2 citations · 2 across the 11 of their papers we have counts for
8 papers · 1 filter
MoWorld: A Flash World Model
Team Moxin, Deyi Ji, Tianrun Chen +37
The future of World Models depends not only on scaling model capability, but also on scaling practicality and inference efficiency. High-frame-rate inference enables responsive per…
Video-Zero: Self-Evolution Video Understanding
Ruixu Zhang, Deyi Ji, Lanyun Zhu +4
Self-evolution offers a promising path for improving reasoning models without relying on intensive human annotation. However, extending this paradigm to video understanding remains…
4DVGGT-D: 4D Visual Geometry Transformer with Improved Dynamic Depth Estimation
Ying Zang, Xuanyi Liu, Yidong Han +9
Reconstructing dynamic 4D scenes from monocular videos is a fundamental yet challenging task. While recent 3D foundation models provide strong geometric priors, their performance s…
StreamCacheVGGT: Streaming Visual Geometry Transformers with Robust Scoring and Hybrid Cache Compression
Xuanyi Liu, Chunan Yu, Deyi Ji +6
Reconstructing dense 3D geometry from continuous video streams requires stable inference under a constant memory budget. Existing frameworks primarily rely on a ``pure evict…
Scene Graph-guided SegCaptioning Transformer with Fine-grained Alignment for Controllable Video Segmentation and Captioning
Xu Zhang, Jin Yuan, BinHong Yang +5
Recent advancements in multimodal large models have significantly bridged the representation gap between diverse modalities, catalyzing the evolution of video multimodal interpreta…
Unlocking the Power of SAM 2 for Few-Shot Segmentation
Qianxiong Xu, Lanyun Zhu, Xuanyi Liu +4
Few-Shot Segmentation (FSS) aims to learn class-agnostic segmentation on few classes to segment arbitrary classes, but at the risk of overfitting. To address this, some methods use…
POPEN: Preference-Based Optimization and Ensemble for LVLM-Based Reasoning Segmentation
Lanyun Zhu, Tianrun Chen, Qianxiong Xu +5
Existing LVLM-based reasoning segmentation methods often suffer from imprecise segmentation results and hallucinations in their text responses. This paper introduces POPEN, a novel…
Hybrid Mamba for Few-Shot Segmentation
Qianxiong Xu, Xuanyi Liu, Lanyun Zhu +4
Many few-shot segmentation (FSS) methods use cross attention to fuse support foreground (FG) into query features, regardless of the quadratic complexity. A recent advance Mamba can…