Han Liu

Affiliations

University of Chicago

papers

567

total citations

papers (23)

Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints

ICLR 2024arXiv

157

citations

VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models

NEURIPS 2023arXiv

citations

On Computational Limits of Modern Hopfield Models: A Fine-Grained Complexity Analysis

ICML 2024arXiv

citations

STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction

ICLR 2024arXiv

citations

BiSHop: Bi-Directional Cellular Learning for Tabular Data with Generalized Sparse Modern Hopfield Model

ICML 2024arXiv

citations

Nonparametric Modern Hopfield Models

ICML 2025arXiv

citations

HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Text

NEURIPS 2023arXiv

citations

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency

ICLR 2025arXiv

citations

VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models

AAAI 2024arXiv

citations

A Goal Interaction Graph Planning Framework for Conversational Recommendation

AAAI 2024

citations

Liberating Seen Classes: Boosting Few-Shot and Zero-Shot Text Classification via Anchor

AAAI 2024arXiv

citations

Attention Mechanism, Max-Affine Partition, and Universal Approximation

NEURIPS 2025arXiv

citations

Fast and Low-Cost Genomic Foundation Models via Outlier Removal

ICML 2025arXiv

citations

Multi-Label Few-Shot Image Classification via Pairwise Feature Augmentation and Flexible Prompt Learning

AAAI 2025

citations

Uncertainty-Aware Contrastive Learning with Hard Negative Sampling for Code Search Tasks

AAAI 2025

citations

EGSRAL:An Enhanced 3D Gaussian Splatting Based Renderer with Automated Labeling for Large-Scale Driving Scene

AAAI 2025arXiv

citations

Improving Accuracy and Calibration via Differentiated Deep Mutual Learning

CVPR 2025

citations

Posterior Promoted GAN With Distribution Discriminator for Unsupervised Image Synthesis

CVPR 2021

citations

SlowLiDAR: Increasing the Latency of LiDAR-Based Detection Using Adversarial Examples

CVPR 2023

citations

RIATIG: Reliable and Imperceptible Adversarial Text-to-Image Generation With Natural Prompts

CVPR 2023

citations

Han Liu

Affiliations

papers (23)

Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints

VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models

On Computational Limits of Modern Hopfield Models: A Fine-Grained Complexity Analysis

Uniform Memory Retrieval with Larger Capacity for Modern Hopfield Models

On Sparse Modern Hopfield Model

Outlier-Efficient Hopfield Layers for Large Transformer-Based Models

STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction

BiSHop: Bi-Directional Cellular Learning for Tabular Data with Generalized Sparse Modern Hopfield Model

Nonparametric Modern Hopfield Models

HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Text

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency

VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models

A Goal Interaction Graph Planning Framework for Conversational Recommendation

Liberating Seen Classes: Boosting Few-Shot and Zero-Shot Text Classification via Anchor

Attention Mechanism, Max-Affine Partition, and Universal Approximation

Fast and Low-Cost Genomic Foundation Models via Outlier Removal

Multi-Label Few-Shot Image Classification via Pairwise Feature Augmentation and Flexible Prompt Learning

Uncertainty-Aware Contrastive Learning with Hard Negative Sampling for Code Search Tasks

EGSRAL:An Enhanced 3D Gaussian Splatting Based Renderer with Automated Labeling for Large-Scale Driving Scene

Improving Accuracy and Calibration via Differentiated Deep Mutual Learning

Posterior Promoted GAN With Distribution Discriminator for Unsupervised Image Synthesis

SlowLiDAR: Increasing the Latency of LiDAR-Based Detection Using Adversarial Examples

RIATIG: Reliable and Imperceptible Adversarial Text-to-Image Generation With Natural Prompts

papers (23)

Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints

VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models

On Computational Limits of Modern Hopfield Models: A Fine-Grained Complexity Analysis

Uniform Memory Retrieval with Larger Capacity for Modern Hopfield Models

On Sparse Modern Hopfield Model

Outlier-Efficient Hopfield Layers for Large Transformer-Based Models

STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction

BiSHop: Bi-Directional Cellular Learning for Tabular Data with Generalized Sparse Modern Hopfield Model

Nonparametric Modern Hopfield Models

HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Text

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency

VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models

A Goal Interaction Graph Planning Framework for Conversational Recommendation

Liberating Seen Classes: Boosting Few-Shot and Zero-Shot Text Classification via Anchor

Attention Mechanism, Max-Affine Partition, and Universal Approximation

Fast and Low-Cost Genomic Foundation Models via Outlier Removal

Multi-Label Few-Shot Image Classification via Pairwise Feature Augmentation and Flexible Prompt Learning

Uncertainty-Aware Contrastive Learning with Hard Negative Sampling for Code Search Tasks

EGSRAL:An Enhanced 3D Gaussian Splatting Based Renderer with Automated Labeling for Large-Scale Driving Scene

Improving Accuracy and Calibration via Differentiated Deep Mutual Learning

Posterior Promoted GAN With Distribution Discriminator for Unsupervised Image Synthesis

SlowLiDAR: Increasing the Latency of LiDAR-Based Detection Using Adversarial Examples

RIATIG: Reliable and Imperceptible Adversarial Text-to-Image Generation With Natural Prompts