Xinyi Zhang

papers

936

total citations

papers (11)

Multi-Scale Boosted Dehazing Network With Dense Feature Fusion

CVPR 2020arXiv

902

citations

Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network

AAAI 2025arXiv

citations

LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models

COLM 2025arXiv

citations

No Loss, No Gain: Gated Refinement and Adaptive Compression for Prompt Optimization

NEURIPS 2025arXiv

citations

Joint Knowledge Editing for Information Enrichment and Probability Promotion

AAAI 2025arXiv

citations

Unsupervised Surface Anomaly Detection with Diffusion Probabilistic Model

ICCV 2023

citations

Learning To Restore Hazy Video: A New Real-World Dataset and a New Method

CVPR 2021

citations

Blind Face Restoration via Integrating Face Shape and Generative Priors

CVPR 2022

citations

Xinyi Zhang

papers (11)

Multi-Scale Boosted Dehazing Network With Dense Feature Fusion

Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network

LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models

DNF: Unconditional 4D Generation with Dictionary-based Neural Fields

Training-Free Generation of Temporally Consistent Rewards from VLMs

Exploiting Continuous Motion Clues for Vision-Based Occupancy Prediction

No Loss, No Gain: Gated Refinement and Adaptive Compression for Prompt Optimization

Joint Knowledge Editing for Information Enrichment and Probability Promotion

Unsupervised Surface Anomaly Detection with Diffusion Probabilistic Model

Learning To Restore Hazy Video: A New Real-World Dataset and a New Method

Blind Face Restoration via Integrating Face Shape and Generative Priors

papers (11)

Multi-Scale Boosted Dehazing Network With Dense Feature Fusion

Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network

LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models

DNF: Unconditional 4D Generation with Dictionary-based Neural Fields

Training-Free Generation of Temporally Consistent Rewards from VLMs

Exploiting Continuous Motion Clues for Vision-Based Occupancy Prediction

No Loss, No Gain: Gated Refinement and Adaptive Compression for Prompt Optimization

Joint Knowledge Editing for Information Enrichment and Probability Promotion

Unsupervised Surface Anomaly Detection with Diffusion Probabilistic Model

Learning To Restore Hazy Video: A New Real-World Dataset and a New Method

Blind Face Restoration via Integrating Face Shape and Generative Priors