{"total":93,"rows":[{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269,"area":null},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152,"area":"inference"},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2407.01885","title":"Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application","created":"2024-07-02","cited_by_count":56,"area":"distill"},{"id":"2409.06857","title":"What is the Role of Small Models in the LLM Era: A Survey","created":"2024-09-10","cited_by_count":41,"area":null},{"id":"2404.05875","title":"CodecLM: Aligning Language Models with Tailored Synthetic Data","created":"2024-04-08","cited_by_count":39,"area":"alignment"},{"id":"2303.03446","title":"Students Parrot Their Teachers: Membership Inference on Model Distillation","created":"2023-03-06","cited_by_count":33,"area":"safety"},{"id":"2410.20011","title":"A Survey of Small Language Models","created":"2024-10-25","cited_by_count":31,"area":null},{"id":"2310.03400","title":"Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning","created":"2023-10-05","cited_by_count":29,"area":null},{"id":"2402.05147","title":"ApiQ: Finetuning of 2-Bit Quantized Large Language Model","created":"2024-02-07","cited_by_count":27,"area":null},{"id":"2305.10010","title":"AD-KD: Attribution-Driven Knowledge Distillation for Language Model Compression","created":"2023-05-17","cited_by_count":26,"area":"distill"},{"id":"2407.16154","title":"DDK: Distilling Domain Knowledge for Efficient Large Language Models","created":"2024-07-23","cited_by_count":26,"area":"distill"},{"id":"2407.19409","title":"LLAVADI: What Matters For Multimodal Large Language Models Distillation","created":"2024-07-28","cited_by_count":26,"area":"mllm"},{"id":"2402.12842","title":"PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt Tuning","created":"2024-02-20","cited_by_count":25,"area":"distill"},{"id":"2412.01282","title":"Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model Enhancement","created":"2024-12-02","cited_by_count":23,"area":"lr"},{"id":"2505.04560","title":"ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\\alpha$-$\\beta$-Divergence","created":"2025-05-07","cited_by_count":23,"area":"distill"},{"id":"2402.01799","title":"Faster and Lighter LLMs: A Survey on Current Challenges and Way Forward","created":"2024-02-02","cited_by_count":21,"area":null},{"id":"2406.13555","title":"BiLD: Bi-directional Logits Difference Loss for Large Language Model Distillation","created":"2024-06-19","cited_by_count":19,"area":null},{"id":"2405.17890","title":"SLMRec: Distilling Large Language Models into Small for Sequential Recommendation","created":"2024-05-28","cited_by_count":18,"area":"distill"},{"id":"2401.15347","title":"A Comprehensive Survey of Compression Algorithms for Language Models","created":"2024-01-27","cited_by_count":15,"area":null},{"id":"2505.12781","title":"A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone","created":"2025-05-19","cited_by_count":15,"area":"distill"},{"id":"2505.19201","title":"DREAM: Drafting with Refined Target Features and Entropy-Adaptive Cross-Attention Fusion for Multimodal Speculative Decoding","created":"2025-05-25","cited_by_count":14,"area":"mllm"},{"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,"area":null},{"id":"2411.07483","title":"Quantifying Knowledge Distillation Using Partial Information Decomposition","created":"2024-11-12","cited_by_count":13,"area":"distill"},{"id":"2510.11615","title":"LLM-Oriented Token-Adaptive Knowledge Distillation","created":"2025-10-13","cited_by_count":13,"area":"distill"},{"id":"2310.04550","title":"Module-wise Adaptive Distillation for Multimodality Foundation Models","created":"2023-10-06","cited_by_count":12,"area":null},{"id":"2406.02886","title":"PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs","created":"2024-06-05","cited_by_count":11,"area":"distill"},{"id":"2409.15895","title":"Preference-Guided Refactored Tuning for Retrieval Augmented Code Generation","created":"2024-09-24","cited_by_count":10,"area":"rag"},{"id":"2501.02173","title":"The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit","created":"2025-01-04","cited_by_count":10,"area":"inference"},{"id":"2407.09111","title":"Inference Optimization of Foundation Models on AI Accelerators","created":"2024-07-12","cited_by_count":9,"area":null},{"id":"2509.03934","title":"SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment","created":"2025-09-04","cited_by_count":9,"area":"rag"},{"id":"2507.04636","title":"Put Teacher in Student's Shoes: Cross-Distillation for Ultra-compact Model Compression Framework","created":"2025-07-07","cited_by_count":8,"area":null},{"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":"2605.06597","title":"UniSD: Towards a Unified Self-Distillation Framework for Large Language Models","created":"2026-05-07","cited_by_count":7,"area":"distill"},{"id":"2411.06448","title":"Over-parameterized Student Model via Tensor Decomposition Boosted Knowledge Distillation","created":"2024-11-10","cited_by_count":5,"area":"distill"},{"id":"2412.09289","title":"Optimising TinyML with Quantization and Distillation of Transformer and Mamba Models for Indoor Localisation on Edge Devices","created":"2024-12-12","cited_by_count":5,"area":"ssm"},{"id":"2412.11180","title":"TINED: GNNs-to-MLPs by Teacher Injection and Dirichlet Energy Distillation","created":"2024-12-15","cited_by_count":5,"area":null},{"id":"2309.09003","title":"RingMo-lite: A Remote Sensing Multi-task Lightweight Network with CNN-Transformer Hybrid Framework","created":"2023-09-16","cited_by_count":4,"area":null},{"id":"2310.07838","title":"Towards the Fundamental Limits of Knowledge Transfer over Finite Domains","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2406.02959","title":"Adversarial Moment-Matching Distillation of Large Language Models","created":"2024-06-05","cited_by_count":4,"area":"distill"},{"id":"2408.04278","title":"LaDiMo: Layer-wise Distillation Inspired MoEfier","created":"2024-08-08","cited_by_count":4,"area":"moe"},{"id":"2412.02054","title":"Redundant Queries in DETR-Based 3D Detection Methods: Unnecessary and Prunable","created":"2024-12-03","cited_by_count":4,"area":null},{"id":"2412.13437","title":"Deploying Foundation Model Powered Agent Services: A Survey","created":"2024-12-18","cited_by_count":4,"area":"agents"},{"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":"2510.21631","title":"Few-Shot Knowledge Distillation of LLMs With Counterfactual Explanations","created":"2025-10-24","cited_by_count":4,"area":"distill"},{"id":"2512.00862","title":"HBLLM: Wavelet-Enhanced High-Fidelity 1-Bit Quantization for LLMs","created":"2025-11-30","cited_by_count":4,"area":null},{"id":"2605.24956","title":"NITP: Next Implicit Token Prediction for LLM Pre-training","created":"2026-05-24","cited_by_count":4,"area":"moe"},{"id":"2406.05276","title":"VTrans: Accelerating Transformer Compression with Variational Information Bottleneck based Pruning","created":"2024-06-07","cited_by_count":3,"area":null},{"id":"2410.13060","title":"AERO: Entropy-Guided Framework for Private LLM Inference","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2412.12785","title":"Activating Distributed Visual Region within LLMs for Efficient and Effective Vision-Language Training and Inference","created":"2024-12-17","cited_by_count":3,"area":"mllm"},{"id":"2505.17988","title":"Towards Revealing the Effectiveness of Small-Scale Fine-tuning in R1-style Reinforcement Learning","created":"2025-05-23","cited_by_count":3,"area":"lr"},{"id":"2507.05617","title":"Flipping Knowledge Distillation: Leveraging Small Models' Expertise to Enhance LLMs in Text Matching","created":"2025-07-08","cited_by_count":3,"area":"distill"},{"id":"2511.05704","title":"TabDistill: Distilling Transformers into Neural Nets for Few-Shot Tabular Classification","created":"2025-11-07","cited_by_count":3,"area":null},{"id":"2602.12172","title":"Pedagogically-Inspired Data Synthesis for Language Model Knowledge Distillation","created":"2026-02-12","cited_by_count":3,"area":"synth"},{"id":"2407.10068","title":"Multi-Granularity Semantic Revision for Large Language Model Distillation","created":"2024-07-14","cited_by_count":2,"area":"distill"},{"id":"2503.08101","title":"Accelerate 3D Object Detection Models via Zero-Shot Attention Key Pruning","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2503.17494","title":"Efficient Knowledge Distillation via Curriculum Extraction","created":"2025-03-21","cited_by_count":2,"area":"distill"},{"id":"2505.23337","title":"Matryoshka Model Learning for Improved Elastic Student Models","created":"2025-05-29","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":"2601.05913","title":"Distilling Lightweight Domain Experts from Large ML Models by Identifying Relevant Subspaces","created":"2026-01-09","cited_by_count":2,"area":"distill"},{"id":"2605.05826","title":"AGPO: Asymmetric Group Policy Optimization for Verifiable Reasoning and Search Ads Relevance at JD","created":"2026-05-07","cited_by_count":2,"area":"lr"},{"id":"2403.00783","title":"On the Roles of LLMs in Planning: Embedding LLMs into Planning Graphs","created":"2024-02-18","cited_by_count":1,"area":null},{"id":"2502.15616","title":"Pastiche Novel Generation Creating: Fan Fiction You Love in Your Favorite Author's Style","created":"2025-02-21","cited_by_count":1,"area":null},{"id":"2503.06184","title":"Sample-aware Adaptive Structured Pruning for Large Language Models","created":"2025-03-08","cited_by_count":1,"area":null},{"id":"2504.14241","title":"A Knowledge-Informed Deep Learning Paradigm for Generalizable and Stability-Optimized Car-Following Models","created":"2025-04-19","cited_by_count":1,"area":null},{"id":"2602.00852","title":"Investigating the Robustness of Subtask Distillation under Spurious Correlation","created":"2026-01-31","cited_by_count":1,"area":"distill"},{"id":"2602.00942","title":"SALAAD: Sparse And Low-Rank Adaptation via ADMM for Large Language Model Inference","created":"2026-02-01","cited_by_count":1,"area":null},{"id":"2602.05393","title":"Late-to-Early Training: LET LLMs Learn Earlier, So Faster and Better","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2602.12674","title":"$\\mathcal{X}$-KD: General Experiential Knowledge Distillation for Large Language Models","created":"2026-02-13","cited_by_count":1,"area":"distill"},{"id":"2609.19553","title":"From Parameters to Behaviors: A Survey of Model Fusion for Large Language Models","created":"2026-09-17","cited_by_count":1,"area":null},{"id":"2402.15991","title":"$C^3$: Confidence Calibration Model Cascade for Inference-Efficient Cross-Lingual Natural Language Understanding","created":"2024-02-25","cited_by_count":0,"area":null},{"id":"2406.11128","title":"Model Adaptation for Time Constrained Embodied Control","created":"2024-06-17","cited_by_count":0,"area":null},{"id":"2407.13911","title":"Continual Distillation Learning for Rehearsal-Free Class-Incremental Learning via Decoupled Prompting","created":"2024-07-18","cited_by_count":0,"area":"distill"},{"id":"2503.17922","title":"WindowKV: Task-Adaptive Group-Wise KV Cache Window Selection for Efficient LLM Inference","created":"2025-03-23","cited_by_count":0,"area":"inference"},{"id":"2509.25253","title":"Knowledge distillation through geometry-aware representational alignment","created":"2025-09-27","cited_by_count":0,"area":"distill"},{"id":"2510.05133","title":"Characterizing Model Behavior Under Synthetic Data Training: An Empirical Study Across Scales and Mixing Ratios","created":"2025-10-01","cited_by_count":0,"area":"lr"},{"id":"2512.21835","title":"LOIP:Collaborative Lossless LLM Inference Serving with Offloading-based Pipeline Parallelism on Edge Devices","created":"2025-12-26","cited_by_count":0,"area":"inference"},{"id":"2601.17625","title":"BrainDistill: Implantable Motor Decoding with Task-Specific Knowledge Distillation","created":"2026-01-24","cited_by_count":0,"area":"distill"},{"id":"2601.21288","title":"Drive-KD: Multi-Teacher Distillation for VLMs in Autonomous Driving","created":"2026-01-29","cited_by_count":0,"area":"driving"},{"id":"2604.15016","title":"DLink: Distilling Layer-wise and Dominant Knowledge from EEG Foundation Models","created":"2026-04-16","cited_by_count":0,"area":"distill"},{"id":"2605.07783","title":"Chain-based Distillation for Effective Initialization of Variable-Sized Small Language Models","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.10777","title":"Locking Pretrained Weights via Deep Low-Rank Residual Distillation","created":"2026-05-11","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":"2605.11513","title":"A Study on Hidden Layer Distillation for Large Language Model Pre-Training","created":"2026-05-12","cited_by_count":0,"area":"distill"},{"id":"2607.08776","title":"A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions","created":"2026-05-05","cited_by_count":0,"area":"distill"},{"id":"2607.10855","title":"Reliability Scaling Laws for Quantized Large Language Models","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2609.19213","title":"Layer-wise Curriculum Learning for Efficient LLM Compression","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2610.12837","title":"COFFEQA: Counterfactual-Guided Few-Shot Distillation for LLM Question Answering","created":"2026-10-09","cited_by_count":0,"area":"distill"},{"id":"2610.14022","title":"OPMD: On-Policy Mechanism Distillation Beyond Output Supervision","created":"2026-09-29","cited_by_count":0,"area":"distill"}],"next_cursor":null}