collaborators

12 papers

cs.LG2026

Kilobyte Models: Neural Networks as a Seed and a Quantized Latent

Sahil Rajesh Dhayalkar

The cost of storing and transmitting a trained neural network scales with its parameter count, a bottleneck for over-the-air updates, on-device libraries, and other bandwidth-bound…

cs.AI2026

Overcoming the Impedance Mismatch: A Theoretical Roadmap for Fusing Foundation Models and Knowledge Graphs

Sahil Rajesh Dhayalkar

Modern artificial intelligence remains fundamentally divided between the continuous, probabilistic spaces of Foundation Models and the discrete, deterministic structures of Knowled…

cs.FL2026

Logic-Gated Time-Shared Feedforward Networks for Alternating Finite Automata: Exact Simulation and Learnability

Sahil Rajesh Dhayalkar

We present a formal and constructive framework for simulating Alternating Finite Automata (AFAs) using Logic-Gated Time-Shared Feedforward Networks (LG-TS-FFNs). Unlike prior neura…

cs.AI2026

Reasoning Stabilization Point: A Training-Time Signal for Stable Evidence and Shortcut Reliance

Sahil Rajesh Dhayalkar

Fine-tuning pretrained language models can improve task performance while subtly altering the evidence a model relies on. We propose a training-time interpretability view that trac…

cs.AI2025

Attention as Binding: A Vector-Symbolic Perspective on Transformer Reasoning

Sahil Rajesh Dhayalkar

Transformer-based language models display impressive reasoning-like behavior, yet remain brittle on tasks that require stable symbolic manipulation. This paper develops a unified p…

stat.CO2025

Particle Filter Made Simple: A Step-by-Step Beginner-friendly Guide

Sahil Rajesh Dhayalkar

The particle filter is a powerful framework for estimating hidden states in dynamic systems where uncertainty, noise, and nonlinearity dominate. This mini-book offers a clear and s…