Li Yi

20

Papers

506

Total Citations

Papers (20)

DreamLLM: Synergistic Multimodal Comprehension and Creation

ShapeLLM: Universal 3D Object Understanding for Embodied Interaction

SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation

NeurIPS 2025arXiv

CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangement

DexVLG: Dexterous Vision-Language-Grasp Model at Scale

GenN2N: Generative NeRF2NeRF Translation

MAP: Unleashing Hybrid Mamba-Transformer Vision Backbone's Potential with Masked Autoregressive Pretraining

Physics-Aware Hand-Object Interaction Denoising

PartRM: Modeling Part-Level Dynamics with Large Cross-State Reconstruction Model

Revisiting Source-Free Domain Adaptation: a New Perspective via Uncertainty Control

Full-Body Motion Reconstruction with Sparse Sensing from Graph Perspective

Adapt Foundational Segmentation Models with Heterogeneous Searching Space

MobileH2R: Learning Generalizable Human to Mobile Robot Handover Exclusively from Scalable and Diverse Synthetic Data

Semantic Complete Scene Forecasting from a 4D Dynamic Point Cloud Sequence

SyncDiff: Synchronized Motion Diffusion for Multi-Body Human-Object Interaction Synthesis

Self-Supervised Monocular 4D Scene Reconstruction for Egocentric Videos

GenH2R: Learning Generalizable Human-to-Robot Handover via Scalable Simulation Demonstration and Imitation

TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding

Learning Physics-Based Full-Body Human Reaching and Grasping from Brief Walking References

4DSegStreamer: Streaming 4D Panoptic Segmentation via Dual Threads