I’m currently a second-year PhD student at the Halıcıoğlu Data Science Institute at UC San Diego, where I have the privilege of being advised by Prof. Zhuowen Tu. My research lies at the intersection of Computer Vision and Trustworthy AI, primarily focusing on developing controllable deep neural network architectures. Please find my CV here.

Publications

• Lay-Your-Scene: Open-Vocabulary Text to Layout Generation
  Divyansh Srivastava, Xiang Zhang, Chenru Wen, He Wen, Zhuowen Tu
  Under review
  arXiv (coming soon)

• SAND: Enhancing Open-Set Neuron Descriptions through Spatial Awareness
  Anvita Srinivas, Tuomas Oikarinen, Divyansh Srivastava, and Tsui-Wei Weng
  Winter Conference on Applications of Computer Vision, 2025 (WACV 2025)
  arXiv (coming soon)

• VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance
  Divyansh Srivastava*, Ge Yan*, and Tsui-Wei Weng
  Neural Information Processing Systems, 2024 (NeurIPS 2024)
  Paper Link | Code | Project Page

• Corrupting Neuron Explanations of Deep Visual Features
  Divyansh Srivastava, Tuomas Oikarinen, and Tsui-Wei Weng
  International Conference on Computer Vision, 2023 (ICCV 2023)
  Paper Link | Code

• Structured Aleatoric Uncertainty in Human Pose Estimation
  Nitesh B. Gundavarapu, Divyansh Srivastava, Rahul Mitra, Abhishek Sharma, and Arjun Jain
  IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2019 (CVPR 2019)
  Paper Link | Code