{"total":113,"rows":[{"id":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255,"area":null},{"id":"2306.11222","title":"LoSparse: Structured Compression of Large Language Models based on Low-Rank and Sparse Approximation","created":"2023-06-20","cited_by_count":104,"area":null},{"id":"2309.11765","title":"Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation","created":"2023-09-21","cited_by_count":96,"area":null},{"id":"2210.01351","title":"Less is More: Task-aware Layer-wise Distillation for Language Model Compression","created":"2022-10-04","cited_by_count":93,"area":null},{"id":"2104.02096","title":"Compressing Visual-linguistic Model via Knowledge Distillation","created":"2021-04-05","cited_by_count":86,"area":"distill"},{"id":"2203.08243","title":"Unified Visual Transformer Compression","created":"2022-03-15","cited_by_count":79,"area":null},{"id":"2203.05402","title":"Representation Compensation Networks for Continual Semantic Segmentation","created":"2022-03-10","cited_by_count":72,"area":null},{"id":"2304.04487","title":"Inference with Reference: Lossless Acceleration of Large Language Models","created":"2023-04-10","cited_by_count":65,"area":null},{"id":"2106.04570","title":"BERT Learns to Teach: Knowledge Distillation with Meta Learning","created":"2021-06-08","cited_by_count":61,"area":"distill"},{"id":"2109.05472","title":"Compute and Energy Consumption Trends in Deep Learning Inference","created":"2021-09-12","cited_by_count":61,"area":null},{"id":"2107.11817","title":"Go Wider Instead of Deeper","created":"2021-07-25","cited_by_count":57,"area":"moe"},{"id":"2105.14444","title":"NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search","created":"2021-05-30","cited_by_count":56,"area":null},{"id":"2210.07795","title":"EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning","created":"2022-10-14","cited_by_count":56,"area":"mllm"},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2302.04089","title":"ZipLM: Inference-Aware Structured Pruning of Language Models","created":"2023-02-07","cited_by_count":49,"area":null},{"id":"2205.15308","title":"Parameter-Efficient and Student-Friendly Knowledge Distillation","created":"2022-05-28","cited_by_count":47,"area":"distill"},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2110.06696","title":"Mengzi: Towards Lightweight yet Ingenious Pre-trained Models for Chinese","created":"2021-10-13","cited_by_count":45,"area":null},{"id":"2202.07105","title":"A Survey on Model Compression and Acceleration for Pretrained Language Models","created":"2022-02-15","cited_by_count":45,"area":null},{"id":"2110.07038","title":"Towards Efficient NLP: A Standard Evaluation and A Strong Baseline","created":"2021-10-13","cited_by_count":44,"area":null},{"id":"2402.05406","title":"Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes","created":"2024-02-08","cited_by_count":43,"area":null},{"id":"2106.06168","title":"Generate, Annotate, and Learn: NLP with Synthetic Text","created":"2021-06-11","cited_by_count":42,"area":"distill"},{"id":"2104.08682","title":"Rethinking Network Pruning -- under the Pre-train and Fine-tune Paradigm","created":"2021-04-18","cited_by_count":40,"area":null},{"id":"2203.06321","title":"Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation","created":"2022-03-12","cited_by_count":39,"area":"distill"},{"id":"2109.03228","title":"Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT Compression","created":"2021-09-07","cited_by_count":38,"area":null},{"id":"2109.11295","title":"Dynamic Knowledge Distillation for Pre-trained Language Models","created":"2021-09-23","cited_by_count":38,"area":"distill"},{"id":"2204.07675","title":"MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation","created":"2022-04-15","cited_by_count":37,"area":"moe"},{"id":"2212.10670","title":"In-context Learning Distillation: Transferring Few-shot Learning Ability of Pre-trained Language Models","created":"2022-12-20","cited_by_count":37,"area":null},{"id":"2111.04130","title":"NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework","created":"2021-11-07","cited_by_count":34,"area":null},{"id":"2109.08359","title":"Distilling Linguistic Context for Language Model Compression","created":"2021-09-17","cited_by_count":33,"area":"distill"},{"id":"2205.11098","title":"PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection","created":"2022-05-23","cited_by_count":33,"area":"distill"},{"id":"2203.01670","title":"A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation","created":"2022-03-03","cited_by_count":32,"area":"inference"},{"id":"2508.02694","title":"Efficient Agents: Building Effective Agents While Reducing Cost","created":"2025-07-24","cited_by_count":32,"area":"agents"},{"id":"2310.13671","title":"Let's Synthesize Step by Step: Iterative Dataset Synthesis with Large Language Models by Extrapolating Errors from Small Models","created":"2023-10-20","cited_by_count":30,"area":null},{"id":"2410.16215","title":"Pre-training Distillation for Large Language Models: A Design Space Exploration","created":"2024-10-21","cited_by_count":27,"area":"distill"},{"id":"2302.09632","title":"HomoDistil: Homotopic Task-Agnostic Distillation of Pre-trained Transformers","created":"2023-02-19","cited_by_count":25,"area":"distill"},{"id":"2202.07101","title":"A Survey on Dynamic Neural Networks for Natural Language Processing","created":"2022-02-15","cited_by_count":24,"area":null},{"id":"2206.00621","title":"Cross-View Language Modeling: Towards Unified Cross-Lingual Cross-Modal Pre-training","created":"2022-06-01","cited_by_count":24,"area":null},{"id":"2311.17431","title":"Grounding Foundation Models through Federated Transfer Learning: A General Framework","created":"2023-11-29","cited_by_count":24,"area":null},{"id":"2204.10496","title":"Multimodal Adaptive Distillation for Leveraging Unimodal Encoders for Vision-Language Tasks","created":"2022-04-22","cited_by_count":23,"area":null},{"id":"2110.08190","title":"Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm","created":"2021-10-15","cited_by_count":21,"area":null},{"id":"2202.07959","title":"EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation","created":"2022-02-16","cited_by_count":21,"area":null},{"id":"2108.12821","title":"Analyzing and Mitigating Interference in Neural Architecture Search","created":"2021-08-29","cited_by_count":20,"area":null},{"id":"2109.06243","title":"KroneckerBERT: Learning Kronecker Decomposition for Pre-trained Language Models via Knowledge Distillation","created":"2021-09-13","cited_by_count":20,"area":"distill"},{"id":"2105.13792","title":"Early Exiting with Ensemble Internal Classifiers","created":"2021-05-28","cited_by_count":19,"area":null},{"id":"2203.08991","title":"AdapLeR: Speeding up Inference by Adaptive Length Reduction","created":"2022-03-16","cited_by_count":19,"area":null},{"id":"2306.10014","title":"Coaching a Teachable Student","created":"2023-06-16","cited_by_count":19,"area":"distill"},{"id":"2305.11170","title":"Efficient Prompting via Dynamic In-Context Learning","created":"2023-05-18","cited_by_count":18,"area":null},{"id":"2305.11916","title":"F-PABEE: Flexible-patience-based Early Exiting for Single-label and Multi-label text Classification Tasks","created":"2023-05-21","cited_by_count":18,"area":null},{"id":"2102.04887","title":"NewsBERT: Distilling Pre-trained Language Model for Intelligent News Application","created":"2021-02-09","cited_by_count":17,"area":"distill"},{"id":"2206.07699","title":"Write and Paint: Generative Vision-Language Models are Unified Modal Learners","created":"2022-06-15","cited_by_count":17,"area":"mllm"},{"id":"2110.08460","title":"A Short Study on Compressing Decoder-Based Language Models","created":"2021-10-16","cited_by_count":16,"area":null},{"id":"2503.04543","title":"Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model","created":"2025-03-06","cited_by_count":16,"area":"lr"},{"id":"2205.10036","title":"Exploring Extreme Parameter Compression for Pre-trained Language Models","created":"2022-05-20","cited_by_count":15,"area":null},{"id":"2306.06629","title":"GKD: A General Knowledge Distillation Framework for Large-scale Pre-trained Language Model","created":"2023-06-11","cited_by_count":15,"area":"distill"},{"id":"2103.11367","title":"ROSITA: Refined BERT cOmpreSsion with InTegrAted techniques","created":"2021-03-21","cited_by_count":14,"area":null},{"id":"2106.02435","title":"You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient","created":"2021-06-04","cited_by_count":14,"area":null},{"id":"2106.03441","title":"Attention Temperature Matters in Abstractive Summarization Distillation","created":"2021-06-07","cited_by_count":14,"area":null},{"id":"2101.00416","title":"Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting","created":"2021-01-02","cited_by_count":13,"area":null},{"id":"2205.12399","title":"Sparse Mixers: Combining MoE and Mixing to build a more efficient BERT","created":"2022-05-24","cited_by_count":12,"area":"moe"},{"id":"2205.15237","title":"VLUE: A Multi-Task Benchmark for Evaluating Vision-Language Models","created":"2022-05-30","cited_by_count":11,"area":"mllm"},{"id":"2306.14152","title":"Low-Rank Prune-And-Factorize for Language Model Compression","created":"2023-06-25","cited_by_count":11,"area":null},{"id":"2104.02704","title":"Blow the Dog Whistle: A Chinese Dataset for Cant Understanding with Common Sense and World Knowledge","created":"2021-04-06","cited_by_count":10,"area":null},{"id":"2409.17564","title":"General Compression Framework for Efficient Transformer Object Tracking","created":"2024-09-26","cited_by_count":10,"area":"distill"},{"id":"2410.12085","title":"Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning","created":"2024-10-15","cited_by_count":10,"area":null},{"id":"2112.15139","title":"Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks","created":"2021-12-30","cited_by_count":9,"area":null},{"id":"2206.02976","title":"Recall Distortion in Neural Network Pruning and the Undecayed Pruning Algorithm","created":"2022-06-07","cited_by_count":9,"area":null},{"id":"2507.01887","title":"MiCoTA: Bridging the Learnability Gap with Intermediate CoT and Teacher Assistants","created":"2025-07-02","cited_by_count":9,"area":"lr"},{"id":"2305.09098","title":"Weight-Inherited Distillation for Task-Agnostic BERT Compression","created":"2023-05-16","cited_by_count":8,"area":"distill"},{"id":"2211.04898","title":"Mask More and Mask Later: Efficient Pre-training of Masked Language Models by Disentangling the [MASK] Token","created":"2022-11-09","cited_by_count":7,"area":null},{"id":"2305.15033","title":"SmartTrim: Adaptive Tokens and Attention Pruning for Efficient Vision-Language Models","created":"2023-05-24","cited_by_count":7,"area":"mllm"},{"id":"2110.04711","title":"SuperShaper: Task-Agnostic Super Pre-training of BERT Models with Variable Hidden Dimensions","created":"2021-10-10","cited_by_count":6,"area":null},{"id":"2310.08797","title":"A Comparative Analysis of Task-Agnostic Distillation Methods for Compressing Transformer Language Models","created":"2023-10-13","cited_by_count":6,"area":null},{"id":"2509.22075","title":"CoSpaDi: Compressing LLMs via Calibration-Guided Sparse Dictionary Learning","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2103.01435","title":"Improved Techniques for Quantizing Deep Networks with Adaptive Bit-Widths","created":"2021-03-02","cited_by_count":5,"area":null},{"id":"2308.16475","title":"$\\rm SP^3$: Enhancing Structured Pruning via PCA Projection","created":"2023-08-31","cited_by_count":5,"area":null},{"id":"2309.01479","title":"Parameter and Computation Efficient Transfer Learning for Vision-Language Pre-trained Models","created":"2023-09-04","cited_by_count":5,"area":"mllm"},{"id":"2402.16918","title":"m2mKD: Module-to-Module Knowledge Distillation for Modular Transformers","created":"2024-02-26","cited_by_count":5,"area":"moe"},{"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":"2107.05377","title":"A Flexible Multi-Task Model for BERT Serving","created":"2021-07-12","cited_by_count":4,"area":null},{"id":"2306.02379","title":"Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient Inference","created":"2023-06-04","cited_by_count":4,"area":"distill"},{"id":"2503.20436","title":"Siformer: Feature-isolated Transformer for Efficient Skeleton-based Sign Language Recognition","created":"2025-03-26","cited_by_count":4,"area":null},{"id":"2201.12854","title":"Fast Monte-Carlo Approximation of the Attention Mechanism","created":"2022-01-30","cited_by_count":3,"area":null},{"id":"2202.12411","title":"TrimBERT: Tailoring BERT for Trade-offs","created":"2022-02-24","cited_by_count":3,"area":null},{"id":"2207.08006","title":"S4: a High-sparsity, High-performance AI Accelerator","created":"2022-07-16","cited_by_count":3,"area":null},{"id":"2211.08398","title":"Structured Knowledge Distillation Towards Efficient and Compact Multi-View 3D Detection","created":"2022-11-14","cited_by_count":3,"area":"distill"},{"id":"2302.01921","title":"Transformers in Action Recognition: A Review on Temporal Modeling","created":"2022-12-29","cited_by_count":3,"area":null},{"id":"2310.13183","title":"Breaking through Deterministic Barriers: Randomized Pruning Mask Generation and Selection","created":"2023-10-19","cited_by_count":3,"area":null},{"id":"2402.05948","title":"DE$^3$-BERT: Distance-Enhanced Early Exiting for BERT based on Prototypical Networks","created":"2024-02-03","cited_by_count":3,"area":"inference"},{"id":"2501.18596","title":"DeltaLLM: Compress LLMs with Low-Rank Deltas between Shared Weights","created":"2025-01-30","cited_by_count":3,"area":null},{"id":"2108.00775","title":"Self-supervised Answer Retrieval on Clinical Notes","created":"2021-08-02","cited_by_count":2,"area":null},{"id":"2307.11764","title":"Sensi-BERT: Towards Sensitivity Driven Fine-Tuning for Parameter-Efficient BERT","created":"2023-07-14","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":"2605.01374","title":"MTA: Multi-Granular Trajectory Alignment for Large Language Model Distillation","created":"2026-05-02","cited_by_count":2,"area":"alignment"},{"id":"2503.02053","title":"EPEE: Towards Efficient and Effective Foundation Models in Biomedicine","created":"2025-03-03","cited_by_count":1,"area":null},{"id":"2505.14592","title":"Adaptive Pruning of Deep Neural Networks for Resource-Aware Embedded Intrusion Detection on the Edge","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2509.18762","title":"When Long Helps Short: How Context Length in Supervised Fine-tuning Affects Behavior of Large Language Models","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2511.05476","title":"A Metamorphic Testing Perspective on Knowledge Distillation for Language Models of Code: Does the Student Deeply Mimic the Teacher?","created":"2025-11-07","cited_by_count":1,"area":"distill"},{"id":"2602.03563","title":"ACL: Aligned Contrastive Learning Improves BERT and Multi-exit BERT Fine-tuning","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2109.08627","title":"Classification-based Quality Estimation: Small and Efficient Models for Real-world Applications","created":"2021-09-17","cited_by_count":0,"area":null}],"next_cursor":"100"}