activity
20242026
collaborators

9 papers

cs.CL2026

Thinking into the Future: Latent Lookahead Training for Transformers

Lorenzo Noci, Gregor Bachmann, Seyed-Mohsen Moosavi-Dezfooli +1

Autoregressive language models trained with next-token prediction generate text by sampling one discrete token at a time. Although very scalable, this objective forces the model to…

cs.CV2025

Tracing the Roots: Leveraging Temporal Dynamics in Diffusion Trajectories for Origin Attribution

Andreas Floros, Seyed-Mohsen Moosavi-Dezfooli, Pier Luigi Dragotti

Diffusion models have transformed image synthesis through iterative denoising, by defining trajectories from noise to coherent data. While their capabilities are widely celebrated,…

cs.LG2025

LORE: Lagrangian-Optimized Robust Embeddings for Visual Encoders

Borna Khodabandeh, Amirabbas Afzali, Amirhossein Afsharrad +4

Visual encoders have become fundamental components in modern computer vision pipelines. However, ensuring robustness against adversarial perturbations remains a critical challenge.…

cs.LG2025

On the Anisotropy of Score-Based Generative Models

Andreas Floros, Seyed-Mohsen Moosavi-Dezfooli, Pier Luigi Dragotti

We investigate the role of network architecture in shaping the inductive biases of modern score-based generative models. To this end, we introduce the Score Anisotropy Directions (…

cs.LG2025

Rewriting the Budget: A General Framework for Black-Box Attacks Under Cost Asymmetry

Mahdi Salmani, Alireza Abdollahpoorrostam, Seyed-Mohsen Moosavi-Dezfooli

Traditional decision-based black-box adversarial attacks on image classifiers aim to generate adversarial examples by slightly modifying input images while keeping the number of qu…

cs.CV2025

Certified Human Trajectory Prediction

Mohammadhossein Bahari, Saeed Saadatnejad, Amirhossein Askari Farsangi +2

Predicting human trajectories is essential for the safe operation of autonomous vehicles, yet current data-driven models often lack robustness in case of noisy inputs such as adver…