{"total":56,"rows":[{"id":"2505.22375","title":"Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition","created":"2025-05-28","cited_by_count":62,"area":"lr"},{"id":"2503.06424","title":"Training LLM-based Tutors to Improve Student Learning Outcomes in Dialogues","created":"2025-03-09","cited_by_count":43,"area":null},{"id":"2504.09629","title":"Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization","created":"2025-04-13","cited_by_count":41,"area":null},{"id":"2412.04315","title":"Densing Law of LLMs","created":"2024-12-05","cited_by_count":40,"area":null},{"id":"2510.04040","title":"FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning","created":"2025-10-05","cited_by_count":26,"area":"lr"},{"id":"2504.17119","title":"The Rise of Small Language Models in Healthcare: A Comprehensive Survey","created":"2025-04-23","cited_by_count":18,"area":null},{"id":"2506.03320","title":"The Future of Continual Learning in the Era of Foundation Models: Three Key Directions","created":"2025-06-03","cited_by_count":17,"area":null},{"id":"2508.19843","title":"SoK: Large Language Model Copyright Auditing via Fingerprinting","created":"2025-08-27","cited_by_count":15,"area":null},{"id":"2605.07711","title":"SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation","created":"2026-05-08","cited_by_count":12,"area":"distill"},{"id":"2506.06278","title":"Distillation Robustifies Unlearning","created":"2025-06-06","cited_by_count":11,"area":"safety"},{"id":"2502.19335","title":"Gatekeeper: Improving Model Cascades Through Confidence Tuning","created":"2025-02-26","cited_by_count":10,"area":null},{"id":"2407.17447","title":"FLRT: Fluent Student-Teacher Redteaming","created":"2024-07-24","cited_by_count":9,"area":"safety"},{"id":"2505.13792","title":"Interpretable Traces, Unexpected Outcomes: Investigating the Disconnect in Trace-Based Knowledge Distillation","created":"2025-05-20","cited_by_count":8,"area":"lr"},{"id":"2505.20112","title":"ERC-SVD: Error-Controlled SVD for Large Language Model Compression","created":"2025-05-26","cited_by_count":7,"area":null},{"id":"2504.13825","title":"Feature Alignment and Representation Transfer in Knowledge Distillation for Large Language Models","created":"2025-04-18","cited_by_count":6,"area":"distill"},{"id":"2507.15198","title":"Collaborative Distillation Strategies for Parameter-Efficient Language Model Deployment","created":"2025-07-21","cited_by_count":5,"area":"distill"},{"id":"2607.09084","title":"A Survey on the Green Development of Large Models: From Resource-Efficient Architectures to Hardware-Software Co-Design","created":"2026-07-10","cited_by_count":5,"area":null},{"id":"2504.17421","title":"Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks","created":"2025-04-24","cited_by_count":4,"area":null},{"id":"2506.05695","title":"Being Strong Progressively! Enhancing Knowledge Distillation of Large Language Models through a Curriculum Learning Framework","created":"2025-06-06","cited_by_count":4,"area":"distill"},{"id":"2602.03075","title":"ReMiT: RL-Guided Mid-Training for Iterative LLM Evolution","created":"2026-02-03","cited_by_count":4,"area":null},{"id":"2502.15873","title":"Practical Principles for AI Cost and Compute Accounting","created":"2025-02-21","cited_by_count":3,"area":null},{"id":"2509.17866","title":"Understanding Post-Training Structural Changes in Large Language Models","created":"2025-09-22","cited_by_count":3,"area":null},{"id":"2503.09030","title":"Adaptive Temperature Based on Logits Correlation in Knowledge Distillation","created":"2025-03-12","cited_by_count":2,"area":"distill"},{"id":"2505.02390","title":"Quantitative Analysis of Performance Drop in DeepSeek Model Quantization","created":"2025-05-05","cited_by_count":2,"area":null},{"id":"2510.07782","title":"RCPU: Rotation-Constrained Error Compensation for Structured Pruning of Large Language Models","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2510.16968","title":"Leave It to the Experts: Detecting Knowledge Distillation via MoE Expert Signatures","created":"2025-10-19","cited_by_count":2,"area":"moe"},{"id":"2512.14052","title":"HyperVL: An Efficient and Dynamic Multimodal Large Language Model for Edge Devices","created":"2025-12-16","cited_by_count":2,"area":"lr"},{"id":"2609.23697","title":"Distill What You Trust: Reliability-Aware Multi-Teacher On-Policy Distillation","created":"2026-09-20","cited_by_count":2,"area":"distill"},{"id":"2408.05952","title":"Optimizing Vision Transformers with Data-Free Knowledge Transfer","created":"2024-08-12","cited_by_count":1,"area":"distill"},{"id":"2410.16924","title":"SleepCoT: A Lightweight Personalized Sleep Health Model via Chain-of-Thought Distillation","created":"2024-10-22","cited_by_count":1,"area":"lr"},{"id":"2504.02521","title":"UNDO: Understanding Distillation as Optimization","created":"2025-04-03","cited_by_count":1,"area":null},{"id":"2505.08793","title":"Onboard Optimization and Learning: A Survey","created":"2025-05-07","cited_by_count":1,"area":null},{"id":"2602.01956","title":"Efficient Epistemic Uncertainty Estimation for Large Language Models via Knowledge Distillation","created":"2026-02-02","cited_by_count":1,"area":"distill"},{"id":"2603.19266","title":"Probing to Refine: Reinforcement Distillation of LLMs via Explanatory Inversion","created":"2026-02-26","cited_by_count":1,"area":"lr"},{"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,"area":"distill"},{"id":"2603.24361","title":"LATS: Large Language Model Assisted Teacher-Student Framework for Multi-Agent Reinforcement Learning in Traffic Signal Control","created":"2026-03-25","cited_by_count":1,"area":"agents"},{"id":"2605.08568","title":"Different Prompts, Different Ranks: Prompt-aware Dynamic Rank Selection for SVD-based LLM Compression","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2505.01391","title":"Learning and Transferring Physical Models through Derivatives","created":"2025-05-02","cited_by_count":0,"area":null},{"id":"2505.10822","title":"Distilled Circuits: A Mechanistic Study of Internal Restructuring in Knowledge Distillation","created":"2025-05-16","cited_by_count":0,"area":"distill"},{"id":"2506.02014","title":"Research on Driving Scenario Technology Based on Multimodal Large Lauguage Model Optimization","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2506.15337","title":"Knowledge Distillation Framework for Accelerating High-Accuracy Neural Network-Based Molecular Dynamics Simulations","created":"2025-06-18","cited_by_count":0,"area":"distill"},{"id":"2506.18496","title":"Distilling Balanced Knowledge from a Biased Teacher","created":"2025-06-23","cited_by_count":0,"area":"distill"},{"id":"2507.10059","title":"GeLaCo: An Evolutionary Approach to Layer Compression","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2508.13439","title":"Structured Prompting and Multi-Agent Knowledge Distillation for Traffic Video Interpretation and Risk Inference","created":"2025-08-19","cited_by_count":0,"area":"agents"},{"id":"2509.00347","title":"LLM-Driven Policy Diffusion: Enhancing Generalization in Offline Reinforcement Learning","created":"2025-08-30","cited_by_count":0,"area":"offlinerl"},{"id":"2509.00560","title":"Efficient Graph Knowledge Distillation from GNNs to Kolmogorov--Arnold Networks via Self-Attention Dynamic Sampling","created":"2025-08-30","cited_by_count":0,"area":"distill"},{"id":"2601.09722","title":"ADMEDTAGGER: an annotation framework for distillation of expert knowledge for the Polish medical language","created":"2025-12-27","cited_by_count":0,"area":null},{"id":"2601.13122","title":"Responsible AI for General-Purpose Systems: Overview, Challenges, and A Path Forward","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2601.19089","title":"EPAS: Efficient Training with Progressive Activation Sharing","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2605.11290","title":"ReAD: Reinforcement-Guided Capability Distillation for Large Language Models","created":"2026-05-11","cited_by_count":0,"area":"distill"},{"id":"2608.00573","title":"TrimMoE A communication aware and adaptive depth framework for distributed edge inference","created":"2026-08-01","cited_by_count":0,"area":"moe"},{"id":"2609.18321","title":"Trajectory Learnability for Offline On-Policy Distillation with Imperfect Teachers","created":"2026-09-16","cited_by_count":0,"area":"distill"},{"id":"2609.25643","title":"Ladders of Thought: A Self-Evolving Curriculum of Progressively Simplified Reasoning Traces","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2609.33727","title":"A Statistical Perspective on Knowledge Distillation: Foundations, Classical Methods, and Large Language Model Extensions","created":"2026-09-27","cited_by_count":0,"area":"distill"},{"id":"2609.35362","title":"d-OPD: Future-Aware On-Policy Distillation for Block Diffusion Language Models","created":"2026-09-28","cited_by_count":0,"area":"diffusion"},{"id":"2610.12837","title":"COFFEQA: Counterfactual-Guided Few-Shot Distillation for LLM Question Answering","created":"2026-10-09","cited_by_count":0,"area":"distill"}],"next_cursor":null}