Modern visual tokenizers aim to preserve fine-grained visual details while learning high-level semantic representations for downstream generation and understanding. Query-based 1D visual tokenizers encode images into flexible latent sequences, yet how individual learnable queries gather and encode image information rem...
Jia-Hao Guo, Bao Tang, Hao-Xiang Cao et al.· 0 citations
Reconstructing high-quality, renderable 3D scenes from long videos is essential for robotic perception and embodied intelligence. Many feed-forward Gaussian reconstruction methods rapidly predict 3D scenes from a small set of images, but extending them to longer sequences presents two bottlenecks: jointly processing al...
Zhou-Feng Xie, Guan-Jun Wu, Shuai Zhang et al.· 0 citations
Zero-shot anomaly detection aims to transfer anomaly discrimination from auxiliary training domains to unseen categories while localizing subtle defects. A key challenge is to construct discriminative references that combine contextual representations with complementary local evidence. We present Cross-Encoder Anchor R...
Kai-Song Ji, Ziyang Xu, Chang-Long Bian et al.· 0 citations
World-action models jointly learn robot policies and predict future observations, making the representation space an interface between control and prediction. We study the design of this space through controlled comparisons, finding that neither reconstruction fidelity nor pre-trained perceptual features alone ensure e...
Hao-Yi Jiang, Liu Liu, Xin-Jiang Wang et al.· arXiv.org· 5 citations
Driving policies require capabilities of scene understanding and future evolution prediction. To achieve this goal, current end-to-end models typically construct complex perception-planning pipelines or introduce world models that explicitly predict future states, resulting in a complex system architecture. Inspired by...
Yue-Ting Zhu, Shao-Yu Chen, Yue-Hao Song et al.· arXiv.org· 0 citations
We present Multimodal Flow, a fully continuous generative model of language and vision. Most unified multimodal models either model both language and quantized images as discrete tokens or combine discrete language prediction with continuous image generation. The former introduces a visual quantization bottleneck. The...
Open-vocabulary segmentation identifies and segments objects from arbitrary textual descriptions. SAM 3 supports noun-phrase-guided segmentation and achieves competitive open-vocabulary performance through exhaustive vocabulary traversal, yet suffers from prohibitive computational overhead as target categories scale. I...
Hao Peng, Yong-Kang Li, Zhao-Xiang Liu et al.· 0 citations
ForeDrive is proposed, which learns a planning-relevant latent representation and couples it asymmetrically to a Diffusion Transformer (DiT) planner and attains 89.9 PDMS on NAVSIM v1 and 90.0 one-stage EPDMS on NAVSIM v2, without reinforcement learning or an external trajectory scorer.
DreamWAM is introduced, which reformulates future prediction as structured world modeling beyond RGB, representing future states through complementary views of appearance, motion, geometry, and semantics, showing that robust world-action learning depends not only on predicting the future, but on representing it in a fo...
Shanglin Yuan, Weiheng Zhao, Xin Shi et al.· 4 citations
Faster-WAM introduces a sparse future-conditioning framework that computes future representations once and selectively reuses them throughout action denoising, and proposes SparseMoT to replace ubiquitous layer-wise fusion with selective video-action interaction at a compact subset of network stages, and Interval KV-Fu...
Weiheng Zhao, Haoyi Jiang, Xin Shi et al.· 10 citations
This work reformulates the video diffusion sampling as a frame-indexed stochastic process over noise levels, and constructs a continuous training trajectory along which the sampling schedule progressively evolves from independent sampling to inference-consistent sampling.
Yue-Ting Zhu, Yue-Hao Song, Kai-Chen Zhang et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.