{"total":79,"rows":[{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576,"area":null},{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843,"area":null},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"area":null},{"id":"2206.01861","title":"ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers","created":"2022-06-04","cited_by_count":526,"area":null},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"id":"2210.07558","title":"DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation","created":"2022-10-14","cited_by_count":233,"area":null},{"id":"2309.10668","title":"Language Modeling Is Compression","created":"2023-09-19","cited_by_count":225,"area":null},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2209.13325","title":"Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models","created":"2022-09-27","cited_by_count":181,"area":null},{"id":"2406.01721","title":"DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs","created":"2024-06-03","cited_by_count":167,"area":null},{"id":"2407.13623","title":"Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies","created":"2024-07-18","cited_by_count":118,"area":null},{"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":"2303.08302","title":"ZeroQuant-V2: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation","created":"2023-03-15","cited_by_count":79,"area":null},{"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":"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":"2304.09145","title":"Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling","created":"2023-04-18","cited_by_count":61,"area":null},{"id":"2301.13741","title":"UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers","created":"2023-01-31","cited_by_count":54,"area":null},{"id":"2404.07947","title":"ExeGPT: Constraint-Aware Resource Scheduling for LLM Inference","created":"2024-03-15","cited_by_count":45,"area":null},{"id":"2210.05528","title":"Model Cascading: Towards Jointly Improving Efficiency and Accuracy of NLP Systems","created":"2022-10-11","cited_by_count":44,"area":null},{"id":"2305.17455","title":"CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers","created":"2023-05-27","cited_by_count":44,"area":"mllm"},{"id":"2404.07236","title":"Lightweight Deep Learning for Resource-Constrained Environments: A Survey","created":"2024-04-08","cited_by_count":38,"area":null},{"id":"2406.13035","title":"D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models","created":"2024-06-18","cited_by_count":31,"area":"inference"},{"id":"2302.03773","title":"What Matters In The Structured Pruning of Generative Language Models?","created":"2023-02-07","cited_by_count":30,"area":null},{"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":"2508.14896","title":"Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs","created":"2025-08-20","cited_by_count":23,"area":null},{"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":"2407.12327","title":"Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale","created":"2024-07-17","cited_by_count":21,"area":null},{"id":"2308.06744","title":"Token-Scaled Logit Distillation for Ternary Weight Generative Language Models","created":"2023-08-13","cited_by_count":20,"area":"distill"},{"id":"2307.00331","title":"Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision","created":"2023-07-01","cited_by_count":17,"area":null},{"id":"2210.11621","title":"SMaLL-100: Introducing Shallow Multilingual Machine Translation Model for Low-Resource Languages","created":"2022-10-20","cited_by_count":16,"area":null},{"id":"2402.10787","title":"Squat: Quant Small Language Models on the Edge","created":"2024-02-16","cited_by_count":16,"area":null},{"id":"2401.15347","title":"A Comprehensive Survey of Compression Algorithms for Language Models","created":"2024-01-27","cited_by_count":15,"area":null},{"id":"2312.08583","title":"ZeroQuant(4+2): Redefining LLMs Quantization with a New FP6-Centric Strategy for Diverse Generative Tasks","created":"2023-12-14","cited_by_count":14,"area":null},{"id":"2402.02563","title":"Synergy-of-Thoughts: Eliciting Efficient Reasoning in Hybrid Language Models","created":"2024-02-04","cited_by_count":13,"area":"lr"},{"id":"2410.05078","title":"Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Data","created":"2024-10-07","cited_by_count":13,"area":null},{"id":"2211.12707","title":"Can Open-Domain QA Reader Utilize External Knowledge Efficiently like Humans?","created":"2022-11-23","cited_by_count":10,"area":null},{"id":"2211.16912","title":"Quadapter: Adapter for GPT-2 Quantization","created":"2022-11-30","cited_by_count":10,"area":null},{"id":"2402.05628","title":"RepQuant: Towards Accurate Post-Training Quantization of Large Transformer Models via Scale Reparameterization","created":"2024-02-08","cited_by_count":10,"area":null},{"id":"2405.10299","title":"HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models","created":"2024-05-16","cited_by_count":10,"area":null},{"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":"2205.10828","title":"What Do Compressed Multilingual Machine Translation Models Forget?","created":"2022-05-22","cited_by_count":9,"area":null},{"id":"2210.16536","title":"Differentiable Data Augmentation for Contrastive Sentence Representation Learning","created":"2022-10-29","cited_by_count":9,"area":null},{"id":"2307.04905","title":"FedYolo: Augmenting Federated Learning with Pretrained Transformers","created":"2023-07-10","cited_by_count":9,"area":null},{"id":"2312.00960","title":"The Cost of Compression: Investigating the Impact of Compression on Parametric Knowledge in Language Models","created":"2023-12-01","cited_by_count":9,"area":null},{"id":"2409.16997","title":"INT-FlashAttention: Enabling Flash Attention for INT8 Quantization","created":"2024-09-25","cited_by_count":9,"area":null},{"id":"2305.09098","title":"Weight-Inherited Distillation for Task-Agnostic BERT Compression","created":"2023-05-16","cited_by_count":8,"area":"distill"},{"id":"2306.01841","title":"Binary and Ternary Natural Language Generation","created":"2023-06-02","cited_by_count":7,"area":null},{"id":"2303.05295","title":"Dynamic Stashing Quantization for Efficient Transformer Training","created":"2023-03-09","cited_by_count":6,"area":null},{"id":"2411.05036","title":"From Word Vectors to Multimodal Embeddings: Techniques, Applications, and Future Directions For Large Language Models","created":"2024-11-06","cited_by_count":6,"area":null},{"id":"2210.15184","title":"Too Brittle To Touch: Comparing the Stability of Quantization and Distillation Towards Developing Lightweight Low-Resource MT Models","created":"2022-10-27","cited_by_count":5,"area":"distill"},{"id":"2306.00014","title":"PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models","created":"2023-05-30","cited_by_count":5,"area":null},{"id":"2310.15477","title":"CRaSh: Clustering, Removing, and Sharing Enhance Fine-tuning without Full Large Language Model","created":"2023-10-24","cited_by_count":5,"area":"alignment"},{"id":"2405.00632","title":"When Quantization Affects Confidence of Large Language Models?","created":"2024-05-01","cited_by_count":5,"area":null},{"id":"2303.05378","title":"Greener yet Powerful: Taming Large Code Generation Models with Quantization","created":"2023-03-09","cited_by_count":4,"area":null},{"id":"2305.12330","title":"Task-agnostic Distillation of Encoder-Decoder Language Models","created":"2023-05-21","cited_by_count":4,"area":null},{"id":"2308.04025","title":"MSAC: Multiple Speech Attribute Control Method for Reliable Speech Emotion Recognition","created":"2023-08-08","cited_by_count":4,"area":null},{"id":"2402.11819","title":"Head-wise Shareable Attention for Large Language Models","created":"2024-02-19","cited_by_count":4,"area":null},{"id":"2406.18832","title":"OutlierTune: Efficient Channel-Wise Quantization for Large Language Models","created":"2024-06-27","cited_by_count":4,"area":null},{"id":"2407.16207","title":"Graph-Structured Speculative Decoding","created":"2024-07-23","cited_by_count":4,"area":"inference"},{"id":"2503.07654","title":"MergeQuant: Accurate 4-bit Static Quantization of Large Language Models by Channel-wise Calibration","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2310.15594","title":"Retrieval-based Knowledge Transfer: An Effective Approach for Extreme Large Language Model Compression","created":"2023-10-24","cited_by_count":3,"area":null},{"id":"2403.13901","title":"Train & Constrain: Phonologically Informed Tongue-Twister Generation from Topics and Paraphrases","created":"2024-03-20","cited_by_count":3,"area":null},{"id":"2411.17309","title":"PIM-AI: A Novel Architecture for High-Efficiency LLM Inference","created":"2024-11-26","cited_by_count":3,"area":null},{"id":"2306.06371","title":"A Comprehensive Review of State-of-The-Art Methods for Java Code Generation from Natural Language Text","created":"2023-06-10","cited_by_count":2,"area":null},{"id":"2310.13315","title":"Zero-Shot Sharpness-Aware Quantization for Pre-trained Language Models","created":"2023-10-20","cited_by_count":2,"area":null},{"id":"2403.05365","title":"The Impact of Quantization on the Robustness of Transformer-based Text Classifiers","created":"2024-03-08","cited_by_count":2,"area":null},{"id":"2411.04637","title":"Hands-On Tutorial: Labeling with LLM and Human-in-the-Loop","created":"2024-11-07","cited_by_count":2,"area":null},{"id":"2501.03289","title":"Adaptive Pruning of Pretrained Transformer via Differential Inclusions","created":"2025-01-06","cited_by_count":2,"area":null},{"id":"2508.15423","title":"An Empirical Study of Knowledge Distillation for Code Understanding Tasks","created":"2025-08-21","cited_by_count":2,"area":"distill"},{"id":"2310.07911","title":"Pit One Against Many: Leveraging Attention-head Embeddings for Parameter-efficient Multi-head Attention","created":"2023-10-11","cited_by_count":1,"area":null},{"id":"2310.17723","title":"ZeroQuant-HERO: Hardware-Enhanced Robust Optimized Post-Training Quantization Framework for W8A8 Transformers","created":"2023-10-26","cited_by_count":1,"area":null},{"id":"2311.03216","title":"Mini Minds: Exploring Bebeshka and Zlata Baby Models","created":"2023-11-06","cited_by_count":1,"area":null},{"id":"2406.02599","title":"Privacy-Aware Randomized Quantization via Linear Programming","created":"2024-06-01","cited_by_count":1,"area":null},{"id":"2506.02077","title":"Assigning Distinct Roles to Quantized and Low-Rank Matrices Toward Optimal Weight Decomposition","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2210.08701","title":"ODG-Q: Robust Quantization via Online Domain Generalization","created":"2022-10-17","cited_by_count":0,"area":null},{"id":"2210.13578","title":"Speeding Up Question Answering Task of Language Models via Inverted Index","created":"2022-10-24","cited_by_count":0,"area":null},{"id":"2407.09943","title":"Minimizing PLM-Based Few-Shot Intent Detectors","created":"2024-07-13","cited_by_count":0,"area":null},{"id":"2408.10729","title":"Towards Efficient Large Language Models for Scientific Text: A Review","created":"2024-08-20","cited_by_count":0,"area":null},{"id":"2508.00220","title":"Semantic Compression for Word and Sentence Embeddings using Discrete Wavelet Transform","created":"2025-07-31","cited_by_count":0,"area":null}],"next_cursor":null}