Behzad Dariush

Select the Key, Then Generate the Rest: Improving Multi-Modal Learning with Limited Data Budget

From Shortcuts to Reasoning: Robust Post-Training of Theory of Mind with Reinforcement Learning

Leveraging Prediction Inconsistency for Online Error Detection in Procedural Videos

COMBO: Compositional World Models for Embodied Multi-Agent Cooperation

$UQ-Merge$: UNCERTAINTY GUIDED MULTIMODAL LARGE LANGUAGE MODEL MERGING

Beyond Fixed Resolution: Enhancing VLLMs with Adaptive Input Scaling