Recent advancements in multimodal diffusion language models (MDLMs) have exhibited strong global modeling capabilities through iterative refinement. We observe that mask uncertainty follows an overall downward trend during iterative denoising, while a few denoising steps exhibit localized entropy spikes closely associa...
Zhong-Xing Xu, Zhong-Hua Wang, Zhe Qian et al.· 0 citations
Feed-forward novel view synthesis has recently shown promising results from sparse posed images, but most existing methods assume that context and target views share a fixed camera family. This homogeneous-camera assumption breaks in practical multi-sensor systems, where perspective, fisheye, and panoramic cameras may...
Meng Wei, Cheng Zhang, Bo-Ying Li et al.· 0 citations
JRDB-AVR is introduced, a benchmark derived from existing real-world JRDB robotics data through a structured question-generation engine that turns this gap between answer accuracy and evidence accuracy in current baselines into an explicit evaluation.
Zhixi Cai, Fu-Cai Ke, Sukai Huang et al.· 0 citations
Compared with classical reinforcement-learning baselines, in-context learning from trial-and-error experience followed by Experience Distillation matches their performance with at least \(9.6\times\) fewer environment samples.