Author

Sreedath Panat

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Oct 2026

What pass@k Cannot Measure: Evaluating Diversity and Capability Retention after Post-Training

pass@$k$, the fraction of problems a model solves within $k$ sampled attempts, is the field's default protocol for deciding whether reinforcement-learning (RL) post-training on verifiable rewards improved a model. At the population level, pass@$k$ depends only on a problem's probability of a correct sample, with no ter...

Subham Rath, R. Dandekar, R. Dandekar et al. · 0 citations

#machine learning Preprint Aug 2026

PRISM-UDE: Physics-Regularized Iterative Symbolic Modeling of 3nm FinFETs via Universal Differential Equation

PRISM-UDE (Physics-Regularized Iterative Symbolic Modeling via Universal Differential Equations), a framework that embeds a small neural network inside a physics-based transistor model, using the network only to learn the transport behavior that the analytical baseline misses, rather than replacing the physics altogeth...

Pranavanath Balamurali, Prathamesh Dinesh Joshi, R. Dandekar et al. · 0 citations

#artificial intelligence Preprint Aug 2026

BiasMix-Finance: Post-Generation KYC Guardrails for LLM Portfolio Advice

BiasMix-Finance (Mini) is introduced, a compact stress-test benchmark for constrained decision-making under biased LLM generations, with a 16-ETF universe, three investor profiles, and eight bias prompts, and the dataset, prompts, caps, and code are released.

Gaurav Kukreja, Parul Kukreja, Mohammed Abraar et al. · 0 citations