PPaperPicks

Kurt Keutzer

University of California, Berkeley, USA

44 papers at tracked venues · 35 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0003-3868-8501 ↗Google Scholar ↗Homepage ↗

Venues

NeurIPS ×9ICML ×8CVPR ×5EMNLP ×5ICLR ×5ACL ×3ICCV ×3ECCV ×2AAAI ×1ACM MM ×1MLSys ×1WACV ×1

Frequent coauthors

Coleman Hooper
DBLP profile ↗ORCID search ↗
×3
Chensheng Peng
DBLP profile ↗ORCID search ↗
×2
Qinsi Wang
DBLP profile ↗ORCID search ↗
×2
Haocheng Xi
DBLP profile ↗ORCID search ↗
×2
Lutfi Eren Erdogan
DBLP profile ↗ORCID search ↗
×2
Sehoon Kim
DBLP profile ↗ORCID search ↗
×2
Rongyu Zhang
DBLP profile ↗ORCID search ↗
×2
Denis A. Gudovskiy
DBLP profile ↗ORCID search ↗
×1
Qiyang Qian
DBLP profile ↗ORCID search ↗
×1
Hao Lu
DBLP profile ↗ORCID search ↗
×1
Zhikai Li
DBLP profile ↗ORCID search ↗
×1
Feng Liang
DBLP profile ↗ORCID search ↗
×1

Papers

  1. ODEt(ODEl): Shortcutting the Time and the Length in Diffusion and Flow Models for Faster Sampling
    WACV 2026 ·
    Denis A. Gudovskiy
    DBLP profile ↗ORCID search ↗
  2. A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervision
    ICCV 2025 ·
    Chensheng Peng
    DBLP profile ↗ORCID search ↗
  3. Angles Don't Lie: Unlocking Training‑Efficient RL Through the Model's Own Signals
    NeurIPS 2025 ·
    Qinsi Wang
    DBLP profile ↗ORCID search ↗
  4. Bridging Viewpoint Gaps: Geometric Reasoning Boosts Semantic Correspondence
    CVPR 2025 ·
    Qiyang Qian
    DBLP profile ↗ORCID search ↗
  5. COAT: Compressing Optimizer states and Activations for Memory-Efficient FP8 Training
    ICLR 2025 ·
    Haocheng Xi
    DBLP profile ↗ORCID search ↗
  6. DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes
    CVPR 2025 ·
    Chensheng Peng
    DBLP profile ↗ORCID search ↗
  7. Dobi-SVD: Differentiable SVD for LLM Compression and Some New Perspectives
    ICLR 2025 ·
    Qinsi Wang
    DBLP profile ↗ORCID search ↗
  8. DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving
    NeurIPS 2025 ·
    Hao Lu
    DBLP profile ↗ORCID search ↗
  9. K-Sort Arena: Efficient and Reliable Benchmarking for Generative Models via K-wise Human Preferences
    CVPR 2025 ·
    Zhikai Li
    DBLP profile ↗ORCID search ↗
  10. Looking Backward: Streaming Video-to-Video Translation with Feature Banks
    ICLR 2025 ·
    Feng Liang
    DBLP profile ↗ORCID search ↗
  11. Multipole Attention for Efficient Long Context Reasoning
    NeurIPS 2025 ·
    Coleman Hooper
    DBLP profile ↗ORCID search ↗
  12. Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks
    ICML 2025 ·
    Lutfi Eren Erdogan
    DBLP profile ↗ORCID search ↗
  13. QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache
    ICML 2025 ·
    Rishabh Tiwari
    DBLP profile ↗ORCID search ↗
  14. Radial Attention: 𝒪(n log n) Sparse Attention with Energy Decay for Long Video Generation
    NeurIPS 2025 ·
    Xingyang Li
    DBLP profile ↗ORCID search ↗
  15. S*: Test Time Scaling for Code Generation
    EMNLP 2025 ·
    Dacheng Li
    DBLP profile ↗ORCID search ↗
  16. STORM: Token-Efficient Long Video Understanding for Multimodal LLMs
    ICCV 2025 ·
    Jindong Jiang
    DBLP profile ↗ORCID search ↗
  17. Segment Any Motion in Videos
    CVPR 2025 ·
    Nan Huang
    DBLP profile ↗ORCID search ↗
  18. Sparse Video-Gen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
    ICML 2025 ·
    Haocheng Xi
    DBLP profile ↗ORCID search ↗
  19. Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
    NeurIPS 2025 ·
    Shuo Yang
    DBLP profile ↗ORCID search ↗
  20. SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity
    ICML 2025 ·
    Samir Khaki
    DBLP profile ↗ORCID search ↗
  21. SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
    ICML 2025 ·
    Yuan Zhang
    DBLP profile ↗ORCID search ↗
  22. Squeezed Attention: Accelerating Long Context Length LLM Inference
    ACL 2025 ·
    Coleman Richard Charles Hooper
    DBLP profile ↗ORCID search ↗
  23. StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation
    ICCV 2025 ·
    Akio Kodaira
    DBLP profile ↗ORCID search ↗
  24. UniDrive: Towards Universal Driving Perception Across Camera Configurations
    ICLR 2025 ·
    Ye Li
    DBLP profile ↗ORCID search ↗
  25. Why Do Multi-Agent LLM Systems Fail?
    NeurIPS 2025 ·
    Mert Cemri
    DBLP profile ↗ORCID search ↗
  26. Aligning Large Multimodal Models with Factually Augmented RLHF
    ACL 2024 ·
    Zhiqing Sun
    DBLP profile ↗ORCID search ↗
  27. An LLM Compiler for Parallel Function Calling
    ICML 2024 ·
    Sehoon Kim
    DBLP profile ↗ORCID search ↗
  28. Efficient Deweahter Mixture-of-Experts with Uncertainty-Aware Feature-Wise Linear Modulation
    AAAI 2024 ·
    Rongyu Zhang
    DBLP profile ↗ORCID search ↗
  29. Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment
    NeurIPS 2024 ·
    Yiheng Li
    DBLP profile ↗ORCID search ↗
  30. KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
    NeurIPS 2024 ·
    Coleman Hooper
    DBLP profile ↗ORCID search ↗
  31. LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement
    ACL 2024 ·
    Nicholas Lee
    DBLP profile ↗ORCID search ↗
  32. LLoCO: Learning Long Contexts Offline
    EMNLP 2024 ·
    Sijun Tan
    DBLP profile ↗ORCID search ↗
  33. MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration
    EMNLP 2024 ·
    Lin Xu
    DBLP profile ↗ORCID search ↗
  34. Magic-Me: Identity-Specific Video Customized Diffusion
    ECCV 2024 ·
    Ze Ma
    DBLP profile ↗ORCID search ↗
  35. Mixture-of-Experts Meets Instruction Tuning: A Winning Combination for Large Language Models
    ICLR 2024 ·
    Sheng Shen
    DBLP profile ↗ORCID search ↗
  36. One Model is All You Need: ByT5-Sanskrit, a Unified Model for Sanskrit NLP Tasks
    EMNLP 2024 ·
    Sebastian Nehrdich
    DBLP profile ↗ORCID search ↗
  37. PromptCoT: Align Prompt Distribution via Adapted Chain-of-Thought
    CVPR 2024 ·
    Junyi Yao
    DBLP profile ↗ORCID search ↗
  38. SLoRA: Scalable Serving of Thousands of LoRA Adapters
    MLSys 2024 ·
    Ying Sheng
    DBLP profile ↗ORCID search ↗
  39. Sharpness-diversity tradeoff: improving flat ensembles with SharpBalance
    NeurIPS 2024 ·
    Haiquan Lu
    DBLP profile ↗ORCID search ↗
  40. Sparse Refinement for Efficient High-Resolution Semantic Segmentation
    ECCV 2024 ·
    Zhijian Liu
    DBLP profile ↗ORCID search ↗
  41. Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting
    ICML 2024 ·
    Anthony Chen
    DBLP profile ↗ORCID search ↗
  42. SqueezeLLM: Dense-and-Sparse Quantization
    ICML 2024 ·
    Sehoon Kim
    DBLP profile ↗ORCID search ↗
  43. TinyAgent: Function Calling at the Edge
    EMNLP 2024 ·
    Lutfi Eren Erdogan
    DBLP profile ↗ORCID search ↗
  44. VeCAF: Vision-language Collaborative Active Finetuning with Training Objective Awareness
    ACM MM 2024 ·
    Rongyu Zhang
    DBLP profile ↗ORCID search ↗