Lukas Balles - RankMe

28 papers A* 6A 1Journal 19Unranked 2

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	A Family of LLMs Liberated from Static Vocabularies. CoRR Adnen Abdessaied, Artur Baranowski, Lukas Balles, Michael Barlow, Fabien C. Y. Benureau, Felix Berkenkamp, Lukas Bluebaum, Bastian Boll, Thomas F. Burns, Björn Deiseroth, Constantin Eichenberg, David Friede, Pablo Iyu Guerrero, Ahmed Hammam, Bastian Harren, Johann Higl, Yasser Jadidi, Carina Kauf, Johannes Messner, Jan Hendrik Metzen, Max Meuer, Vedant Nanda, Pit Neitemeier, Koen Oostermeijer, Letitia Parcalabescu, Markus Pernpointner, Felix Reinfurt, Dylan Rodriquez, Grégory Schott, Philipp Siedler, Martin Simonovsky, Till Speicher, Volker Stampa, Stephan Wäldchen, Samuel Weinbach, Gregor Ziegltrum
2026	J	`jnl`	SOMBRERO: Measuring and Steering Boundary Placement in End-to-End Hierarchical Sequence Models. CoRR Pit Neitemeier, Alessio Serra, Jiaze Li, Sascha Wirges, Lukas Balles, Jan Hendrik Metzen
2025	A*	`conf`	Hierarchical Autoregressive Transformers: Combining Byte- and Word-Level Processing for Robust, Adaptable Language Models. ICLR Pit Neitemeier, Björn Deiseroth, Constantin Eichenberg, Lukas Balles
2025	J	`jnl`	Hierarchical Autoregressive Transformers: Combining Byte- and Word-Level Processing for Robust, Adaptable Language Models. CoRR Pit Neitemeier, Björn Deiseroth, Constantin Eichenberg, Lukas Balles
2025	A*	`conf`	u-μP: The Unit-Scaled Maximal Update Parametrization. ICLR Charlie Blake, Constantin Eichenberg, Josef Dean, Lukas Balles, Luke Yuri Prince, Björn Deiseroth, Andrés Felipe Cruz-Salinas, Carlo Luschi, Samuel Weinbach, Douglas Orr
2024	J	`jnl`	Choice of PEFT Technique in Continual Learning: Prompt Tuning is Not All You Need. CoRR Martin Wistuba, Prabhu Teja Sivaprasad, Lukas Balles, Giovanni Zappella
2024	J	`jnl`	On the Choice of Learning Rate for Local SGD. Trans. Mach. Learn. Res. Lukas Balles, Prabhu Teja Sivaprasad, Cédric Archambeau
2024	J	`jnl`	u-μP: The Unit-Scaled Maximal Update Parametrization. CoRR Charlie Blake, Constantin Eichenberg, Josef Dean, Lukas Balles, Luke Y. Prince, Björn Deiseroth, Andrés Felipe Cruz-Salinas, Carlo Luschi, Samuel Weinbach, Douglas Orr
2023	J	`jnl`	A Negative Result on Gradient Matching for Selective Backprop. CoRR Lukas Balles, Cédric Archambeau, Giovanni Zappella
2023	J	`jnl`	Continual Learning with Low Rank Adaptation. CoRR Martin Wistuba, Prabhu Teja Sivaprasad, Lukas Balles, Giovanni Zappella
2023	A*	`conf`	PASHA: Efficient HPO and NAS with Progressive Resource Allocation. ICLR Ondrej Bohdal, Lukas Balles, Martin Wistuba, Beyza Ermis, Cédric Archambeau, Giovanni Zappella
2023	J	`jnl`	Renate: A Library for Real-World Continual Learning. CoRR Martin Wistuba, Martin Ferianc, Lukas Balles, Cédric Archambeau, Giovanni Zappella
2022	J	`jnl`	Gradient-Matching Coresets for Rehearsal-Based Continual Learning. CoRR Lukas Balles, Giovanni Zappella, Cédric Archambeau
2022	J	`jnl`	PASHA: Efficient HPO with Progressive Resource Allocation. CoRR Ondrej Bohdal, Lukas Balles, Beyza Ermis, Cédric Archambeau, Giovanni Zappella
2021	J	`jnl`	Gradient-matching coresets for continual learning. CoRR Lukas Balles, Giovanni Zappella, Cédric Archambeau
2020	—	`conf`	Self-Tuning Stochastic Optimization with Curvature-Aware Gradient Filtering. ICBINB@NeurIPS Ricky T. Q. Chen, Dami Choi, Lukas Balles, David Duvenaud, Philipp Hennig
2020	J	`jnl`	Self-Tuning Stochastic Optimization with Curvature-Aware Gradient Filtering. CoRR Ricky T. Q. Chen, Dami Choi, Lukas Balles, David Duvenaud, Philipp Hennig
2020	J	`jnl`	The Geometry of Sign Gradient Descent. CoRR Lukas Balles, Fabian Pedregosa, Nicolas Le Roux
2019	A*	`conf`	Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation. CVPR Anurag Ranjan, Varun Jampani, Lukas Balles, Kihwan Kim, Deqing Sun, Jonas Wulff, Michael J. Black
2019	—	`conf`	DeepOBS: A Deep Learning Optimizer Benchmark Suite. ICLR (Poster) Frank Schneider, Lukas Balles, Philipp Hennig
2019	J	`jnl`	DeepOBS: A Deep Learning Optimizer Benchmark Suite. CoRR Frank Schneider, Lukas Balles, Philipp Hennig
2019	J	`jnl`	Limitations of the Empirical Fisher Approximation. CoRR Frederik Kunstner, Lukas Balles, Philipp Hennig
2019	A*	`conf`	Limitations of the empirical Fisher approximation for natural gradient descent. NeurIPS Frederik Kunstner, Philipp Hennig, Lukas Balles
2018	A*	`conf`	Dissecting Adam: The Sign, Magnitude and Variance of Stochastic Gradients. ICML Lukas Balles, Philipp Hennig
2017	A	`conf`	Coupling Adaptive Batch Sizes with Learning Rates. UAI Lukas Balles, Javier Romero, Philipp Hennig
2017	J	`jnl`	Early Stopping without a Validation Set. CoRR Maren Mahsereci, Lukas Balles, Christoph Lassner, Philipp Hennig
2017	J	`jnl`	Follow the Signs for Robust Stochastic Optimization. CoRR Lukas Balles, Philipp Hennig
2016	J	`jnl`	Coupling Adaptive Batch Sizes with Learning Rates. CoRR Lukas Balles, Javier Romero, Philipp Hennig