Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
Clarify Before Executing: A Self-Evolving Agent for Resolving Intent Asymmetry in 3D Tool Orchestration
Xiaoye Zhu, Weixin Li, Junan Huo +5
A fundamental intent asymmetry plagues modern 3D asset creation: while state-of-the-art 3D toolchains demand precise, executable parameters, ordinary users typically provide vague,…
cs.CV2026
Memory-Guided View Refinement for Dynamic Human-in-the-loop EQA
Xin Lu, Rui Li, Xun Huang +6
Embodied Question Answering (EQA) has traditionally been evaluated in temporally stable environments where visual evidence can be accumulated reliably. However, in dynamic, human-p…
cs.CV2025
MSGNav: Unleashing the Power of Multi-modal 3D Scene Graph for Zero-Shot Embodied Navigation
Xun Huang, Shijia Zhao, Yunxiang Wang +6
Embodied navigation is a fundamental capability for robotic agents operating. Real-world deployment requires open vocabulary generalization and low training overhead, motivating ze…