Skip to content

Author

Jian-Bing Shen

We have 3 of 23 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

UMM-JEPA: Generative Pretraining via Masked Next-Scale Representation Prediction for Unified Multimodal Models

Unified multimodal models can support both visual understanding and generation, yet generative training does not necessarily improve understanding. We argue that this limitation may arise from a mismatch between the representation targeted by generation and the perceptual representation used for understanding. Conventi...

Yu-Cheng Zhou, Yun-Jia Xi, Di Yin et al. · 0 citations
#computer vision Jun 2026

World Models Meet Language Models: On the Complementarity of Concrete and Abstract Reasoning

This work constructs two human-verified benchmarks, VRQABench for controllable spatial lookahead and OpenWorldQA for open-domain physical prediction, and proposes Privileged-Future On-Policy Self-Distillation (PF-OPSD), a model that outperforms baseline by 10.6% and 10.9% on VRQABench and OpenWorldQA, respectively, whi...

Yu-Chen Zhou, Wei Tao, Yiwen Guo et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.