{"total":58,"rows":[{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2402.04833","title":"Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning","created":"2024-02-07","cited_by_count":85,"area":"alignment"},{"id":"2312.16862","title":"TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones","created":"2023-12-28","cited_by_count":77,"area":"mllm"},{"id":"2403.15042","title":"LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement","created":"2024-03-22","cited_by_count":70,"area":null},{"id":"2402.12501","title":"Your Vision-Language Model Itself Is a Strong Filter: Towards High-Quality Instruction Tuning with Data Selection","created":"2024-02-19","cited_by_count":48,"area":"mllm"},{"id":"2405.08603","title":"A Comprehensive Survey of Large Language Models and Multimodal Large Language Models in Medicine","created":"2024-05-14","cited_by_count":45,"area":"mllm"},{"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":"2412.02980","title":"Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models","created":"2024-12-04","cited_by_count":35,"area":"synth"},{"id":"2312.11508","title":"Rethinking the Instruction Quality: LIFT is What You Need","created":"2023-12-12","cited_by_count":34,"area":"lr"},{"id":"2307.12966","title":"Aligning Large Language Models with Human: A Survey","created":"2023-07-24","cited_by_count":32,"area":"alignment"},{"id":"2410.10877","title":"Improving Data Efficiency via Curating LLM-Driven Rating Systems","created":"2024-10-09","cited_by_count":29,"area":null},{"id":"2503.11441","title":"D3: Diversity, Difficulty, and Dependability-Aware Data Selection for Sample-Efficient LLM Instruction Tuning","created":"2025-03-14","cited_by_count":21,"area":null},{"id":"2405.00705","title":"SHED: Shapley-Based Automated Dataset Refinement for Instruction Fine-Tuning","created":"2024-04-23","cited_by_count":19,"area":null},{"id":"2501.09213","title":"FineMedLM-o1: Enhancing Medical Knowledge Reasoning Ability of LLM from Supervised Fine-Tuning to Test-Time Training","created":"2025-01-16","cited_by_count":19,"area":"lr"},{"id":"2501.09024","title":"Social-LLaVA: Enhancing Robot Navigation through Human-Language Reasoning in Social Spaces","created":"2024-12-30","cited_by_count":17,"area":"lr"},{"id":"2504.06438","title":"Don't Let It Hallucinate: Premise Verification via Retrieval-Augmented Logical Reasoning","created":"2025-04-08","cited_by_count":15,"area":"lr"},{"id":"2505.19051","title":"Efficient Data Selection at Scale via Influence Distillation","created":"2025-05-25","cited_by_count":15,"area":null},{"id":"2501.18578","title":"R.I.P.: Better Models by Survival of the Fittest Prompts","created":"2025-01-30","cited_by_count":13,"area":null},{"id":"2502.04380","title":"Diversity as a Reward: Fine-Tuning LLMs on a Mixture of Domain-Undetermined Data","created":"2025-02-05","cited_by_count":13,"area":null},{"id":"2506.01317","title":"T-SHIRT: Token-Selective Hierarchical Data Selection for Instruction Tuning","created":"2025-06-02","cited_by_count":13,"area":null},{"id":"2406.07657","title":"OPTune: Efficient Online Preference Tuning","created":"2024-06-11","cited_by_count":10,"area":"alignment"},{"id":"2503.07557","title":"AutoSpatial: Visual-Language Reasoning for Social Robot Navigation through Efficient Spatial Reasoning Learning","created":"2025-03-10","cited_by_count":10,"area":"lr"},{"id":"2406.18082","title":"Octo-planner: On-device Language Model for Planner-Action Agents","created":"2024-06-26","cited_by_count":8,"area":"agents"},{"id":"2410.05090","title":"HyperINF: Unleashing the HyperPower of the Schulz's Method for Data Influence Estimation","created":"2024-10-07","cited_by_count":7,"area":null},{"id":"2505.16066","title":"Merge to Mix: Mixing Datasets via Model Merging","created":"2025-05-21","cited_by_count":7,"area":null},{"id":"2505.17266","title":"Select2Reason: Efficient Instruction-Tuning Data Selection for Long-CoT Reasoning","created":"2025-05-22","cited_by_count":7,"area":"lr"},{"id":"2508.21589","title":"Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning","created":"2025-08-29","cited_by_count":7,"area":null},{"id":"2601.23155","title":"SPICE: Submodular Penalized Information-Conflict Selection for Efficient Large Language Model Training","created":"2026-01-30","cited_by_count":7,"area":null},{"id":"2410.14940","title":"Baichuan Alignment Technical Report","created":"2024-10-19","cited_by_count":6,"area":"alignment"},{"id":"2512.00884","title":"Towards Active Synthetic Data Generation for Finetuning Language Models","created":"2025-11-30","cited_by_count":6,"area":"synth"},{"id":"2502.08512","title":"Measuring Diversity in Synthetic Datasets","created":"2025-02-12","cited_by_count":5,"area":"synth"},{"id":"2502.12594","title":"PASER: Post-Training Data Selection for Efficient Pruned Large Language Model Recovery","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2505.18458","title":"A Survey of LLM $\\times$ DATA","created":"2025-05-24","cited_by_count":4,"area":"rag"},{"id":"2411.03768","title":"A Bayesian Approach to Data Point Selection","created":"2024-11-06","cited_by_count":3,"area":null},{"id":"2510.07118","title":"TRIM: Token-wise Attention-Derived Saliency for Data-Efficient Instruction Tuning","created":"2025-10-08","cited_by_count":3,"area":"alignment"},{"id":"2510.13022","title":"On the Role of Preference Variance in Preference Optimization","created":"2025-10-14","cited_by_count":3,"area":"alignment"},{"id":"2412.09990","title":"Small Language Model as Data Prospector for Large Language Model","created":"2024-12-13","cited_by_count":2,"area":null},{"id":"2412.16686","title":"NILE: Internal Consistency Alignment in Large Language Models","created":"2024-12-21","cited_by_count":2,"area":null},{"id":"2506.04272","title":"Understanding the Impact of Sampling Quality in Direct Preference Optimization","created":"2025-06-03","cited_by_count":2,"area":"alignment"},{"id":"2606.08574","title":"OrderDP: A Theoretically Guaranteed Lossless Dynamic Data Pruning Framework","created":"2026-06-07","cited_by_count":2,"area":null},{"id":"2310.16713","title":"SkyMath: Technical Report","created":"2023-10-25","cited_by_count":1,"area":"lr"},{"id":"2405.19787","title":"From Symbolic Tasks to Code Generation: Diversification Yields Better Task Performers","created":"2024-05-30","cited_by_count":1,"area":null},{"id":"2412.17365","title":"Boosting LLM via Learning from Data Iteratively and Selectively","created":"2024-12-23","cited_by_count":1,"area":null},{"id":"2510.14459","title":"Holdout-Loss-Based Data Selection for LLM Finetuning via In-Context Learning","created":"2025-10-16","cited_by_count":1,"area":"alignment"},{"id":"2511.07198","title":"Synergy over Discrepancy: A Partition-Based Approach to Multi-Domain LLM Fine-Tuning","created":"2025-11-10","cited_by_count":1,"area":null},{"id":"2607.04135","title":"Broken Ergodicity and the Violation of the Fluctuation-Dissipation Theorem Lead to Generalization Beyond Overfitting in Machine Learning","created":"2026-07-05","cited_by_count":1,"area":null},{"id":"2403.00013","title":"Prioritizing Informative Features and Examples for Deep Learning from Noisy Data","created":"2024-02-27","cited_by_count":0,"area":null},{"id":"2411.14121","title":"Learning from \"Silly\" Questions Improves Large Language Models, But Only Slightly","created":"2024-11-21","cited_by_count":0,"area":null},{"id":"2506.09329","title":"Towards Efficient and Effective Alignment of Large Language Models","created":"2025-06-11","cited_by_count":0,"area":"alignment"},{"id":"2506.21573","title":"Instruction Learning Paradigms: A Dual Perspective on White-box and Black-box LLMs","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2509.18585","title":"TsqLoRA: Towards Sensitivity and Quality Low-Rank Adaptation for Efficient Fine-Tuning","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2601.21759","title":"Influence Guided Sampling for Domain Adaptation of Text Retrievers","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.01227","title":"Supervised Fine-Tuning Needs to Unlock the Potential of Token Priority","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2604.26170","title":"EvoSelect: Data-Efficient LLM Evolution for Targeted Task Adaptation","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.09665","title":"Learning Multi-Indicator Weights for Data Selection: A Joint Task-Model Adaptation Framework with Efficient Proxies","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.13130","title":"GRACE: Gradient-aligned Reasoning Data Curation for Efficient Post-training","created":"2026-05-13","cited_by_count":0,"area":"alignment"},{"id":"2605.15012","title":"Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2606.10706","title":"Unifying Data, Memory, and Compute Efficiency in LLM training: A Survey","created":"2026-06-09","cited_by_count":0,"area":null}],"next_cursor":null}