{"total":204,"rows":[{"id":"2405.09673","title":"LoRA Learns Less and Forgets Less","created":"2024-05-15","cited_by_count":328,"area":null},{"id":"2505.19789","title":"What Can RL Bring to VLA Generalization? An Empirical Study","created":"2025-05-26","cited_by_count":108,"area":"vla"},{"id":"2412.16075","title":"Formal Mathematical Reasoning: A New Frontier in AI","created":"2024-12-20","cited_by_count":81,"area":"lr"},{"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":"2405.16640","title":"A Survey of Multimodal Large Language Model from A Data-centric Perspective","created":"2024-05-26","cited_by_count":75,"area":"mllm"},{"id":"2505.14069","title":"Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning","created":"2025-05-20","cited_by_count":70,"area":"rag"},{"id":"2506.19676","title":"A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures","created":"2025-06-24","cited_by_count":57,"area":"agents"},{"id":"2507.09404","title":"Scaling Laws for Optimal Data Mixtures","created":"2025-07-12","cited_by_count":52,"area":null},{"id":"2506.18896","title":"ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs","created":"2025-06-23","cited_by_count":46,"area":"lr"},{"id":"2406.07515","title":"Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification","created":"2024-06-11","cited_by_count":45,"area":"synth"},{"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":"2502.17578","title":"How Do Large Language Monkeys Get Their Power (Laws)?","created":"2025-02-24","cited_by_count":43,"area":"safety"},{"id":"2409.12993","title":"CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair","created":"2024-09-19","cited_by_count":42,"area":"synth"},{"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":"2405.20099","title":"Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks","created":"2024-05-30","cited_by_count":37,"area":"safety"},{"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":"2601.04748","title":"When Single-Agent with Skills Replace Multi-Agent Systems and When They Fail","created":"2026-01-08","cited_by_count":35,"area":"agents"},{"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":"2411.15382","title":"On the Impact of Fine-Tuning on Chain-of-Thought Reasoning","created":"2024-11-22","cited_by_count":32,"area":"lr"},{"id":"2505.10475","title":"Parallel Scaling Law for Language Models","created":"2025-05-15","cited_by_count":30,"area":"lr"},{"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":"2412.00383","title":"Unified Parameter-Efficient Unlearning for LLMs","created":"2024-11-30","cited_by_count":25,"area":"lr"},{"id":"2508.12800","title":"Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Reward","created":"2025-08-18","cited_by_count":25,"area":"lr"},{"id":"2406.12034","title":"Self-MoE: Towards Compositional Large Language Models with Self-Specialized Experts","created":"2024-06-17","cited_by_count":23,"area":"moe"},{"id":"2412.01175","title":"OBI-Bench: Can LMMs Aid in Study of Ancient Script on Oracle Bones?","created":"2024-12-02","cited_by_count":22,"area":"mllm"},{"id":"2409.09603","title":"Towards Data-Centric RLHF: Simple Metrics for Preference Dataset Comparison","created":"2024-09-15","cited_by_count":21,"area":"alignment"},{"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":"2504.14891","title":"Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Survey","created":"2025-04-21","cited_by_count":20,"area":"rag"},{"id":"2505.14582","title":"Can Pruning Improve Reasoning? Revisiting Long-CoT Compression with Capability in Mind for Better Reasoning","created":"2025-05-20","cited_by_count":19,"area":"lr"},{"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":"2501.09798","title":"Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface","created":"2025-01-16","cited_by_count":17,"area":"safety"},{"id":"2508.09210","title":"MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Models","created":"2025-08-11","cited_by_count":17,"area":"mllm"},{"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":"2504.00509","title":"Recitation over Reasoning: How Cutting-Edge Language Models Can Fail on Elementary School-Level Reasoning Problems?","created":"2025-04-01","cited_by_count":15,"area":"lr"},{"id":"2506.00073","title":"The Automated but Risky Game: Modeling and Benchmarking Agent-to-Agent Negotiations and Transactions in Consumer Markets","created":"2025-05-29","cited_by_count":15,"area":"agents"},{"id":"2506.20963","title":"EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corpora","created":"2025-06-26","cited_by_count":15,"area":"rag"},{"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":"2505.10937","title":"Reasoning with OmniThought: A Large CoT Dataset with Verbosity and Cognitive Difficulty Annotations","created":"2025-05-16","cited_by_count":14,"area":"lr"},{"id":"2602.04118","title":"Learning to Reason in 13 Parameters","created":"2026-02-04","cited_by_count":14,"area":"lr"},{"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":"2502.03009","title":"Scaling Laws for Upcycling Mixture-of-Experts Language Models","created":"2025-02-05","cited_by_count":13,"area":"moe"},{"id":"2410.03717","title":"Revisiting the Superficial Alignment Hypothesis","created":"2024-09-27","cited_by_count":12,"area":"alignment"},{"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":"2501.11877","title":"From Drafts to Answers: Unlocking LLM Potential via Aggregation Fine-Tuning","created":"2025-01-21","cited_by_count":12,"area":"lr"},{"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":"2508.16861","title":"Learning from Diverse Reasoning Paths with Routing and Collaboration","created":"2025-08-23","cited_by_count":12,"area":"lr"},{"id":"2408.08343","title":"API-guided Dataset Synthesis to Finetune Large Code Models","created":"2024-08-15","cited_by_count":11,"area":null},{"id":"2508.04117","title":"Unveiling Over-Memorization in Finetuning LLMs for Reasoning Tasks","created":"2025-08-06","cited_by_count":11,"area":"lr"},{"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":"2408.00620","title":"Are Bigger Encoders Always Better in Vision Large Models?","created":"2024-08-01","cited_by_count":9,"area":"mllm"},{"id":"2408.16947","title":"An Empirical Study of Scaling Laws for Transfer","created":"2024-08-30","cited_by_count":9,"area":null},{"id":"2409.15361","title":"Multitask Mayhem: Unveiling and Mitigating Safety Gaps in LLMs Fine-tuning","created":"2024-09-18","cited_by_count":8,"area":"safety"},{"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":"2602.04896","title":"Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models","created":"2026-02-03","cited_by_count":8,"area":"alignment"},{"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":"2507.13158","title":"Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities","created":"2025-07-17","cited_by_count":7,"area":"alignment"},{"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":"2502.09955","title":"Diverse Inference and Verification for Advanced Reasoning","created":"2025-02-14","cited_by_count":6,"area":"lr"},{"id":"2505.17436","title":"Scaling Up Biomedical Vision-Language Models: Fine-Tuning, Instruction Tuning, and Multi-Modal Learning","created":"2025-05-23","cited_by_count":6,"area":"mllm"},{"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":"2505.22543","title":"Scaling-up Perceptual Video Quality Assessment","created":"2025-05-28","cited_by_count":5,"area":"mllm"},{"id":"2506.00027","title":"From Mathematical Reasoning to Code: Generalization of Process Reward Models in Test-Time Scaling","created":"2025-05-24","cited_by_count":5,"area":"lr"},{"id":"2602.15481","title":"LLM-as-Judge on a Budget","created":"2026-02-17","cited_by_count":5,"area":"lr"},{"id":"2607.16097","title":"Understanding Reasoning from Pretraining to Post-Training","created":"2026-07-17","cited_by_count":5,"area":"lr"},{"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}],"next_cursor":"100"}