activity
20242026
collaborators

5 papers

cs.LG2026

ComplianceGate: Classifier-Gated Multi-Tier LLM Routing for Inference in Regulated Industries

Abhishek Dey

Large language models deployed in regulated industries operate under two constraints: compliance enforcement and cost efficiency. Personally identifiable information (PII) in user…

cs.CL2026

Batch Prompting Suppresses Overthinking Reasoning Under Constraint: How Batch Prompting Suppresses Overthinking in Reasoning Models

Saurabh Srivastava, Janit Bidhan, Hao Yan +7

Large Reasoning Models (LRMs) achieve strong performance through explicit chain-of-thought reasoning but suffer from \textit{overthinking}: generating excessive reasoning tokens ev…

cs.SE2025

Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)

Abhishek Dey, Saurabh Srivastava, Gaurav Singh +1

This paper presents PICO-TINYML-BENCHMARK, a modular and platform-agnostic framework for benchmarking the real-time performance of TinyML models on resource-constrained embedded sy…

cs.CL2025

Multimodal Event Detection: Current Approaches and Defining the New Playground through LLMs and VLMs

Abhishek Dey, Aabha Bothera, Samhita Sarikonda +5

In this paper, we study the challenges of detecting events on social media, where traditional unimodal systems struggle due to the rapid and multimodal nature of data dissemination…

cs.CV2024

ResEmoteNet: Bridging Accuracy and Loss Reduction in Facial Emotion Recognition

Arnab Kumar Roy, Hemant Kumar Kathania, Adhitiya Sharma +2

The human face is a silent communicator, expressing emotions and thoughts through its facial expressions. With the advancements in computer vision in recent years, facial emotion r…