Sriram Mandalika
Scholar

Sriram Mandalika

Google Scholar ID: 7DQaLdgAAAAJ
Hasso Plattner Institute, University of Potsdam
Deep LearningComputer VisionLearning MethodsDecision Making
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
7
 
H-index
2
 
i10-index
0
 
Publications
6
 
Co-authors
2
list available
Contact
Emailsriam.mandalika@uni-potsdam.deCVOpen ↗GitHubOpen ↗LinkedInOpen ↗
Publications
4 items
CoMAD: A Multiple-Teacher Self-Supervised Distillation Framework
2025
Cited
0
Generalizable Vision-Language Few-Shot Adaptation with Predictive Prompts and Negative Learning
2025
Cited
0
Replay to Remember (R2R): An Efficient Uncertainty-driven Unsupervised Continual Learning Framework Using Generative Replay
2025
Cited
0
PRIMEDrive-CoT: A Precognitive Chain-of-Thought Framework for Uncertainty-Aware Object Interaction in Driving Scene Scenario
2025
Cited
0
Resume (English only)
Academic Achievements
  • - Publications:
  • - Our Paper on Unsupervised Continual Learning got selected for Spotlight Presentation at ECAI 2025
  • - Paper on Unsupervised Continual Learning accepted at ECAI 2025, arxiv
  • - Paper on Precognitive Uncertainty-aware Chain-of-Thought (CoT) accepted at CVPR Precognition Workshop 2025, arxiv
  • - Our work on Active Learning is accepted at ICPR'24
  • - Awards: Outstanding Research Contribution Award 2025, SRM IST!
Research Experience
  • - Actively looking for working student (Werkstudent) or internship positions in Machine Learning, Computer Vision, and Product Management/Building
Education
  • - Master's Degree: Computer Science at Hasso Plattner Institute (HPI) & University of Potsdam
  • - Bachelor's Degree: Bachelor of Technology (B.Tech) from SRM Institute of Science and Technology, supervised by Prof. Dr. Athira M. Nambiar, focused on vision models, learning methodologies, and reasoning at the Center for AI in Computer Vision
Background
  • - Research Interests: Computer Vision and Deep Learning
  • - Professional Field: Learning methods for vision models, label-efficient (semi-supervised/unsupervised/self-supervised) approaches
  • - Introduction: Focused on methods that can independently perform iterative self-improvement and world models, open to new ideas and collaborations in related fields
Miscellany
  • - Personal Interests: Not specifically mentioned
Co-authors
2 total
Athira Nambiar
Athira Nambiar
Research Associate Professor, Dept. of Computational Intelligence, SRMIST, Chennai
LALITHA V
LALITHA V
S.R.M Institute of Science and Technology