Author

Feng Tian

h-index 0 View on Semantic Scholar

3 papers indexed here

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 Sep 2026

RepFlow: Reciprocal Supervision Improves Generation and Representation in Flow Models

Generative models learn visual structure through denoising, yet their internal states are entangled with both noise level and network depth, making it difficult to obtain a stable visual representation from the generator itself. We introduce RepFlow, which learns such a representation from the generator's evolving comp...

Wei-Li Zeng, Feng Tian, Sheng-Qi Liu et al. · 0 citations

2026

Enfold: Folding World-Generator Computation into Predictive Representations for Efficient Embodied Control

Enfold is presented, which transfers this computation into a representation predicted from the current visual context and language instruction, and recast a world generator as a source of predictive control representations: its future need not be materialized at every step if its internal structure can be enfolded into...

Wei-Li Zeng, Yi-Tong Xing, Fu-Long Liu et al. · arXiv.org · 0 citations

Preprint Jul 2026

Enfold: Folding World Model Imagination into Predictive Representations for Ultra-Efficient Embodied Control

This work presents Enfold, which transfers this computation that constructs a future into a representation predicted from the current visual context and language instruction, and recast a world generator as a source of predictive control representations if its internal structure can be enfolded into the present.

Wei-Li Zeng, Yi-Tong Xing, Fu-Long Liu et al. · 1 citation