1 citations · 2 across the 18 of their papers we have counts for
8 papers · 1 filter
NavHarness: Adaptive Goals for Agentic Vision-Language Navigation
Haoxiang Shi, Zaijing Li, Muhe Ding +3
Vision-Language Navigation (VLN) requires embodied agents to generate actions based on instructions and observations. General-purpose multimodal agents offer a promising basis for…
Dual-Layer Semantic-Spatial Belief Mapping for Aerial Object Goal Navigation
Jianqiang Xiao, Xiang Deng, Yuexuan Sun +3
Aerial Object Goal Navigation (ObjectNav) requires an unmanned aerial vehicle (UAV) to locate a described target in an unknown outdoor environment using onboard visual observations…
Hermite Curves as Trajectory Priors for Vision-Language-Action Models
Qi Lv, Jianming Xing, Zhao Yang +5
Despite recent progress in Vision-Language-Action (VLA) models for robotic manipulation, the action chunk remains a weakly structured interface. Existing work typically flatten eac…
Technical Report of RoboSpatial Challenge at CVPR 2026: Selective Reasoning Activation and Reference-Frame Disambiguation for Embodied Spatial Reasoning
Yuxiang Xie, Qi Lv, Jianming Xing +4
Vision-language models achieve strong general perception but often struggle with the spatial reasoning required for embodied tasks. We present RoboSpatialBrain, our submission to t…
Efficient Visual Pointing for Embodied AI:Agent-Driven Data Synthesis, Cross-Block Attention, and Iterative Correction
Zijian Hong, Qi Lv, Yuxiang Xie +4
Visual pointing maps a language instruction to pixel co ordinates, a core skill for embodied AI. We describe our PointArena 2026 solution, which achieves 77.2% overall accuracy and…
Beyond Waypoints: A Trajectory-Centric Waypointing Paradigm for Vision-Language Navigation
Haoxiang Shi, Xiang Deng, Haoyu Zhang +3
Vision-Language Navigation in Continuous Environments (VLN-CE) requires agents to follow natural-language instructions while navigating in real-world-like environments. Most VLN-CE…
Cortical Policy: A Dual-Stream View Transformer for Robotic Manipulation
Xuening Zhang, Qi Lv, Xiang Deng +3
View transformers process multi-view observations to predict actions and have shown impressive performance in robotic manipulation. Existing methods typically extract static visual…
EnergyAction: Unimanual to Bimanual Composition with Energy-Based Models
Mingchen Song, Xiang Deng, Jie Wei +3
Recent advances in unimanual manipulation policies have achieved remarkable success across diverse robotic tasks through abundant training data and well-established model architect…