🧑‍🔬 Kurt Keutzer — all works

45 works · ← Kurt Keutzer

1. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size ↗arXiv (Cornell University) · no summary yetForrest Iandola et al.2016 · 6,402 citations
2. FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture SearchIEEE Computer Society Conference on Computer Vision and Pattern RecognitionBichen Wu, Xiaoliang Dai, Peizhao Zhang, et al.2018 · 1,405 citations
3. DenseNet: Implementing Efficient ConvNet Descriptor Pyramids ↗arXiv (Cornell University) · no summary yetForrest Iandola et al.2014 · 646 citations
4. Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetSheng Shen et al.2020 · 619 citations
5. HAWQ: Hessian AWare Quantization of Neural Networks With Mixed-Precision ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetZhen Dong et al.2019 · 551 citations
6. Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization Without Accessing Target Domain Data ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetXiangyu Yue et al.2019 · 378 citations
7. FireCaffe: near-linear acceleration of deep neural network training on compute clusters ↗arXiv:1511.00175 · no summary yetForrest N. Iandola et al.2015 · 310 citations
8. KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache QuantizationConference on Neural Information Processing Systems (NeurIPS)Coleman Hooper, Sehoon Kim, Hiva Mohammadzadeh, et al.2024 · 294 citations
9. Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetColorado Reed et al.2023 · 248 citations
10. How Much Can CLIP Benefit Vision-and-Language Tasks? ↗arXiv (Cornell University) · no summary yetSheng Shen et al.2021 · 220 citations
11. Multi-Source Distilling Domain Adaptation ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetSicheng Zhao et al.2020 · 215 citations
12. ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetZhewei Yao et al.2021 · 212 citations
13. Aligning Large Multimodal Models with Factually Augmented RLHFarXiv:2309.14525Zhiqing Sun, Sheng Shen, Shengcao Cao, et al.2023 · 176 citations
14. SqueezeLLM: Dense-and-Sparse QuantizationarXiv:2306.07629Sehoon Kim, Coleman Hooper, Amir Gholami, et al.2023 · 170 citations
15. Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetXiangyu Yue et al.2021 · 163 citations
16. Aligning Large Multimodal Models with Factually Augmented RLHF ↗Findings of the Association for Computational Linguistics: ACL 2024 · no summary yetZhiqing Sun et al.2024 · 136 citations
17. Train Big, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers ↗International Conference on Machine Learning · no summary yetZhuohan Li et al.2020 · 133 citations
18. I-BERT: Integer-only BERT QuantizationInternational Conference on Machine Learning (ICML)Sehoon Kim, Amir Gholami, Zhewei Yao, et al.2021 · 122 citations
19. ImageNet Training in MinutesarXiv:1709.05011Yang You, Zhao Zhang, Cho-Jui Hsieh, et al.2017 · 112 citations
20. Self-Supervised Pretraining Improves Self-Supervised Pretraining ↗IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · no summary yetColorado Reed et al.2022 · 108 citations
21. Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization ↗MLSys 2020 · no summary yetParas Jain et al.2019 · 98 citations
22. ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentation ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetSicheng Zhao et al.2021 · 97 citations
23. Visual Transformers: Where Do Transformers Really Belong in Vision Models? ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetBichen Wu et al.2021 · 96 citations
24. Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers ↗arXiv (Cornell University) · no summary yetZhuohan Li et al.2020 · 93 citations
25. Why Do Multi-Agent LLM Systems Fail?arXiv:2503.13657Mert Cemri, Melissa Z. Pan, Shuyi Yang, et al.2025 · 89 citations
26. Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetBo Li et al.2021 · 88 citations
27. Region Similarity Representation Learning ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetTete Xiao et al.2021 · 84 citations
28. S-LoRA: Serving Thousands of Concurrent LoRA AdaptersMLSys 2024Ying Sheng, Shiyi Cao, Dacheng Li, et al.2023 · 80 citations
29. Scaling Vision-Language Models with Sparse Mixture of Experts ↗Findings of the Association for Computational Linguistics: EMNLP 2023 · no summary yetSheng Shen et al.2023 · 70 citations
30. Multitask Vision-Language Prompt Tuning ↗IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · no summary yetSheng Shen et al.2022 · 65 citations
31. Trust Region Based Adversarial Attack on Neural Networks ↗arXiv:1812.06371 · CVPR 2019 · no summary yetZhewei Yao et al.2018 · 65 citations
32. K-LITE: Learning Transferable Visual Models with External Knowledge ↗neural information processing systems · no summary yetSheng Shen et al.2022 · 61 citations
33. Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity ↗arXiv:2502.01776 · no summary yetHaocheng Xi et al.2025 · 56 citations
34. CycleEmotionGAN: Emotional Semantic Consistency Preserved CycleGAN for Adapting Image Emotions ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetSicheng Zhao et al.2019 · 54 citations
35. Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation ↗arXiv:2505.18875 · no summary yetShuo Yang et al.2025 · 44 citations
36. SelfAugment: Automatic Augmentation Policies for Self-Supervised Learning ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetColorado Reed et al.2021 · 41 citations
37. S*: Test Time Scaling for Code Generation ↗Findings of the Association for Computational Linguistics: EMNLP 2025 · no summary yetDacheng Li et al.2025 · 26 citations
38. Large Language Models are Visual Reasoning Coordinators ↗neural information processing systems · no summary yetLiangyu Chen et al.2023 · 25 citations
39. Radial Attention: O(n n) Sparse Attention with Energy Decay for Long Video Generation ↗arXiv (Cornell University) · no summary yetLi, Xingyang et al.2025 · 23 citations
40. Learning Adaptive Parallel Reasoning with Language Models ↗arXiv (Cornell University) · no summary yetJiayi Pan et al.2025 · 15 citations
41. MITRA-zh-eval: Using a Buddhist Chinese Language Evaluation Dataset to Assess Machine Translation and Evaluation Metrics ↗Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities · no summary yetSebastian Nehrdich et al.2025 · 4 citations
42. Prior Knowledge-Guided Attention in Self-Supervised Vision Transformers ↗arXiv (Cornell University) · no summary yetMiao, Kevin et al.2022 · 4 citations
43. Radial Attention: O(n n) Sparse Attention with Energy Decay for Long Video Generation ↗neural information processing systems · no summary yetXingyang Li et al.2025 · 3 citations
44. FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution ↗arXiv:2608.16157 · no summary yetShuo Yang et al.2026 · 1 citation
45. Descriptors on a plane!Stitch to large plane!~25 Resolutions!Input Image! ↗no summary yetForrest Iandola et al.2016

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/kurt-keutzer/works/