2 papers
cs.CV2026
HeatKV: Head-tuned KV-cache Compression for Visual Autoregressive Modeling
Jonathan Cederlund, Axel Berg, William Isaksson +3
Visual Autoregressive (VAR) models have recently demonstrated impressive image generation quality while maintaining low latency. However, they suffer from severe KV-cache memory co…
cs.LG2025
Towards Federated Learning with On-device Training and Communication in 8-bit Floating Point
Bokun Wang, Axel Berg, Durmus Alp Emre Acar +1
Recent work has shown that 8-bit floating point (FP8) can be used for efficiently training neural networks with reduced computational cost compared to training in FP32/FP16. In thi…