3 papers
cs.LG2026
On Efficient Scaling of GNNs via IO-Aware Layers Implementations
Daria Fomina, Daniil Krasylnikov, Alexey Boykov +3
Graph Neural Networks (GNNs) are bottlenecked by sparse, irregular memory access. Popular frameworks such as DGL and PyTorch Geometric support general message passing, but complex…
cs.LG2026
KV Cache Offloading for Context-Intensive Tasks
Andrey Bocharnikov, Ivan Ermakov, Denis Kuznedelev +2
With the growing demand for long-context LLMs across a wide range of applications, the key-value (KV) cache has become a critical bottleneck for both latency and memory usage. Rece…
cs.LG2026
Asynchronous Reasoning: Training-Free Interactive Thinking LLMs
George Yakushev, Nataliia Babina, Masoud Vahid Dastgerdi +4
Many state-of-the-art LLMs are trained to think before giving their answer. Reasoning can greatly improve language model capabilities, but it also makes them less interactive: give…