JT
Juanxi Tian
cs.CVcs.AIcs.LGcs.CLcs.CY
On Valency
published · living versionsW_bcr6ukuw·v1 · currentpublished
PixelBench: Can LLMs Understand and Generate Images Pixel by Pixel?
with Haoquan Zhang, Feiyang Liu, Wanhua Li, Haodong Duan +1
1 version
Preprints & journals
7 papers in the corpus · 2024–2026PixelControl: Fine-Grained Condition Fidelity in Text-to-Image Diffusion2608.15705v1 · Xin Lin, Haodong Li, Zhifei Zhang et al.2026 · 0 citationsarXiv
VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System2607.27380v2 · Haodong Li, Tianfei Ren, Xiaoxiao Ma et al.2026 · 0 citationsarXiv
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models2604.04707v2 · DataFlow Team, Bohan Zeng, Daili Hua et al.2026 · 0 citationsarXiv
GUI-GenBench: Evaluating Image Generation Models as Interactive GUI Environments2602.09007v3 · Haodong Li, Jingwei Wu, Quan Sun et al.2026 · 0 citationsarXiv
MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization2504.00999v1 · Siyuan Li, Luyuan Zhang, Zedong Wang et al.2025 · 4 citationsarXiv
Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning2410.06373v1 · Siyuan Li, Juanxi Tian, Zedong Wang et al.2024 · 0 citationsarXiv
CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models2406.06007v3 · Peng Xia, Ze Chen, Juanxi Tian et al.2024 · 19 citationsarXiv
Career total: 9 works. 7 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.