Kurt Keutzer

ODEt(ODEl): Shortcutting the Time and the Length in Diffusion and Flow Models for Faster Sampling WACV 2026 Segment Any Motion in Videos CVPR 2025 DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes CVPR 2025 K-Sort Arena: Efficient and Reliable Benchmarking for Generative Models via K-wise Human Preferences CVPR 2025 Sparse Video-Gen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity ICML 2025 QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache ICML 2025 SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity ICML 2025 Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks ICML 2025 SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference ICML 2025 MITRA-zh-eval: Using a Buddhist Chinese Language Evaluation Dataset to Assess Machine Translation and Evaluation Metrics NAACL 2025 UniDrive: Towards Universal Driving Perception Across Camera Configurations ICLR 2025 COAT: Compressing Optimizer states and Activations for Memory-Efficient FP8 Training ICLR 2025 Dobi-SVD: Differentiable SVD for LLM Compression and Some New Perspectives ICLR 2025 Looking Backward: Streaming Video-to-Video Translation with Feature Banks ICLR 2025 A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervision ICCV 2025 Squeezed Attention: Accelerating Long Context Length LLM Inference ACL 2025 StreamDiffusion: A Pipeline-level Solution for Real-Time Interactive Generation ICCV 2025 S*: Test Time Scaling for Code Generation EMNLP 2025 Bridging Viewpoint Gaps: Geometric Reasoning Boosts Semantic Correspondence CVPR 2025 Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting ICML 2024 LLoCO: Learning Long Contexts Offline EMNLP 2024 MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration EMNLP 2024 Sparse Refinement for Efficient High-Resolution Semantic Segmentation ECCV 2024 One Model is All You Need: ByT5-Sanskrit, a Unified Model for Sanskrit NLP Tasks EMNLP 2024 Mixture-of-Experts Meets Instruction Tuning: A Winning Combination for Large Language Models ICLR 2024 Efficient Deweahter Mixture-of-Experts with Uncertainty-Aware Feature-Wise Linear Modulation AAAI 2024 TinyAgent: Function Calling at the Edge EMNLP 2024 LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement ACL 2024 PromptCoT: Align Prompt Distribution via Adapted Chain-of-Thought CVPR 2024 Multitask Vision-Language Prompt Tuning WACV 2024 Aligning Large Multimodal Models with Factually Augmented RLHF ACL 2024 KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization NIPS 2024 Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment NIPS 2024 Sharpness-diversity tradeoff: improving flat ensembles with SharpBalance NIPS 2024 RoVi-Aug: Robot and Viewpoint Augmentation for Cross-Embodiment Robot Learning CORL 2024 Q-SLAM: Quadric Representations for Monocular SLAM CORL 2024 An LLM Compiler for Parallel Function Calling ICML 2024 SqueezeLLM: Dense-and-Sparse Quantization ICML 2024 Open-Vocabulary Point-Cloud Object Detection Without 3D Annotation CVPR 2023 Speculative Decoding with Big Little Decoder NIPS 2023 Large Language Models are Visual Reasoning Coordinators NIPS 2023 Towards Foundation Models for Scientific Machine Learning: Characterizing Scaling and Transfer Behavior NIPS 2023 NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers CVPR 2023 Simple and Effective Input Reformulations for Translation EMNLP 2023 Scaling Vision-Language Models with Sparse Mixture of Experts EMNLP 2023 NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection ICCV 2023 Q-Diffusion: Quantizing Diffusion Models ICCV 2023 SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection ICCV 2023 Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning ICCV 2023 QD-BEV : Quantization-aware View-guided Distillation for Multi-view 3D Object Detection ICCV 2023 Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection ICLR 2023 Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models ECCV 2022 Invariant Information Bottleneck for Domain Generalization AAAI 2022 Hessian-Aware Pruning and Optimal Neural Implant WACV 2022 Self-Supervised Pretraining Improves Self-Supervised Pretraining WACV 2022 How Much Can CLIP Benefit Vision-and-Language Tasks? ICLR 2022 MTTrans: Cross-Domain Object Detection with Mean Teacher Transformer ECCV 2022 Squeezeformer: An Efficient Transformer for Automatic Speech Recognition NIPS 2022 K-LITE: Learning Transferable Visual Models with External Knowledge NIPS 2022 A Fast Post-Training Pruning Framework for Transformers NIPS 2022 Staged Training for Transformer Language Models ICML 2022 Domain-Adaptive Text Classification with Structured Knowledge from Unlabeled Data IJCAI 2022 PreTraM: Self-Supervised Pre-training via Connecting Trajectory and Map ECCV 2022 What’s Hidden in a One-layer Randomly Weighted Transformer? EMNLP 2021 Prototypical Cross-Domain Self-Supervised Learning for Few-Shot Unsupervised Domain Adaptation CVPR 2021 Region Similarity Representation Learning ICCV 2021 Visual Transformers: Where Do Transformers Really Belong in Vision Models? ICCV 2021 Reservoir Transformers IJCNLP 2021 Reservoir Transformers ACL 2021 ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning AAAI 2021 ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentation AAAI 2021 I-BERT: Integer-only BERT Quantization ICML 2021 HAWQ-V3: Dyadic Neural Network Quantization ICML 2021 NovelD: A Simple yet Effective Exploration Criterion NIPS 2021 SelfAugment: Automatic Augmentation Policies for Self-Supervised Learning CVPR 2021 Learning Invariant Representations and Risks for Semi-Supervised Domain Adaptation CVPR 2021 Multi-Source Distilling Domain Adaptation AAAI 2020 Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT AAAI 2020 Train Big, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers ICML 2020 PowerNorm: Rethinking Batch Normalization in Transformers ICML 2020 ZeroQ: A Novel Zero Shot Quantization Framework CVPR 2020 Inefficiency of K-FAC for Large Batch Size Training AAAI 2020 An End-to-End Visual-Audio Attention Network for Emotion Recognition in User-Generated Videos AAAI 2020 HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks NIPS 2020 Large Batch Optimization for Deep Learning: Training BERT in 76 minutes ICLR 2020 Boundary thickness and robustness in learning models NIPS 2020 SqueezeBERT: What can computer vision teach NLP about efficient neural networks? EMNLP 2020 SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation ECCV 2020 HAWQ: Hessian AWare Quantization of Neural Networks With Mixed-Precision ICCV 2019 FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search CVPR 2019 ANODE: Unconditionally Accurate Memory-Efficient Gradients for Neural ODEs IJCAI 2019 Multi-source Domain Adaptation for Semantic Segmentation NIPS 2019 Trust Region Based Adversarial Attack on Neural Networks CVPR 2019 Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization Without Accessing Target Domain Data ICCV 2019 ANODEV2: A Coupled Neural ODE Framework NIPS 2019 CycleEmotionGAN: Emotional Semantic Consistency Preserved CycleGAN for Adapting Image Emotions AAAI 2019 Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions CVPR 2018 Regret Minimization for Partially Observable Deep Reinforcement Learning ICML 2018 Counterexample-Guided Data Augmentation IJCAI 2018 Affective Image Content Analysis: A Comprehensive Survey IJCAI 2018 Hessian-based Analysis of Large Batch Training and Robustness to Adversaries NIPS 2018 FireCaffe: Near-Linear Acceleration of Deep Neural Network Training on Compute Clusters CVPR 2016