":"2024-10-17","cited_by_count":2,"area":null},{"id":"2509.22480","title":"Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2509.23963","title":"Evaluating the Robustness of Chinchilla Compute-Optimal Scaling","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2510.06548","title":"Reusing Overtrained Language Models Saturates Scaling","created":"2025-10-08","cited_by_count":2,"area":null},{"id":"2511.00056","title":"MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling","created":"2025-10-28","cited_by_count":2,"area":null},{"id":"2605.06901","title":"Reflections and New Directions for Human-Centered Large Language Models","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2410.12325","title":"$M^3$ Scaling Law: Optimizing Multi-Epoch, Multi-Lingual, and Multi-Stage Training for Low-Resource Language Models","created":"2024-10-16","cited_by_count":1,"area":null},{"id":"2410.15163","title":"Optimizing Large Language Models for Dynamic Constraints through Human-in-the-Loop Discriminators","created":"2024-10-19","cited_by_count":1,"area":null},{"id":"2509.04512","title":"Scaling behavior of large language models in emotional safety classification across sizes and tasks","created":"2025-09-02","cited_by_count":1,"area":null},{"id":"2510.05049","title":"KEEP: Integrating Medical Ontologies with Clinical Data for Robust Code Embeddings","created":"2025-10-06","cited_by_count":1,"area":null},{"id":"2510.19036","title":"From Memorization to Generalization: Fine-Tuning Large Language Models for Biomedical Term-to-Identifier Normalization","created":"2025-10-21","cited_by_count":1,"area":null},{"id":"2512.24991","title":"Efficiently Estimating Data Efficiency for Language Model Fine-tuning","created":"2025-12-31","cited_by_count":1,"area":null},{"id":"2602.14492","title":"Query as Anchor: Scenario-Adaptive User Representation via Large Language Model","created":"2026-02-16","cited_by_count":1,"area":null},{"id":"2603.19149","title":"Optimal Splitting of Language Models from Mixtures to Specialized Domains","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2604.17650","title":"Measuring Distribution Shift in User Prompts and Its Effects on LLM Performance","created":"2026-04-19","cited_by_count":1,"area":null},{"id":"2604.23267","title":"Fine-tuning vs. In-context Learning in Large Language Models: A Formal Language Learning Perspective","created":"2026-04-25","cited_by_count":1,"area":null},{"id":"2605.00610","title":"Decouple before Integration: Test-time Synthesis of SFT and RLVR Task Vectors","created":"2026-05-01","cited_by_count":1,"area":null},{"id":"2605.27564","title":"The Future of Facts: Tracing the Factual Generation-Verification Gap","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2605.27631","title":"Poison with Style: A Practical Poisoning Attack on Code Large Language Models","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2406.00004","title":"Navigating the Future of Federated Recommendation Systems with Foundation Models","created":"2024-05-12","cited_by_count":0,"area":null},{"id":"2501.03152","title":"The Scaling Law for LoRA Base on Mutual Information Upper Bound","created":"2025-01-06","cited_by_count":0,"area":null},{"id":"2501.10487","title":"Theme-Explanation Structure for Table Summarization using Large Language Models: A Case Study on Korean Tabular Data","created":"2025-01-17","cited_by_count":0,"area":null},{"id":"2502.12372","title":"Factual Inconsistency in Data-to-Text Generation Scales Exponentially with LLM Size: A Statistical Validation","created":"2025-02-17","cited_by_count":0,"area":null},{"id":"2503.05852","title":"Evaluating Large Language Models in Code Generation: INFINITE Methodology for Defining the Inference Index","created":"2025-03-07","cited_by_count":0,"area":null},{"id":"2505.15835","title":"Transforming Decoder-Only Transformers for Accurate WiFi-Telemetry Based Indoor Localization","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2505.22146","title":"Flexible Tool Selection through Low-dimensional Attribute Alignment of Vision and Language","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2506.07940","title":"Gradients: When Markets Meet Fine-tuning -- A Distributed Approach to Model Optimisation","created":"2025-06-09","cited_by_count":0,"area":null}],"next_cursor":"100"}