48 citations · 83 across the 20 of their papers we have counts for
22 papers
PhyAgentOS: A Self-Evolving Operating System for Embodied Agents with Decoupled Cognitive Planning and Physical Execution
Yang Liu, Weixing Chen, Xinshuai Song +8
Vision-language-action models, world models, and agentic planners each advance physical intelligence, yet their composition lacks a common execution abstraction, shared state, sema…
EG-VQA: Benchmarking Verifiable Video Question Answering with Grounded Temporal Evidence
Linpeng Huang, Weixing Chen, Zexin Chen +2
Recent advances in Video Large Language Models (Video-LLMs) have yielded promising performance on Video Question Answering (VideoQA). Nevertheless, existing benchmarks are predomin…
PhyScene3D: Physically Consistent Interactive 3D Tabletop Scene Generation
Weixing Chen, Zhuoqian Feng, Yang Liu +6
Generating physically consistent 3D tabletop scenes is a fundamental yet underexplored problem for interactive and generalist robotic learning. The challenge stems from dense objec…
LASAR: Towards Spatio-temporal Reasoning with Latent Cognitive Map
Jinzhou Tang, Sidi Liu, Waikit Xiu +2
A fundamental challenge in embodied AI is verifying if agents build internal models of spatial structure or merely learn to mimic task-specific expert trajectories. This is critica…
DDP-WM: Disentangled Dynamics Prediction for Efficient World Models
Shicheng Yin, Kaixuan Yin, Weixing Chen +3
World models are essential for autonomous robotic planning. However, the substantial computational overhead of existing dense Transformerbased models significantly hinders real-tim…
Learning to See and Act: Task-Aware Virtual View Exploration for Robotic Manipulation
Yongjie Bai, Zhouxia Wang, Yang Liu +8
Recent vision-language-action (VLA) models for multi-task robot manipulation often rely on fixed camera setups and shared visual encoders, which limit their performance under occlu…
AutoLayout: Closed-Loop Layout Synthesis via Slow-Fast Collaborative Reasoning
Weixing Chen, Dafeng Chi, Yang Liu +7
The automated generation of layouts is vital for embodied intelligence and autonomous systems, supporting applications from virtual environment construction to home robot deploymen…
DART: Differentiable Dynamic Adaptive Region Tokenizer for Vision Foundation Models
Shicheng Yin, Kaixuan Yin, Yang Liu +2
The content-agnostic, fixed-grid tokenizers used by standard large-scale vision models like Vision Transformer (ViT) and Vision Mamba (Vim) represent a fundamental performance bott…
3DAffordSplat: Efficient Affordance Reasoning with 3D Gaussians
Zeming Wei, Junyi Lin, Yang Liu +4
3D affordance reasoning is essential in associating human instructions with the functional regions of 3D objects, facilitating precise, task-oriented manipulations in embodied AI.…
DSPNet: Dual-vision Scene Perception for Robust 3D Question Answering
Jingzhou Luo, Yang Liu, Weixing Chen +4
3D Question Answering (3D QA) requires the model to comprehensively understand its situated 3D scene described by the text, then reason about its surrounding environment and answer…
Cross-modal Causal Relation Alignment for Video Question Grounding
Weixing Chen, Yang Liu, Binglin Chen +3
Video question grounding (VideoQG) requires models to answer the questions and simultaneously infer the relevant video segments to support the answers. However, existing VideoQG me…
Beyond the Destination: A Novel Benchmark for Exploration-Aware Embodied Question Answering
Kaixuan Jiang, Yang Liu, Weixing Chen +5
Embodied Question Answering (EQA) is a challenging task in embodied intelligence that requires agents to dynamically explore 3D environments, actively gather visual information, an…
VisionGRU: A Linear-Complexity RNN Model for Efficient Image Analysis
Shicheng Yin, Kaixuan Yin, Weixing Chen +2
Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) are two dominant models for image analysis. While CNNs excel at extracting multi-scale features and ViTs effecti…
Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method
Xinshuai Song, Weixing Chen, Yang Liu +3
Existing Vision-Language Navigation (VLN) methods primarily focus on single-stage navigation, limiting their effectiveness in multi-stage and long-horizon tasks within complex and…
Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI
Yang Liu, Weixing Chen, Yongjie Bai +4
Embodied Artificial Intelligence (Embodied AI) is crucial for achieving Artificial General Intelligence (AGI) and serves as a foundation for various applications (e.g., intelligent…
MEIA: Multimodal Embodied Perception and Interaction in Unknown Environments
Yang Liu, Xinshuai Song, Kaixuan Jiang +4
With the surge in the development of large language models, embodied intelligence has attracted increasing attention. Nevertheless, prior works on embodied intelligence typically e…
Towards CausalGPT: A Multi-Agent Approach for Faithful Knowledge Reasoning via Promoting Causal Consistency in LLMs
Ziyi Tang, Ruilin Wang, Weixing Chen +6
Despite the progress of foundation models, knowledge-based reasoning remains a persistent challenge due to their limited capacity for knowledge recall and inference. Existing metho…
CausalVLR: A Toolbox and Benchmark for Visual-Linguistic Causal Reasoning
Yang Liu, Weixing Chen, Guanbin Li +1
We present CausalVLR (Causal Visual-Linguistic Reasoning), an open-source toolbox containing a rich set of state-of-the-art causal relation discovery and causal inference methods f…
Cross-Modal Causal Intervention for Medical Report Generation
Weixing Chen, Yang Liu, Ce Wang +4
Radiology Report Generation (RRG) is essential for computer-aided diagnosis and medication guidance, which can relieve the heavy burden of radiologists by automatically generating…
A Deep Reinforcement Learning Framework for Rapid Diagnosis of Whole Slide Pathological Images
Tingting Zheng, Weixing chen, Shuqin Li +7
The deep neural network is a research hotspot for histopathological image analysis, which can improve the efficiency and accuracy of diagnosis for pathologists or be used for disea…
Global Contrast Masked Autoencoders Are Powerful Pathological Representation Learners
Hao Quan, Xingyu Li, Weixing Chen +7
Based on digital pathology slice scanning technology, artificial intelligence algorithms represented by deep learning have achieved remarkable results in the field of computational…
Dynamic radiomics: a new methodology to extract quantitative time-related features from tomographic images
Fengying Che, Ruichuan Shi, Jian Wu +6
The feature extraction methods of radiomics are mainly based on static tomographic images at a certain moment, while the occurrence and development of disease is a dynamic process…