KK
Kurt Keutzer
cs.CVcs.LGcs.AIcs.CLstat.MLcs.DCcs.ROcs.MMeess.IVcs.NE
On Valency
published · living versionsW_ssszqkn3·v1 · currentpublished
DenseNet: Implementing Efficient ConvNet Descriptor Pyramids
with Forrest Iandola, Matt Moskewicz, Sergey Karayev, Ross Girshick +1
1 version
Preprints & journals
203 papers in the corpus · 2012–2026LLM Inference in a Flash!2609.16161v1 · Sebastian Zhao, Minseo Kim, Coleman Hooper et al.2026 · 0 citationsarXiv
Agentic Test-Time Scaling for WebAgents2602.12276v2 · Nicholas Lee, Lutfi Eren Erdogan, Chris Joseph John et al.2026 · 0 citationsarXiv
FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution2608.16157v1 · Shuo Yang, Xiaoze Fan, Melissa Pan et al.2026 · 0 citationsarXiv
SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing2603.08982v2 · Xuanyi Zhou, Qiuyang Mang, Shuo Yang et al.2026 · 0 citationsarXiv
Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility2505.18521v2 · Yiheng Li, Feng Liang, Dan Kondratyuk et al.2025 · 0 citationsarXiv
Residual Context Diffusion Language Models2601.22954v2 · Yuezhou Hu, Harman Singh, Monishwaran Maheswaran et al.2026 · 0 citationsarXiv
SEED: Targeted Data Selection by Weighted Independent Set2605.15691v2 · Yuan Zhang, Lifeng Guo, Junwen Pan et al.2026 · 0 citationsarXiv
Learning, Fast and Slow: Towards LLMs That Adapt Continually2605.12484v2 · Rishabh Tiwari, Kusha Sareen, Lakshya A Agrawal et al.2026 · 0 citationsarXiv
Proxy3D: Efficient 3D Representations for Vision-Language Models via Semantic Clustering and Alignment2605.08064v1 · Jerry Jiang, Haowen Sun, Denis Gudovskiy et al.2026 · 0 citationsarXiv
Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization2602.02958v5 · Haocheng Xi, Shuo Yang, Yilong Zhao et al.2026 · 0 citationsarXiv
R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation2506.07826v2 · William Ljungbergh, Bernardo Taveira, Wenzhao Zheng et al.2025 · 0 citationsarXiv
SciML Agents: Write the Solver, Not the Solution2509.09936v1 · Saarth Gaonkar, Xiang Zheng, Haocheng Xi et al.2025 · 0 citationsNeurIPS 2025 Math-AI Workshop
LoSA: Locality Aware Sparse Attention for Block-Wise Diffusion Language Models2604.12056v1 · Haocheng Xi, Harman Singh, Yuezhou Hu et al.2026 · 0 citationsarXiv
Flash-KMeans: Fast and Memory-Efficient Exact K-Means2603.09229v2 · Shuo Yang, Haocheng Xi, Yilong Zhao et al.2026 · 0 citationsarXiv
Squeeze Evolve: Unified Multi-Model Orchestration for Verifier-Free Evolution2604.07725v2 · Monishwaran Maheswaran, Leon Lakhani, Zhongzhu Zhou et al.2026 · 0 citationsarXiv
QFT: Quantized Full-parameter Tuning of LLMs with Affordable Resources2310.07147v3 · Zhikai Li, Xiaoxuan Liu, Banghua Zhu et al.2023 · 1 citationarXiv
EvoX: Meta-Evolution for Automated Discovery2602.23413v2 · Shu Liu, Shubham Agarwal, Monishwaran Maheswaran et al.2026 · 1 citationarXiv
Reward Under Attack: Analyzing the Robustness and Hackability of Process Reward Models2603.06621v1 · Rishabh Tiwari, Aditya Tomar, Udbhav Bamba et al.2026 · 0 citationsarXiv
K-Sort Eval: Efficient Preference Evaluation for Visual Generation via Corrected VLM-as-a-Judge2602.09411v1 · Zhikai Li, Jiatong Li, Xuewen Liu et al.2026 · 0 citationsarXiv
Simple and Effective Input Reformulations for Translation2311.06696v1 · Brian Yu, Hansen Lillemark, Kurt Keutzer2023 · 0 citationsarXiv
Multipole Attention for Efficient Long Context Reasoning2506.13059v2 · Coleman Hooper, Sebastian Zhao, Luca Manolache et al.2025 · 0 citationsNeurIPS 2025
Beyond Next-Token Prediction: A Performance Characterization of Diffusion versus Autoregressive Language Models2510.04146v2 · Minseo Kim, Coleman Hooper, Aditya Tomar et al.2025 · 0 citationsarXiv
Arbitrage: Efficient Reasoning via Advantage-Aware Speculation2512.05033v2 · Monishwaran Maheswaran, Rishabh Tiwari, Yuezhou Hu et al.2025 · 0 citationsarXiv
Radial Attention: $O(n\log n)$ Sparse Attention with Energy Decay for Long Video Generation2506.19852v2 · Xingyang Li, Muyang Li, Tianle Cai et al.2025 · 0 citationsarXiv
Squeezed Attention: Accelerating Long Context Length LLM Inference2411.09688v3 · Coleman Hooper, Sehoon Kim, Hiva Mohammadzadeh et al.2024 · 6 citationsACL 2025
Angles Don't Lie: Unlocking Training-Efficient RL Through the Model's Own Signals2506.02281v2 · Qinsi Wang, Jinghan Ke, Hancheng Ye et al.2025 · 0 citationsarXiv
Learning Adaptive Parallel Reasoning with Language Models2504.15466v2 · Jiayi Pan, Xiuyu Li, Long Lian et al.2025 · 0 citationsarXiv
DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes2411.11921v2 · Chensheng Peng, Chengwei Zhang, Yixiao Wang et al.2024 · 21 citationsarXiv
A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervision2412.00623v3 · Chensheng Peng, Ido Sobol, Masayoshi Tomizuka et al.2024 · 0 citationsarXiv
UniDrive: Towards Universal Driving Perception Across Camera Configurations2410.13864v2 · Ye Li, Wenzhao Zheng, Xiaonan Huang et al.2024 · 0 citationsarXiv
ETS: Efficient Tree Search for Inference-Time Scaling2502.13575v2 · Coleman Hooper, Sehoon Kim, Suhong Moon et al.2025 · 0 citationsarXiv
SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference2410.04417v4 · Yuan Zhang, Chun-Kai Fan, Junpeng Ma et al.2024 · 1 citationarXiv
KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization2401.18079v6 · Coleman Hooper, Sehoon Kim, Hiva Mohammadzadeh et al.2024 · 59 citationsarXiv
GeoDrive: 3D Geometry-Informed Driving World Model with Precise Action Control2505.22421v2 · Anthony Chen, Wenzhao Zheng, Yida Wang et al.2025 · 0 citationsarXiv
Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity2502.01776v2 · Haocheng Xi, Shuo Yang, Yilong Zhao et al.2025 · 1 citationarXiv
Segment Any Motion in Videos2503.22268v2 · Nan Huang, Wenzhao Zheng, Chenfeng Xu et al.2025 · 5 citationsarXiv
K-Sort Arena: Efficient and Reliable Benchmarking for Generative Models via K-wise Human Preferences2408.14468v2 · Zhikai Li, Xuewen Liu, Dongrong Joe Fu et al.2024 · 1 citationarXiv
S*: Test Time Scaling for Code Generation2502.14382v1 · Dacheng Li, Shiyi Cao, Chengkun Cao et al.2025 · 4 citationsarXiv
Looking Backward: Streaming Video-to-Video Translation with Feature Banks2405.15757v3 · Feng Liang, Akio Kodaira, Chenfeng Xu et al.2024 · 0 citationsarXiv
QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache2502.10424v1 · Rishabh Tiwari, Haocheng Xi, Aditya Tomar et al.2025 · 0 citationsarXiv
COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training2410.19313v3 · Haocheng Xi, Han Cai, Ligeng Zhu et al.2024 · 0 citationsarXiv
Dobi-SVD: Differentiable SVD for LLM Compression and Some New Perspectives2502.02723v1 · Qinsi Wang, Jinghan Ke, Masayoshi Tomizuka et al.2025 · 0 citationsarXiv
DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving2412.09043v1 · Hao Lu, Tianshuo Xu, Wenzhao Zheng et al.2024 · 2 citationsarXiv
Driv3R: Learning Dense 4D Reconstruction for Autonomous Driving2412.06777v1 · Xin Fei, Wenzhao Zheng, Yueqi Duan et al.2024 · 0 citationsarXiv
MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration2311.08562v3 · Lin Xu, Zhiyuan Hu, Daquan Zhou et al.2023 · 15 citationsarXiv
Q-SLAM: Quadric Representations for Monocular SLAM2403.08125v2 · Chensheng Peng, Chenfeng Xu, Yue Wang et al.2024 · 1 citationarXiv
Stochastic Communication Avoidance for Recommendation Systems2411.01611v1 · Lutfi Eren Erdogan, Vijay Anand Raghava Kanakagiri, Kurt Keutzer et al.2024 · 0 citationsConference on Artificial Intelligence (IEEE CAI) 2024
Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment2406.12303v2 · Yiheng Li, Heyang Jiang, Akio Kodaira et al.2024 · 1 citationarXiv
DQRM: Deep Quantized Recommendation Models2410.20046v1 · Yang Zhou, Zhen Dong, Ellick Chan et al.2024 · 0 citationsarXiv
TinyAgent: Function Calling at the Edge2409.00608v3 · Lutfi Eren Erdogan, Nicholas Lee, Siddharth Jha et al.2024 · 20 citationsarXiv
Career total: 625 works. 203 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.