works on

From the 1 of 5 linked papers with an AI index.

collaborators

5 papers

cs.LG2026

Consensus as Privileged Context for Label-Free Self-Distillation

John Gkountouras, Josip Jukić, Ivan Titov

The paper introduces CANON, a label‑free self‑distillation method that uses the majority answer from multiple sampled solutions as dense token‑level supervision to improve reasonin…

cs.LG2026

Geometric Self-Distillation for Reasoning Generalization

Josip Jukić, Ivan Titov

On-policy distillation is a practical post-training recipe for large language models, supplying dense teacher supervision on the student's own trajectories. In privileged-context s…

cs.CL2026

Context Parametrization with Compositional Adapters

Josip Jukić, Martin Tutek, Jan Šnajder

Large language models (LLMs) often seamlessly adapt to new tasks through in-context learning (ICL) or supervised fine-tuning (SFT). However, ICL is inefficient when handling many d…

cs.CL2025

Disentangling Latent Shifts of In-Context Learning with Weak Supervision

Josip Jukić, Jan Šnajder

In-context learning (ICL) enables large language models to perform few-shot learning by conditioning on labeled examples in the prompt. Despite its flexibility, ICL suffers from in…

cs.CL2025

Improving Data and Parameter Efficiency of Neural Language Models Using Representation Analysis

Josip Jukić

This thesis addresses challenges related to data and parameter efficiency in neural language models, with a focus on representation analysis and the introduction of new optimizatio…