collaborators

7 papers

cs.AI2026

When Prompts Become Pixels: Prompt-Region Grounding for Multimodal Reasoning

Yongxin Wang, Ruizhe Zhou, Yueling Tang +4

Multimodal large language models increasingly reason over screenshots and documents where the task itself may be written in pixels. Yet benchmarks usually place questions in text,…

cs.CV2026

MOGeo: Beyond One-to-One Cross-View Object Geo-localization

Bo Lv, Qingwang Zhang, Le Wu +2

Cross-View Object Geo-Localization (CVOGL) aims to locate an object of interest in a query image within a corresponding satellite image. Existing methods typically assume that the…

cs.CV2026

From Horizontal to Rotated: Cross-View Object Geo-Localization with Orientation Awareness

Chenlin Fu, Ao Gong, Yingying Zhu

Cross-View object geo-localization (CVOGL) aims to precisely determine the geographic coordinates of a query object from a ground or drone perspective by referencing a satellite ma…

cs.LG2026

CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal Reasoning

Yongxin Wang, Zhicheng Yang, Meng Cao +5

Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures. When all rollouts are wrong, gradients stal…

cs.CV2025

Seeing the Unseen: Mask-Driven Positional Encoding and Strip-Convolution Context Modeling for Cross-View Object Geo-Localization

Shuhan Hu, Yiru Li, Yuanyuan Li +1

Cross-view object geo-localization enables high-precision object localization through cross-view matching, with critical applications in autonomous driving, urban management, and d…

cs.CV2025

SETR: A Two-Stage Semantic-Enhanced Framework for Zero-Shot Composed Image Retrieval

Yuqi Xiao, Yingying Zhu

Zero-shot Composed Image Retrieval (ZS-CIR) aims to retrieve a target image given a reference image and a relative text, without relying on costly triplet annotations. Existing CLI…