activity
20242026
collaborators

38 papers

cs.CV2026

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…

cs.CV2026

Explain Before You Answer: A Survey on Compositional Visual Reasoning

Fucai Ke, Joy Hsu, Zhixi Cai +10

Compositional visual reasoning has emerged as a key research frontier in multimodal AI, aiming to endow machines with the human-like ability to decompose visual scenes, ground inte…

cs.CV2026

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…

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.CV2026

One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory

Chenhao Zheng, Jieyu Zhang, Mohammadreza Salehi +5

Effective video tokenization is critical for scaling transformer models for long videos. Current approaches tokenize videos using space-time patches, leading to excessive tokens an…