Research
My research centers on building multimodal intelligence; machines that can perceive, reason over, and ground language in what they hear and see. Most of my recent work focuses on Large Audio(-Visual)-Language Models: how they fuse audio, vision, and text, where that fusion fails (temporal grounding, modality bias), and how to post-train them for stronger reasoning over long and complex real-world videos.
Alongside this, I study reasoning and reinforcement learning in language agents; what cooperative and strategic capabilities emerge in LLMs, and what actually transfers when RL trains an agent. My earlier work at IIT Madras and on the Govt. of India Bhashini project built robust multilingual speech systems for low-resource Indian languages.
Audio
-
TEMPO: Temporally-grounded Multi-task Post-training for Large Audio-Language Models
Project Page / arXiv / Code / Dataset / Checkpoints
EMNLP 2026 (Main Conference) (Oral) -
A Closer Look at Failure Modes in Temporal Understanding of Large Audio-Language Models
arXiv / Project Page / Dataset
Interspeech 2026 -
The Tag-Team Approach: Leveraging CLS and Language Tagging for Enhancing Multilingual ASR
arXiv
Interspeech 2023
Audio-Visual
-
Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos
arXiv / Project Page
NeurIPS 2026 -
MMOU: Massive Multi-Task Omni Understanding and Reasoning Benchmark for Long and Complex Real-World Videos
arXiv / Project Page / Data
NeurIPS 2026 Dataset and Benchmark Track -
Do Audio-Visual Large Language Models Really See and Hear?
arXiv / Project Page
CVPR 2026 (Findings)
LLM Post-training
-
Sparks of Cooperative Reasoning: LLMs as Strategic Hanabi Agents
arXiv / Project Page / Environment
ICML 2026 -
Playing with Fire: What Transfers When RL Trains a Language Agent?
Project Page
ICML Workshop on RL from World Feedback · 2026
COLM Workshop on Efficient Reasoning · 2026 (Spotlight)