{"total":34,"rows":[{"id":"2403.17887","title":"The Unreasonable Ineffectiveness of the Deeper Layers","created":"2024-03-26","cited_by_count":226,"area":"lr"},{"id":"2404.02657","title":"Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models","created":"2024-04-03","cited_by_count":65,"area":"lr"},{"id":"2505.13775","title":"Beyond Semantics: The Unreasonable Effectiveness of Reasonless Intermediate Tokens","created":"2025-05-19","cited_by_count":41,"area":"lr"},{"id":"2504.09762","title":"Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!","created":"2025-04-14","cited_by_count":37,"area":"lr"},{"id":"2502.20339","title":"Thinking Slow, Fast: Scaling Inference Compute with Distilled Reasoners","created":"2025-02-27","cited_by_count":22,"area":"lr"},{"id":"2403.16385","title":"Synthesize Step-by-Step: Tools, Templates and LLMs as Data Generators for Reasoning-Based Chart VQA","created":"2024-03-25","cited_by_count":19,"area":"lr"},{"id":"2311.09214","title":"Mind's Mirror: Distilling Self-Evaluation Capability and Comprehensive Thinking from Large Language Models","created":"2023-11-15","cited_by_count":13,"area":"lr"},{"id":"2504.02010","title":"When Reasoning Meets Compression: Understanding the Effects of LLMs Compression on Large Reasoning Models","created":"2025-04-02","cited_by_count":13,"area":"lr"},{"id":"2605.13230","title":"Teacher-Guided Policy Optimization for On-Policy Reasoning Distillation under Large Policy Divergence","created":"2026-05-13","cited_by_count":13,"area":"lr"},{"id":"2606.19327","title":"Rethinking Reward Supervision: Rubric-Conditioned Self-Distillation","created":"2026-06-17","cited_by_count":13,"area":"lr"},{"id":"2508.16861","title":"Learning from Diverse Reasoning Paths with Routing and Collaboration","created":"2025-08-23","cited_by_count":12,"area":"lr"},{"id":"2601.16547","title":"CORD: Bridging the Audio-Text Reasoning Gap via Weighted On-policy Cross-modal Distillation","created":"2026-01-23","cited_by_count":11,"area":"lr"},{"id":"2509.16456","title":"GPO: Learning from Critical Steps to Improve LLM Reasoning","created":"2025-09-19","cited_by_count":10,"area":"lr"},{"id":"2608.08726","title":"PAST: Privileged Adaptation from Complete Student Trajectories for On-Policy Self-Distillation","created":"2026-08-09","cited_by_count":6,"area":"lr"},{"id":"2509.21549","title":"Correct Reasoning Paths Visit Shared Decision Pivots","created":"2025-09-25","cited_by_count":5,"area":"lr"},{"id":"2510.07048","title":"Search-R3: Unifying Reasoning and Embedding in Large Language Models","created":"2025-10-08","cited_by_count":4,"area":"lr"},{"id":"2604.02819","title":"Student-in-the-Loop Chain-of-Thought Distillation via Generation-Time Selection","created":"2026-04-03","cited_by_count":4,"area":"lr"},{"id":"2605.21851","title":"OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in LLM Reasoning","created":"2026-05-21","cited_by_count":4,"area":"lr"},{"id":"2504.20946","title":"Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition","created":"2025-04-29","cited_by_count":3,"area":"lr"},{"id":"2509.22921","title":"Rethinking Large Language Model Distillation: A Constrained Markov Decision Process Perspective","created":"2025-09-26","cited_by_count":3,"area":"lr"},{"id":"2607.21550","title":"X$^3$-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment","created":"2026-07-23","cited_by_count":3,"area":"lr"},{"id":"2510.00078","title":"Adaptive and Resource-efficient Agentic AI Systems for Mobile and Embedded Devices: A Survey","created":"2025-09-30","cited_by_count":2,"area":"lr"},{"id":"2605.30290","title":"Self-Trained Verification for Training- and Test-Time Self-Improvement","created":"2026-05-28","cited_by_count":2,"area":"lr"},{"id":"2604.18936","title":"Fine-Tuning Small Reasoning Models for Quantum Field Theory","created":"2026-04-21","cited_by_count":1,"area":"lr"},{"id":"2607.21552","title":"MIRROR: Learning from the Other View for Multi-Modal Reasoning","created":"2026-07-23","cited_by_count":1,"area":"lr"},{"id":"2312.07046","title":"Rethinking Compression: Reduced Order Modelling of Latent Features in Large Language Models","created":"2023-12-12","cited_by_count":0,"area":"lr"},{"id":"2507.00054","title":"Enhancing Reasoning Capabilities in SLMs with Reward Guided Dataset Distillation","created":"2025-06-25","cited_by_count":0,"area":"lr"},{"id":"2508.05234","title":"Resource-Limited Joint Multimodal Sentiment Reasoning and Classification via Chain-of-Thought Enhancement and Distillation","created":"2025-08-07","cited_by_count":0,"area":"lr"},{"id":"2602.22508","title":"Metacognitive Behavioral Tuning of Large Language Models for Multi-Hop Question Answering","created":"2026-02-26","cited_by_count":0,"area":"lr"},{"id":"2608.08146","title":"Long SKILL Compliance as Logical Reasoning: Closure-Grounded Detection with Scaling-Guided On-Policy Distillation","created":"2026-08-08","cited_by_count":0,"area":"lr"},{"id":"2608.09745","title":"SR-OPSD: Self-Referenced On-Policy Self-Distillation","created":"2026-08-10","cited_by_count":0,"area":"lr"},{"id":"2609.07103","title":"Revisiting Complete Reasoning Traces for Post-Training","created":"2026-09-07","cited_by_count":0,"area":"lr"},{"id":"2610.03515","title":"Learning from Repaired Reasoning: Root-Cause-Guided On-Policy Distillation","created":"2026-10-02","cited_by_count":0,"area":"lr"},{"id":"2610.19687","title":"Function-Space Temporal Self-Distillation for Policy Optimization","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}