activity
20242026
collaborators

10 papers

cs.AI2026

Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models

Mahtab Bigverdi, Linjie Li, Weikai Huang +9

Vision language models (VLMs) excel at many tasks but still struggle with spatial reasoning when critical information is not directly observable. Many such problems require imagina…

cs.CV2026

TrajTok: Learning Trajectory Tokens enables better Video Understanding

Chenhao Zheng, Jieyu Zhang, Jianing Zhang +6

Tokenization in video models, typically through patchification, generates an excessive and redundant number of tokens. This severely limits video efficiency and scalability. While…

cs.RO2026

MolmoAct2: Action Reasoning Models for Real-world Deployment

Haoquan Fang, Jiafei Duan, Donovan Clay +26

Vision-Language-Action (VLA) models aim to provide a single generalist controller for robots, but today's systems fall short on the criteria that matter for real-world deployment.…

cs.CV2026

WildDet3D: Scaling Promptable 3D Detection in the Wild

Weikai Huang, Jieyu Zhang, Sijun Li +15

Understanding objects in 3D from a single image is a cornerstone of spatial intelligence. A key step toward this goal is monocular 3D object detection--recovering the extent, locat…

cs.CV2026

Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding

Christopher Clark, Jieyu Zhang, Zixian Ma +18

Today's strongest video-language models (VLMs) remain proprietary. The strongest open-weight models either rely on synthetic data from proprietary VLMs, effectively distilling from…

cs.CV2026

Generate Any Scene: Scene Graph Driven Data Synthesis for Visual Generation Training

Ziqi Gao, Weikai Huang, Jieyu Zhang +2

Recent advances in text-to-vision generation excel in visual fidelity but struggle with compositional generalization and semantic alignment. Existing datasets are noisy and weakly…