{"total":130,"rows":[{"id":"2406.20094","title":"Scaling Synthetic Data Creation with 1,000,000,000 Personas","created":"2024-06-28","cited_by_count":417,"area":"synth"},{"id":"2508.05004","title":"R-Zero: Self-Evolving Reasoning LLM from Zero Data","created":"2025-08-07","cited_by_count":228,"area":"lr"},{"id":"2410.18982","title":"O1 Replication Journey: A Strategic Progress Report -- Part 1","created":"2024-10-08","cited_by_count":143,"area":"lr"},{"id":"2406.09358","title":"Understanding Hallucinations in Diffusion Models through Mode Interpolation","created":"2024-06-13","cited_by_count":91,"area":"diffusion"},{"id":"2402.07712","title":"Model Collapse Demystified: The Case of Regression","created":"2024-02-12","cited_by_count":82,"area":"synth"},{"id":"2404.05090","title":"How Bad is Training on Synthetic Data? A Statistical Analysis of Language Model Collapse","created":"2024-04-07","cited_by_count":79,"area":"synth"},{"id":"2410.04840","title":"Strong Model Collapse","created":"2024-10-07","cited_by_count":65,"area":"synth"},{"id":"2406.08466","title":"Scaling Laws in Linear Regression: Compute, Parameters, and Data","created":"2024-06-12","cited_by_count":57,"area":null},{"id":"2405.20309","title":"Large Language Models Can Self-Improve At Web Agent Tasks","created":"2024-05-30","cited_by_count":55,"area":"agents"},{"id":"2410.16713","title":"Collapse or Thrive? Perils and Promises of Synthetic Data in a Self-Generating World","created":"2024-10-22","cited_by_count":52,"area":null},{"id":"2501.18101","title":"Diverse Preference Optimization","created":"2025-01-30","cited_by_count":52,"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":"2502.17578","title":"How Do Large Language Monkeys Get Their Power (Laws)?","created":"2025-02-24","cited_by_count":43,"area":"safety"},{"id":"2405.20469","title":"Is Synthetic Data all We Need? Benchmarking the Robustness of Models Trained with Synthetic Images","created":"2024-05-30","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":"2407.09499","title":"Self-Consuming Generative Models with Curated Data Provably Optimize Human Preferences","created":"2024-06-12","cited_by_count":39,"area":"alignment"},{"id":"2408.16333","title":"Self-Improving Diffusion Models with Synthetic Data","created":"2024-08-29","cited_by_count":35,"area":"diffusion"},{"id":"2404.03502","title":"AI and the Problem of Knowledge Collapse","created":"2024-04-04","cited_by_count":34,"area":null},{"id":"2503.03150","title":"Position: Model Collapse Does Not Mean What You Think","created":"2025-03-05","cited_by_count":33,"area":"synth"},{"id":"2502.01612","title":"Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges","created":"2025-02-03","cited_by_count":31,"area":"synth"},{"id":"2410.22812","title":"Universality of the $\\pi^2/6$ Pathway in Avoiding Model Collapse","created":"2024-10-30","cited_by_count":26,"area":null},{"id":"2510.01631","title":"Demystifying Synthetic Data in LLM Pre-training: A Systematic Study of Scaling Laws, Benefits, and Pitfalls","created":"2025-10-02","cited_by_count":26,"area":"synth"},{"id":"2412.14689","title":"How to Synthesize Text Data without Model Collapse?","created":"2024-12-19","cited_by_count":25,"area":"synth"},{"id":"2412.17646","title":"Rate of Model Collapse in Recursive Training","created":"2024-12-23","cited_by_count":25,"area":"synth"},{"id":"2402.17896","title":"Researchy Questions: A Dataset of Multi-Perspective, Decompositional Questions for LLM Web Agents","created":"2024-02-27","cited_by_count":23,"area":"agents"},{"id":"2410.07074","title":"Let's Ask GNN: Empowering Large Language Model for Graph In-Context Learning","created":"2024-10-09","cited_by_count":21,"area":null},{"id":"2509.16499","title":"A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective","created":"2025-09-20","cited_by_count":18,"area":"diffusion"},{"id":"2407.04503","title":"When LLMs Play the Telephone Game: Cultural Attractors as Conceptual Tools to Evaluate LLMs in Multi-turn Settings","created":"2024-07-05","cited_by_count":17,"area":null},{"id":"2502.15588","title":"Improving the Scaling Laws of Synthetic Data with Deliberate Practice","created":"2025-02-21","cited_by_count":17,"area":null},{"id":"2502.18865","title":"A Theoretical Perspective: How to Prevent Model Collapse in Self-consuming Training Loops","created":"2025-02-26","cited_by_count":16,"area":"synth"},{"id":"2411.12925","title":"Loss-to-Loss Prediction: Scaling Laws for All Datasets","created":"2024-11-19","cited_by_count":15,"area":null},{"id":"2502.15654","title":"Machine-generated text detection prevents language model collapse","created":"2025-02-21","cited_by_count":14,"area":"synth"},{"id":"2411.00750","title":"Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling","created":"2024-11-01","cited_by_count":13,"area":"synth"},{"id":"2505.19046","title":"When Models Don't Collapse: On the Consistency of Iterative MLE","created":"2025-05-25","cited_by_count":13,"area":"synth"},{"id":"2407.17493","title":"Model Collapse in the Self-Consuming Chain of Diffusion Finetuning: A Novel Perspective from Quantitative Trait Modeling","created":"2024-07-04","cited_by_count":12,"area":"synth"},{"id":"2410.15234","title":"Bias Amplification: Large Language Models as Increasingly Biased Media","created":"2024-10-19","cited_by_count":12,"area":"synth"},{"id":"2502.20258","title":"LLM as a Broken Telephone: Iterative Generation Distorts Information","created":"2025-02-27","cited_by_count":12,"area":null},{"id":"2410.07041","title":"Emergent properties with repeated examples","created":"2024-10-09","cited_by_count":11,"area":null},{"id":"2502.08924","title":"Escaping Collapse: The Strength of Weak Data for Large Language Model Training","created":"2025-02-13","cited_by_count":11,"area":null},{"id":"2506.06112","title":"Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completeness","created":"2025-06-06","cited_by_count":11,"area":"safety"},{"id":"2506.08415","title":"Improved Scaling Laws in Linear Regression via Data Reuse","created":"2025-06-10","cited_by_count":11,"area":null},{"id":"2502.04235","title":"Reformulation for Pretraining Data Augmentation","created":"2025-02-06","cited_by_count":10,"area":null},{"id":"2502.18049","title":"Recursive Learning Without Collapse: A Weighting-Based Stabilization Framework","created":"2025-02-25","cited_by_count":10,"area":"synth"},{"id":"2602.13103","title":"R-Diverse: Mitigating Diversity Illusion in Self-Play LLM Training","created":"2026-02-13","cited_by_count":10,"area":"lr"},{"id":"2410.09005","title":"Analyzing Neural Scaling Laws in Two-Layer Networks with Power-Law Data Spectra","created":"2024-10-11","cited_by_count":9,"area":null},{"id":"2412.17061","title":"Multi-Agent Sampling: Scaling Inference Compute for Data Synthesis with Tree Search-Based Agentic Collaboration","created":"2024-12-22","cited_by_count":9,"area":"agents"},{"id":"2509.22341","title":"Preventing Model Collapse Under Overparametrization: Optimal Mixing Ratios for Interpolation Learning and Ridge Regression","created":"2025-09-26","cited_by_count":9,"area":"synth"},{"id":"2506.22802","title":"Riemannian-Geometric Fingerprints of Generative Models","created":"2025-06-28","cited_by_count":8,"area":null},{"id":"2511.03492","title":"Why Less is More (Sometimes): A Theory of Data Curation","created":"2025-11-05","cited_by_count":8,"area":null},{"id":"2408.14960","title":"Multilingual Arbitrage: Optimizing Data Pools to Accelerate Multilingual Progress","created":"2024-08-27","cited_by_count":7,"area":null},{"id":"2412.11979","title":"AlphaZero Neural Scaling and Zipf's Law: a Tale of Board Games and Power Laws","created":"2024-12-16","cited_by_count":7,"area":null},{"id":"2410.21526","title":"Not All LLM-Generated Data Are Equal: Rethinking Data Weighting in Text Classification","created":"2024-10-28","cited_by_count":6,"area":"lr"},{"id":"2510.10681","title":"RePro: Training Language Models to Faithfully Recycle the Web for Pretraining","created":"2025-10-12","cited_by_count":6,"area":null},{"id":"2510.16657","title":"Escaping Model Collapse via Synthetic Data Verification: Near-term Improvements and Long-term Convergence","created":"2025-10-18","cited_by_count":6,"area":"synth"},{"id":"2510.03597","title":"Neon: Negative Extrapolation From Self-Training Improves Image Generation","created":"2025-10-04","cited_by_count":5,"area":null},{"id":"2603.11784","title":"Language Generation with Replay: A Learning-Theoretic View of Model Collapse","created":"2026-03-12","cited_by_count":5,"area":"synth"},{"id":"2603.25681","title":"Self-Improvement of Large Language Models: A Technical Overview and Future Outlook","created":"2026-03-26","cited_by_count":5,"area":"synth"},{"id":"2409.03734","title":"Safety vs. Performance: How Multi-Objective Learning Reduces Barriers to Market Entry","created":"2024-09-05","cited_by_count":4,"area":null},{"id":"2412.14872","title":"Theoretical Proof that Auto-regressive Language Models Collapse when Real-world Data is a Finite Set","created":"2024-12-19","cited_by_count":4,"area":null},{"id":"2506.23174","title":"Data Can Speak for Itself: Quality-guided Utilization of Wireless Synthetic Data","created":"2025-06-29","cited_by_count":4,"area":null},{"id":"2510.18072","title":"Fine-tuning Flow Matching Generative Models with Intermediate Feedback","created":"2025-10-20","cited_by_count":4,"area":"diffusion"},{"id":"2602.16601","title":"Quantifying Error Propagation and Model Collapse in Diffusion Models","created":"2026-02-18","cited_by_count":4,"area":"diffusion"},{"id":"2411.00680","title":"Zipfian Whitening","created":"2024-11-01","cited_by_count":3,"area":null},{"id":"2501.00747","title":"DIVE: Diversified Iterative Self-Improvement","created":"2025-01-01","cited_by_count":3,"area":"synth"},{"id":"2502.11466","title":"GiFT: Gibbs Fine-Tuning for Code Generation","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2510.04268","title":"LongTail-Swap: benchmarking language models' abilities on rare words","created":"2025-10-05","cited_by_count":3,"area":null},{"id":"2405.13972","title":"Infinite-Dimensional Feature Interaction","created":"2024-05-22","cited_by_count":2,"area":null},{"id":"2406.14473","title":"Data-Centric AI in the Age of Large Language Models","created":"2024-06-20","cited_by_count":2,"area":null},{"id":"2407.09549","title":"Recursive InPainting (RIP): how much information is lost under recursive inferences?","created":"2024-06-27","cited_by_count":2,"area":null},{"id":"2410.12341","title":"Learning by Surprise: Adaptive Mitigation of Model Collapse in Large Language Models","created":"2024-10-16","cited_by_count":2,"area":"synth"},{"id":"2412.15652","title":"Error-driven Data-efficient Large Multimodal Model Tuning","created":"2024-12-20","cited_by_count":2,"area":"mllm"},{"id":"2501.17980","title":"Limits to AI Growth: The Ecological and Social Consequences of Scaling","created":"2025-01-29","cited_by_count":2,"area":null},{"id":"2501.18962","title":"Spend Wisely: Maximizing Post-Training Gains in Iterative Synthetic Data Bootstrapping","created":"2025-01-31","cited_by_count":2,"area":"synth"},{"id":"2503.08117","title":"Convergence Dynamics and Stabilization Strategies of Co-Evolving Generative Models","created":"2025-03-11","cited_by_count":2,"area":"synth"},{"id":"2504.03814","title":"Recursive Training Loops in LLMs: How training data properties modulate distribution shift in generated data?","created":"2025-04-04","cited_by_count":2,"area":null},{"id":"2505.12822","title":"Emergent Specialization: Rare Token Neurons in Language Models","created":"2025-05-19","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":"2510.00034","title":"Review of Hallucination Understanding in Large Language and Vision Models","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2512.12381","title":"Entropy Collapse: A Universal Failure Mode of Intelligent Systems","created":"2025-12-13","cited_by_count":2,"area":null},{"id":"2512.15011","title":"Epistemic diversity across language models mitigates knowledge collapse","created":"2025-12-17","cited_by_count":2,"area":null},{"id":"2601.05184","title":"Observations and Remedies for Large Language Model Bias in Self-Consuming Performative Loop","created":"2026-01-08","cited_by_count":2,"area":null},{"id":"2601.15417","title":"Ambient Dataloops: Generative Models for Dataset Refinement","created":"2026-01-21","cited_by_count":2,"area":"diffusion"},{"id":"2605.17849","title":"Generating Pretraining Tokens from Organic Data for Data-Bound Scaling","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2606.28438","title":"When AI Reviews Its Own Code: Recursive Self-Training Collapse in Code LLMs","created":"2026-06-26","cited_by_count":2,"area":"synth"},{"id":"2410.21088","title":"Shallow Diffuse: Robust and Invisible Watermarking through Low-Dimensional Subspaces in Diffusion Models","created":"2024-10-28","cited_by_count":1,"area":"diffusion"},{"id":"2506.09401","title":"A theoretical basis for model collapse in recursive training","created":"2025-06-11","cited_by_count":1,"area":null},{"id":"2506.19262","title":"What Matters in LLM-generated Data: Diversity and Its Effect on Model Fine-Tuning","created":"2025-06-24","cited_by_count":1,"area":"synth"},{"id":"2509.04796","title":"Knowledge Collapse in LLMs: When Fluency Survives but Facts Fail under Recursive Synthetic Training","created":"2025-09-05","cited_by_count":1,"area":"synth"},{"id":"2509.08972","title":"ForTIFAI: Fending Off Recursive Training Induced Failure for AI Model Collapse","created":"2025-09-10","cited_by_count":1,"area":"synth"},{"id":"2509.12679","title":"Large Language Model Scaling Laws for Neural Quantum States in Quantum Chemistry","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2509.21163","title":"Distributed Specialization: Rare-Token Neurons in Large Language Models","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2511.01490","title":"Synthetic Eggs in Many Baskets: The Impact of Synthetic Data Diversity on LLM Fine-Tuning","created":"2025-11-03","cited_by_count":1,"area":"synth"},{"id":"2511.13640","title":"Data Value in the Age of Scaling: Understanding LLM Scaling Dynamics Under Real-Synthetic Data Mixtures","created":"2025-11-17","cited_by_count":1,"area":"synth"},{"id":"2601.05280","title":"Large Language Models are Shannon Lossy Compressors Not Solomonoff Induction Estimators: Self-improvement and Singularity Are Not Near Without Symbolic Model Synthesis","created":"2026-01-05","cited_by_count":1,"area":null},{"id":"2602.10531","title":"From Collapse to Improvement: Statistical Perspectives on the Evolutionary Dynamics of Iterative Training on Contaminated Sources","created":"2026-02-11","cited_by_count":1,"area":"synth"},{"id":"2605.04127","title":"Position: the Stochastic Parrot in the Coal Mine. Model Collapse is a Threat to Low-Resource Communities","created":"2026-05-05","cited_by_count":1,"area":"synth"},{"id":"2605.23054","title":"Model Collapse as Cultural Evolution","created":"2026-05-21","cited_by_count":1,"area":"synth"},{"id":"2605.30642","title":"Diffusion Models Preferentially Memorize Prototypical Examples or: Why Does My Diffusion Model Love Slop?","created":"2026-05-28","cited_by_count":1,"area":"diffusion"},{"id":"2607.15623","title":"Retraining Seeks Stable Signals","created":"2026-07-17","cited_by_count":1,"area":null},{"id":"2607.17043","title":"Learning from Synthetic Data without Model Collapse in Iterative Instruction Tuning","created":"2026-07-19","cited_by_count":1,"area":"synth"}],"next_cursor":"100"}