← Authors

Xinyi Zhang

14 papers · 2020–2025 · 8 conferences · across top CS/AI conferences

Achievements

🌈 Renaissance Researcher (9) πŸ—ΊοΈ Taxonomy Completionist (39) πŸŒ‰ Interdisciplinary Bridge 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (8) πŸƒ Academic Marathon (5) 🧭 Keyword Pioneer 🐝 Cross-Pollinator (12) πŸ”₯ Unstoppable (6) πŸ’Ž Century Club (14) ⚑ Prolific Year (7) πŸ—ƒοΈ Keyword Collector (85)

Conferences

CVPR (4) AAAI (3) ICCV (2) ICLR (1) INTERSPEECH (1) NIPS (1) OSDI (1) WACV (1)

Top co-authors

Qingmin Liao (3) Qinpeng Cui (3) Qiqi Bao (3) Naiqi Li (2) Fei Wang (2) Hang Dong (2) Jinshan Pan (2) Ying Tai (2) Chengjie Wang (2) Zhengping Che (1)

Keywords

image restoration (4) diffusion model (3) large language model (2) stochastic differential equation (2) generative model (2) temporal modeling (2) temporal consistency (2) scene understanding (1) factual knowledge (1) reinforcement learning (1) knowledge representation (1) autonomous driving (1) 3d vision (1) image dehazing (1) knowledge editing (1) image generation (1) efficient computing (1) model editing (1) speaker embedding (1) deformable convolution (1)

Papers

Elucidating the Solution Space of Extended Reverse-Time SDE for Diffusion Models WACV 2025
Exploiting Continuous Motion Clues for Vision-Based Occupancy Prediction AAAI 2025
Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network AAAI 2025
Joint Knowledge Editing for Information Enrichment and Probability Promotion AAAI 2025
DNF: Unconditional 4D Generation with Dictionary-based Neural Fields CVPR 2025
Training-free Generation of Temporally Consistent Rewards from VLMs ICCV 2025
An Information Criterion for Controlled Disentanglement of Multimodal Data ICLR 2025
Taming Diffusion Prior for Image Super-Resolution with Domain Shift SDEs NIPS 2024
Llumnix: Dynamic Scheduling for Large Language Model Serving OSDI 2024
Unsupervised Surface Anomaly Detection with Diffusion Probabilistic Model ICCV 2023
Blind Face Restoration via Integrating Face Shape and Generative Priors CVPR 2022
End-to-End Language Diarization for Bilingual Code-Switching Speech INTERSPEECH 2021
Learning To Restore Hazy Video: A New Real-World Dataset and a New Method CVPR 2021
Multi-Scale Boosted Dehazing Network With Dense Feature Fusion CVPR 2020