4 papers
SimpleSearch-VL: A Simple Recipe for Multimodal Agentic Deep Search
Ming Dai, Zhihong Lu, Jinjie Gu +5
We present SimpleSearch-VL, an efficient, reliable, and practical framework for multimodal agentic search. Its core idea is to improve the agent's own search-and-verification proce…
VideoSEG-O3: A Multi-turn Reinforcement Learning Framework for Reasoning Video Object Segmentation
Ming Dai, Sen Yang, Boqiang Duan +4
Reasoning Video Object Segmentation (RVOS) demands a sophisticated integration of temporal dynamics, spatial details, and linguistic reasoning to achieve precise pixel-level locali…
PropVG: End-to-End Proposal-Driven Visual Grounding with Multi-Granularity Discrimination
Ming Dai, Wenxuan Cheng, Jiedong Zhuang +4
Recent advances in visual grounding have largely shifted away from traditional proposal-based two-stage frameworks due to their inefficiency and high computational complexity, favo…
Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints
Ming Dai, Jian Li, Jiedong Zhuang +2
Multi-task visual grounding involves the simultaneous execution of localization and segmentation in images based on textual expressions. The majority of advanced methods predominan…