OS
Oscar Agustin Stanchi
cs.AIcs.CLcs.CVcs.LG
On Valency
published · living versionsW_n6rj4p5u·v1 · currentpublished
Humans Correct Their Judgments Through Debate, but Weaker AI Models Do Not
with Maria Victoria Carro, Denise Alejandra Mester, Facundo Nieto, Guido Ernesto Bergman +12
1 version
Preprints & journals
8 papers in the corpus · 2022–2026Humans Correct Their Judgments Through Debate, but Weaker AI Models Do Not2610.28539v1 · Maria Victoria Carro, Denise Alejandra Mester, Facundo Nieto et al.2026 · 0 citationsarXivon Valency
Target-Side Paraphrase Augmentation for Sign Language Translation with Large Language Models2605.31393v2 · Pedro Dal Bianco, Jean Paul Nunes Reinhold, Oscar Stanchi et al.2026 · 0 citationsarXiv
Mind the Performance Gap: Capability-Behavior Trade-offs in Feature Steering2602.04903v1 · Eitan Sprejer, Oscar Agust'in Stanchi, Mar'ia Victoria Carro et al.2026 · 0 citationsarXiv
AI Debaters are More Persuasive when Arguing in Alignment with Their Own Beliefs2510.13912v3 · Mar'ia Victoria Carro, Denise Alejandra Mester, Facundo Nieto et al.2025 · 0 citationsarXiv
HandCraft: Dynamic Sign Generation for Synthetic Data Augmentation2508.14345v2 · Gaston Gustavo Rios, Pedro Dal Bianco, Franco Ronchetti et al.2025 · 0 citationsarXiv
Bringing Balance to Hand Shape Classification: Mitigating Data Imbalance Through Generative Models2507.17008v1 · Gaston Gustavo Rios, Pedro Dal Bianco, Franco Ronchetti et al.2025 · 1 citationApplied Soft Computing (2025)
SignAttention: On the Interpretability of Transformer Models for Sign Language Translation2410.14506v1 · Pedro Alejandro Dal Bianco, Oscar Agust'in Stanchi, Facundo Manuel Quiroga et al.2024 · 1 citationarXiv
LSA-T: The first continuous Argentinian Sign Language dataset for Sign Language Translation2211.15481v1 · Pedro Dal Bianco, Gast'on R'ios, Franco Ronchetti et al.2022 · 12 citationsarXiv
Career total: 31 works. 8 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.