9 papers
UniPhysGen: Unified Physical Grounding for Simulation-Ready 3D Assets
Xian Li, Rong Wei, Lujie Yang +6
Physically grounded 3D assets are increasingly important for embodied AI and robotic simulation. However, most existing 3D assets lack unified physical semantics, including articul…
Rein3D: Reinforced 3D Indoor Scene Generation with Panoramic Video Diffusion Models
Dehui Wang, Rong Wei, Yue Shi +9
The growing demand for Embodied AI and VR applications has highlighted the need for synthesizing high-quality 3D indoor scenes from sparse inputs. However, existing approaches stru…
SpatiaLQA: A Benchmark for Evaluating Spatial Logical Reasoning in Vision-Language Models
Yuechen Xie, Xiaoyan Zhang, Yicheng Shan +6
Vision-Language Models (VLMs) have been increasingly applied in real-world scenarios due to their outstanding understanding and reasoning capabilities. Although VLMs have already d…
VLNVerse: A Benchmark for Vision-Language Navigation with Versatile, Embodied, Realistic Simulation and Evaluation
Sihao Lin, Zerui Li, Xunyi Zhao +10
Despite remarkable progress in Vision-Language Navigation (VLN), existing benchmarks remain confined to fixed, small-scale datasets with naive physical simulation. These shortcomin…
Arcadia: Toward a Full-Lifecycle Framework for Embodied Lifelong Learning
Minghe Gao, Juncheng Li, Yuze Lin +15
We contend that embodied learning is fundamentally a lifecycle problem rather than a single-stage optimization. Systems that optimize only one link (data collection, simulation, le…
Syn-GRPO: Self-Evolving Data Synthesis for MLLM Perception Reasoning
Qihan Huang, Haofei Zhang, Rong Wei +4
RL (reinforcement learning) methods (e.g., GRPO) for MLLM (Multimodal LLM) perception ability has attracted wide research interest owing to its remarkable generalization ability. N…
Towards Physically Executable 3D Gaussian for Embodied Navigation
Bingchen Miao, Rong Wei, Zhiqi Ge +8
3D Gaussian Splatting (3DGS), a 3D representation method with photorealistic real-time rendering capabilities, is regarded as an effective tool for narrowing the sim-to-real gap. H…
Interpretable Few-Shot Image Classification via Prototypical Concept-Guided Mixture of LoRA Experts
Zhong Ji, Rongshuai Wei, Jingren Liu +2
Self-Explainable Models (SEMs) rely on Prototypical Concept Learning (PCL) to enable their visual recognition processes more interpretable, but they often struggle in data-scarce s…
R3GS: Gaussian Splatting for Robust Reconstruction and Relocalization in Unconstrained Image Collections
Xu yan, Zhaohui Wang, Rong Wei +3
We propose R3GS, a robust reconstruction and relocalization framework tailored for unconstrained datasets. Our method uses a hybrid representation during training. Each anchor comb…