1 citations · 2 across the 18 of their papers we have counts for
20 papers
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…
Task-Aware 3D Affordance Segmentation via 2D Guidance and Geometric Refinement
Lian He, Meng Liu, Qilang Ye +3
Understanding 3D scene-level affordances from natural language instructions is essential for enabling embodied agents to interact meaningfully in complex environments. However, thi…
F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions
Qi Lv, Weijie Kong, Hao Li +7
Executing language-conditioned tasks in dynamic visual environments remains a central challenge in embodied AI. Existing Vision-Language-Action (VLA) models predominantly adopt rea…
DAgger Diffusion Navigation: DAgger Boosted Diffusion Policy for Vision-Language Navigation
Haoxiang Shi, Xiang Deng, Zaijing Li +3
Vision-Language Navigation in Continuous Environments (VLN-CE) requires agents to follow natural language instructions through free-form 3D spaces. Existing VLN-CE approaches typic…
STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization
Hao Li, Qi Lv, Rui Shao +4
Transforming complex actions into discrete skill abstractions has demonstrated strong potential for robotic manipulation. Existing approaches mainly leverage latent variable models…
Few-Shot Vision-Language Action-Incremental Policy Learning
Mingchen Song, Xiang Deng, Guoqiang Zhong +5
Recently, Transformer-based robotic manipulation methods utilize multi-view spatial representations and language instructions to learn robot motion trajectories by leveraging numer…
Spatial-Temporal Graph Diffusion Policy with Kinematic Modeling for Bimanual Robotic Manipulation
Qi Lv, Hao Li, Xiang Deng +6
Despite the significant success of imitation learning in robotic manipulation, its application to bimanual tasks remains highly challenging. Existing approaches mainly learn a poli…
3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds
Hengshuo Chu, Xiang Deng, Qi Lv +4
3D Affordance detection is a challenging problem with broad applications on various robotic tasks. Existing methods typically formulate the detection paradigm as a label-based sema…
Embodied Crowd Counting
Runling Long, Yunlong Wang, Jia Wan +5
Occlusion is one of the fundamental challenges in crowd counting. In the community, various data-driven approaches have been developed to address this issue, yet their effectivenes…
EPD: Long-term Memory Extraction, Context-awared Planning and Multi-iteration Decision @ EgoPlan Challenge ICML 2024
Letian Shi, Qi Lv, Xiang Deng +1
In this technical report, we present our solution for the EgoPlan Challenge in ICML 2024. To address the real-world egocentric task planning problem, we introduce a novel planning…
Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL
Qi Lv, Xiang Deng, Gongwei Chen +2
While the conditional sequence modeling with the transformer architecture has demonstrated its effectiveness in dealing with offline reinforcement learning (RL) tasks, it is strugg…
RoboMP: A Robotic Multimodal Perception-Planning Framework with Multimodal Large Language Models
Qi Lv, Hao Li, Xiang Deng +3
Multimodal Large Language Models (MLLMs) have shown impressive reasoning abilities and general intelligence in various domains. It inspires researchers to train end-to-end MLLMs or…
LION : Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge
Gongwei Chen, Leyang Shen, Rui Shao +2
Multimodal Large Language Models (MLLMs) have endowed LLMs with the ability to perceive and understand multi-modal signals. However, most of the existing MLLMs mainly adopt vision…