{"list":"other","total":57,"rows":[{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"2306.13649","title":"On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes","created":"2023-06-23","cited_by_count":939},{"id":"1506.03099","title":"Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks","created":"2015-06-09","cited_by_count":803},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269},{"id":"2402.03898","title":"DistiLLM: Towards Streamlined Distillation for Large Language Models","created":"2024-02-06","cited_by_count":163},{"id":"2312.14852","title":"TACO: Topics in Algorithmic COde generation dataset","created":"2023-12-22","cited_by_count":160},{"id":"2402.14830","title":"Orca-Math: Unlocking the potential of SLMs in Grade School Math","created":"2024-02-16","cited_by_count":151},{"id":"2407.14679","title":"Compact Language Models via Pruning and Knowledge Distillation","created":"2024-07-19","cited_by_count":148},{"id":"2402.10176","title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","created":"2024-02-15","cited_by_count":143},{"id":"2306.08543","title":"MiniLLM: On-Policy Distillation of Large Language Models","created":"2023-06-14","cited_by_count":139},{"id":"1906.02448","title":"Bridging the Gap between Training and Inference for Neural Machine Translation","created":"2019-06-06","cited_by_count":123},{"id":"2503.02951","title":"KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding","created":"2025-03-04","cited_by_count":119},{"id":"2503.07067","title":"DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs","created":"2025-03-10","cited_by_count":84},{"id":"2009.07253","title":"Autoregressive Knowledge Distillation through Imitation Learning","created":"2020-09-15","cited_by_count":74},{"id":"2404.02657","title":"Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models","created":"2024-04-03","cited_by_count":65},{"id":"2402.12030","title":"Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs","created":"2024-02-19","cited_by_count":63},{"id":"2504.04030","title":"OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs","created":"2025-04-05","cited_by_count":60},{"id":"2511.10643","title":"Black-Box On-Policy Distillation of Large Language Models","created":"2025-11-13","cited_by_count":59},{"id":"2407.01885","title":"Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application","created":"2024-07-02","cited_by_count":56},{"id":"2503.20083","title":"Universal Cross-Tokenizer Distillation via Approximate Likelihood Matching","created":"2025-03-25","cited_by_count":41},{"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":"2602.14337","title":"LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces","created":"2026-02-15","cited_by_count":34},{"id":"2601.11044","title":"AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts","created":"2026-01-16","cited_by_count":28},{"id":"2406.17328","title":"Dual-Space Knowledge Distillation for Large Language Models","created":"2024-06-25","cited_by_count":25},{"id":"2510.24021","title":"SelecTKD: Selective Token-Weighted Knowledge Distillation for LLMs","created":"2025-10-28","cited_by_count":22},{"id":"2510.27598","title":"InnovatorBench: Evaluating Agents' Ability to Conduct Innovative LLM Research","created":"2025-10-31","cited_by_count":19},{"id":"2601.18418","title":"daVinci-Dev: Agent-native Mid-training for Software Engineering","created":"2026-01-26","cited_by_count":18},{"id":"2509.17567","title":"LIMI: Less is More for Agency","created":"2025-09-22","cited_by_count":17},{"id":"2603.13023","title":"daVinci-Env: Open SWE Environment Synthesis at Scale","created":"2026-03-13","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":"2506.03690","title":"Robust Preference Optimization via Dynamic Target Margins","created":"2025-06-04","cited_by_count":13},{"id":"2502.11104","title":"Enhancing Cross-Tokenizer Knowledge Distillation with Contextual Dynamical Mapping","created":"2025-02-16","cited_by_count":10},{"id":"2504.11426","title":"A Dual-Space Framework for General Knowledge Distillation of Large Language Models","created":"2025-04-15","cited_by_count":8},{"id":"2604.07466","title":"Cross-Tokenizer LLM Distillation through a Byte-Level Interface","created":"2026-04-08","cited_by_count":8},{"id":"2603.01875","title":"KDFlow: A User-Friendly and Efficient Knowledge Distillation Framework for Large Language Models","created":"2026-03-02","cited_by_count":7},{"id":"2501.12595","title":"A Unified Invariant Learning Framework for Graph Classification","created":"2025-01-22","cited_by_count":5},{"id":"2509.25837","title":"Distillation of Large Language Models via Concrete Score Matching","created":"2025-09-30","cited_by_count":5},{"id":"2512.14954","title":"Cross-Tokenizer Likelihood Scoring Algorithms for Language Model Distillation","created":"2025-12-16","cited_by_count":5},{"id":"2604.00223","title":"Diversity-Aware Reverse Kullback-Leibler Divergence for Large Language Model Distillation","created":"2026-03-31","cited_by_count":5},{"id":"2502.16806","title":"CoT2Align: Cross-Chain of Thought Distillation via Optimal Transport Alignment for Language Models with Different Tokenizers","created":"2025-02-24","cited_by_count":4},{"id":"2503.19123","title":"Overcoming Vocabulary Mismatch: Vocabulary-agnostic Teacher Guided Language Modeling","created":"2025-03-24","cited_by_count":4},{"id":"2604.07737","title":"SepSeq: A Training-Free Framework for Long Numerical Sequence Processing in LLMs","created":"2026-04-09","cited_by_count":2},{"id":"2410.15817","title":"LaMP-Val: Large Language Models Empower Personalized Valuation in Auction","created":"2024-10-21","cited_by_count":1},{"id":"2603.22056","title":"Dual-Space Knowledge Distillation with Key-Query Matching for Large Language Models with Vocabulary Mismatch","created":"2026-03-23","cited_by_count":1}],"next_cursor":null}