Zhewei Yao

GRAD: Generalizing RAG Adaptation with Decoding ACL 2026 TAGQuant: Token-Aware Clustering for Group-Wise Quantization EACL 2026 CORD: Balancing COnsistency and Rank Distillation for Robust Retrieval-Augmented Generation NAACL 2025 Inference Scaling for Bridging Retrieval and Augmented Generation NAACL 2025 Optimizing Reasoning for Text-to-SQL with Execution Feedback ACL 2025 STUN: Structured-Then-Unstructured Pruning for Scalable MoE Pruning ACL 2025 SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation EMNLP 2025 DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routing AAAI 2024 Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation AAAI 2024 Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding NeurIPS 2024 ZeRO++: Extremely Efficient Collective Communication for Large Model Training ICLR 2024 DySR: Adaptive Super-Resolution via Algorithm and System Co-design ICLR 2023 Scaling Vision-Language Models with Sparse Mixture of Experts EMNLP 2023 Understanding Int4 Quantization for Language Models: Latency Speedup, Composability, and Failure Cases ICML 2023 DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale ICML 2022 Hessian-Aware Pruning and Optimal Neural Implant WACV 2022 How Much Can CLIP Benefit Vision-and-Language Tasks? ICLR 2022 XTC: Extreme Compression for Pre-trained Transformers Made Simple and Efficient NeurIPS 2022 ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers NeurIPS 2022 ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training ICML 2021 ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning AAAI 2021 HAWQ-V3: Dyadic Neural Network Quantization ICML 2021 I-BERT: Integer-only BERT Quantization ICML 2021 What’s Hidden in a One-layer Randomly Weighted Transformer? EMNLP 2021 A Statistical Framework for Low-bitwidth Training of Deep Neural Networks NeurIPS 2020 HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks NeurIPS 2020 Inefficiency of K-FAC for Large Batch Size Training AAAI 2020 MAF: Multimodal Alignment Framework for Weakly-Supervised Phrase Grounding EMNLP 2020 PowerNorm: Rethinking Batch Normalization in Transformers ICML 2020 Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT AAAI 2020 ZeroQ: A Novel Zero Shot Quantization Framework CVPR 2020 ANODEV2: A Coupled Neural ODE Framework NeurIPS 2019 HAWQ: Hessian AWare Quantization of Neural Networks With Mixed-Precision ICCV 2019 Trust Region Based Adversarial Attack on Neural Networks CVPR 2019 Hessian-based Analysis of Large Batch Training and Robustness to Adversaries NeurIPS 2018