Pillars and Envy

Posted by : at

Category : Personal


I remember hearing that plants wither bearing the sorrow of its surrounding. As sad as it sounds, I think I feel good knowing this. At least there's an existing object that makes progress towards a perceived goal, at least one that its convinced of? I used to consider this specific trait a superpower, being able to take sorrow? or someone else's pain? that they don't really deserve and inflict it upon one-self, and have one of the versions of myself (in the parallel fantasy world that I keep slipping into while day dreaming every other hour) be able to do that! Well, now my pillars argue if it is from a place of empathy, you know, that I do not want someone else to go through hardship, or is it just plain savior complex?

For someone who is lost and confused of one-self, conflicting pillars can feel like echos that only keep getting louder and louder and louder. I'd like to believe that the internal pillars in one's minds are more 'mixture of experts' than 'hierarchical models' (At least I try to convince myself so). Everytime you have a hypothesis or a simple thought even, and you think for a little while and you hear arguments against it, it helps to convince yourself, that just because your questions come after more thinking and time, it doesn't mean it comes from a higher place or a more logical one.

I think, we humans, work in a way where, unfortunately, no matter what your first hypothesis/thought is, you are likely to question it after giving it some time, and if you inherently believe your system1 (first) thinking is always wrong, and you always need system2, this unfortunately gets in a never ending loop of doom. That way, no matter what the scenario or the situation is, all you're sure of or what you've learnt over time, is the fact that you question yourself about everything you think.

I’d like to think my pillars are a bunch of skeptical experts. I guess I choose a pillar given a scenario, and the moment this pillar provides me with a suggestion, the doubters rush in to question this. That way, I don’t have to believe all I am is ā€˜questions and doubts’, but rather, a bunch of ā€˜cynical gramps’ who, as much as they fight each other wanting to be right, are also trying to be wrong for my sake. :D

Side note, I’ve been a very jealous and envious kid (more jealous than envious, but, oh no, is this from a place of vanity?) that I’ve let it drive me to horrible places, be it friendships, relationships or even my own self, but I should be honest that it’s the same lil bros up in my head, although through harsh and rash methods, that have made me more understanding of myself and the world around me. It is only ironical that, maybe despite all this, its the same undecisive council thats the only (only?) thing (that I believe) that my I’m not the most happy with, about myself. I think I should be honest and agree that sometimes I’m envious of people who has got their pillars aligned (Or am I really? Well most pillars would agree on this one haha). Damn, I wonder what that must feel like!

About Vihaan Akshaay

I am an Applied AI Researcher with first-author publications at top-tier venues, including ICLR 2025 and NeurIPS 2023, in Computer Vision and Deep Reinforcement Learning. My work spans five research internships across premier institutions, including The Jackson Laboratory (JAX), IIT Madras, Georgia Tech, NTU Singapore, and a joint role at UC Santa Barbara and Carnegie Mellon University.

My research bridges disciplines—developing AI systems for biological behavior analysis, robotics, mechanical systems, and Earth sciences. At IIT Madras, I led the iBot Robotics Club and co-developed the ARTEMIS Railroad Crack Detection Robot, winning the International James Dyson Award. My Master’s thesis on unsupervised behavior recognition in mice was advised by B. Ravindran and Dr. Vivek Kumar at JAX.

I recently completed my M.S. in Computer Science at UC Santa Barbara, working under Lei Li and Yu-Xiang Wang. Inspired by human problem-solving strategies, I proposed a bi-directional framework for goal conditioning in state-space search. I also introduced an edge-attention-based U-Net for environmental segmentation and helped curate a large-scale landslide detection dataset with Gen Li using 40 years of Landsat imagery.

Other projects include analyzing the stability of Deep Q-Networks with Siva Theja Maguluri at Georgia Tech and designing kernelized deep randomized models (eDRVFLs) with P. N. Suganthan at NTU Singapore.

I specialize in translating cutting-edge AI theory into practical, high-impact solutions across domains. I am currently seeking opportunities in applied AI research or machine learning engineering roles, particularly those focused on impactful, real-world applications.

Useful Links