7 citations · 31 across the 43 of their papers we have counts for
12 papers · 2 filters
OmniTaskonomy: When Does Visual Generation Improve Visual Understanding?
Jiaxin Ge, Yiming Qin, Ji Xie +13
Training a model to generate visual content can encourage it to learn rich perceptual capabilities related to geometry, spatial relationships, and objectness; yet, its benefits for…
Vision-Language Grounding as Bidirectional Concept Correspondence
Jieyu Zhang, Ziqi Gao, Luke Zettlemoyer +1
Vision-language grounding connects language to visual content, yet most existing formulations reduce grounding to a unidirectional localization problem: given a prespecified text p…
MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction
Jianing Zhang, Chenhao Zheng, Yajun Yang +10
Motion forecasting is central to visual intelligence: agents must anticipate how objects will move in order to plan actions, reason about physical interactions, and synthesize real…
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…
You Only Judge Once: Multi-response Reward Modeling in a Single Forward Pass
Yinuo Yang, Zixian Ma, Manasi Ganti +2
We present a discriminative multimodal reward model that scores all candidate responses in a single forward pass. Conventional discriminative reward models evaluate each response i…
MolmoPoint: Better Pointing for VLMs with Grounding Tokens
Christopher Clark, Yue Yang, Jae Sung Park +8
Grounding has become a fundamental capability of vision-language models (VLMs). Most existing VLMs point by generating coordinates as part of their text output, which requires lear…
Unified Spatio-Temporal Token Scoring for Efficient Video VLMs
Jianrui Zhang, Yue Yang, Rohun Tripathi +5
Token pruning is essential for enhancing the computational efficiency of vision-language models (VLMs), particularly for video-based tasks where temporal redundancy is prevalent. P…
Video-Based Reward Modeling for Computer-Use Agents
Linxin Song, Jieyu Zhang, Huanxin Sheng +6
Computer-using agents (CUAs) are becoming increasingly capable; however, it remains difficult to scale evaluation of whether a trajectory truly fulfills a user instruction. In this…
Synthetic Visual Genome 2: Extracting Large-scale Spatio-Temporal Scene Graphs from Videos
Ziqi Gao, Jieyu Zhang, Wisdom Oluchi Ikezogwo +10
We introduce Synthetic Visual Genome 2 (SVG2), a large-scale panoptic video scene graph dataset. SVG2 contains over 636K videos with 6.6M objects, 52.0M attributes, and 6.7M relati…
VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models
Qijia He, Xunmei Liu, Hammaad Memon +6
Scalable Vector Graphics (SVG) are essential for technical illustration and digital design, offering resolution independence and semantic editability. In practice, original vector…
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…
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…