Hong Liu

34

Papers

262

Total Citations

1

Affiliations

Affiliations

Stanford University

Papers (34)

Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training

Audio Generation with Multiple Conditional Diffusion Model

Near-Optimal Resilient Aggregation Rules for Distributed Learning Using 1-Center and 1-Mean Clustering with Outliers

SVTformer: Spatial-View-Temporal Transformer for Multi-View 3D Human Pose Estimation

PDDM: Pseudo Depth Diffusion Model for RGB-PD Semantic Segmentation Based in Complex Indoor Scenes

Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation

Position: Towards Implicit Prompt For Text-To-Image Models

Cross-Modality Binary Code Learning via Fusion Similarity Hashing

Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation

Separate to Adapt: Open Set Domain Adaptation via Progressive Separation

Towards Visual Feature Translation

Projection & Probability-Driven Black-Box Attack

Spatial Pyramid Based Graph Reasoning for Semantic Segmentation

MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation

STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection

Universal Adversarial Perturbation via Prior Driven Uncertainty Approximation

Universal Perturbation Attack Against Image Retrieval

Expectation-Maximization Attention Networks for Semantic Segmentation

Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Video

Learning Concordant Attention via Target-aware Alignment for Visible-Infrared Person Re-identification

FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillation

Anti-Bandit Neural Architecture Search for Model Defense

API-Net: Robust Generative Classifier via a Single Discriminator

Black-Box Dissector: Towards Erasing-Based Hard-Label Model Stealing Attack

An Information Theoretic Approach for Attention-Driven Face Forgery Detection

UST-SSM: Unified Spatio-Temporal State Space Models for Point Cloud Video Modeling

Recognizing Actions from Robotic View for Natural Human-Robot Interaction

TCPFormer: Learning Temporal Correlation with Implicit Pose Proxy for 3D Human Pose Estimation

LiD-FL: Towards List-Decodable Federated Learning

ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language Models

Learning to Adapt to Evolving Domains

Cycle Self-Training for Domain Adaptation

Improving Adversarial Robustness via Information Bottleneck Distillation

Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers