2 citations · 10 across the 26 of their papers we have counts for
5 papers · 1 filter
What pass@k Cannot Measure: Evaluating Diversity and Capability Retention after Post-Training
Subham Rath, Raj Dandekar, Rajat Dandekar +1
pass@, the fraction of problems a model solves within sampled attempts, is the field's default protocol for deciding whether reinforcement-learning (RL) post-training on ver…
PRISM-UDE: Physics-Regularized Iterative Symbolic Modeling of 3nm FinFETs via Universal Differential Equation
Pranavanath Balamurali, Prathamesh Dinesh Joshi, Raj Abhijit Dandekar +2
Compact transistor models are the mathematical backbone of circuit simulation. However, at advanced nodes such as 3nm, transport physics becomes too complex for traditional hand-de…
BiasMix-Finance: Post-Generation KYC Guardrails for LLM Portfolio Advice
Gaurav Kukreja, Parul Kukreja, Mohammed Abraar +3
Large language models (LLMs) can generate plausible-sounding ETF portfolios while silently violating basic KYC-style constraints on risk, fees, and diversification. This is especia…
SciML in the Wild: A Diagnostic Study of When Structural Priors Help and When They Hurt
Vrishank Sai Anand, Prathamesh Dinesh Joshi, Raj Abhijit Dandekar +2
Scientific Machine Learning (SciML) methods such as Neural Ordinary Differential Equations (NODEs), Physics-Informed Neural Networks (PINNs), and Universal Differential Equations (…
Beyond Passive Viewing: A Pilot Study of a Hybrid Learning Platform Augmenting Video Lectures with Conversational AI
Mohammed Abraar, Raj Abhijit Dandekar, Rajat Dandekar +1
The exponential growth of AI education has brought millions of learners to online platforms, yet this massive scale has simultaneously exposed critical pedagogical shortcomings. Tr…