Dinesh Manocha

5 papers University of Maryland, College Park

• Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models
• Does Thinking More Always Help? Mirage of Test-Time Scaling in Reasoning Models
• MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks
• RPG360: Robust 360 Depth Estimation with Perspective Foundation Models and Graph Optimization
• VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding