Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
About
Viswonathan Manoranjan is an M.S. Computer Science student at UNC Chapel Hill working on multimodal human behavior, gesture generation, and language model evaluation.
Posts
Future Blog Post
Published:
This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.
Blog Post number 4
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 3
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 2
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 1
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
portfolio
Recipe App - RNN-based Recipe Suggestion
Python application that takes input queries (ingredients) and suggests recipes through an RNN model
Face Recognition Attendance System
OpenCV-based facial recognition application that takes attendance based on facial features detected through the HOG method
Monocular Depth Estimation
Application that generates depth maps from monocular images for autonomous electric vehicles
Multi-person Pose Detection
Python program that detects individual people from video frames using YOLO and Mediapipe pose detection
Optimized Reversible Cellular Automata Based Clustering
Final year project on optimizations to clustering using Reversible Cellular Automata
INTEL Hackathon - Automatic Personality Recognition
An automatic personality recognition system trained and running on Intel oneAPI Optimization for Tensorflow and PyTorch
Hyper-Personalization - Financial Guidance Platform
A comprehensive platform that leverages AI to deliver hyper-personalised financial insights and product recommendations
IdentAI - Identity Impersonation Detection
Identity impersonation detection web application using ML models for speech, language, and emotion detection
Multi-lingual LLM Evaluation and Alignment
Evaluated alignment methods for large language models across 10+ languages, focusing on fairness, robustness, and safety
Polylogue: A Multi-Persona Debate Simulation Framework
Automated evaluation pipeline assessing environmental and ethical alignment across large language models
publications
Learning Personalised Models for Automatic Self-Reported Personality Recognition
Published in Understanding Social Behavior in Dyadic and Small Group Interactions, PMLR 173:53-73, 2022
This paper presents personalized models for automatic personality recognition from self-reported data.
Optimized Reversible Cellular Automata Based Clustering
Published in Cellular Automata and Discrete Complex Systems (AUTOMATA 2023), 2023
This paper presents an optimized approach to clustering using reversible cellular automata.
Generalised Bias Mitigation for Personality Computing
Published in Proceedings of the 1st International Workshop on MRAC 2023, ACM MM conference, 2023
This paper presents generalized methods for bias mitigation in personality computing applications.
Towards Generalised and Incremental Bias Mitigation in Personality Computing
Published in IEEE Transactions on Affective Computing, 2024
This paper presents novel approaches for generalized and incremental bias mitigation in personality computing systems.
When Identity Overrides Incentives: Representational Choices as Governance Decisions in Multi-Agent LLM Systems
Published in ACM FAccT 2026, 2026
We investigate whether LLM agents function as payoff-sensitive strategic actors or as identity-driven role followers, showing that representational design choices are not implementation details but governance decisions.
SHARD: Safe and Helpful Alignment via Self-Reframing Distillation
Published in Under Review, 2026
We introduce SHARD, a self-reframing distillation method that rewrites sensitive prompts to surface benign intent, reframes responses into safe and helpful ones, and fine-tunes the model on its self-reframed outputs — improving safe-helpfulness without sacrificing safety.
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
CSPC31: Principles of Programming Languages
Teaching Assistant, National Institute of Technology, Tiruchirappalli, 2023
Teaching Assistant for Principles of Programming Languages course. Class size: 75 students.
INLS 509-001: Information Retrieval
Teaching Assistant, University of North Carolina at Chapel Hill, 2026
Teaching Assistant for INLS 509-001: Information Retrieval (Fall 2026), taught by Yue “Ray” Wang.