Tijmen Blankevoort

69 papers A* 16A 2Journal 40Unranked 11

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Data Repetition Beats Data Scaling in Long-CoT Supervised Fine-Tuning. CoRR Dawid Jan Kopiczko, Sagar Vaze, Tijmen Blankevoort, Yuki M. Asano
2026	J	`jnl`	Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery. CoRR Meng Xin, Sweta Priyadarshi, Jingyu Xin, Bilal Kartal, Aditya Vavre, Asma Kuriparambil Thekkumpate, Zijia Chen, Ameya Sunil Mahabaleshwarkar, Ido Shahaf, Akhiad Bercovich, Kinjal Patel, Suguna Varshini Velury, Chenjie Luo, Zhiyu Cheng, Jenny Chen, Chen-Han Yu, Wei Ping, Oleg Rybakov, Nima Tajbakhsh, Oluwatobi Olabiyi, Dusan Stosic, Di Wu, Song Han, Eric Chung, Sharath Turuvekere Sreenivas, Bryan Catanzaro, Yoshi Suhara, Tijmen Blankevoort, Huizi Mao
2025	A*	`conf`	Bitune: Leveraging Bidirectional Attention to Improve Decoder-Only LLMs. EMNLP Dawid Jan Kopiczko, Tijmen Blankevoort, Yuki M. Asano
2025	J	`jnl`	Elastic ViTs from Pretrained Models without Retraining. CoRR Walter Simoncini, Michael Dorkenwald, Tijmen Blankevoort, Cees G. M. Snoek, Yuki M. Asano
2025	J	`jnl`	ParetoQ: Scaling Laws in Extremely Low-bit LLM Quantization. CoRR Zechun Liu, Changsheng Zhao, Hanxian Huang, Sijia Chen, Jing Zhang, Jiawei Zhao, Scott Roy, Lisa Jin, Yunyang Xiong, Yangyang Shi, Lin Xiao, Yuandong Tian, Bilge Soran, Raghuraman Krishnamoorthi, Tijmen Blankevoort, Vikas Chandra
2025	A*	`conf`	SpinQuant: LLM Quantization with Learned Rotations. ICLR Zechun Liu, Changsheng Zhao, Igor Fedorov, Bilge Soran, Dhruv Choudhary, Raghuraman Krishnamoorthi, Vikas Chandra, Yuandong Tian, Tijmen Blankevoort
2024	J	`jnl`	Bitune: Bidirectional Instruction-Tuning. CoRR Dawid Jan Kopiczko, Tijmen Blankevoort, Yuki M. Asano
2024	J	`jnl`	GPTVQ: The Blessing of Dimensionality for LLM Quantization. CoRR Mart van Baalen, Andrey Kuzmin, Markus Nagel, Peter Couperus, Cédric Bastoul, Eric Mahurin, Tijmen Blankevoort, Paul N. Whatmough
2024	A	`conf`	InterroGate: Learning to Share, Specialize, and Prune Representations for Multi-task Learning. BMVC Babak Ehteshami Bejnordi, Gaurav Kumar, Amelie Royer, Christos Louizos, Tijmen Blankevoort, Mohsen Ghafoorian
2024	J	`jnl`	InterroGate: Learning to Share, Specialize, and Prune Representations for Multi-task Learning. CoRR Babak Ehteshami Bejnordi, Gaurav Kumar, Amelie Royer, Christos Louizos, Tijmen Blankevoort, Mohsen Ghafoorian
2024	J	`jnl`	Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations. CoRR Igor Fedorov, Kate Plawiak, Lemeng Wu, Tarek Elgamal, Naveen Suda, Eric Smith, Hongyuan Zhan, Jianfeng Chi, Yuriy Hulovatyy, Kimish Patel, Zechun Liu, Changsheng Zhao, Yangyang Shi, Tijmen Blankevoort, Mahesh Pasupuleti, Bilge Soran, Zacharie Delpierre Coudert, Rachad Alao, Raghuraman Krishnamoorthi, Vikas Chandra
2024	J	`jnl`	SpinQuant: LLM quantization with learned rotations. CoRR Zechun Liu, Changsheng Zhao, Igor Fedorov, Bilge Soran, Dhruv Choudhary, Raghuraman Krishnamoorthi, Vikas Chandra, Yuandong Tian, Tijmen Blankevoort
2024	A*	`conf`	The LLM Surgeon. ICLR Tycho F. A. van der Ouderaa, Markus Nagel, Mart van Baalen, Tijmen Blankevoort
2024	J	`jnl`	Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding. CoRR Benjamin Bergner, Andrii Skliar, Amelie Royer, Tijmen Blankevoort, Yuki M. Asano, Babak Ehteshami Bejnordi
2024	A*	`conf`	VeRA: Vector-based Random Matrix Adaptation. ICLR Dawid Jan Kopiczko, Tijmen Blankevoort, Yuki M. Asano
2023	—	`conf`	A Practical Mixed Precision Algorithm for Post-Training Quantization. BMVC Workshop Nilesh Prasad Pandey, Markus Nagel, Mart van Baalen, Yin Huang, Chirag Patel, Tijmen Blankevoort
2023	J	`jnl`	A Practical Mixed Precision Algorithm for Post-Training Quantization. CoRR Nilesh Prasad Pandey, Markus Nagel, Mart van Baalen, Yin Huang, Chirag Patel, Tijmen Blankevoort
2023	—	`conf`	Efficient Neural PDE-Solvers using Quantization Aware Training. ICCV (Workshops) Winfried van den Dool, Tijmen Blankevoort, Max Welling, Yuki M. Asano
2023	J	`jnl`	Efficient Neural PDE-Solvers using Quantization Aware Training. CoRR Winfried van den Dool, Tijmen Blankevoort, Max Welling, Yuki M. Asano
2023	J	`jnl`	FP8 versus INT8 for efficient deep learning inference. CoRR Mart van Baalen, Andrey Kuzmin, Suparna S. Nair, Yuwei Ren, Eric Mahurin, Chirag Patel, Sundar Subramanian, Sanghyuk Lee, Markus Nagel, Joseph Soriaga, Tijmen Blankevoort
2023	J	`jnl`	MSViT: Dynamic Mixed-Scale Tokenization for Vision Transformers. CoRR Jakob Drachmann Havtorn, Amelie Royer, Tijmen Blankevoort, Babak Ehteshami Bejnordi
2023	—	`conf`	MSViT: Dynamic Mixed-scale Tokenization for Vision Transformers. ICCV (Workshops) Jakob Drachmann Havtorn, Amélie Royer, Tijmen Blankevoort, Babak Ehteshami Bejnordi
2023	A*	`conf`	Pruning vs Quantization: Which is Better? NeurIPS Andrey Kuzmin, Markus Nagel, Mart van Baalen, Arash Behboodi, Tijmen Blankevoort
2023	J	`jnl`	Pruning vs Quantization: Which is Better? CoRR Andrey Kuzmin, Markus Nagel, Mart van Baalen, Arash Behboodi, Tijmen Blankevoort
2023	—	`conf`	QBitOpt: Fast and Accurate Bitwidth Reallocation during Training. ICCV (Workshops) Jorn Peters, Marios Fournarakis, Markus Nagel, Mart van Baalen, Tijmen Blankevoort
2023	J	`jnl`	QBitOpt: Fast and Accurate Bitwidth Reallocation during Training. CoRR Jorn Peters, Marios Fournarakis, Markus Nagel, Mart van Baalen, Tijmen Blankevoort
2023	A*	`conf`	Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing. NeurIPS Yelysei Bondarenko, Markus Nagel, Tijmen Blankevoort
2023	J	`jnl`	Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing. CoRR Yelysei Bondarenko, Markus Nagel, Tijmen Blankevoort
2023	J	`jnl`	Revisiting Single-gated Mixtures of Experts. CoRR Amelie Royer, Ilia Karmanov, Andrii Skliar, Babak Ehteshami Bejnordi, Tijmen Blankevoort
2023	A*	`conf`	Scalarization for Multi-Task and Multi-Domain Learning at Scale. NeurIPS Amelie Royer, Tijmen Blankevoort, Babak Ehteshami Bejnordi
2023	J	`jnl`	Scalarization for Multi-Task and Multi-Domain Learning at Scale. CoRR Amelie Royer, Tijmen Blankevoort, Babak Ehteshami Bejnordi
2023	J	`jnl`	The LLM Surgeon. CoRR Tycho F. A. van der Ouderaa, Markus Nagel, Mart van Baalen, Yuki M. Asano, Tijmen Blankevoort
2023	J	`jnl`	VeRA: Vector-based Random Matrix Adaptation. CoRR Dawid Jan Kopiczko, Tijmen Blankevoort, Yuki Markus Asano
2022	—	`conf`	Cyclical Pruning for Sparse Neural Networks. CVPR Workshops Suraj Srinivas, Andrey Kuzmin, Markus Nagel, Mart van Baalen, Andrii Skliar, Tijmen Blankevoort
2022	J	`jnl`	Cyclical Pruning for Sparse Neural Networks. CoRR Suraj Srinivas, Andrey Kuzmin, Markus Nagel, Mart van Baalen, Andrii Skliar, Tijmen Blankevoort
2022	A*	`conf`	FP8 Quantization: The Power of the Exponent. NeurIPS Andrey Kuzmin, Mart van Baalen, Yuwei Ren, Markus Nagel, Jorn Peters, Tijmen Blankevoort
2022	J	`jnl`	FP8 Quantization: The Power of the Exponent. CoRR Andrey Kuzmin, Mart van Baalen, Yuwei Ren, Markus Nagel, Jorn Peters, Tijmen Blankevoort
2022	J	`jnl`	Neural Network Quantization with AI Model Efficiency Toolkit (AIMET). CoRR Sangeetha Siddegowda, Marios Fournarakis, Markus Nagel, Tijmen Blankevoort, Chirag Patel, Abhijit Khobare
2022	A*	`conf`	Overcoming Oscillations in Quantization-Aware Training. ICML Markus Nagel, Marios Fournarakis, Yelysei Bondarenko, Tijmen Blankevoort
2022	J	`jnl`	Overcoming Oscillations in Quantization-Aware Training. CoRR Markus Nagel, Marios Fournarakis, Yelysei Bondarenko, Tijmen Blankevoort
2022	A	`conf`	Revisiting single-gated Mixtures of Experts. BMVC Amelie Royer, Ilia Karmanov, Andrii Skliar, Babak Ehteshami Bejnordi, Tijmen Blankevoort
2022	—	`conf`	Simple and Efficient Architectures for Semantic Segmentation. CVPR Workshops Dushyant Mehta, Andrii Skliar, Haitam Ben Yahia, Shubhankar Borse, Fatih Porikli, Amirhossein Habibian, Tijmen Blankevoort
2022	J	`jnl`	Simple and Efficient Architectures for Semantic Segmentation. CoRR Dushyant Mehta, Andrii Skliar, Haitam Ben Yahia, Shubhankar Borse, Fatih Porikli, Amirhossein Habibian, Tijmen Blankevoort
2022	—	`conf`	Simulated Quantization, Real Power Savings. CVPR Workshops Mart van Baalen, Brian Kahne, Eric Mahurin, Andrey Kuzmin, Andrii Skliar, Markus Nagel, Tijmen Blankevoort
2021	J	`jnl`	A White Paper on Neural Network Quantization. CoRR Markus Nagel, Marios Fournarakis, Rana Ali Amjad, Yelysei Bondarenko, Mart van Baalen, Tijmen Blankevoort
2021	A*	`conf`	Distilling Optimal Neural Networks: Rapid Search in Diverse Spaces. ICCV Bert Moons, Parham Noorzad, Andrii Skliar, Giovanni Mariani, Dushyant Mehta, Chris Lott, Tijmen Blankevoort
2021	—	`conf`	Understanding and Overcoming the Challenges of Efficient Transformer Quantization. EMNLP (1) Yelysei Bondarenko, Markus Nagel, Tijmen Blankevoort
2021	J	`jnl`	Understanding and Overcoming the Challenges of Efficient Transformer Quantization. CoRR Yelysei Bondarenko, Markus Nagel, Tijmen Blankevoort
2020	A*	`conf`	Batch-shaping for learning conditional channel gated networks. ICLR Babak Ehteshami Bejnordi, Tijmen Blankevoort, Max Welling
2020	A*	`conf`	Bayesian Bits: Unifying Quantization and Pruning. NeurIPS Mart van Baalen, Christos Louizos, Markus Nagel, Rana Ali Amjad, Ying Wang, Tijmen Blankevoort, Max Welling
2020	J	`jnl`	Bayesian Bits: Unifying Quantization and Pruning. CoRR Mart van Baalen, Christos Louizos, Markus Nagel, Rana Ali Amjad, Ying Wang, Tijmen Blankevoort, Max Welling
2020	A*	`conf`	Conditional Channel Gated Networks for Task-Aware Continual Learning. CVPR Davide Abati, Jakub M. Tomczak, Tijmen Blankevoort, Simone Calderara, Rita Cucchiara, Babak Ehteshami Bejnordi
2020	J	`jnl`	Conditional Channel Gated Networks for Task-Aware Continual Learning. CoRR Davide Abati, Jakub M. Tomczak, Tijmen Blankevoort, Simone Calderara, Rita Cucchiara, Babak Ehteshami Bejnordi
2020	—	`conf`	Differentiable Joint Pruning and Quantization for Hardware Efficiency. ECCV (29) Ying Wang, Yadong Lu, Tijmen Blankevoort
2020	J	`jnl`	Differentiable Joint Pruning and Quantization for Hardware Efficiency. CoRR Ying Wang, Yadong Lu, Tijmen Blankevoort
2020	J	`jnl`	Distilling Optimal Neural Networks: Rapid Search in Diverse Spaces. CoRR Bert Moons, Parham Noorzad, Andrii Skliar, Giovanni Mariani, Dushyant Mehta, Chris Lott, Tijmen Blankevoort
2020	A*	`conf`	Gradient $\ell_1$ Regularization for Quantization Robustness. ICLR Milad Alizadeh, Arash Behboodi, Mart van Baalen, Christos Louizos, Tijmen Blankevoort, Max Welling
2020	J	`jnl`	Gradient 𝓁 CoRR Milad Alizadeh, Arash Behboodi, Mart van Baalen, Christos Louizos, Tijmen Blankevoort, Max Welling
2020	—	`conf`	LSQ+: Improving low-bit quantization through learnable offsets and better initialization. CVPR Workshops Yash Bhalgat, Jinwon Lee, Markus Nagel, Tijmen Blankevoort, Nojun Kwak
2020	J	`jnl`	LSQ+: Improving low-bit quantization through learnable offsets and better initialization. CoRR Yash Bhalgat, Jinwon Lee, Markus Nagel, Tijmen Blankevoort, Nojun Kwak
2020	J	`jnl`	Learned Threshold Pruning. CoRR Kambiz Azarian, Yash Bhalgat, Jinwon Lee, Tijmen Blankevoort
2020	A*	`conf`	Up or Down? Adaptive Rounding for Post-Training Quantization. ICML Markus Nagel, Rana Ali Amjad, Mart van Baalen, Christos Louizos, Tijmen Blankevoort
2020	J	`jnl`	Up or Down? Adaptive Rounding for Post-Training Quantization. CoRR Markus Nagel, Rana Ali Amjad, Mart van Baalen, Christos Louizos, Tijmen Blankevoort
2019	J	`jnl`	Batch-Shaped Channel Gated Networks. CoRR Babak Ehteshami Bejnordi, Tijmen Blankevoort, Max Welling
2019	A*	`conf`	Data-Free Quantization Through Weight Equalization and Bias Correction. ICCV Markus Nagel, Mart van Baalen, Tijmen Blankevoort, Max Welling
2019	J	`jnl`	Data-Free Quantization through Weight Equalization and Bias Correction. CoRR Markus Nagel, Mart van Baalen, Tijmen Blankevoort, Max Welling
2019	—	`conf`	Relaxed Quantization for Discretized Neural Networks. ICLR (Poster) Christos Louizos, Matthias Reisser, Tijmen Blankevoort, Efstratios Gavves, Max Welling
2019	J	`jnl`	Taxonomy and Evaluation of Structured Compression of Convolutional Neural Networks. CoRR Andrey Kuzmin, Markus Nagel, Saurabh Pitre, Sandeep Pendyam, Tijmen Blankevoort, Max Welling
2018	J	`jnl`	Relaxed Quantization for Discretized Neural Networks. CoRR Christos Louizos, Matthias Reisser, Tijmen Blankevoort, Efstratios Gavves, Max Welling