Ashutosh Chaubey

About Me

I am a CS PhD student at the Institute for Creative Technologies, University of Southern California, where I am advised by Prof. Mohammad Soleymani at the Intelligent Human Perception Lab. I am a Bronze Medallist from the 2021 batch of Indian Institute of Technology, Roorkee.

During my PhD, I am working on post-training techniques such as preference optimization for multimodal (audio/video/omni) LLMs to improve their social and emotion understanding. I also collaborate on projects related to video generation for social behaviors.

Prior to this, I was a Founding Research Engineer at Anoki AI where I worked on multimodal content understanding and retrieval. I have also worked at LG Ad Solutions on speaker recognition, automatic content recognition using audio and voice cloning. Over the past I have interned at Adobe Research, with Sumit Shekhar, at Vision and AI Lab, IISc. Bengaluru with Prof. R. Venkatesh Babu, and at IIT Roorkee with Prof. R. Balasubramanian

I am looking for Research/Applied Scientist internship positions for Fall 2026 and Spring/Summer 2027 on multimodal LLMs (audio/visual/omni) and video generation. Please reach out if you have open positions.

Masters/Undergrad Students

If you are a student and want to have a discussion with me regarding my papers or how to apply for a PhD program in the US, please email me at achaubey at usc dot edu

For students who wish to join our lab, please check our lab's open positions.

Ashutosh Chaubey
Areas of Interest

Multimodal LLM Tuning and Post-training, Emotion understanding, Social AI

News

Selected Publications

View all publications

MoD-DPO

MoD-DPO: Towards Mitigating Cross-modal Hallucinations in Omni LLMs using Modality Decoupled Preference Optimization

Ashutosh Chaubey, Jiacheng Pang, Mohammad Soleymani

Multimodal LLMs Computer Vision Reinforcement Learning Audio
AVERE logo

AVERE: Improving Audiovisual Emotion Reasoning with Preference Optimization

Ashutosh Chaubey, Jiacheng Pang, Maksim Siniukov, Mohammad Soleymani

Multimodal LLMs Computer Vision Reinforcement Learning Audio
Face-LLaVA logo

Face-LLaVA: Facial Expression and Attribute Understanding through Instruction Tuning

Ashutosh Chaubey, Xulang Guan, Mohammad Soleymani

WACV, 2026 (Round 1)
Multimodal LLMs Computer Vision Face Analysis
ContextIQ: A Multimodal Expert-Based Video Retrieval System for Contextual Advertising

ContextIQ: A Multimodal Expert-Based Video Retrieval System for Contextual Advertising

Ashutosh Chaubey, Anoubhav Agarwaal, Sartaki Sinha Roy, Aayush Agrawal, Susmita Ghose

WACV, 2025
Multimodal LLMs Computer Vision

Education

University of Southern California – PhD, Computer Science (2024 - Present), GPA: 4.0/4.0

Graduate Researcher – Intelligent Human Perception Lab, Institute for Creative Technologies

Indian Institute of Technology Roorkee – BS, Computer Science (2017 - 2021), GPA: 9.718/10

Chair - ACM IIT Roorke Chapter | Co-President - Vision and Language Group

Academic Duties

Reviewer

Teaching Assistant

  • CSCI 561 – Foundations of Artificial Intelligence (USC, Fall 2025)
  • CSCI 535 – Multimodal Probabilistic Learning of Human Communication (USC, Spring 2026)