Bernardo Magnini

Investigating Proactivity in Multimodal Task-Guidance Dialogues

From Vision to Language: Investigating Causal Information Flow in Multimodal Decision-Making

This work investigates cross-modal information flow in a video-based generative multiple-choice-like setting by applying a layer-wise causal intervention on video-text attention pathways and identifies a distinct pattern in temporal reasoning.

ViPlan: A Benchmark for Visual Planning with Symbolic Predicates and Vision-Language Models

ViPlan domains capture fundamental shortcomings of both VLM-grounded symbolic approaches and direct VLM planning methods, and is presented, the first open-source benchmark for comparing VLM-grounded symbolic approaches (VLM-as-grounder) with direct VLM planning methods (VLM-as-planner).

Selective Agent Guidance via Entropy: Learning Autonomous Policies from Imperfect VLM Teachers

SAGE (Selective Agent Guidance via Entropy), a framework that queries a VLM only when the learner is uncertain, executes the suggested action during training, and distills guidance into a lightweight Reinforcement Learning policy, is proposed.

Towards Detecting Inconsistencies in End-to-end Generated TODs

This work investigates a method for automatically detecting inconsistencies in Task-Oriented Dialogues by conceptualizing TODs as a Constraint Satisfaction Problem (CSP), where variables represent dialogue segments referencing the conversational domain and constraints among variables capture dialogue properties such as...