feat: add Karthik Soma's profile to the people section

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Author: karthiks1701

assets/images/people/karthik-soma.jpg

@@ -2,26 +2,22 @@
 name: Karthik Soma
 role: phd
 title: PhD Student
-short_bio: PhD student at Mila and Polytechnique Montréal working on swarm intelligence, collective decision-making, and multi-agent reinforcement learning.
+photo: karthik-soma.jpg
+short_bio: PhD student at Mila and Polytechnique Montréal working on collective intelligence, reinforcement learning, and robotics.
 supervisor: Giovanni Beltrame
-tags: [Swarm Robotics, Multi-Agent Reinforcement Learning, Collective Intelligence]
+tags: [Collective Intelligence, Reinforcement Learning, Robotics]
 email: karthik.soma@etud.polymtl.ca
 github: karthiks1701
 linkedin: https://www.linkedin.com/in/karthik-soma-b92166162/
 scholar: eJ5jLXoAAAAJ
 ---
 
-Karthik Soma is a PhD student at Polytechnique Montréal and Mila Quebec AI Institute, supervised by Prof. Giovanni Beltrame. He holds a B.Tech in Instrument and Control Engineering from the National Institute of Technology, Tiruchirappalli (GPA: 8.98/10.00).
-
-His research spans swarm intelligence, collective decision-making, and multi-agent reinforcement learning. He has published work at top robotics and AI venues including ICRA, TMLR, MRS, DARS, and ECAI.
+Karthik Soma is a PhD student at Polytechnique Montréal and Mila Quebec AI Institute, supervised by Prof. Giovanni Beltrame. His research investigates how simple agents following simple rules can give rise to a Hive Mind that exhibits sophisticated collective intelligence.
 
 ## Current Work
 
-Karthik's doctoral work focuses on collective intelligence in robot swarms — exploring how large groups of simple robots can make decisions, share resources, and navigate collaboratively. Current projects include:
-
-- **Swarm Biotactics**: Developing collective strategies for centroid estimation, flocking, and navigation using bio-hybrid swarms.
-- **Multi-Agent Reinforcement Learning**: Benchmarking MARL algorithms in complex coordination tasks with heterogeneous agents, in collaboration with Thales Digital Solutions Inc.
-- **The Hive Mind**: Investigating how swarm behavior emerges from a single RL agent trained across a population of robots.
+- **Hive Mind**: Exploring applications of the Hive Mind for RL, collective intelligence, and Meta Learning.
+- **Collective Spatial Intelligence**: Designing decentralised strategies that enable robot swarms to navigate complex environments collaboratively, relying only on local interactions and simple rules.
 
 ## Contact