6 papers
Supervising the Visible State: Separating Representation from View Selection in Streaming Video
Yihao Hu, Pan Wang, Yitong Lin +8
An action seen once and the same action seen three times receive the same action-recognition label, so that supervision does not require a model to count. Answers shared across his…
ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligence
Yihao Hu, Yitong Lin, Pan Wang +8
Training a spatial VLM to answer which side an object lies on does not require it to preserve the metric displacement that determines that answer, while supervision for a distance…
HOFAR: High-Order Augmentation of Flow Autoregressive Transformers
Yingyu Liang, Zhizhou Sha, Zhenmei Shi +2
Flow Matching and Transformer architectures have demonstrated remarkable performance in image generation tasks, with recent work FlowAR [Ren et al., 2024] synergistically integrati…
Force Matching with Relativistic Constraints: A Physics-Inspired Approach to Stable and Efficient Generative Modeling
Yang Cao, Bo Chen, Xiaoyu Li +5
This paper introduces Force Matching (ForM), a novel framework for generative modeling that represents an initial exploration into leveraging special relativistic mechanics to enha…
High-Order Matching for One-Step Shortcut Diffusion Models
Bo Chen, Chengyue Gong, Xiaoyu Li +5
One-step shortcut diffusion models [Frans, Hafner, Levine and Abbeel, ICLR 2025] have shown potential in vision generation, but their reliance on first-order trajectory supervision…
Theoretical Constraints on the Expressive Power of -based Tensor Attention Transformers
Xiaoyu Li, Yingyu Liang, Zhenmei Shi +2
Tensor Attention extends traditional attention mechanisms by capturing high-order correlations across multiple modalities, addressing the limitations of classical matrix-based atte…