Yifan Xu

papers

1,321

total citations

papers (12)

Co-Scale Conv-Attentional Image Transformers

ICCV 2021arXiv

437

citations

Pose Recognition With Cascade Transformers

CVPR 2021arXiv

249

citations

BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions

AAAI 2024arXiv

192

citations

Ladybird: Quasi-Monte Carlo Sampling for Deep Implicit Field Based 3D Reconstruction with Symmetry

ECCV 2020arXiv

citations

MMGDreamer: Mixed-Modality Graph for Geometry-Controllable 3D Indoor Scene Generation

AAAI 2025arXiv

citations

Libra: Building Decoupled Vision System on Large Language Models

ICML 2024arXiv

citations

Neural Motion Simulator Pushing the Limit of World Models in Reinforcement Learning

CVPR 2025arXiv

citations

RFNet: Recurrent Forward Network for Dense Point Cloud Completion

ICCV 2021

citations

Yifan Xu

papers (12)

Co-Scale Conv-Attentional Image Transformers

Pose Recognition With Cascade Transformers

BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions

Line Segment Detection Using Transformers Without Edges

Guided Variational Autoencoder for Disentanglement Learning

VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents

Multi-modal Queried Object Detection in the Wild

Ladybird: Quasi-Monte Carlo Sampling for Deep Implicit Field Based 3D Reconstruction with Symmetry

MMGDreamer: Mixed-Modality Graph for Geometry-Controllable 3D Indoor Scene Generation

Libra: Building Decoupled Vision System on Large Language Models

Neural Motion Simulator Pushing the Limit of World Models in Reinforcement Learning

RFNet: Recurrent Forward Network for Dense Point Cloud Completion

papers (12)

Co-Scale Conv-Attentional Image Transformers

Pose Recognition With Cascade Transformers

BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions

Line Segment Detection Using Transformers Without Edges

Guided Variational Autoencoder for Disentanglement Learning

VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents

Multi-modal Queried Object Detection in the Wild

Ladybird: Quasi-Monte Carlo Sampling for Deep Implicit Field Based 3D Reconstruction with Symmetry

MMGDreamer: Mixed-Modality Graph for Geometry-Controllable 3D Indoor Scene Generation

Libra: Building Decoupled Vision System on Large Language Models

Neural Motion Simulator Pushing the Limit of World Models in Reinforcement Learning

RFNet: Recurrent Forward Network for Dense Point Cloud Completion