{"list":"other","total":66,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2308.08155","title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","created":"2023-08-16","cited_by_count":1988},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","created":"2022-07-04","cited_by_count":1251},{"id":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"id":"2312.07104","title":"SGLang: Efficient Execution of Structured Language Model Programs","created":"2023-12-12","cited_by_count":1141},{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100},{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061},{"id":"2307.07924","title":"ChatDev: Communicative Agents for Software Development","created":"2023-07-16","cited_by_count":919},{"id":"1907.10529","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","created":"2019-07-24","cited_by_count":834},{"id":"1606.07947","title":"Sequence-Level Knowledge Distillation","created":"2016-06-25","cited_by_count":801},{"id":"2401.02385","title":"TinyLlama: An Open-Source Small Language Model","created":"2024-01-04","cited_by_count":618},{"id":"1805.01954","title":"Behavioral Cloning from Observation","created":"2018-05-04","cited_by_count":492},{"id":"1710.02410","title":"End-to-end Driving via Conditional Imitation Learning","created":"2017-10-06","cited_by_count":485},{"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":"2305.17144","title":"Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory","created":"2023-05-25","cited_by_count":289},{"id":"1703.01541","title":"Soft-DTW: a Differentiable Loss Function for Time-Series","created":"2017-03-05","cited_by_count":271},{"id":"2305.18323","title":"ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models","created":"2023-05-23","cited_by_count":184},{"id":"2401.04925","title":"The Impact of Reasoning Step Length on Large Language Models","created":"2024-01-10","cited_by_count":153},{"id":"2403.07714","title":"StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models","created":"2024-03-12","cited_by_count":132},{"id":"1808.01097","title":"CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images","created":"2018-08-03","cited_by_count":126},{"id":"1908.08962","title":"Well-Read Students Learn Better: On the Importance of Pre-training Compact Models","created":"2019-08-23","cited_by_count":120},{"id":"2305.01879","title":"SCOTT: Self-Consistent Chain-of-Thought Distillation","created":"2023-05-03","cited_by_count":105},{"id":"2008.02496","title":"ConvBERT: Improving BERT with Span-based Dynamic Convolution","created":"2020-08-06","cited_by_count":88},{"id":"2010.14876","title":"Fighting Copycat Agents in Behavioral Cloning from Observation Histories","created":"2020-10-28","cited_by_count":71},{"id":"2303.15083","title":"UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye View","created":"2023-03-27","cited_by_count":43},{"id":"2503.20083","title":"Universal Cross-Tokenizer Distillation via Approximate Likelihood Matching","created":"2025-03-25","cited_by_count":41},{"id":"2412.12444","title":"LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers","created":"2024-12-17","cited_by_count":37},{"id":"2412.14528","title":"Multi-Level Optimal Transport for Universal Cross-Tokenizer Knowledge Distillation on Language Models","created":"2024-12-19","cited_by_count":36},{"id":"2108.08910","title":"Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search","created":"2021-08-18","cited_by_count":34},{"id":"2208.02225","title":"Sequence Model Imitation Learning with Unobserved Contexts","created":"2022-08-03","cited_by_count":34},{"id":"2206.01198","title":"Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization","created":"2022-06-02","cited_by_count":32},{"id":"2310.12972","title":"CCIL: Continuity-based Data Augmentation for Corrective Imitation Learning","created":"2023-10-19","cited_by_count":29},{"id":"2409.18962","title":"Exploring Token Pruning in Vision State Space Models","created":"2024-09-27","cited_by_count":28},{"id":"2004.12817","title":"LightPAFF: A Two-Stage Distillation Framework for Pre-training and Fine-tuning","created":"2020-04-27","cited_by_count":25},{"id":"2412.12441","title":"Numerical Pruning for Efficient Autoregressive Models","created":"2024-12-17","cited_by_count":25},{"id":"2301.11596","title":"ThoughtSource: A central hub for large language model reasoning data","created":"2023-01-27","cited_by_count":23},{"id":"2505.14708","title":"DraftAttention: Fast Video Diffusion via Low-Resolution Attention Guidance","created":"2025-05-17","cited_by_count":22},{"id":"2207.12577","title":"Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution","created":"2022-07-25","cited_by_count":20},{"id":"2410.15567","title":"Pruning Foundation Models for High Accuracy without Retraining","created":"2024-10-21","cited_by_count":20},{"id":"2502.03304","title":"Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning","created":"2025-02-05","cited_by_count":18},{"id":"2402.10787","title":"Squat: Quant Small Language Models on the Edge","created":"2024-02-16","cited_by_count":16},{"id":"2411.01171","title":"Fast and Memory-Efficient Video Diffusion Using Streamlined Inference","created":"2024-11-02","cited_by_count":14},{"id":"2306.05426","title":"SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking","created":"2023-06-08","cited_by_count":13},{"id":"2403.10799","title":"Toward Adaptive Large Language Models Structured Pruning via Hybrid-grained Weight Importance Assessment","created":"2024-03-16","cited_by_count":13},{"id":"2403.05018","title":"InstructGIE: Towards Generalizable Image Editing","created":"2024-03-08","cited_by_count":12},{"id":"2505.14709","title":"FastCar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge","created":"2025-05-17","cited_by_count":10},{"id":"1606.00968","title":"Smooth Imitation Learning for Online Sequence Prediction","created":"2016-06-03","cited_by_count":9},{"id":"2212.04280","title":"Model-based trajectory stitching for improved behavioural cloning and its applications","created":"2022-12-08","cited_by_count":9},{"id":"2501.04315","title":"RoRA: Efficient Fine-Tuning of LLM with Reliability Optimization for Rank Adaptation","created":"2025-01-08","cited_by_count":9},{"id":"2504.20314","title":"Perturbation-efficient Zeroth-order Optimization for Hardware-friendly On-device Training","created":"2025-04-28","cited_by_count":9},{"id":"2503.16709","title":"QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge","created":"2025-03-20","cited_by_count":8},{"id":"2303.02646","title":"Seq2Seq Imitation Learning for Tactile Feedback-based Manipulation","created":"2023-03-05","cited_by_count":6},{"id":"2409.19583","title":"Brain Tumor Classification on MRI in Light of Molecular Markers","created":"2024-09-29","cited_by_count":5},{"id":"2001.06944","title":"Nested-Wasserstein Self-Imitation Learning for Sequence Generation","created":"2020-01-20","cited_by_count":3},{"id":"2409.05289","title":"Developing Path Planning with Behavioral Cloning and Proximal Policy Optimization for Path-Tracking and Static Obstacle Nudging","created":"2024-09-09","cited_by_count":3},{"id":"2008.01205","title":"Concurrent Training Improves the Performance of Behavioral Cloning from Observation","created":"2020-08-03","cited_by_count":2},{"id":"2310.09461","title":"MAC: ModAlity Calibration for Object Detection","created":"2023-10-14","cited_by_count":2}],"next_cursor":null}