# Tianchen Zhao — Publications > Research papers by Tianchen Zhao spanning deepfake detection, face anti-spoofing, generative modeling, neural quantum states, and scientific machine learning. ## Topic Areas - Deepfake Detection and Face Security - Generative Modeling, Robustness, and Vision-Language Adaptation - Neural Quantum States and Scientific Machine Learning - Quantum-Inspired Scientific Computing and Finance ## Papers ### Deepfake Detection and Face Security - [Learning Self-Consistency for Deepfake Detection](https://ericolony.github.io/Publications/learning-self-consistency-for-deepfake-detection/) (ICCV 2021): Detects deepfakes by learning to extract and compare source-feature inconsistencies within forged images, achieving state-of-the-art cross-dataset generalization. - [Principles of Designing Robust Remote Face Anti-Spoofing Systems](https://ericolony.github.io/Publications/principles-of-designing-robust-remote-face-anti-spoofing-systems/) (arXiv 2024): Presents a comprehensive taxonomy of face anti-spoofing threats and proposes design principles for building robust systems resilient to digital injection, deepfake, and replay attacks. - [Optimal Transport-Guided Source-Free Adaptation for Face Anti-Spoofing](https://ericolony.github.io/Publications/optimal-transport-guided-source-free-adaptation-for-face-anti-spoofing/) (CVPR 2025): Enables privacy-preserving test-time adaptation of face anti-spoofing models via optimal transport-guided prototype matching and geodesic mixup augmentation. - [AuthGuard: Generalizable Deepfake Detection via Language Guidance](https://ericolony.github.io/Publications/authguard-generalizable-deepfake-detection-via-language-guidance/) (WACV 2025): Integrates language guidance and commonsense reasoning into deepfake detection via vision-language contrastive learning, achieving state-of-the-art generalization across unseen forgery methods. ### Generative Modeling, Robustness, and Vision-Language Adaptation - [Diversity-Sensitive Conditional Generative Adversarial Networks](https://ericolony.github.io/Publications/diversity-sensitive-conditional-generative-adversarial-networks/) (ICLR 2019): Proposes a simple diversity-sensitive regularization for conditional GANs that explicitly encourages diverse outputs, solving mode collapse across image translation, inpainting, and video prediction. - [Adversarial Defense via Learning to Generate Diverse Attacks](https://ericolony.github.io/Publications/adversarial-defense-via-learning-to-generate-diverse-attacks/) (ICCV 2019): Trains a stochastic generator to produce diverse adversarial attacks, yielding more robust defenses than single-attack adversarial training. - [Salient Concept-Aware Generative Data Augmentation](https://ericolony.github.io/Publications/salient-concept-aware-generative-data-augmentation/) (arXiv 2025): Proposes a salient concept-aware generative augmentation framework that disentangles class-discriminative features from irrelevant context, improving fine-grained recognition under both conventional and long-tail settings. - [Model Diagnosis and Correction via Linguistic and Implicit Attribute Editing](https://ericolony.github.io/Publications/model-diagnosis-and-correction-via-linguistic-and-implicit-attribute-editing/) (CVPR 2025): Automates model diagnosis and correction by analyzing error patterns, testing causal hypotheses via attribute editing, and generating counterfactual training samples for improved robustness. - [Decoupling Vision and Language: Codebook Anchored Visual Adaptation](https://ericolony.github.io/Publications/decoupling-vision-and-language-codebook-anchored-visual-adaptation/) (arXiv 2026): Introduces CRAFT, a discrete-codebook method for adapting vision encoders in LVLMs to domain-specific tasks without modifying the language model, enabling portable encoder adaptation across architectures. ### Neural Quantum States and Scientific Machine Learning - [Scalable Neural Quantum States Architecture for Quantum Chemistry](https://ericolony.github.io/Publications/scalable-neural-quantum-states-architecture-for-quantum-chemistry/) (Machine Learning: Science and Technology 2023): Introduces GPU-scalable parallelization strategies for neural-network variational Monte Carlo applied to ab-initio quantum chemistry, achieving systematic speedups over existing neural-network methods. - [Natural Evolution Strategies and Variational Monte Carlo](https://ericolony.github.io/Publications/natural-evolution-strategies-and-variational-monte-carlo/) (Machine Learning: Science and Technology 2021): Introduces quantum natural evolution strategies as a geometric unification of quantum/classical black-box optimization algorithms, achieving competitive Max-Cut approximation ratios. - [Overcoming Barriers to Scalability in Variational Quantum Monte Carlo](https://ericolony.github.io/Publications/overcoming-barriers-to-scalability-in-variational-quantum-monte-carlo/) (SC 2021): Replaces MCMC with autoregressive exact sampling in variational quantum Monte Carlo, enabling GPU-scalable parallelism for up to ten-thousand dimensional problems. - [Natural Evolution Strategies and Quantum Approximate Optimization](https://ericolony.github.io/Publications/natural-evolution-strategies-and-quantum-approximate-optimization/) (arXiv 2020): Applies natural evolution strategies to quantum approximate optimization, achieving competitive Max-Cut approximation ratios via neural quantum states. - [Meta Variational Monte Carlo](https://ericolony.github.io/Publications/meta-variational-monte-carlo-arxiv/) (arXiv 2020): Connects meta-learning to quantum ground-state problems, proposing Meta Variational Monte Carlo that accelerates training and improves convergence on random Max-Cut instances. - [Meta-Variational Quantum Monte Carlo](https://ericolony.github.io/Publications/meta-variational-quantum-monte-carlo/) (Quantum Machine Intelligence 2023): Journal version presenting Meta Variational Monte Carlo, which applies meta-learning to accelerate neural quantum state optimization across random Hamiltonian ensembles. - [Neural Quantum States for Scientific Computing](https://ericolony.github.io/Publications/neural-quantum-states-for-scientific-computing/) (PhD Thesis, University of Michigan 2022): PhD thesis synthesizing neural quantum states for scientific computing, covering variational Monte Carlo for quantum chemistry, combinatorial optimization, and financial derivative pricing. ### Quantum-Inspired Scientific Computing and Finance - [Quantum-Inspired Variational Algorithms for Partial Differential Equations: Application to Financial Derivative Pricing](https://ericolony.github.io/Publications/quantum-inspired-variational-algorithms-for-partial-differential-equations/) (Quantitative Finance 2024): Generalizes variational quantum Monte Carlo with neural-network quantum states to solve arbitrary time-dependent PDEs, demonstrated on multi-asset Black-Scholes option pricing. ## Task Pages - [Generalizable Deepfake Detection](https://ericolony.github.io/Publications/tasks/generalizable-deepfake-detection/) - [Face Anti-Spoofing and Liveness Detection](https://ericolony.github.io/Publications/tasks/face-anti-spoofing/) - [Neural Quantum States for Quantum Chemistry](https://ericolony.github.io/Publications/tasks/neural-quantum-states-quantum-chemistry/) - [Diverse Conditional Image Generation](https://ericolony.github.io/Publications/tasks/diverse-conditional-generation/) - [Adversarial Robustness via Diverse Attack Generation](https://ericolony.github.io/Publications/tasks/adversarial-robustness/) - [Vision-Language Model Adaptation](https://ericolony.github.io/Publications/tasks/vision-language-model-adaptation/) - [Quantum-Inspired Algorithms for Scientific Computing and Finance](https://ericolony.github.io/Publications/tasks/quantum-inspired-scientific-computing/) ## Machine-Readable Index - papers.json: https://ericolony.github.io/Publications/papers.json - citation.bib: https://ericolony.github.io/Publications/citation.bib - corpus/papers.jsonl: https://ericolony.github.io/Publications/corpus/papers.jsonl (one paper per line, all metadata) - corpus/chunks.jsonl: https://ericolony.github.io/Publications/corpus/chunks.jsonl (300-800 token chunks for embedding retrieval) ## How to Cite Each paper page includes a BibTeX entry. Visit the individual paper page listed above and copy the BibTeX block. For bulk citations, download `citation.bib` which contains entries for all papers.