Matthijs Van Keirsbilck

15 papers A* 1A 2B 1Journal 8Unranked 3

Year	Rank	Type	Title / Venue / Authors
2025	A*	`conf`	Hymba: A Hybrid-head Architecture for Small Language Models. ICLR Xin Dong, Yonggan Fu, Shizhe Diao, Wonmin Byeon, Zijia Chen, Ameya Sunil Mahabaleshwarkar, Shih-Yang Liu, Matthijs Van Keirsbilck, Min-Hung Chen, Yoshi Suhara, Yingyan Celine Lin, Jan Kautz, Pavlo Molchanov
2025	J	`jnl`	Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models. CoRR Yonggan Fu, Xin Dong, Shizhe Diao, Matthijs Van Keirsbilck, Hanrong Ye, Wonmin Byeon, Yashaswi Karnati, Lucas Liebenwein, Hannah Zhang, Nikolaus Binder, Maksim Khadkevich, Alexander Keller, Jan Kautz, Yingyan (Celine) Lin, Pavlo Molchanov
2024	A	`conf`	Conformer without Convolutions. INTERSPEECH Matthijs Van Keirsbilck, Alexander Keller
2024	J	`jnl`	Hymba: A Hybrid-head Architecture for Small Language Models. CoRR Xin Dong, Yonggan Fu, Shizhe Diao, Wonmin Byeon, Zijia Chen, Ameya Sunil Mahabaleshwarkar, Shih-Yang Liu, Matthijs Van Keirsbilck, Min-Hung Chen, Yoshi Suhara, Yingyan Lin, Jan Kautz, Pavlo Molchanov
2022	B	`conf`	Deep Learning-Based Synchronization for Uplink NB-IoT. GLOBECOM Fayçal Aït Aoudia, Jakob Hoydis, Sebastian Cammerer, Matthijs Van Keirsbilck, Alexander Keller
2022	J	`jnl`	Deep Learning-Based Synchronization for Uplink NB-IoT. CoRR Fayçal Aït Aoudia, Jakob Hoydis, Sebastian Cammerer, Matthijs Van Keirsbilck, Alexander Keller
2021	J	`jnl`	Artificial Neural Networks generated by Low Discrepancy Sequences. CoRR Alexander Keller, Matthijs Van Keirsbilck
2021	A	`conf`	Compressing 1D Time-Channel Separable Convolutions Using Sparse Random Ternary Matrices. Interspeech Gonçalo Mordido, Matthijs Van Keirsbilck, Alexander Keller
2021	J	`jnl`	Compressing 1D Time-Channel Separable Convolutions using Sparse Random Ternary Matrices. CoRR Gonçalo Mordido, Matthijs Van Keirsbilck, Alexander Keller
2020	—	`conf`	Artificial Neural Networks Generated by Low Discrepancy Sequences. MCQMC Alexander Keller, Matthijs Van Keirsbilck
2020	—	`conf`	Monte Carlo Gradient Quantization. CVPR Workshops Gonçalo Mordido, Matthijs Van Keirsbilck, Alexander Keller
2019	—	`conf`	Instant Quantization of Neural Networks using Monte Carlo Methods. EMC2@NeurIPS Gonçalo Mordido, Matthijs Van Keirsbilck, Alexander Keller
2019	J	`jnl`	Instant Quantization of Neural Networks using Monte Carlo Methods. CoRR Gonçalo Mordido, Matthijs Van Keirsbilck, Alexander Keller
2019	J	`jnl`	Rethinking Full Connectivity in Recurrent Neural Networks. CoRR Matthijs Van Keirsbilck, Alexander Keller, Xiaodong Yang
2018	J	`jnl`	Resource aware design of a deep convolutional-recurrent neural network for speech recognition through audio-visual sensor fusion. CoRR Matthijs Van Keirsbilck, Bert Moons, Marian Verhelst