Publications

2026

Preprint
FastGuide: Accelerating Reward Guidance for Diffusion Large Language Models
Darshan Thaker, Lachlan MacDonald, René Vidal
PDF
Preprint
ANaLOG: Anisotropic Native-Latent Operator Guidance for Solving Inverse Problems
Darshan Thaker, Lachlan MacDonald, René Vidal
PDF
ICML
REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
Buyun Liang, Jinqi Luo, Liangzu Peng, Kwan Ho Ryan Chan, Darshan Thaker, Kaleab A. Kinfu, Fengrui Tian, Hamed Hassani, René Vidal
PDF
ICLR Workshop
SSCD: Sparse Semantic Concept Defense Against Semantic Adversarial Attacks to Image Classifiers
Nghia Nguyen, Darshan Thaker, Konstantinos Emmanouilidis, Tianjiao Ding, Rene Vidal
PDF
ISBI
Scale-Cascaded Diffusion Models for Super-Resolution in Medical Imaging
Darshan Thaker, Mahmoud Mostapha, Radu Miron, Shihan Qiu, Mariappan Nadar
PDF

2025

ICCV
Frequency-Guided Posterior Sampling for Diffusion-Based Image Restoration
Darshan Thaker, Abhishek Goyal, René Vidal
PDF
NeurIPS
SECA: Semantically Equivalent & Coherent Attacks for Eliciting LLM Hallucinations
Buyun Liang, Liangzu Peng, Jinqi Luo, Darshan Thaker, Kwan Ho Ryan Chan, René Vidal
PDF
Preprint
KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs
Buyun Liang, Kwan Ho Ryan Chan, Darshan Thaker, Jinqi Luo, René Vidal
PDF

2024

NeurIPS
PaCE: Parsimonious Concept Engineering for Large Language Models
Jinqi Luo, Tianjiao Ding, Kwan Ho Ryan Chan, Darshan Thaker, Aditya Chattopadhyay, Chris Callison-Burch, René Vidal
PDF

2023

Preprint
A Linearly Convergent GAN Inversion-based Algorithm for Reverse Engineering of Deceptions
Darshan Thaker, Paris Giampouras, René Vidal
PDF

2022

ICML
Reverse Engineering $\ell_p$ attacks: A block-sparse optimization approach with recovery guarantees
Darshan Thaker, Paris Giampouras, René Vidal
PDF

2019

MS Thesis
Understanding the Convergence of Adversarial Training for Overparameterized Linear Neural Networks
Darshan Thaker
PDF
AAAI Workshop
Combinatorial Optimization by Graph Pointer Networks and Hierarchical Reinforcement Learning
Qiang Ma, Suwen Ge, Danyang He, Darshan Thaker, Iddo Drori
PDF
MLCB
Accurate Protein Structure Prediction by Embeddings and Deep Learning Representations
Iddo Drori, Darshan Thaker, Arjun Srivatsa, Daniel Jeong, Yueqi Wang, Linyong Nan, Fan Wu, Dimitri Leggas, Jinhao Lei, Weiyi Lu, others
PDF

2018

UG Thesis
Generating Synthetic Question-Answer Pairs for Transfer Learning in Biomedical Question Answering
Darshan Thaker
PDF