影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
83.16/100
前 1.1%
全站排名 #711
发表论文19 篇
平均评分
年均产出6.3 篇/年
Tong He
研究方向
general 3D model · Point cloud Instance Segmentation · Semantic Segmentation · Scene text detection and recognition
13
$\pi^3$: Permutation-Equivariant Visual Geometry Learning
ICLR 2026Poster
通讯14
BRIDGE - Building Reinforcement-Learning Depth-to-Image Data Generation Engine for Monocular Depth Estimation
ICLR 2026Desk Rejected
通讯12
InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Models
ICLR 2026Poster
28
OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling
ICLR 2026Poster
通讯15
WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool
ICLR 2026Poster
通讯5
DeepVerse: 4D Autoregressive Video Generation as a World Model
ICLR 2026Withdrawn
通讯5
CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning
ICLR 2026Withdrawn
27
DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks
NeurIPS 2025Spotlight
24
ND-SDF: Learning Normal Deflection Fields for High-Fidelity Indoor Reconstruction
ICLR 2025Spotlight
21
Lumina-T2X: Scalable Flow-based Large Diffusion Transformer for Flexible Resolution Generation
ICLR 2025Spotlight
23
Depth Any Video with Scalable Synthetic Data
ICLR 2025Poster
通讯33
SPA: 3D Spatial-Awareness Enables Effective Embodied Representation
ICLR 2025Poster
通讯21
Where Am I and What Will I See: An Auto-Regressive Model for Spatial Localization and View Prediction
ICLR 2025Poster
通讯25
MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers
ICLR 2025Poster
二作6
Tra-MoE: Scaling Trajectory Prediction Models for Adaptive Policy Conditioning
ICLR 2025Withdrawn