{"total":167,"rows":[{"id":"2111.15366","title":"AI and the Everything in the Whole Wide World Benchmark","created":"2021-11-26","cited_by_count":349,"area":null},{"id":"2205.13147","title":"Matryoshka Representation Learning","created":"2022-05-26","cited_by_count":282,"area":null},{"id":"2206.02770","title":"Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts","created":"2022-06-06","cited_by_count":203,"area":"moe"},{"id":"2106.08962","title":"Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better","created":"2021-06-16","cited_by_count":154,"area":null},{"id":"2106.09647","title":"Deep Learning Through the Lens of Example Difficulty","created":"2021-06-17","cited_by_count":141,"area":null},{"id":"2306.05949","title":"Evaluating the Social Impact of Generative AI Systems in Systems and Society","created":"2023-06-09","cited_by_count":92,"area":null},{"id":"2310.07707","title":"MatFormer: Nested Transformer for Elastic Inference","created":"2023-10-11","cited_by_count":85,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2106.02890","title":"Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?","created":"2021-06-05","cited_by_count":75,"area":null},{"id":"2204.03632","title":"The Effects of Regularization and Data Augmentation are Class Dependent","created":"2022-04-07","cited_by_count":67,"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":"2106.11872","title":"Randomness In Neural Network Training: Characterizing The Impact of Tooling","created":"2021-06-22","cited_by_count":59,"area":null},{"id":"2111.13445","title":"How Well Do Sparse Imagenet Models Transfer?","created":"2021-11-26","cited_by_count":50,"area":null},{"id":"2110.03036","title":"The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation","created":"2021-10-06","cited_by_count":47,"area":null},{"id":"2307.02973","title":"Pruning vs Quantization: Which is Better?","created":"2023-07-06","cited_by_count":46,"area":null},{"id":"2202.03335","title":"Membership Inference Attacks and Defenses in Neural Network Pruning","created":"2022-02-07","cited_by_count":45,"area":"safety"},{"id":"2106.03225","title":"Efficient Lottery Ticket Finding: Less Data is More","created":"2021-06-06","cited_by_count":44,"area":null},{"id":"2205.13574","title":"Pruning has a disparate impact on model accuracy","created":"2022-05-26","cited_by_count":44,"area":null},{"id":"2406.06385","title":"Low-Rank Quantization-Aware Training for LLMs","created":"2024-06-10","cited_by_count":43,"area":null},{"id":"2407.03211","title":"How Does Quantization Affect Multilingual LLMs?","created":"2024-07-03","cited_by_count":43,"area":null},{"id":"2302.08476","title":"Counting Carbon: A Survey of Factors Influencing the Emissions of Machine Learning","created":"2023-02-16","cited_by_count":42,"area":null},{"id":"2203.04466","title":"The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks","created":"2022-03-09","cited_by_count":41,"area":null},{"id":"2205.03295","title":"The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanations","created":"2022-05-06","cited_by_count":41,"area":null},{"id":"2108.01250","title":"Your fairness may vary: Pretrained language model fairness in toxic text classification","created":"2021-08-03","cited_by_count":39,"area":null},{"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":"2209.15328","title":"Sparse Random Networks for Communication-Efficient Federated Learning","created":"2022-09-30","cited_by_count":32,"area":null},{"id":"2210.13738","title":"Pruning's Effect on Generalization Through the Lens of Training and Regularization","created":"2022-10-25","cited_by_count":31,"area":null},{"id":"2407.09141","title":"Accuracy is Not All You Need","created":"2024-07-12","cited_by_count":31,"area":null},{"id":"2207.10888","title":"FairGRAPE: Fairness-aware GRAdient Pruning mEthod for Face Attribute Classification","created":"2022-07-22","cited_by_count":30,"area":null},{"id":"2110.06282","title":"The Rich Get Richer: Disparate Impact of Semi-Supervised Learning","created":"2021-10-12","cited_by_count":28,"area":null},{"id":"2209.10015","title":"Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics","created":"2022-09-20","cited_by_count":26,"area":null},{"id":"2307.04138","title":"On The Impact of Machine Learning Randomness on Group Fairness","created":"2023-07-09","cited_by_count":26,"area":null},{"id":"2102.08329","title":"An Information-Theoretic Justification for Model Pruning","created":"2021-02-16","cited_by_count":25,"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":"2109.03300","title":"Hi, my name is Martha: Using names to measure and mitigate bias in generative dialogue models","created":"2021-09-07","cited_by_count":23,"area":null},{"id":"2109.04144","title":"Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning","created":"2021-09-09","cited_by_count":23,"area":null},{"id":"2312.01397","title":"Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective","created":"2023-12-03","cited_by_count":23,"area":null},{"id":"2310.04621","title":"Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences","created":"2023-10-06","cited_by_count":21,"area":null},{"id":"2201.08542","title":"Can Model Compression Improve NLP Fairness","created":"2022-01-21","cited_by_count":20,"area":null},{"id":"2201.09486","title":"Bias in Automated Speaker Recognition","created":"2022-01-24","cited_by_count":20,"area":null},{"id":"2205.12694","title":"Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models","created":"2022-05-25","cited_by_count":20,"area":null},{"id":"2306.16788","title":"Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging","created":"2023-06-29","cited_by_count":20,"area":null},{"id":"2102.07804","title":"Scaling Up Exact Neural Network Compression by ReLU Stability","created":"2021-02-15","cited_by_count":19,"area":null},{"id":"2107.13098","title":"A Tale Of Two Long Tails","created":"2021-07-27","cited_by_count":19,"area":null},{"id":"2110.15766","title":"NxMTransformer: Semi-Structured Sparsification for Natural Language Understanding via ADMM","created":"2021-10-28","cited_by_count":19,"area":null},{"id":"2312.05662","title":"Understanding the Effect of Model Compression on Social Bias in Large Language Models","created":"2023-12-09","cited_by_count":19,"area":null},{"id":"2502.07617","title":"Scaling Pre-training to One Hundred Billion Data for Vision Language Models","created":"2025-02-11","cited_by_count":19,"area":"mllm"},{"id":"2407.05694","title":"On the Limitations of Compute Thresholds as a Governance Strategy","created":"2024-07-08","cited_by_count":18,"area":null},{"id":"2111.01582","title":"LMdiff: A Visual Diff Tool to Compare Language Models","created":"2021-11-02","cited_by_count":17,"area":null},{"id":"2206.02633","title":"Towards Fair Federated Recommendation Learning: Characterizing the Inter-Dependence of System and Data Heterogeneity","created":"2022-05-30","cited_by_count":17,"area":null},{"id":"2106.08895","title":"Masked Training of Neural Networks with Partial Gradients","created":"2021-06-16","cited_by_count":16,"area":null},{"id":"2302.12578","title":"Fairness in Language Models Beyond English: Gaps and Challenges","created":"2023-02-24","cited_by_count":16,"area":null},{"id":"2405.15743","title":"Sparse maximal update parameterization: A holistic approach to sparse training dynamics","created":"2024-05-24","cited_by_count":16,"area":null},{"id":"2101.08430","title":"Generative Zero-shot Network Quantization","created":"2021-01-21","cited_by_count":15,"area":null},{"id":"2106.07849","title":"Simon Says: Evaluating and Mitigating Bias in Pruned Neural Networks with Knowledge Distillation","created":"2021-06-15","cited_by_count":15,"area":"distill"},{"id":"2211.02738","title":"Intriguing Properties of Compression on Multilingual Models","created":"2022-11-04","cited_by_count":15,"area":null},{"id":"2402.07745","title":"Predictive Churn with the Set of Good Models","created":"2024-02-12","cited_by_count":15,"area":null},{"id":"2408.04154","title":"The Data Addition Dilemma","created":"2024-08-08","cited_by_count":15,"area":null},{"id":"2304.04653","title":"Do We Train on Test Data? The Impact of Near-Duplicates on License Plate Recognition","created":"2023-04-10","cited_by_count":14,"area":null},{"id":"2201.01709","title":"The Effect of Model Compression on Fairness in Facial Expression Recognition","created":"2022-01-05","cited_by_count":13,"area":null},{"id":"2105.04144","title":"Transitioning from Real to Synthetic data: Quantifying the bias in model","created":"2021-05-10","cited_by_count":12,"area":null},{"id":"2110.08419","title":"Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding","created":"2021-10-16","cited_by_count":12,"area":null},{"id":"2304.05967","title":"Angler: Helping Machine Translation Practitioners Prioritize Model Improvements","created":"2023-04-12","cited_by_count":12,"area":null},{"id":"2401.01867","title":"Dataset Difficulty and the Role of Inductive Bias","created":"2024-01-03","cited_by_count":12,"area":null},{"id":"2110.13220","title":"Demystifying and Generalizing BinaryConnect","created":"2021-10-25","cited_by_count":11,"area":null},{"id":"2204.02426","title":"OccamNets: Mitigating Dataset Bias by Favoring Simpler Hypotheses","created":"2022-04-05","cited_by_count":11,"area":null},{"id":"2304.12622","title":"Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures","created":"2023-04-25","cited_by_count":11,"area":null},{"id":"2305.01645","title":"Distill or Annotate? Cost-Efficient Fine-Tuning of Compact Models","created":"2023-05-02","cited_by_count":11,"area":null},{"id":"2111.05454","title":"DP-REC: Private & Communication-Efficient Federated Learning","created":"2021-11-09","cited_by_count":10,"area":null},{"id":"2308.02060","title":"Accurate Neural Network Pruning Requires Rethinking Sparse Optimization","created":"2023-08-03","cited_by_count":10,"area":null},{"id":"2606.00206","title":"Quantized Reasoning Models Think They Need to Think Longer, but They Do Not","created":"2026-05-29","cited_by_count":10,"area":"lr"},{"id":"2104.14014","title":"Algorithmic Factors Influencing Bias in Machine Learning","created":"2021-04-28","cited_by_count":9,"area":null},{"id":"2205.10828","title":"What Do Compressed Multilingual Machine Translation Models Forget?","created":"2022-05-22","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":"2305.00927","title":"Cross-Institutional Transfer Learning for Educational Models: Implications for Model Performance, Fairness, and Equity","created":"2023-05-01","cited_by_count":9,"area":null},{"id":"2305.03355","title":"A Comprehensive Study on Dataset Distillation: Performance, Privacy, Robustness and Fairness","created":"2023-05-05","cited_by_count":9,"area":null},{"id":"2308.11840","title":"Compressed Models Decompress Race Biases: What Quantized Models Forget for Fair Face Recognition","created":"2023-08-23","cited_by_count":9,"area":null},{"id":"2406.17433","title":"Mind the Graph When Balancing Data for Fairness or Robustness","created":"2024-06-25","cited_by_count":9,"area":null},{"id":"2410.19503","title":"SWITCH: Studying with Teacher for Knowledge Distillation of Large Language Models","created":"2024-10-25","cited_by_count":9,"area":"distill"},{"id":"2102.07725","title":"Neural Network Compression for Noisy Storage Devices","created":"2021-02-15","cited_by_count":8,"area":null},{"id":"2201.07677","title":"Tiny, always-on and fragile: Bias propagation through design choices in on-device machine learning workflows","created":"2022-01-19","cited_by_count":8,"area":null},{"id":"2301.07966","title":"Getting Away with More Network Pruning: From Sparsity to Geometry and Linear Regions","created":"2023-01-19","cited_by_count":8,"area":null},{"id":"2208.13400","title":"Towards Explaining Demographic Bias through the Eyes of Face Recognition Models","created":"2022-08-29","cited_by_count":7,"area":null},{"id":"2310.04680","title":"The Cost of Down-Scaling Language Models: Fact Recall Deteriorates before In-Context Learning","created":"2023-10-07","cited_by_count":7,"area":null},{"id":"2310.13191","title":"Towards Robust Pruning: An Adaptive Knowledge-Retention Pruning Strategy for Language Models","created":"2023-10-19","cited_by_count":7,"area":null},{"id":"2310.18590","title":"Using Early Readouts to Mediate Featural Bias in Distillation","created":"2023-10-28","cited_by_count":7,"area":null},{"id":"2406.12837","title":"LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging","created":"2024-06-18","cited_by_count":7,"area":null},{"id":"2206.06479","title":"Robust Distillation for Worst-class Performance","created":"2022-06-13","cited_by_count":6,"area":"distill"},{"id":"2302.11187","title":"Debiased Distillation by Transplanting the Last Layer","created":"2023-02-22","cited_by_count":6,"area":"distill"},{"id":"2205.06404","title":"Fast Conditional Network Compression Using Bayesian HyperNetworks","created":"2022-05-13","cited_by_count":5,"area":null},{"id":"2211.04256","title":"Bridging Fairness and Environmental Sustainability in Natural Language Processing","created":"2022-11-08","cited_by_count":5,"area":null},{"id":"2211.11835","title":"Fairness Increases Adversarial Vulnerability","created":"2022-11-21","cited_by_count":5,"area":null},{"id":"2305.14864","title":"Just CHOP: Embarrassingly Simple LLM Compression","created":"2023-05-24","cited_by_count":5,"area":"lr"},{"id":"2306.11550","title":"Query Encoder Distillation via Embedding Alignment is a Strong Baseline Method to Boost Dense Retriever Online Efficiency","created":"2023-06-05","cited_by_count":5,"area":null},{"id":"2411.14984","title":"Adaptive Group Robust Ensemble Knowledge Distillation","created":"2024-11-22","cited_by_count":5,"area":"distill"},{"id":"2111.01306","title":"On the Current and Emerging Challenges of Developing Fair and Ethical AI Solutions in Financial Services","created":"2021-11-02","cited_by_count":4,"area":null},{"id":"2208.09684","title":"Combining Compressions for Multiplicative Size Scaling on Natural Language Tasks","created":"2022-08-20","cited_by_count":4,"area":"distill"},{"id":"2211.10285","title":"A Fair Loss Function for Network Pruning","created":"2022-11-18","cited_by_count":4,"area":null},{"id":"2211.13709","title":"Undesirable Biases in NLP: Addressing Challenges of Measurement","created":"2022-11-24","cited_by_count":4,"area":null},{"id":"2406.01757","title":"Position: Cracking the Code of Cascading Disparity Towards Marginalized Communities","created":"2024-06-03","cited_by_count":4,"area":null}],"next_cursor":"100"}