2 citations · 10 across the 26 of their papers we have counts for
17 papers · 1 filter
Three methods, one problem: Classical and AI approaches to no-three-in-line
Pranav Ramanathan, Thomas Prellberg, Matthew Lewis +4
The No-Three-In-Line problem asks for the maximum number of points that can be placed on an n by n grid with no three collinear, representing a famous problem in combinatorial geom…
Forecasting N-Body Dynamics: A Comparative Study of Neural Ordinary Differential Equations and Universal Differential Equations
Suriya R S, Prathamesh Dinesh Joshi, Rajat Dandekar +2
The n body problem, fundamental to astrophysics, simulates the motion of n bodies acting under the effect of their own mutual gravitational interactions. Traditional machine learni…
Adaptive tumor growth forecasting via neural & universal ODEs
Kavya Subramanian, Prathamesh Dinesh Joshi, Raj Abhijit Dandekar +2
Forecasting tumor growth is critical for optimizing treatment. Classical growth models such as the Gompertz and Bertalanffy equations capture general tumor dynamics but may fail to…
Physics-Informed Neural ODEs with Scale-Aware Residuals for Learning Stiff Biophysical Dynamics
Kamalpreet Singh Kainth, Prathamesh Dinesh Joshi, Raj Abhijit Dandekar +2
Neural differential equations offer a powerful framework for modeling continuous-time dynamics, but forecasting stiff biophysical systems remains unreliable. Standard Neural ODEs a…
Simulating Misinformation Propagation in Social Networks using Large Language Models
Raj Gaurav Maurya, Vaibhav Shukla, Raj Abhijit Dandekar +2
Misinformation on social media thrives on surprise, emotion, and identity-driven reasoning, often amplified through human cognitive biases. To investigate these mechanisms, we mode…
EARS-UDE: Evaluating Auditory Response in Sensory Overload with Universal Differential Equations
Miheer Salunke, Prathamesh Dinesh Joshi, Raj Abhijit Dandekar +2
Auditory sensory overload affects 50-70% of individuals with Autism Spectrum Disorder (ASD), yet existing approaches, such as mechanistic models (Hodgkin Huxley type, Wilson Cowan,…
Muon: Training and Trade-offs with Latent Attention and MoE
Sushant Mehta, Raj Dandekar, Rajat Dandekar +1
We present a comprehensive theoretical and empirical study of the Muon optimizer for training transformers only with a small to medium decoder (30M - 200M parameters), with an emph…
A study of Universal ODE approaches to predicting soil organic carbon
Satyanarayana Raju G. V., Prathamesh Dinesh Joshi, Raj Abhijit Dandekar +2
Soil Organic Carbon (SOC) is a foundation of soil health and global climate resilience, yet its prediction remains difficult because of intricate physical, chemical, and biological…
BULL-ODE: Bullwhip Learning with Neural ODEs and Universal Differential Equations under Stochastic Demand
Nachiket N. Naik, Prathamesh Dinesh Joshi, Raj Abhijit Dandekar +2
We study learning of continuous-time inventory dynamics under stochastic demand and quantify when structure helps or hurts forecasting of the bullwhip effect. BULL-ODE compares a f…
Decoders Laugh as Loud as Encoders
Eli Borodach, Raj Dandekar, Rajat Dandekar +1
From the dawn of the computer, Allen Turing dreamed of a robot that could communicate using language as a human being. The recent advances in the field of Large Language Models (LL…
Vision-Language Models display a strong gender bias
Aiswarya Konavoor, Raj Abhijit Dandekar, Rajat Dandekar +1
Vision-language models (VLM) align images and text in a shared representation space that is useful for retrieval and zero-shot transfer. Yet, this alignment can encode and amplify…
Unifying Mixture of Experts and Multi-Head Latent Attention for Efficient Language Models
Sushant Mehta, Raj Dandekar, Rajat Dandekar +1
We present MoE-MLA-RoPE, a novel architecture combination that combines Mixture of Experts (MoE) with Multi-head Latent Attention (MLA) and Rotary Position Embeddings (RoPE) for ef…
Understanding Malware Propagation Dynamics through Scientific Machine Learning
Karthik Pappu, Prathamesh Dinesh Joshi, Raj Abhijit Dandekar +2
Accurately modeling malware propagation is essential for designing effective cybersecurity defenses, particularly against adaptive threats that evolve in real time. While tradition…
Physical Informed Neural Networks for modeling ocean pollutant
Karishma Battina, Prathamesh Dinesh Joshi, Raj Abhijit Dandekar +2
Traditional numerical methods often struggle with the complexity and scale of modeling pollutant transport across vast and dynamic oceanic domains. This paper introduces a Physics-…
Latent Multi-Head Attention for Small Language Models
Sushant Mehta, Raj Dandekar, Rajat Dandekar +1
We present the first comprehensive study of latent multi-head attention (MLA) for small language models, revealing interesting efficiency-quality trade-offs. Training 30M-parameter…
Regional Tiny Stories: Using Small Models to Compare Language Learning and Tokenizer Performance
Nirvan Patil, Malhar Abhay Inamdar, Agnivo Gosai +7
Small Language Models (SLMs) offer efficient alternatives to LLMs for specific domains. The 2023 TinyStories study developed an English dataset that allows SLMs with 1 to 10 millio…
NanoVLMs: How small can we go and still make coherent Vision Language Models?
Mukund Agarwalla, Himanshu Kumar, Raj Dandekar +2
Vision-Language Models (VLMs), such as GPT-4V and Llama 3.2 vision, have garnered significant research attention for their ability to leverage Large Language Models (LLMs) in multi…