Personal website of Vishal V, featuring writing, ideas, projects, and research
Psychostimulants act on monoamine systems including the dopamine transporter (DAT), a key regulator of dopamine reuptake following synaptic release. While these compounds can enhance energy, cognition, and sociability, their clinical utility is often limited by their abuse...
This paper proposes that a fundamental organizational trend in biological, cognitive, cultural, and technological evolution is the emergence of progressively more capable representation–interpretation systems. Across these domains, evolution has repeatedly generated systems in...
Modern AI systems are increasingly being evaluated for their ability to reason, code, prove theorems, use tools, and long-horizon research tasks. These are powerful capabilities, but they share a structural limitation: the representational frame within which the model operates,...
What does it mean to understand the world? Contemporary world models often operationalize understanding as accurate future prediction in latent or observation space. Developmental cognitive science, however, suggests a different view: human understanding emerges through the...
A growing body of work points to the great promise of AI systems that can continually expand their capabilities as they operate in an open-ended environment. But yet there is no coherent definition of open-endedness or theory about how an agent ought to explore an open-ended...
Research notes on Elements of information theory.
Although most theories posit that natural behavior can be explained as maximizing some form of extrinsic reward, often called utility, some behaviors appear to be reward independent. For instance, spontaneous motor babbling in human newborns and curiosity in little kids and other...
In recent years there has been a tremendous surge in the general capabilities of AI systems, mainly fuelled by training foundation models on internet-scale data. Nevertheless, the creation of open-ended, ever self-improving AI remains elusive. In this position paper, we argue...
The Platonic Representation Hypothesis suggests that representations from neural networks are converging to a common statistical model of reality. We show that the existing metrics used to measure representational similarity are confounded by network scale: increasing model depth...
Deep networks learn internal representations whose geometry—how features bend, rotate, and evolve—affects both generalization and robustness. Existing similarity measures such as CKA or SVCCA capture pointwise overlap between activation sets, but miss how representations change...
Progress in embodied intelligence increasingly depends on scalable data infrastructure. While vision and language have scaled with internet corpora, learning physical interaction remains constrained by the lack of large, diverse, and richly annotated human activity data. We...
Research notes on Algebraic topology.
A long-standing goal in robot learning is to develop methods for robots to acquire new skills autonomously. While reinforcement learning (RL) comes with the promise of enabling autonomous data collection, it remains challenging to scale in the real-world partly due to the...
Bayesian inference typically focuses upon two issues. The first is estimating the parameters of some model from data, and the second is quantifying the evidence for alternative hypotheses—formulated as alternative models. This paper focuses upon a third issue. Our interest is in...
Vision-Language-Action (VLA) models have achieved strong semantic generalization for embodied policy learning, yet they learn reactive observation-to-action mappings without explicitly modeling how the physical world evolves under intervention. A growing body of work addresses...
This tutorial serves as a comprehensive guide for understanding graph databases, focusing on the fundamentals of graph theory while showcasing practical applications across various fields. It starts by introducing foundational concepts and delves into the structure of graphs...
Drawing on the correspondence between the graph Laplacian, the Laplace-Beltrami operator on a manifold , and the connections to the heat equation , we propose a geometrically motivated algorithm for constructing a representation for data sampled from a low dimensional manifold...
Research notes on DISCRETE DIFFERENTIAL GEOMETRY: AN APPLIED INTRODUCTION.
Probabilistic graphical modeling is a branch of machine learning that uses probability distributions to describe the world, make predictions, and support decision-making under uncertainty. Underlying this modeling framework is an elegant body of theory that bridges two...
Research notes on CS168: The Modern Algorithmic Toolbox Lectures #11: Spectral Graph Theory, I.
The Hopf fibration is an important object in mathematics and physics. A landmark discovery in topology and a fundamental object in the theory of Lie groups, the Hopf fibration has a wide variety of physical applications including magnetic monopoles, rigid body mechanics, and...
Post-GPU compute is a bet that new hardware will make different primitives cheap. When the primitive changes, the winning model classes change. Extropic is a bet that sampling becomes that primitive.
Connecting probabilistic graphical models to energy-based formulations, and showing how sampling replaces optimization as the core mechanism for inference and computation.
System design evaluation of the Zotero iOS client based on long-term usage as a knowledge power user tool. Zotero is an open-source reference manager widely used in academic and research workflows.
I finally deleted my WordPress setup and replaced it with a system I actually control. Markdown, Git, Next.js and Contentlayer now run the show and this stack will survive anything because it is simple, portable and mine.