{"list":"other","total":52,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739},{"id":"2304.07327","title":"OpenAssistant Conversations -- Democratizing Large Language Model Alignment","created":"2023-04-14","cited_by_count":721},{"id":"2306.11644","title":"Textbooks Are All You Need","created":"2023-06-20","cited_by_count":569},{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532},{"id":"2308.08998","title":"Reinforced Self-Training (ReST) for Language Modeling","created":"2023-08-17","cited_by_count":500},{"id":"2402.00159","title":"Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research","created":"2024-01-31","cited_by_count":483},{"id":"2305.07759","title":"TinyStories: How Small Can Language Models Be and Still Speak Coherent English?","created":"2023-05-12","cited_by_count":449},{"id":"2312.06585","title":"Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models","created":"2023-12-11","cited_by_count":349},{"id":"2302.03169","title":"Data Selection for Language Models via Importance Resampling","created":"2023-02-06","cited_by_count":329},{"id":"2309.06657","title":"Statistical Rejection Sampling Improves Preference Optimization","created":"2023-09-13","cited_by_count":323},{"id":"2406.03877","title":"Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving","created":"2024-06-06","cited_by_count":252},{"id":"2307.01850","title":"Self-Consuming Generative Models Go MAD","created":"2023-07-04","cited_by_count":250},{"id":"2206.07137","title":"Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt","created":"2022-06-14","cited_by_count":236},{"id":"2402.16827","title":"A Survey on Data Selection for Language Models","created":"2024-02-26","cited_by_count":236},{"id":"2402.13446","title":"Large Language Models for Data Annotation and Synthesis: A Survey","created":"2024-02-21","cited_by_count":205},{"id":"2002.05715","title":"Self-Distillation Amplifies Regularization in Hilbert Space","created":"2020-02-13","cited_by_count":173},{"id":"2401.16380","title":"Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling","created":"2024-01-29","cited_by_count":161},{"id":"2404.01413","title":"Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data","created":"2024-04-01","cited_by_count":151},{"id":"2311.01043","title":"LLM4Drive: A Survey of Large Language Models for Autonomous Driving","created":"2023-11-02","cited_by_count":136},{"id":"2404.07965","title":"Rho-1: Not All Tokens Are What You Need","created":"2024-04-11","cited_by_count":133},{"id":"2402.07043","title":"A Tale of Tails: Model Collapse as a Change of Scaling Laws","created":"2024-02-10","cited_by_count":130},{"id":"2310.00429","title":"On the Stability of Iterative Retraining of Generative Models on their own Data","created":"2023-09-30","cited_by_count":100},{"id":"2402.17834","title":"Stable LM 2 1.6B Technical Report","created":"2024-02-27","cited_by_count":90},{"id":"2405.20541","title":"Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models","created":"2024-05-30","cited_by_count":84},{"id":"2402.07712","title":"Model Collapse Demystified: The Case of Regression","created":"2024-02-12","cited_by_count":82},{"id":"2311.16822","title":"Large Language Models Suffer From Their Own Output: An Analysis of the Self-Consuming Training Loop","created":"2023-11-28","cited_by_count":79},{"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},{"id":"2406.03949","title":"UltraMedical: Building Specialized Generalists in Biomedicine","created":"2024-06-06","cited_by_count":67},{"id":"2410.04840","title":"Strong Model Collapse","created":"2024-10-07","cited_by_count":65},{"id":"2406.14491","title":"Instruction Pre-Training: Language Models are Supervised Multitask Learners","created":"2024-06-20","cited_by_count":63},{"id":"2306.06130","title":"Towards Understanding the Interplay of Generative Artificial Intelligence and the Internet","created":"2023-06-08","cited_by_count":54},{"id":"2402.16720","title":"Think2Drive: Efficient Reinforcement Learning by Thinking in Latent World Model for Quasi-Realistic Autonomous Driving (in CARLA-v2)","created":"2024-02-26","cited_by_count":52},{"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},{"id":"2406.07515","title":"Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification","created":"2024-06-11","cited_by_count":45},{"id":"2407.09499","title":"Self-Consuming Generative Models with Curated Data Provably Optimize Human Preferences","created":"2024-06-12","cited_by_count":39},{"id":"2401.05033","title":"Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk","created":"2024-01-10","cited_by_count":34},{"id":"2401.10463","title":"Critical Data Size of Language Models from a Grokking Perspective","created":"2024-01-19","cited_by_count":24},{"id":"2310.08348","title":"LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios","created":"2023-10-12","cited_by_count":20},{"id":"2412.10713","title":"RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviors","created":"2024-12-14","cited_by_count":16},{"id":"2306.00656","title":"Normalization Enhances Generalization in Visual Reinforcement Learning","created":"2023-06-01","cited_by_count":13},{"id":"2411.19930","title":"On Domain-Adaptive Post-Training for Multimodal Large Language Models","created":"2024-11-29","cited_by_count":13},{"id":"2406.10667","title":"UniZero: Generalized and Efficient Planning with Scalable Latent World Models","created":"2024-06-15","cited_by_count":12},{"id":"2208.13423","title":"StoryTrans: Non-Parallel Story Author-Style Transfer with Discourse Representations and Content Enhancing","created":"2022-08-29","cited_by_count":8},{"id":"2405.18718","title":"Efficient Model-agnostic Alignment via Bayesian Persuasion","created":"2024-05-29","cited_by_count":8}],"next_cursor":null}