About me

My name is Amirhosein Javadi, and I am a Ph.D. student in ECE at UCSD, advised by Professor Tara Javidi. Prior to joining UCSD, I received a Bachelor of Science in Electrical Engineering from Sharif University of Technology in 2023, where I was fortunate to be advised by Professor Mohammad Hossein Yassaee and Professor Mohammad Hossein Rohban. I am generally curious about the intersection of Machine Learning, Generative AI, and Active Learning.

Publications

• A Single Image and Multimodality Is All You Need for Novel View Synthesis
  Authors: Amirhosein Javadi, Chi-Shiang Gau, Konstantinos D. Polyzos, Tara Javidi
  Published at ICLR 2026 Workshop on Multimodal Intelligence
  [Project Page] [Code]

• Active Sampling for Ultra-Low-Bit-Rate Video Compression via Conditional Controlled Diffusion
  Authors: Amirhosein Javadi, Shirin Saeedi Bidokhti, Tara Javidi
  [Project Page]

• Active World-Model with 4D-informed Retrieval for Exploration and Awareness
  Authors: Elaheh Vaezpour, Amirhosein Javadi, Tara Javidi
  ICLR 2026, The 2nd Workshop on World Models

• CI-CBM: Class-Incremental Concept Bottleneck Model for Interpretable Continual Learning
  Authors: Amirhosein Javadi, Tuomas Oikarinen, Tara Javidi, Tsui-Wei Weng
  Accepted at TMLR
  [Project Page] [Code]

• BLO-SAM: Bi-Level Optimization Based Finetuning of the Segment Anything Model for Overfitting-Preventing Semantic Segmentation
  Authors: Li Zhang, Youwei Liang, Ruiyi Zhang, Amirhosein Javadi, Pengtao Xie
  ICML 2024

Experience

• Incoming Intern at Apple
  Summer 2026

• Research Intern at Soter Technology, Inc.

  • Visual World Models. Developed camera-controlled novel-view video generation, where users specify the camera trajectory, from single/multi-view images and videos, improving performance on downstream monitoring and safety tasks in extremely complex industrial environments.

News

• The Electrical and Computer Engineering Department Fellowship, University of California San Diego, 2023.