Kaiyi Huang

5 papers · 2023–2026 · 4 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 · Bronze 🗺️ Taxonomy Completionist (10) 🐣 Hot Topic Early Bird 🏆 Keyword Champion (3)

Venues

CVPR (2) AAAI (1) ICCV (1) NeurIPS (1)

Top co-authors

Xihui Liu (5) Yukun Huang (3) Kaiyue Sun (2) Zinan Lin (2) Zhenguo Li (2) Xuefei Ning (2) Yu Wang (2) Jiwen Yu (1) Xintao Wang (1) Xian Liu (1)

Research topics

Computer Vision (4) Deep Learning (4) Generation (4) Models (4) Artificial Intelligence (3) Analysis (2) Core AI (2) Machine Learning (1) Learning Paradigms (1) Learning Types · Machine Learning (1) Learning Types · Deep Learning (1)

Keywords

multimodal large language model (3) compositional generation (3) text-to-video generation (3) diffusion model (2) multi-agent collaboration (1) 3d scene generation (1) attribute binding (1) visual planning (1) camera trajectory (1) panorama generation (1) scene consistency (1) motion binding (1) multi-plane synchronization (1) panoramic image generation (1) image generation benchmark (1) pretrained text-to-image model (1) reward-driven sampling (1) rgb-d panorama (1) 3d-aware feature (1) benchmark evaluation (1)

Papers

CineScene: Implicit 3D as Effective Scene Representation for Cinematic Video Generation CVPR 2026 GENMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration AAAI 2026 DreamCube: RGB-D Panorama Generation via Multi-plane Synchronization ICCV 2025 T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation CVPR 2025 T2I-CompBench: A Comprehensive Benchmark for Open-world Compositional Text-to-image Generation NeurIPS 2023