4 papers · 1 filter
Model Fusion via Retrofitting
Phoomraphee Luenam, Andreas Spanopoulos, Amit Sant +3
Model fusion seeks to combine independently trained neural networks into a single model without retraining, but is complicated by representational divergence arising from permutati…
Generalized Linear Mode Connectivity for Transformers
Alexander Theus, Alessandro Cabodi, Sotiris Anagnostidis +3
Understanding the geometry of neural network loss landscapes is a central question in deep learning, with implications for generalization and optimization. A striking phenomenon is…
FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Compute
Sotiris Anagnostidis, Gregor Bachmann, Yeongmin Kim +7
Despite their remarkable performance, modern Diffusion Transformers are hindered by substantial resource requirements during inference, stemming from the fixed and large amount of…
Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment
Gregor Bachmann, Sotiris Anagnostidis, Albert Pumarola +6
The performance of large language models (LLMs) is closely linked to their underlying size, leading to ever-growing networks and hence slower inference. Speculative decoding has be…