Dev Patel

Dev Patel, Gabrielle Gervacio, Diekola Raimi et al.

Large Language Models require substantial computational resources for inference, posing deployment challenges. While dynamic pruning offers superior efficiency over static methods through adaptive circuit selection, it exacerbates alignment degradation by retaining only input-dependent safety-critical circuit preservation across diverse inputs. As a result, addressing these heightened alignment vulnerabilities remains critical. We introduce Alignment-Aware Probe Pruning (AAPP), a dynamic structured pruning method that adaptively preserves alignment-relevant circuits during inference, building upon Probe Pruning. Experiments on LLaMA 2-7B, Qwen2.5-14B-Instruct, and Gemma-3-12B-IT show AAPP improves refusal rates by 50\% at matched compute, enabling efficient yet safety-preserving LLM deployment.

Siddharth Chaudhary, Dev Patel, Maheep Chaudhary et al.

The quadratic complexity of transformers fundamentally limits reasoning system deployment in resource-constrained and long-context settings. We introduce Hydra, a modular architecture based upon a state-space backbone which adaptively routes between complementary efficiency mechanisms: sparse global attention, mixture-of-experts, and dual memories comprising a reasoning workspace and product key memory. We evaluate a 29M parameter model measuring logical chaining accuracy and throughput on synthetic sequences, plus throughput on WikiText. Ablation studies use component-specific synthetic datasets to isolate individual mechanisms. Hydra achieves $3.01\times$ and $3.0\times$ throughput gains at 8K tokens for synthetic and WikiText datasets, respectively, and $10\times$ accuracy improvements on multi-step logical composition compared to equal-sized transformers. Ablations confirm each component's contribution: sparse attention captures long-range dependencies, experts specialize to input domains, and product key memory enables selective retrieval.

Yash Mehta, Dev Patel, Manik Lal Das

A unique identification for citizens can lead to effective governance to manage and provide citizen-centric services. While ensuring this service, privacy of the citizens needs to be preserved. Aadhaar, the identification system by UIDAI has faced some critics regarding its privacy preserving feature. This paper discusses those concerns in Aadhaar system and proposed a new model for the Aadhaar system. The proposed solution is aimed to address the issue of collusion of third party service providers and profiling of Aadhaar users. The proposed solution uses a distributed model capturing the Aadhaar system, in which data of users is decentralized and stored in zonal office's databases as well as the CIDR. The proposed solution provides the functioning of the authentication process of the Aadhaar system more effective, as it reduces the number of requests being handled directly by the CIDR and also tackles the concern of correlation of data.

Dev Patel, Li Jun Heng, Abesh Rahman et al.

This paper presents a new optimal fuzzy approach based on particle swarm optimization evolutionary algorithm for controlling the servo actuating system. It is clear that attaining the maximum stability margin is the prominent goal in control design of servo actuating systems. To reach the control goal, two main steps of design are required, an appropriate identification method and a controller development. Hence, the nonlinear system is first identified by the fuzzy algorithm. Then, the controller parameters and the algorithms weighting functions are tuned through the Particle Swarm Optimization algorithm. The objective function of optimal control strategy is such that the minimum error between the actual and the identified data is attained. The effectiveness of the proposed approach comparing to the conventional fuzzy control with regular parameter tuning is illustrated and analyzed in the simulations.