Selected publications

I am broadly interested in problems at the intersection of Computer Vision, Computer Audition, and Machine Learning, with the goal of building AI systems that can perceive, reason, and interact with complex real-world environments. My research focuses on multimodal learning (Vision + X), particularly for generative modeling and cross-modal understanding with minimal supervision.

In the past, I have also worked on problems in computational photography, including image reflection removal, intrinsic image decomposition, inverse rendering, and video quality assessment.

Representative papers are highlighted below. For a complete list of publications, please refer to my Google Scholar.

Uncovering the Representation Geometry of Minimal Cores in Overcomplete Reasoning Traces

AMusE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding

MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks

AURELIA: Test-time Reasoning Distillation in Audio-Visual LLMs

AVTrustBench: Assessing and Enhancing Reliability and Robustness in Audio-Visual LLMs

EgoAdapt: Adaptive Multisensory Distillation and Policy Learning for Efficient Egocentric Perception

Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time

Towards Determining Perceived Human Intent for Multimodal Social Media Posts using The Theory of Reasoned Action

ASPIRE: Language-Guided Data Augmentation for Improving Robustness Against Spurious Correlations

Can LLM’s Generate Human-Like Wayfinding Instructions? Towards Platform-Agnostic Embodied Instruction Synthesis

MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models (Highlight, Top 2.8%)

APoLLo : Unified Adapter and Prompt Learning for Vision Language Models

AdVerb: Visually Guided Audio Dereverberation

Measured Albedo in the Wild: Filling the Gap in Intrinsics Evaluation

AudViSum: Self-Supervised Deep Reinforcement Learning for Diverse Audio-Visual Summary Generation

V-DESIRR: Very Fast Deep Embedded Single Image Reflection Removal

Listen to the Pixels