Martin Jaggi
12
Papers
45
Total Citations
1
Affiliations
Affiliations
EPFL
Papers (12)
Effective Interplay between Sparsity and Quantization: From Theory to Practice
ICLR 2025arXiv
19
citations
CoTFormer: A Chain of Thought Driven Architecture with Budget-Adaptive Computation Cost at Inference
ICLR 2025arXiv
12
citations
Enhancing Multilingual LLM Pretraining with Model-Based Data Selection
NeurIPS 2025arXiv
9
citations
On-Device Collaborative Language Modeling via a Mixture of Generalists and Specialists
ICML 2025arXiv
4
citations
GRAPE: Optimize Data Mixture for Group Robust Multi-target Adaptive Pretraining
NeurIPS 2025arXiv
1
citations
The Privacy Power of Correlated Noise in Decentralized Learning
ICML 2024
0
citations
Spectral Preconditioning for Gradient Methods on Graded Non-convex Functions
ICML 2024
0
citations
DOGE: Domain Reweighting with Generalization Estimation
ICML 2024
0
citations
On Convergence of Incremental Gradient for Non-convex Smooth Functions
ICML 2024
0
citations
LASER: Linear Compression in Wireless Distributed Optimization
ICML 2024
0
citations
Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks
ICML 2024
0
citations
Ghost Noise for Regularizing Deep Neural Networks
AAAI 2024
0
citations