Skip to content

Author

Wei-Hang Guo

We have 4 of 9 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.

#artificial intelligence Preprint Nov 2026

Hierarchical Diffusion Transformer for End-to-End Image Generation

Pixel-space diffusion learns visual representations and image generation jointly in a single end-to-end training stage, without a separately pretrained visual encoder. However, plain pixel-space Transformers still trail leading two-stage latent diffusion models in generation quality and training efficiency. We hypothes...

Xiao-Yu Wu, Yi-Fei Wang, Wei-Hang Guo et al. · 0 citations
Sep 2026

Zero-Shot Reactive Obstacle Avoidance for Generative Robot Policies

We propose NUDGE (Nudge Update via Differentiable GEometry), a training-free obstacle-avoidance procedure that can be incorporated in any robot policy based on diffusion or flow matching, including diffusion policies and vision-language-action models. Our work injects gradients from a signed distance field, a function...

Wei-Hang Guo, L. Kavraki · 0 citations
#artificial intelligence Preprint Sep 2026

Scaling Video Generation for Reasoning: At What Cost?

Symbolic state supervision raises the 20M model's frame accuracy from 31.1% to 67.3% at the same training-data budget, suggesting that learning representations of state changes can complement scaling.

Wei-Hang Guo, Xiao-Yu Wu, Yi-Fei Wang et al. · 0 citations

Compress to Remember: Learning Compact Memory via On-Policy Distillation for Long Video Generation

Prediction-Aligned Context Compaction (PACC), which uses a learned compressor to aggregate information across past frames into compact memory tokens, shows that learning to compact historical context can improve long-video memory without modifying the underlying generator.

Xiao-Yu Wu, Wei-Hang Guo, Yi-Fei Wang et al. · 0 citations

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