{"list":"other","total":69,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"2002.10957","title":"MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers","created":"2020-02-25","cited_by_count":1463},{"id":"2503.09516","title":"Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning","created":"2025-03-12","cited_by_count":1444},{"id":"2310.08560","title":"MemGPT: Towards LLMs as Operating Systems","created":"2023-10-12","cited_by_count":1389},{"id":"2503.20783","title":"Understanding R1-Zero-Like Training: A Critical Perspective","created":"2025-03-26","cited_by_count":1345},{"id":"2404.07972","title":"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments","created":"2024-04-11","cited_by_count":1195},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836},{"id":"1704.00051","title":"Reading Wikipedia to Answer Open-Domain Questions","created":"2017-03-31","cited_by_count":777},{"id":"2209.06899","title":"Out of One, Many: Using Language Models to Simulate Human Samples","created":"2022-09-14","cited_by_count":752},{"id":"2305.14387","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","created":"2023-05-22","cited_by_count":748},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"1712.01815","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","created":"2017-12-05","cited_by_count":734},{"id":"2501.17161","title":"SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training","created":"2025-01-28","cited_by_count":672},{"id":"2302.00111","title":"Learning Universal Policies via Text-Guided Video Generation","created":"2023-01-31","cited_by_count":522},{"id":"2310.06114","title":"Learning Interactive Real-World Simulators","created":"2023-10-09","cited_by_count":458},{"id":"2009.13303","title":"Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey","created":"2020-09-24","cited_by_count":413},{"id":"2503.01307","title":"Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs","created":"2025-03-03","cited_by_count":377},{"id":"2206.11795","title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","created":"2022-06-23","cited_by_count":345},{"id":"2409.12183","title":"To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning","created":"2024-09-18","cited_by_count":263},{"id":"2305.03514","title":"Can Large Language Models Transform Computational Social Science?","created":"2023-04-12","cited_by_count":250},{"id":"2411.10109","title":"LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals","created":"2024-11-15","cited_by_count":249},{"id":"2310.17884","title":"Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory","created":"2023-10-27","cited_by_count":230},{"id":"2212.08061","title":"On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning","created":"2022-12-15","cited_by_count":194},{"id":"2306.15448","title":"Understanding Social Reasoning in Language Models with Language Models","created":"2023-06-21","cited_by_count":172},{"id":"2409.00138","title":"PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action","created":"2024-08-29","cited_by_count":171},{"id":"2504.07952","title":"Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory","created":"2025-04-10","cited_by_count":163},{"id":"2508.09123","title":"OpenCUA: Open Foundations for Computer-Use Agents","created":"2025-08-12","cited_by_count":160},{"id":"2311.03285","title":"S-LoRA: Serving Thousands of Concurrent LoRA Adapters","created":"2023-11-06","cited_by_count":152},{"id":"2405.00200","title":"In-Context Learning with Long-Context Models: An In-Depth Exploration","created":"2024-04-30","cited_by_count":128},{"id":"2502.00640","title":"CollabLLM: From Passive Responders to Active Collaborators","created":"2025-02-02","cited_by_count":124},{"id":"2411.04998","title":"HourVideo: 1-Hour Video-Language Understanding","created":"2024-11-07","cited_by_count":113},{"id":"2310.18547","title":"Punica: Multi-Tenant LoRA Serving","created":"2023-10-28","cited_by_count":83},{"id":"2506.00613","title":"WorldGym: World Model as An Environment for Policy Evaluation","created":"2025-05-31","cited_by_count":64},{"id":"2410.17127","title":"PAPILLON: Privacy Preservation from Internet-based and Local Language Model Ensembles","created":"2024-10-22","cited_by_count":57},{"id":"2210.05675","title":"Transformers generalize differently from information stored in context vs in weights","created":"2022-10-11","cited_by_count":49},{"id":"2511.02208","title":"Training Proactive and Personalized LLM Agents","created":"2025-11-04","cited_by_count":46},{"id":"2505.10831","title":"Creating General User Models from Computer Use","created":"2025-05-16","cited_by_count":44},{"id":"2504.13171","title":"Sleep-time Compute: Beyond Inference Scaling at Test-time","created":"2025-04-17","cited_by_count":43},{"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},{"id":"2509.13237","title":"Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors","created":"2025-09-16","cited_by_count":30},{"id":"2510.01367","title":"Is It Thinking or Cheating? Detecting Implicit Reward Hacking by Measuring Reasoning Effort","created":"2025-10-01","cited_by_count":27},{"id":"2510.19488","title":"VideoAgentTrek: Computer Use Pretraining from Unlabeled Videos","created":"2025-10-22","cited_by_count":22},{"id":"2510.02263","title":"RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems","created":"2025-10-02","cited_by_count":21},{"id":"2505.00234","title":"Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks","created":"2025-05-01","cited_by_count":19},{"id":"2510.22780","title":"How Do AI Agents Do Human Work? Comparing AI and Human Workflows Across Diverse Occupations","created":"2025-10-26","cited_by_count":19},{"id":"2410.23214","title":"Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval","created":"2024-10-30","cited_by_count":17},{"id":"2411.01813","title":"So You Think You Can Scale Up Autonomous Robot Data Collection?","created":"2024-11-04","cited_by_count":17},{"id":"2509.16189","title":"Latent learning: episodic memory complements parametric learning by enabling flexible reuse of experiences","created":"2025-09-19","cited_by_count":15},{"id":"2601.20789","title":"SERA: Soft-Verified Efficient Repository Agents","created":"2026-01-28","cited_by_count":10},{"id":"2505.11614","title":"Using Reinforcement Learning to Train Large Language Models to Explain Human Decisions","created":"2025-05-16","cited_by_count":9},{"id":"2601.04436","title":"Learning to Simulate Human Dialogue","created":"2026-01-07","cited_by_count":9}],"next_cursor":null}