Alberto Cazzaniga

most citedThe representation landscape of few-shot learning and fine-tuning in large language models

4 citations · 6 across the 2 of their papers we have counts for

collaborators

3 papers

cs.CL2024★ 4 cited

The representation landscape of few-shot learning and fine-tuning in large language models

Diego Doimo, Alessandro Serra, Alessio Ansuini +1

In-context learning (ICL) and supervised fine-tuning (SFT) are two common strategies for improving the performance of modern large language models (LLMs) on specific tasks. Despite…

math.AG2020★ 2 cited

Higher rank motivic Donaldson-Thomas invariants of $A^{3}$ via wall-crossing, and asymptotics

Alberto Cazzaniga, Dimbinaina Ralaivaosaona, Andrea T. Ricolfi

We compute, via motivic wall-crossing, the generating function of virtual motives of the Quot scheme of points on $A^{3}$ , generalising to higher rank a result of Behrend, B…

math.AG2020

Framed motivic Donaldson-Thomas invariants of small crepant resolutions

Alberto Cazzaniga, Andrea T. Ricolfi

For an arbitrary integer $r \geq 1$ , we compute $r$ -framed motivic PT and DT invariants of small crepant resolutions of toric Calabi-Yau $3$ -folds, establishing a "higher rank" vers…

The representation landscape of few-shot learning and fine-tuning in large language models

Higher rank motivic Donaldson-Thomas invariants of A3 via wall-crossing, and asymptotics

Framed motivic Donaldson-Thomas invariants of small crepant resolutions

Higher rank motivic Donaldson-Thomas invariants of $A^{3}$ via wall-crossing, and asymptotics