Author

Johannes Knittel

h-index 2 View on Semantic Scholar

We have 2 of 6 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Oct 2026

RoleQ: Role-Aligned Scales for Converting Language Models to Ternary

RoleQ is introduced, a quantization framework that places scales by the functional roles of Transformer units rather than by the layout of the weight matrix, as conventional formats do, and leads every post-training ternary method at matched or lower memory-resident bits on perplexity, zero-shot accuracy and MMLU.

Johannes Knittel, Alec Helbling, Hanspeter Pfister · 0 citations

Jul 2026

Sparse Inter-Layer Dependencies of Transformer FFN Neurons

A training-free attribution method that estimates the relative influence of upstream neurons and attention outputs on a target neuron's activation and identifies candidate sparse pathways with potential implications for efficient inference is introduced.

Johannes Knittel, Hanspeter Pfister · arXiv.org · 0 citations