Xinyao Liao

5 papers · 2025–2026 · 2 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 (12) ⭐ Rising Star (5)

Venues

CVPR (4) ICCV (1)

Top co-authors

Xianfang Zeng (3) Gang Yu (3) Guosheng Lin (2) Wei Cheng (2) Chi Zhang (2) Zhoujie Fu (1) Kai Xu (1) Jingwei Wu (1) Ximeng Li (1) SHIYU LIU (1)

Research topics

Computer Vision (5) Generation (4) Artificial Intelligence (3) Deep Learning (3) Core AI (2) Models (2) Processing (2) Machine Learning (1) Analysis (1) Bayesian & Probabilistic (1) Core Methods (1) Learning Types (1)

Keywords

image generation (1) benchmark suite (1) video generation (1) autoregressive generation (1) point cloud (1) image editing (1) story visualization (1) text-to-image generation (1) optical flow (1) diffusion model (1) motion control (1) camera motion (1) text-to-video generation (1) mesh reconstruction (1) temporal coherence (1) signed distance function (1) evidence lower bound (1) image tokenizer (1) prompt alignment (1) video model (1)

Papers

iMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generation CVPR 2026 VA-p: Variational Policy Alignment for Pixel-Aware Autoregressive Generation CVPR 2026 ViStoryBench: Comprehensive Benchmark Suite for Story Visualization CVPR 2026 High-Fidelity Lightweight Mesh Reconstruction from Point Clouds CVPR 2025 MotionAgent: Fine-grained Controllable Video Generation via Motion Field Agent ICCV 2025