3 papers
cs.CL2026
Move by Move: Measuring and Steering How LLMs Conduct Psychotherapy
Afonso Baldo, Hugo Pitorro, Areti Vassilopoulos +5
Users increasingly turn to large language models for emotional support, yet little is known about how these models actually conduct a psychotherapy interaction. We introduce an ont…
cs.LG2026
AdaSplash-2: Faster Differentiable Sparse Attention
Nuno Gonçalves, Hugo Pitorro, Vlad Niculae +4
Sparse attention has been proposed as a way to alleviate the quadratic cost of transformers, a central bottleneck in long-context training. A promising line of work is -entmax…
cs.CL2025
LaTIM: Measuring Latent Token-to-Token Interactions in Mamba Models
Hugo Pitorro, Marcos Treviso
State space models (SSMs), such as Mamba, have emerged as an efficient alternative to transformers for long-context sequence modeling. However, despite their growing adoption, SSMs…