11 papers · 1 filter
DeSpatial: The devil of Agentic Spatial Reasoning Lies in 3D Itself
Yifei Liu, Xiaolong Zhou, Ziyang Gong +8
Spatial agents have access to reconstruction and segmentation tools, yet inconsistent predictions and fragmented object identities can prevent their outputs from becoming reliable…
Holi-Spatial 360: Generative Reconstruction from Sparse Panoramas for Spatial Rendering and Intelligence
Yuanyuan Gao, Zhirui Liu, Yuning Gong +9
Spatial intelligence requires scalable 3D environments that are both photorealistic and semantically grounded, yet existing indoor datasets are dominated by room-scale captures and…
Multi-Branch Policy Optimization for Multimodal Large Language Models
Shuai Lyu, Yuning Gong, Ruiling Gao +7
Group-based reinforcement learning methods for multimodal large language models typically rely on trajectory-level credit assignment that applies a single advantage to all tokens i…
PhotoFlow: Agentic 3D Virtual Photography Missions
Jiarui Guo, Haojia Wei, Yiming Zhang +5
Virtual photography asks an agent to enter a prepared 3D scene with no preselected camera pose or reference image, infer a suitable shot from scene information and a language inten…
Perceptual Flow Network for Visually Grounded Reasoning
Yangfu Li, Yuning Gong, Hongjian Zhan +8
Despite the success of Large-Vision Language Models (LVLMs), general optimization objectives (e.g., standard MLE) fail to constrain visual trajectories, leading to language bias an…
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
Team HY-World, Chenjie Cao, Xuhui Zuo +42
We introduce HY-World 2.0, a multi-modal world model framework that advances our prior project HY-World 1.0. HY-World 2.0 accommodates diverse input modalities, including text prom…
Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence
Yuanyuan Gao, Hao Li, Yifei Liu +14
The pursuit of spatial intelligence fundamentally relies on access to large-scale, fine-grained 3D data. However, existing approaches predominantly construct spatial understanding…
DeepScan: A Training-Free Framework for Visually Grounded Reasoning in Large Vision-Language Models
Yangfu Li, Hongjian Zhan, Jiawei Chen +3
Humans can robustly localize visual evidence and provide grounded answers even in noisy environments by identifying critical cues and then relating them to the full context in a bo…
Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform
Yuning Gong, Yifei Liu, Yifan Zhan +21
Neural rendering, particularly 3D Gaussian Splatting (3DGS), has evolved rapidly and become a key component for building world models. However, existing viewer solutions remain fra…
ExGS: Extreme 3D Gaussian Compression with Diffusion Priors
Jiaqi Chen, Xinhao Ji, Yuanyuan Gao +7
Neural scene representations, such as 3D Gaussian Splatting (3DGS), have enabled high-quality neural rendering; however, their large storage and transmission costs hinder deploymen…
Proxy-GS: Unified Occlusion Priors for Training and Inference in Structured 3D Gaussian Splatting
Yuanyuan Gao, Yuning Gong, Yifei Liu +6
3D Gaussian Splatting (3DGS) has emerged as an efficient approach for achieving photorealistic rendering. Recent MLP-based variants further improve visual fidelity but introduce su…