About Me
I lead Personalized Media Generation in the Llama org at Meta. I received my Master’s degree from Purdue University in 2018 and Bachelor’s degree from IIT Kharagpur in 2014. I work on large-scale machine learning algorithms for image and video generation, object recognition, retrieval and representation learning at the intersection of vision and language.
Interests
- Generative AI
- Computer Vision
- Multimodal Understanding
Education
MS in Computer Science and Statistics, 2018
Purdue University
BS in Computer Science, 2014
Indian Institute of Technology (IIT) Kharagpur
Publications
(2025).
MoCha: Towards Movie-Grade Talking Character Synthesis.
In arxiv:2503.23307.
(2025).
Movie Weaver: Tuning-Free Multi-Concept Video Personalization with Anchored Prompts.
In CVPR 2025.
(2024).
DirectorLLM for Human-Centric Video Generation.
In arxiv:2412.14484.
(2024).
Movie Gen: A Cast of Media Foundation Models.
In arxiv:2410.13720.
(2024).
Imagine yourself: Tuning-Free Personalized Image Generation.
In arxiv:2409.13346.
(2023).
Text-to-Sticker: Style Tailoring Latent Diffusion Models for Human Expression.
In ECCV 2024.
(2023).
Context Diffusion: In-Context Aware Image Generation.
In ECCV 2024.
(2023).
GenTron: Delving Deep into Diffusion Transformers for Image and Video Generation.
In CVPR 2024.
(2023).
Gen2Det: Generate to Detect.
In CVPRW 2024.
(2023).
Unaligned Video-Text Pre-training using Iterative Alignment.
Under Review.
(2022).
FaD-VLP: Fashion Vision-and-Language Pre-training towards Unified Retrieval and Captioning.
In EMNLP 2022.
(2022).
CommerceMM: Large-Scale Commerce MultiModal Representation Learning with Omni Retrieval.
In KDD 2022.
(2021).
Large-Scale Attribute-Object Compositions.
In arxiv:2105.11373.
Experience
Research Engineer
Meta AI
Research in Generative AI, Computer Vision, Vision & Language
Software Engineering Intern
Meta
Improving Ads Ranking
Graduate Student
Purdue University
Computer Science & Statistics
Software Engineer
Housing.com
Building the backend of Housing.com
Software Engineer
Samsung Research
Building Linux Kernel Device Drivers
Summer Intern
Texas Instruments
3D Computer Graphics & Navigation
Undergraduate Student
IIT Kharagpur
Computer Science & Engineering
Projects
*
Contact
- sinha.animesh34@gmail.com
- San Francisco, CA