Publications

Home Research Publications Projects Service Updates Blog CV

For citation metrics and the live publication record, see my Google Scholar.

Selected Accepted and Published Papers

FlipLLM: Efficient Bit-Flip Attacks on Multimodal LLMs using Reinforcement Learning
K. Khalil, K. A. Hoque
IEEE HOST 2026. Accepted.
RIFT: A Scalable Methodology for LLM Accelerator Fault Assessment using Reinforcement Learning
K. Khalil, K. A. Hoque
DATE 2026. Accepted.
The Singular Anchor: First Token Dominance in Large Language Model Attention Sinks
K. Khalil
5th Muslims in ML Workshop at NeurIPS 2025. Accepted.
TOGGLE: Temporal Logic-Guided Large Language Model Compression for Edge
K. Khalil, K. A. Hoque
ICCAD 2025. doi
PEARL: An Adaptive and Explainable Hardware Trojan Detection Using Open Source and Enterprise Large Language Models
R. K. Kundu, K. Khalil, K. A. Hoque
IEEE Access, 2025. doi
EPSILON: Adaptive Fault Mitigation in Approximate Deep Neural Network using Statistical Signatures
K. Khalil, K. A. Hoque
IJCNN 2025. doi
Novel fNIRS study on homogeneous symmetric feature-based transfer learning for brain-computer interface
K. Khalil, U. Asgher, Y. Ayaz
Scientific Reports, 2022.

Under Review

Spec2VLM: Specification-Guided Hardware-Aware Compression of VLMs via Constrained Design Space Exploration.

FairCompress: Fairness- and Energy-aware LLM Compression with Formal Guarantees.

VERMITHOR: Formally Verified Runtime Orchestration for Thermally-Safe Edge CPS Inference.

VeriNAIS: Signal Temporal Logic-Guided Neural Architecture Search for Verified Cyber-Physical AI.

The Dynamic Interaction Field Transformer: A Universal, Tokenizer-Free Language Architecture.