{"total":32,"rows":[{"id":"2212.10071","title":"Large Language Models Are Reasoning Teachers","created":"2022-12-20","cited_by_count":329,"area":"lr"},{"id":"2502.21074","title":"CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation","created":"2025-02-28","cited_by_count":225,"area":"lr"},{"id":"2502.12143","title":"Small Models Struggle to Learn from Strong Reasoners","created":"2025-02-17","cited_by_count":113,"area":"lr"},{"id":"2401.08190","title":"MARIO: MAth Reasoning with code Interpreter Output -- A Reproducible Pipeline","created":"2024-01-16","cited_by_count":81,"area":"lr"},{"id":"2402.04616","title":"Beyond Answers: Transferring Reasoning Capabilities to Smaller LLMs Using Multi-Teacher Knowledge Distillation","created":"2024-02-07","cited_by_count":47,"area":"lr"},{"id":"2502.11569","title":"Towards Reasoning Ability of Small Language Models","created":"2025-02-17","cited_by_count":29,"area":"lr"},{"id":"2505.15925","title":"VERDI: VLM-Embedded Reasoning for Autonomous Driving","created":"2025-05-21","cited_by_count":16,"area":"lr"},{"id":"2310.13332","title":"Democratizing Reasoning Ability: Tailored Learning from Large Language Model","created":"2023-10-20","cited_by_count":13,"area":"lr"},{"id":"2503.04872","title":"TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation","created":"2025-03-06","cited_by_count":12,"area":"lr"},{"id":"2603.24840","title":"Prune as You Generate: Online Rollout Pruning for Faster and Better RLVR","created":"2026-03-25","cited_by_count":10,"area":"lr"},{"id":"2510.24940","title":"SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens","created":"2025-10-28","cited_by_count":8,"area":"lr"},{"id":"2606.29340","title":"PHF: Privileged Hidden Flow for On-Policy Self-Distillation","created":"2026-06-28","cited_by_count":8,"area":"lr"},{"id":"2505.11574","title":"Quantization Meets Reasoning: Exploring and Mitigating Degradation of Low-Bit LLMs in Mathematical Reasoning","created":"2025-05-16","cited_by_count":7,"area":"lr"},{"id":"2505.24181","title":"SCOUT: Teaching Pre-trained Language Models to Enhance Reasoning via Flow Chain-of-Thought","created":"2025-05-30","cited_by_count":7,"area":"lr"},{"id":"2605.09725","title":"On-Policy Distillation with Best-of-N Teacher Rollout Selection","created":"2026-05-10","cited_by_count":7,"area":"lr"},{"id":"2401.13849","title":"TPD: Enhancing Student Language Model Reasoning via Principle Discovery and Guidance","created":"2024-01-24","cited_by_count":6,"area":"lr"},{"id":"2407.19405","title":"Logic Distillation: Learning from Code Function by Function for Decision-making Tasks","created":"2024-07-28","cited_by_count":5,"area":"lr"},{"id":"2602.21103","title":"Prompt-Level Distillation: A Non-Parametric Alternative to Model Fine-Tuning for Efficient Reasoning","created":"2026-02-24","cited_by_count":3,"area":"lr"},{"id":"2510.07790","title":"GCPO: When Contrast Fails, Go Gold","created":"2025-10-09","cited_by_count":2,"area":"lr"},{"id":"2510.26854","title":"Inverse Knowledge Search over Verifiable Reasoning: Synthesizing a Scientific Encyclopedia from a Long Chains-of-Thought Knowledge Base","created":"2025-10-30","cited_by_count":2,"area":"lr"},{"id":"2309.09809","title":"A Stepwise Distillation Learning Strategy for Non-differentiable Visual Programming Frameworks on Visual Reasoning Tasks","created":"2023-09-18","cited_by_count":1,"area":"lr"},{"id":"2408.08869","title":"PEDAL: Enhancing Greedy Decoding with Large Language Models using Diverse Exemplars","created":"2024-08-16","cited_by_count":1,"area":"lr"},{"id":"2510.24652","title":"Optimizing Retrieval for RAG via Reinforcement Learning","created":"2025-10-28","cited_by_count":1,"area":"lr"},{"id":"2510.22909","title":"Rethinking Inference Placement for Deep Learning across Edge and Cloud Platforms: A Multi-Objective Optimization Perspective and Future Directions","created":"2025-10-27","cited_by_count":0,"area":"lr"},{"id":"2511.12368","title":"Fast Reasoning Segmentation for Images and Videos","created":"2025-11-15","cited_by_count":0,"area":"lr"},{"id":"2511.17577","title":"Efficient Mathematical Reasoning Models via Dynamic Pruning and Knowledge Distillation","created":"2025-11-15","cited_by_count":0,"area":"lr"},{"id":"2604.19488","title":"CoDA: Towards Effective Cross-domain Knowledge Transfer via CoT-guided Domain Adaptation","created":"2026-04-21","cited_by_count":0,"area":"lr"},{"id":"2605.09719","title":"Distilling 3D Spatial Reasoning into a Lightweight Vision-Language Model with CoT","created":"2026-05-10","cited_by_count":0,"area":"lr"},{"id":"2606.31048","title":"Knowledge Distillation from Large Reasoning Models to Compact Student Models: A Case Study on the John O Bryan Mathematics Competition","created":"2026-06-30","cited_by_count":0,"area":"lr"},{"id":"2607.20440","title":"Answer-then-Edit: Reasoning Skeleton Editing for Anti-Distillation with Preserved Utility","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2608.17151","title":"Lymphocyte Mimicry Correction via Region-Level Tissue Reasoning and Unbalanced Optimal Transport","created":"2026-08-17","cited_by_count":0,"area":"lr"},{"id":"2609.21432","title":"GVPO++: Group Variance Policy Optimization for LLM Post-Training and On-Policy Distillation","created":"2026-09-18","cited_by_count":0,"area":"lr"}],"next_cursor":null}