activity
20242026
collaborators

12 papers

cs.CV2026

DINO-Tok: Adapting DINO for Visual Tokenizers

Mingkai Jia, Mingxiao Li, Zhijian Shu +12

Recent advances in visual generation have emphasized the importance of Latent Generative Models (LGMs), which critically depend on effective visual tokenizers to bridge pixels and…

cs.CV2026

OccTENS: 3D Occupancy World Model via Temporal Next-Scale Prediction

Bu Jin, Songen Gu, Xiaotao Hu +5

In this paper, we propose OccTENS, a generative occupancy world model that enables controllable, high-fidelity long-term occupancy generation while maintaining computational effici…

cs.CV2026

Entropy-Guided k-Guard Sampling for Long-Horizon Autoregressive Video Generation

Yizhao Han, Tianxing Shi, Zhao Wang +6

Autoregressive (AR) architectures have achieved significant successes in LLMs, inspiring explorations for video generation. In LLMs, top-p/top-k sampling strategies work exceptiona…

cs.CV2025

LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging

Zhijian Shu, Cheng Lin, Tao Xie +8

3D vision foundation models like Visual Geometry Grounded Transformer (VGGT) have advanced greatly in geometric perception. However, it is time-consuming and memory-intensive for l…

cs.CV2025

ComDrive: Comfort-Oriented End-to-End Autonomous Driving

Junming Wang, Xingyu Zhang, Zebin Xing +7

We propose ComDrive: the first comfort-oriented end-to-end autonomous driving system to generate temporally consistent and comfortable trajectories. Recent studies have demonstrate…

cs.CV2025

GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Driving

Zebin Xing, Xingyu Zhang, Yang Hu +5

We propose GoalFlow, an end-to-end autonomous driving method for generating high-quality multimodal trajectories. In autonomous driving scenarios, there is rarely a single suitable…