Shiyi Zhang

8 papers · 2023–2026 · 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 · Bronze 🗺️ Taxonomy Completionist (15) 🐣 Hot Topic Early Bird

Venues

CVPR (6) ECCV (1) ICCV (1)

Top co-authors

Yansong Tang (5) Wenxun Dai (4) CHUNYU WANG (4) Qinglin Lu (4) Tiankai Hang (3) Yiji Cheng (3) Yu Xu (3) Runze He (3) Jiwen Lu (3) Zijin Yin (3)

Research topics

Computer Vision (7) Processing (6) Artificial Intelligence (5) Core AI (5) Deep Learning (4) Generation (3) Learning Types (2) Machine Learning (1) Analysis (1) Application Areas (1) Architectures (1) Learning Paradigms (1) Models (1) Techniques (1)

Keywords

image editing (5) diffusion transformer (2) image generation (2) video understanding (2) attention mechanism (1) multimodal learning (1) generative model (1) diffusion model (1) group action (1) reward hacking (1) mixture of expert (1) temporal logic (1) attention module (1) task interference (1) multimodal understanding (1) kv cache (1) video dataset (1) long-form video (1) training-free method (1) structured reasoning (1)

Papers

JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization CVPR 2026 Meta-CoT: Enhancing Granularity and Generalization in Image Editing CVPR 2026 Re-Align: Structured Reasoning-guided Alignment for In-Context Image Generation and Editing CVPR 2026 TAG-MoE: Task-Aware Gating for Unified Generative Mixture-of-Experts CVPR 2026 KV-Edit: Training-Free Image Editing for Precise Background Preservation ICCV 2025 ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulation ECCV 2024 Narrative Action Evaluation with Prompt-Guided Multimodal Interaction CVPR 2024 LOGO: A Long-Form Video Dataset for Group Action Quality Assessment CVPR 2023