Siyuan Huang | PKU CoRe Lab

Siyuan Huang

Research Scientist

BIGAI

Latest

[CVPR24] Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance
[CVPR24] AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agents
[CVPR24] Scaling Up Dynamic Human-Scene Interaction Modeling
[RA-L24] Grasp Multiple Objects with One Hand
[3DV24] Single-view 3D Scene Reconstruction with High-fidelity Shape and Texture
[ICLR24] Neural-Symbolic Recursive Machine for Systematic Generalization
[NeurIPS23] ProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab
[ICCV23] Full-Body Articulated Human-Object Interaction
[CVPR23] Diffusion-based Generation, Optimization, and Planning in 3D Scenes
[ICLR23] A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics
[ICRA23] GenDexGrasp: Generalizable Dexterous Grasping
[NeurIPS22] HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes
[ECCV22Workshop] PartAfford: Part-level Affordance Discovery from 3D Objects
[ICCV21] YouRefIt: Embodied Reference Understanding with Language and Gesture
[ICCV21] Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds
[ECCV20] LEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task Activities
[Engineering20] Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense
[NeurIPS19] PerspectiveNet: 3D Object Detection from a Single RGB Image via Perspective Points
[ICCV19] Holistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsense
[NeurIPS18] Cooperative Holistic Scene Understanding: Unifying 3D Object, Layout, and Camera Pose Estimation
[ECCV18] Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image
[IJCV18] Configurable 3D Scene Synthesis and 2D Image Rendering with Per-Pixel Ground Truth using Stochastic Grammars
[CVPR18] Human-centric Indoor Scene Synthesis Using Stochastic Grammar