{"list":"other","total":72,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"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":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210},{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963},{"id":"2211.14275","title":"Solving math word problems with process- and outcome-based feedback","created":"2022-11-25","cited_by_count":901},{"id":"2308.09687","title":"Graph of Thoughts: Solving Elaborate Problems with Large Language Models","created":"2023-08-18","cited_by_count":886},{"id":"2306.14048","title":"H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models","created":"2023-06-24","cited_by_count":832},{"id":"2412.06769","title":"Training Large Language Models to Reason in a Continuous Latent Space","created":"2024-12-09","cited_by_count":797},{"id":"2406.18665","title":"RouteLLM: Learning to Route LLMs with Preference Data","created":"2024-06-26","cited_by_count":682},{"id":"2503.06749","title":"Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models","created":"2025-03-09","cited_by_count":665},{"id":"2402.02750","title":"KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache","created":"2024-02-05","cited_by_count":637},{"id":"2502.03387","title":"LIMO: Less is More for Reasoning","created":"2025-02-05","cited_by_count":498},{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384},{"id":"2502.17419","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","created":"2025-02-24","cited_by_count":320},{"id":"2502.18600","title":"Chain of Draft: Thinking Faster by Writing Less","created":"2025-02-25","cited_by_count":297},{"id":"2501.09686","title":"Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models","created":"2025-01-16","cited_by_count":293},{"id":"2311.12320","title":"A Survey on Multimodal Large Language Models for Autonomous Driving","created":"2023-11-21","cited_by_count":290},{"id":"2103.04918","title":"A Survey of Embodied AI: From Simulators to Research Tasks","created":"2021-03-08","cited_by_count":261},{"id":"2502.04463","title":"Training Language Models to Reason Efficiently","created":"2025-02-06","cited_by_count":247},{"id":"2405.14838","title":"From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step","created":"2024-05-23","cited_by_count":235},{"id":"2502.21074","title":"CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation","created":"2025-02-28","cited_by_count":225},{"id":"2404.15758","title":"Let's Think Dot by Dot: Hidden Computation in Transformer Language Models","created":"2024-04-24","cited_by_count":191},{"id":"2502.07266","title":"When More is Less: Understanding Chain-of-Thought Length in LLMs","created":"2025-02-11","cited_by_count":183},{"id":"2503.10460","title":"Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond","created":"2025-03-13","cited_by_count":175},{"id":"2310.05694","title":"A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics","created":"2023-10-09","cited_by_count":163},{"id":"2407.06023","title":"Distilling System 2 into System 1","created":"2024-07-08","cited_by_count":159},{"id":"2401.04925","title":"The Impact of Reasoning Step Length on Large Language Models","created":"2024-01-10","cited_by_count":153},{"id":"2503.07572","title":"Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning","created":"2025-03-10","cited_by_count":123},{"id":"2503.05179","title":"Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching","created":"2025-03-07","cited_by_count":117},{"id":"2502.12134","title":"SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs","created":"2025-02-17","cited_by_count":116},{"id":"2502.12143","title":"Small Models Struggle to Learn from Strong Reasoners","created":"2025-02-17","cited_by_count":113},{"id":"2410.20290","title":"Fast Best-of-N Decoding via Speculative Rejection","created":"2024-10-26","cited_by_count":112},{"id":"2410.21333","title":"Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse","created":"2024-10-27","cited_by_count":109},{"id":"2005.09814","title":"Mirror Descent Policy Optimization","created":"2020-05-20","cited_by_count":106},{"id":"2408.09559","title":"HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model","created":"2024-08-18","cited_by_count":106},{"id":"2502.12893","title":"H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking","created":"2025-02-18","cited_by_count":99},{"id":"2407.18003","title":"Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumption","created":"2024-07-25","cited_by_count":97},{"id":"2502.02542","title":"OverThink: Slowdown Attacks on Reasoning LLMs","created":"2025-02-04","cited_by_count":96},{"id":"2412.15208","title":"OpenEMMA: Open-Source Multimodal Model for End-to-End Autonomous Driving","created":"2024-12-19","cited_by_count":93},{"id":"2410.13284","title":"Learning to Route LLMs with Confidence Tokens","created":"2024-10-17","cited_by_count":67},{"id":"2401.05618","title":"The Benefits of a Concise Chain of Thought on Problem-Solving in Large Language Models","created":"2024-01-11","cited_by_count":63},{"id":"2411.01855","title":"Can Language Models Learn to Skip Steps?","created":"2024-11-04","cited_by_count":59},{"id":"2410.05695","title":"Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thought","created":"2024-10-08","cited_by_count":56},{"id":"2502.13260","title":"Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models","created":"2025-02-18","cited_by_count":51},{"id":"2310.08582","title":"Tree-Planner: Efficient Close-loop Task Planning with Large Language Models","created":"2023-10-12","cited_by_count":48},{"id":"2407.01527","title":"KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches","created":"2024-07-01","cited_by_count":42},{"id":"2412.15206","title":"AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Driving","created":"2024-12-19","cited_by_count":35},{"id":"2503.14607","title":"Can Large Vision Language Models Read Maps Like a Human?","created":"2025-03-18","cited_by_count":30},{"id":"2502.04428","title":"Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization","created":"2025-02-06","cited_by_count":29},{"id":"2502.11569","title":"Towards Reasoning Ability of Small Language Models","created":"2025-02-17","cited_by_count":29},{"id":"2403.17359","title":"Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models","created":"2024-03-26","cited_by_count":27},{"id":"2502.13943","title":"AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence","created":"2025-02-19","cited_by_count":24},{"id":"2502.10835","title":"Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models","created":"2025-02-15","cited_by_count":23},{"id":"2404.09170","title":"Distilling Reasoning Ability from Large Language Models with Adaptive Thinking","created":"2024-04-14","cited_by_count":13},{"id":"2503.06252","title":"Can Atomic Step Decomposition Enhance the Self-structured Reasoning of Multimodal Large Models?","created":"2025-03-08","cited_by_count":10},{"id":"2503.01923","title":"Output Length Effect on DeepSeek-R1's Safety in Forced Thinking","created":"2025-03-02","cited_by_count":6}],"next_cursor":null}