3 citations · 8 across the 10 of their papers we have counts for
11 papers
SVD-Surgeon: Optimal Singular-Value Surgery for Large Language Model Compression
Mahmoud Safari, Frank Hutter
Large language models (LLMs) achieve remarkable performance across a wide range of tasks, but their deployment is constrained by substantial memory and compute requirements. Low-ra…
Speedrunning Tabular Foundation Model Pretraining
Salih Bora Ozturk, Alexander Pfefferle, Frank Hutter
Pretraining cost is a major bottleneck for research on tabular foundation models, slowing the iteration cycle for new architectures, priors, and optimization ideas. Yet the communi…
Where to Begin: Efficient Pretraining via Subnetwork Selection and Distillation
Arjun Krishnakumar, Rhea Sanjay Sukthanker, Hannan Javed Mahadik +5
Small Language models (SLMs) offer an efficient and accessible alternative to Large Language Models (LLMs), delivering strong performance while using far fewer resources. We introd…
confopt: A Library for Implementation and Evaluation of Gradient-based One-Shot NAS Methods
Abhash Kumar Jha, Shakiba Moradian, Arjun Krishnakumar +2
Gradient-based one-shot neural architecture search (NAS) has significantly reduced the cost of exploring architectural spaces with discrete design choices, such as selecting operat…
Gompertz Linear Units: Leveraging Asymmetry for Enhanced Learning Dynamics
Indrashis Das, Mahmoud Safari, Steven Adriaensen +1
Activation functions are fundamental elements of deep learning architectures as they significantly influence training dynamics. ReLU, while widely used, is prone to the dying neuro…
Compressing Large Language Models with Automated Sub-Network Search
Rhea Sanjay Sukthanker, Benedikt Staffler, Frank Hutter +1
Large Language Models (LLMs) demonstrate exceptional reasoning abilities, enabling strong generalization across diverse tasks such as commonsense reasoning and instruction followin…
Efficient Search for Customized Activation Functions with Gradient Descent
Lukas Strack, Mahmoud Safari, Frank Hutter
Different activation functions work best for different deep learning models. To exploit this, we leverage recent advancements in gradient-based search techniques for neural archite…
HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models
Rhea Sanjay Sukthanker, Arber Zela, Benedikt Staffler +4
The increasing size of language models necessitates a thorough analysis across multiple dimensions to assess trade-offs among crucial hardware metrics such as latency, energy consu…
Surprisingly Strong Performance Prediction with Neural Graph Features
Gabriela Kadlecová, Jovita Lukasik, Martin Pilát +4
Performance prediction has been a key part of the neural architecture search (NAS) process, allowing to speed up NAS algorithms by avoiding resource-consuming network training. Alt…
Multi-objective Differentiable Neural Architecture Search
Rhea Sanjay Sukthanker, Arber Zela, Benedikt Staffler +3
Pareto front profiling in multi-objective optimization (MOO), i.e., finding a diverse set of Pareto optimal solutions, is challenging, especially with expensive objectives that req…
Weight-Entanglement Meets Gradient-Based Neural Architecture Search
Rhea Sanjay Sukthanker, Arjun Krishnakumar, Mahmoud Safari +1
Weight sharing is a fundamental concept in neural architecture search (NAS), enabling gradient-based methods to explore cell-based architectural spaces significantly faster than tr…