7 papers · 1 filter
SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models
Junchao Huang, Guian Fang, Shengju Qian +15
We introduce SolarWM, a fully open foundation for building interactive video world models from data preparation through long-horizon inference. Training across heterogeneous data s…
Amodal SAM: A Unified Amodal Segmentation Framework with Generalization
Bo Zhang, Zhuotao Tian, Xin Tao +3
Amodal segmentation is a challenging task that aims to predict the complete geometric shape of objects, including their occluded regions. Although existing methods primarily focus…
Video-ToC: Video Tree-of-Cue Reasoning
Qizhong Tan, Zhuotao Tian, Guangming Lu +2
Existing Video Large Language Models (Video LLMs) struggle with complex video understanding, exhibiting limited reasoning capabilities and potential hallucinations. In particular,…
FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging
Ziyang Fan, Keyu Chen, Ruilong Xing +3
Although Video Large Language Models (VLLMs) have shown remarkable capabilities in video understanding, they are required to process high volumes of visual tokens, causing signific…
Memory Forcing: Spatio-Temporal Memory for Consistent Scene Generation on Minecraft
Junchao Huang, Xinting Hu, Boyao Han +4
Autoregressive video diffusion models have proved effective for world modeling and interactive scene generation, with Minecraft gameplay as a representative application. To faithfu…
Mitigating Object Hallucinations via Sentence-Level Early Intervention
Shangpin Peng, Senqiao Yang, Li Jiang +1
Multimodal large language models (MLLMs) have revolutionized cross-modal understanding but continue to struggle with hallucinations - fabricated content contradicting visual inputs…
Enhancing Spatial Reasoning in Multimodal Large Language Models through Reasoning-based Segmentation
Zhenhua Ning, Zhuotao Tian, Shaoshuai Shi +4
Recent advances in point cloud perception have demonstrated remarkable progress in scene understanding through vision-language alignment leveraging large language models (LLMs). Ho…