Author

Johannes Bjerva

2 papers indexed here

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 Sep 2026

Capable yet Parsimonious: Extracting and Characterizing Hidden Chain-of-Thought in Frontier Models

It is found that Astra exhibits token-efficient directed reasoning, selecting a correct trajectory earlier, while resolving elementary steps internally and externalizing only crucial reasoning, which provides a behavioral lens on frontier-model reasoning beyond benchmark scores.

Xiao-Yu Luo, Tao Ren, Wen-Rui Yu et al. · 0 citations

#natural language process... May 2026

When Discourse Pressures Conflict: Information Structure in Vision-Language Model Outputs

This research gap using information structure (IS) is addressed, testing whether VLMs distinguish discourse-old Topics from discourse-new Foci in visually grounded question answering and suggesting that VLM evaluation should look beyond content accuracy to how content is packaged for the discourse.

Marcell Richard Fekete, Johannes Bjerva, Tamás Káldi · arXiv.org · 0 citations