Farhan Sheth
Multimodal, trustworthy, and applied AI across clinical privacy, speech forensics, human-centered learning, scientific machine learning, and agricultural intelligence.
2026–2027 research opportunities
Seeking prospective advisors and funded PhD opportunities for 2026–2027.
Academic impact
- Total citations
- 116
- h-index
- 7
- i10-index
- 6
- Publications
- 18
News
Uc-PrUn accepted at ACM Transactions on Computing for Healthcare
Learning heat accepted at International Communications in Heat and Mass Transfer
SIGNAL accepted at EACL 2026
ORBIT accepted at Interspeech 2026
Two synthetic-speech papers accepted at IJCNLP-AACL 2025
How the work connects
I study multimodal and trustworthy AI across clinical, speech, agricultural, and scientific applications.
Selected publications
- Selective Token-Level Cryptographic Redaction for Privacy-Preserving Clinical Deployment of Large Language Models
HERALD protects selected sensitive tokens with client-side deterministic ciphertext while preserving context and downstream clinical utility.
- RecruitView: A Multimodal Dataset for Predicting Personality and Interview Performance for Human Resources Applications
RecruitView contributes a 2,011-clip multimodal interview dataset and CRMF, a geometry-aware model that improves correlation while using fewer parameters.
- Synergizing Zero-Shot Cross-Lingual Alzheimer Detection with Language-Invariant Multimodal Bi-Geometric Adversarial Learning
ORBIT combines cross-attentive multimodal fusion, language adversaries, and spherical-hyperbolic learning for zero-shot cross-lingual Alzheimer detection.
- Bridging Attribution and Open-Set Detection using Graph-Augmented Instance Learning in Synthetic Speech
SIGNAL joins graph neural networks with confidence-aware KNN inference to attribute synthetic speech and detect unseen generators.
Discuss research
Open to conversations with prospective PhD advisors, research mentors, and academic collaborators.