7 papers
Training Transformers for KV Cache Compressibility
Yoav Gelberg, Yam Eitan, Michael Bronstein +2
Long-context language modeling is increasingly constrained by the Key-Value (KV) cache, whose memory and decode-time access costs scale linearly with the prefix length. This bottle…
GraphBench: Next-generation graph learning benchmarking
Timo Stoll, Chendi Qian, Ben Finkelshtein +16
Machine learning on graphs has made substantial progress across domains such as molecular property prediction and chip design. Yet benchmarking practices remain fragmented, often r…
GradMetaNet: An Equivariant Architecture for Learning on Gradients
Yoav Gelberg, Yam Eitan, Aviv Navon +5
Gradients of neural networks encode valuable information for optimization, editing, and analysis of models. Therefore, practitioners often treat gradients as inputs to task-specifi…
Multi-domain Distribution Learning for De Novo Drug Design
Arne Schneuing, Ilia Igashov, Adrian W. Dobbelstein +3
We introduce DrugFlow, a generative model for structure-based drug design that integrates continuous flow matching with discrete Markov bridges, demonstrating state-of-the-art perf…
Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based Centrality
Joshua Southern, Yam Eitan, Guy Bar-Shalom +3
Subgraph GNNs have emerged as promising architectures that overcome the expressiveness limitations of Graph Neural Networks (GNNs) by processing bags of subgraphs. Despite their co…
Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks
Maya Bechler-Speicher, Ben Finkelshtein, Fabrizio Frasca +9
While machine learning on graphs has demonstrated promise in drug design and molecular property prediction, significant benchmarking challenges hinder its further progress and rele…