conftrace_

Kanghyun Choi

4 papers · 2021–2025 · 4 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 · Bronze

Venues

AAAI (1) CVPR (1) ICML (1) NeurIPS (1)

Top co-authors

Noseong Park (4) Jinho Lee (4) Dain Kwon (2) SunJong Park (2) Youngsok Kim (2) Jonghyun Choi (2) Deokki Hong (2) Hyeyoon Lee (2) Mayoore Selvarasa Jaiswal (1) Kyuyeun Kim (1)

Research topics

Deep Learning (3) Machine Learning (3) Application Areas (3) Artificial Intelligence (2) Core AI (2) Models (2) Architectures (1) Learning Types (1) Optimization & Theory · Deep Learning (1) Optimization & Theory · Machine Learning (1) Techniques (1)

Keywords

model quantization (2) knowledge distillation (2) model compression (2) vision transformer (1) adversarial robustness (1) adversarial training (1) data-free learning (1) neural network optimization (1) synthetic data generation (1) generative model (1) edge computing (1) attention alignment (1) attention distillation (1) data-free quantization (1) surrogate dataset (1) inter-head attention (1) pretrained weight (1) data-free (1) neural network compression (1) zero-shot learning (1)

Papers

MimiQ: Low-Bit Data-Free Quantization of Vision Transformers with Encouraging Inter-Head Attention Similarity AAAI 2025 DataFreeShield: Defending Adversarial Attacks without Training Data ICML 2024 It's All in the Teacher: Zero-Shot Quantization Brought Closer to the Teacher CVPR 2022 Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples NeurIPS 2021