Representation autoencoders (RAEs) reuse features from a pretrained visual encoder as reconstruction and diffusion latents, integrating strong visual representations into image generation. However, RAEs still need to decide which encoder layers form the shared latent space for the generator and pixel decoder. This choi...
Hong-Yang Du, Yun-Fei Xie, Jun-Jie Ye et al.· 0 citations
PhysWAM is presented, a unified world-action model for autonomous driving that co-denoises multiview video, metric depth, and ego motion within a single flow-matching transformer and Coupled Point Projection is introduced, demonstrating that the geometric relationship between scene depth and ego motion provides a direc...
Dhruv Parikh, Feng-Cheng Yu, Quan-Kai Gao et al.· 0 citations
FiberTune is proposed, a training-time objective that preserves teacher-structured visual residuals without adding inference-time overhead and improves over task-loss-only fine-tuning in every one of six controlled simulation settings spanning two benchmarks and two architectures.
Haihao Lin, Xiang-Sheng Huang, Xiao Yang et al.· arXiv.org· 2 citations
A benchmark with tab-and-blank interlocking pieces where geometric constraints provide strong local compatibility requirements that, combined with visual content, yield unambiguous ground truth is introduced, establishing scalable geometric reasoning as an open challenge for vision-language models.
This work proposes Token Radius Attention (TRA), a training-free framework that maps query entropy to an analytic token budget and converts it into a temporally decayed radius without explicit key ranking and achieves 1.05x speedup with competitive generation quality.
Jia-Yu Chen, Zhi-Kun Jiang, Mao-Liang Li 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.
