collaborators

9 papers

cs.AI2026

DiSCO: Defending text-to-image generation through distribution-guided contrastive prompt optimization

Tong Zhang, Motasem Alfarra, Carlos Hinojosa +2

As text-to-image generative models advance, they raise critical safety concerns, particularly the generation of Not-Safe-For-Work (NSFW) content such as violence and nudity, furthe…

cs.LG2026

Distilling Safe LLM Systems via Soft Prompts for On Device Settings

Motasem Alfarra, Cristina Pinneri, Dana Kianfar +2

Deploying safe large language models (LLMs) on resource-constrained edge devices presents a critical challenge: while dual-model systems combining LLMs with guard models provide ef…

cs.LG2026

Masks Can Be Distracting: On Context Comprehension in Diffusion Language Models

Julianna Piskorz, Cristina Pinneri, Alvaro Correia +3

Masked Diffusion Language Models (MDLMs) have recently emerged as a promising alternative to Autoregressive Language Models (ARLMs), leveraging a denoising objective that, in princ…

cs.LG2026

Fundamental bounds on efficiency-confidence trade-off for transductive conformal prediction

Arash Behboodi, Alvaro H. C. Correia, Fabio Valerio Massoli +1

Transductive conformal prediction addresses the simultaneous prediction for multiple data points. Given a desired confidence level, the objective is to construct a prediction set t…

cs.CL2026

Search or Accelerate: Confidence-Switched Position Beam Search for Diffusion Language Models

Mingyu Cao, Alvaro H. C. Correia, Christos Louizos +2

Diffusion Language Models (DLMs) generate text by iteratively denoising a masked sequence, repeatedly deciding which positions to commit at each step. Standard decoding follows a g…

cs.LG2026

Analyzing and Improving Chain-of-Thought Monitorability Through Information Theory

Usman Anwar, Tim Bakker, Dana Kianfar +2

Chain-of-thought (CoT) monitors are LLM-based systems that analyze reasoning traces to detect when outputs may exhibit attributes of interest, such as test-hacking behavior during…