collaborators

9 papers

cs.CL2026

Calibration Drift Under Reasoning: How Chain-of-Thought Budgets Induce Overconfidence in Large Language Models

Prakul Sunil Hiremath, Harshit R. Hiremath

The ability of large language models (LLMs) to express calibrated uncertainty is important for safe deployment. Chain-of-thought (CoT) reasoning is widely used to improve accuracy…

cs.LG2026

Early Detection of Latent Microstructure Regimes in Limit Order Books

Prakul Sunil Hiremath, Vruksha Arun Hiremath

Limit order books can transition rapidly from stable to stressed conditions, yet standard early-warning signals such as order flow imbalance and short-term volatility are inherentl…

cs.CR2026

Sensitivity Uncertainty Alignment in Large Language Models

Prakul Sunil Hiremath, Harshit R. Hiremath

We propose Sensitivity-Uncertainty Alignment (SUA), a framework for analyzing failures of large language models under adversarial and ambiguous inputs. We argue that adversarial se…

cs.AR2026

Photonic AI: A Hybrid Diffractive Holographic Neural System for Passive Optical Real-Time Image Classification

Prakul Sunil Hiremath

Edge intelligence is constrained by the energy and latency costs of shuttling data through electronic memory hierarchies. Optical systems offer a fundamentally different computatio…

cs.LG2026

Regret-Aware Policy Optimization: Environment-Level Memory for Replay Suppression under Delayed Harm

Prakul Sunil Hiremath

Safety in reinforcement learning (RL) is typically enforced through objective shaping while keeping environment dynamics stationary with respect to observable state-action pairs. U…

cs.LG2026

GIRL: Generative Imagination Reinforcement Learning via Information-Theoretic Hallucination Control

Prakul Sunil Hiremath

Model-based reinforcement learning (MBRL) improves sample efficiency by optimizing policies inside imagined rollouts, but long-horizon planning degrades when model errors compound…