Xinyu Gao

8 papers · 2022–2026 · 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 · Silver 🗺️ Taxonomy Completionist (24) 🐣 Hot Topic Early Bird 🗃️ Keyword Collector (50)

Venues

CVPR (3) NeurIPS (2) AAAI (1) ACL (1) EMNLP (1)

Top co-authors

Ziyi Yang (5) Xiaogang Jin (5) Shaohui Jiao (2) Wen Zhou (2) Yu Qiao (1) Sipeng Yang (1) Ruyi Gan (1) Xinyuan Chen (1) Yuqing Zhang (1) Shaonan Wang (1)

Research topics

Deep Learning (7) Computer Vision (6) Generation (4) Models (4) Computer Science (3) Natural Language Processing (3) Analysis (3) Applications (3) Architectures (3) Learning Types (3) Processing (3) Artificial Intelligence (2) Machine Learning (2) Core AI (2) Application Areas (1)

Keywords

3d gaussian splatting (3) neural radiance field (3) neural rendering (2) real-time rendering (2) implicit representation (2) gaussian splatting (2) novel view synthesis (2) computer graphics (1) semantic segmentation (1) constituency parsing (1) dynamic scene (1) foundation model (1) prompt optimization (1) prompt engineering (1) deformation field (1) natural language understanding (1) text classification (1) text-to-video generation (1) zero-shot learning (1) 3d reconstruction (1)

Papers

Gated Tree Cross-Attention for Checkpoint-Compatible Syntax Injection in Decoder-Only LLMs ACL 2026 The Devil is in the Prompts: Retrieval-Augmented Prompt Optimization for Text-to-Video Generation CVPR 2025 Towards Realistic Example-based Modeling via 3D Gaussian Stitching CVPR 2025 A General Implicit Framework for Fast NeRF Composition and Rendering AAAI 2024 Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction CVPR 2024 RobIR: Robust Inverse Rendering for High-Illumination Scenes NeurIPS 2024 Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian Splatting NeurIPS 2024 Zero-Shot Learners for Natural Language Understanding via a Unified Multiple Choice Perspective EMNLP 2022