collaborators

5 papers

cs.AI2026

CausalCache: Conditional High-Fidelity Restoration for Long-Horizon GUI Agents

Jiaxuan Luo, Zhanfeng Liao, Jiayao Teng +1

Long-horizon GUI agents can retain complete action histories as compact text, but only a few historical screenshots fit in active context. We formulate this as budgeted fidelity re…

cs.CV2026

From Corpora to Co-Evolving Capabilities: Capability-Centric Data Design for Generalist Image Generation

Xingjian Wang, Zhao Wang, Taihang Hu +17

Large-scale image generation has benefited from advances in data scale, quality, rebalancing, and recaptioning, yet conventional pipelines typically optimize task-specific datasets…

cs.CV2026

Exploring the Performance Frontier of Compact Unified Image Generation Models

Taihang Hu, Zhao Wang, Zuan Gao +20

We present Swift-Image, a compact unified model for text-to-image generation, single-image editing, and multi-image editing. Our goal is to explore how far a relatively small visua…

cs.CV2026

CPI-Bench: A Comprehensive, Practical and Intelligent Benchmark for Real-World Image Editing

Qinye Zhou, Jun Zheng, Yongchao Du +17

With the rapid advancement of image editing models and their widespread application across various domains, there is an increasingly urgent need to deploy these model capabilities…

cs.CV2026

ExpertVerse: A General-Purpose Benchmark for Expert-Level Reasoning in Knowledge-Intensive Visual Synthesis

Yuan Wang, Yongchao Du, Mengting Chen +4

Recent advances in multimodal generative models have enabled instruction-based image generation to move beyond semantic manipulation to knowledge-driven visual reasoning. However,…