MC

Minghong Cai

0009-0003-7037-4251

cs.CVcs.ROcs.AIcs.MM

On Valency

published · living versions

W_j7v8p9xw·v1 · currentpublished

PhysEvolve: Verifier-grounded Self-evolution for Physical Reasoning with Executable Worlds

with Jinyuan Hu, Yilei Jiang, Chen Tang, Xinran Liu +1

1 version

Preprints & journals

7 papers in the corpus · 2024–2026

Edit in Sync: Unified End-to-End Audio-Visual Editing for Human-Centric Videos2610.27947v1 · Ziye Yuan, Minghong Cai, Xu He et al.2026 · 0 citationsarXiv

AffordanceWAM: Affordance-Aware Joint World-Action Modeling for Robot Manipulation2609.22332v3 · Jiadi You, Qize Yu, Yue Chen et al.2026 · 0 citationsarXiv

PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives2608.13552v2 · Kaixin Ding, Xi Chen, Minghong Cai et al.2026 · 0 citationsarXiv

AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding2606.06155v2 · Qize Yu, Jiadi You, Yuran Wang et al.2026 · 0 citationsarXiv

X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding2606.02482v3 · Peiwen Sun, Xudong Lu, Huadai Liu et al.2026 · 0 citationsarXiv

VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning2510.08555v2 · Minghong Cai, Qiulin Wang, Zongli Ye et al.2025 · 0 citationsarXiv

FairGen: Enhancing Fairness in Text-to-Image Diffusion Models via Self-Discovering Latent Directions2412.18810v3 · Yilei Jiang, Weihong Li, Yiyuan Zhang et al.2024 · 0 citationsarXiv

Career total: 8 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.