Agneet Chatterjee

I am a Computer Science PhD student at Arizona State University, where I am advised by Chitta Baral and Yezhou Yang. I have also worked as a student researcher at Stability AI and LLNL. My current research interests are in developing controllable image and video generative models.

I received my Bachelors in Computer Science from Jadavpur University in 2019. Before I started my PhD, I was a software engineer at Salesforce.

 /   /   /   / 

profile photo
News

  • September, 2025 - Stable Cinemetrics is out and will be presented at NeurIPS 2025!
  • September, 2025 - 1 paper accepted at TMLR.
  • September, 2025 - 1 paper accepted at EMNLP 2025.
  • June, 2025 - Best paper award at CVPR BEAM Workshop 2025.
  • January, 2025 - Joining Stability AI as a Research Scientist Intern to work on video generative models.
  • July, 2024 - SPRIGHT and REVISION accepted to ECCV 2024!
  • May, 2024 - Spending the summer at LLNL.
  • April, 2024 - New preprint out. More details on our website.
  • March, 2024 - 1 paper accepted to NAACL 2024.
  • March, 2024 - Received travel grants from SCAI and GPSA.
  • February, 2024 - 1 paper accepted to CVPR 2024!
  • February, 2024 - Received the SCAI Doctoral Fellowship.
  • March, 2023 - Received the SCAI Engineering Fellowship.
  • January, 2023 - Started my PhD.

Publications
Selected / All
spright
Stable Cinemetrics : Structured Taxonomy and Evaluation for Professional Video Generation
Agneet Chatterjee, Rahim Entezari, Maksym Zhuravinskyi, Max Lapin, Reshinth Adithyan, Amit Raj, Chitta Baral, Yezhou Yang, Varun Jampani
NeurIPS 2025

Paper | Project

act2i
AcT2I: Evaluating and Improving Action Depiction in Text-to-Image Models
Vatsal Malaviya, Agneet Chatterjee, Maitreya Patel, Yezhou Yang, Chitta Baral
EMNLP 2025 (Main)

Paper

dcpo
Dual Caption Preference Optimization for Diffusion Models
Amir Saeidi, Yiran Luo, Agneet Chatterjee, Shamanthak Hegde, Bimsara Pathiraja, Yezhou Yang, Chitta Baral
TMLR

Paper

textinvision
TextInVision: Text and Prompt Complexity Driven Visual Text Generation Benchmark
Forouzan Fallah, Maitreya Patel, Agneet Chatterjee, Vlad Morariu, Chitta Baral, Yezhou Yang
CVPR BEAM Workshop 2025 | Best Paper Award

Paper

spright
Getting it Right: Improving Spatial Consistency in Text-to-Image Models
Agneet Chatterjee*, Gabriela Ben Melech Stan*, Estelle Aflalo, Sayak Paul, Dhruba Ghosh, Tejas Gokhale, Ludwig Schmidt, Hannaneh Hajishirzi, Vasudev Lal, Chitta Baral, Yezhou Yang
ECCV 2024

Paper | Project | Code

revision
REVISION: Rendering Tools Enable Spatial Fidelity in Vision-Language Models
Agneet Chatterjee*, Yiran Luo*, Tejas Gokhale, Yezhou Yang, Chitta Baral
ECCV 2024

Paper | Project | Data | Code

lang_depth
On the Robustness of Language Guidance for Low-Level Vision Tasks: Findings from Depth Estimation
Agneet Chatterjee, Tejas Gokhale, Chitta Baral, Yezhou Yang
CVPR 2024

Paper | Project | Code

eval_dist_shift
Evaluating Multimodal Large Language Models Across Distribution Shifts and Augmentations
Aayush Atul Verma*, Amir Saeidi*, Shamanthak Hegde*, Ajay Therala*, Fenil Denish Bardoliya*, Nagaraju Machavarapu*, Shri Ajay Kumar Ravindhiran*, Srija Malyala*, Agneet Chatterjee*, Yezhou Yang, Chitta Baral
CVPR 2024 Workshop - Evaluation of Generative Foundation Models

Paper

neg_hallucination
Investigating and Addressing Hallucinations of LLMs in Tasks Involving Negation
Neeraj Varshney, Satyam Raj, Venkatesh Mishra, Agneet Chatterjee, Ritika Sarkar, Amir Saeidi, Chitta Baral
NAACL TrustNLP 2025 Workshop

Paper

lite
Accelerating LLM Inference by Enabling Intermediate Layer Decoding
Neeraj Varshney, Agneet Chatterjee, Mihir Parmar, Chitta Baral
NAACL 2024 (Findings)

Paper


This website's source code is borrowed from Jon Barron.
Last Updated: September 2025