Samir Khaki

7 papers · 2023–2025 · 5 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13)

Venues

ECCV (2) ICCV (2) CVPR (1) ICLR (1) ICML (1)

Top co-authors

Konstantinos N. Plataniotis (4) Zhijian Liu (3) Song Han (3) Ahmad Sajedi (3) Lucy Z. Liu (2) Junxian Guo (2) Kurt Keutzer (2) Ehsan Amjadian (2) Shang Yang (2) Yuri A. Lawryshyn (2)

Research topics

Machine Learning (4) Artificial Intelligence (3) Deep Learning (3) Application Areas (3) Core AI (3) Architectures (2) Optimization & Theory · Machine Learning (2) Computer Vision (1) Core Methods (1) Learning Types (1) Optimization & Theory · Deep Learning (1) Processing (1) Techniques (1)

Keywords

dataset distillation (2) synthetic data (2) image classification (2) multimodal learning (1) image synthesis (1) network pruning (1) efficient inference (1) vision-language model (1) computational cost (1) token pruning (1) sparse attention (1) contextual sparsity (1) one-shot pruning (1) discriminative feature (1) feature distillation (1) synthetic image (1) trainable parameter (1) trajectory matching (1) neural network (1) attention matching (1)

Papers

Emphasizing Discriminative Features for Dataset Distillation in Complex Scenarios CVPR 2025 SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity ICML 2025 SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference ICCV 2025 Data-to-Model Distillation: Data-Efficient Learning Framework ECCV 2024 Sparse Refinement for Efficient High-Resolution Semantic Segmentation ECCV 2024 The Need for Speed: Pruning Transformers with One Recipe ICLR 2024 DataDAM: Efficient Dataset Distillation with Attention Matching ICCV 2023