Haoxiang Hu

4 papers · 2024–2026 · 3 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 · Bronze 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (11)

Venues

CVPR (2) AAAI (1) IJCAI (1)

Top co-authors

Xiaoming Deng (4) Cuixia Ma (4) Yong-jin Liu (4) Cangjun Gao (3) Hongan Wang (3) Yaokun Li (2) Ran Zuo (2) Yu-Kun Lai (2) YuKun Lai (1) Qingkun Li (1)

Research topics

Artificial Intelligence (3) Computer Vision (3) Core AI (3) Deep Learning (2) Analysis (2) Generation (2) Computer Science (1) Natural Language Processing (1) Applications · Computer Science (1) Applications · Natural Language Processing (1) Architectures (1) Models (1) Processing (1)

Keywords

diffusion model (2) scene understanding (1) image retrieval (1) question answering (1) multimodal large language model (1) contrastive alignment (1) semantic reasoning (1) graph transformer network (1) large language model (1) diagram editing (1) text-sketch fusion (1) generative latent space (1) handwritten diagram recognition (1) online handwriting recognition (1) stroke restoration (1) spatial integration (1) diagram segmentation (1) sketch completion (1) diagram reconstruction (1) diagram recognition (1)

Papers

Diagram2Structure: Unlocking LLMs' Diagram Comprehension through DiagramDiff, a Framework for Structuring Offline Diagrams CVPR 2026 SketchRevive: Fine-Grained Pixel-to-Vector Sketch Completion with Diffusion-Prior-Guided Multimodal LLMs CVPR 2026 SceneDiff: Generative Scene-Level Image Retrieval with Text and Sketch Using Diffusion Models IJCAI 2024 SpaceGTN: A Time-Agnostic Graph Transformer Network for Handwritten Diagram Recognition and Segmentation AAAI 2024