model accuracy

Effective Interplay between Sparsity and Quantization: From Theory to Practice ICLR 2025 LLM Evaluate: An Industry-Focused Evaluation Tool for Large Language Models COLING 2025 MEET: Towards Memory-Efficient Temporal Sparse Deep Neural Networks CVPR 2025 NEAR: A Training-Free Pre-Estimator of Machine Learning Model Performance ICLR 2025 Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy ICLR 2025 AMLB: an AutoML Benchmark JMLR 2024 Data, Data Everywhere: A Guide for Pretraining Dataset Construction EMNLP 2024 Delving into Differentially Private Transformer ICML 2024 Fairness without Harm: An Influence-Guided Active Sampling Approach NeurIPS 2024 NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes NeurIPS 2024 Partially Interpretable Models with Guarantees on Coverage and Accuracy ALT 2024 Practical Hybrid Gradient Compression for Federated Learning Systems IJCAI 2024 Quilt: Robust Data Segment Selection against Concept Drifts AAAI 2024 The Entropy Enigma: Success and Failure of Entropy Minimization ICML 2024 Adversarial Amendment is the Only Force Capable of Transforming an Enemy into a Friend IJCAI 2023 A Mixed-Precision Quantization Method without Accuracy Degradation Using Semilayers ACML 2023 Beyond probability partitions: Calibrating neural networks with semantic aware grouping NeurIPS 2023 Deconstructing Distributions: A Pointwise Framework of Learning ICLR 2023 FreeREA: Training-Free Evolution-Based Architecture Search WACV 2023 Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement ICCV 2023 Characterizing the Efficiency vs. Accuracy Trade-off for Long-Context NLP Models ACL 2022 How Much Does Input Data Type Impact Final Face Model Accuracy? CVPR 2022 Iterative Stratified Testing and Measurement for Automated Model Updates EMNLP 2022 Mismatched No More: Joint Model-Policy Optimization for Model-Based RL NeurIPS 2022 Secure Quantized Training for Deep Learning ICML 2022