Jiaxi Gu

5 papers · 2022–2025 · 5 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11) 🐣 Hot Topic Early Bird

Venues

CVPR (1) ECCV (1) ICCV (1) ICML (1) NeurIPS (1)

Top co-authors

Hang Xu (4) Wei Zhang (2) Songcen Xu (2) FangYuan Zou (1) Youliang Yan (1) Weimian Li (1) Yu-Gang Jiang (1) Qingping Zheng (1) Bin Shao (1) Runhui Huang (1)

Research topics

Deep Learning (3) Models (3) Computer Vision (2) Machine Learning (2) Generation (2) Learning Types · Machine Learning (2) Artificial Intelligence (1) Core AI (1) Core Methods (1) Learning Types · Deep Learning (1) Processing (1)

Keywords

contrastive learning (2) video generation (2) video synthesis (1) multimodal learning (1) cross-modal learning (1) dynamic routing (1) human motion (1) diffusion model (1) video editing (1) image-text retrieval (1) vision-language pre-training (1) zero-shot classification (1) temporal consistency (1) text-video retrieval (1) image diffusion (1) latent fusion (1) pose guidance (1) training-free framework (1) cross-modal dataset (1) chinese multimodal dataset (1)

Papers

MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance ICML 2025 BIVDiff: A Training-Free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models CVPR 2024 MagDiff: Multi-Alignment Diffusion for High-Fidelity Video Generation and Editing ECCV 2024 PIDRo: Parallel Isomeric Attention with Dynamic Routing for Text-Video Retrieval ICCV 2023 Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark NeurIPS 2022