Zhuotao Tian

12

Papers

866

Total Citations

Papers (12)

LISA: Reasoning Segmentation via Large Language Model

Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training

Unified Language-driven Zero-shot Domain Adaptation

GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding

SaCo Loss: Sample-wise Affinity Consistency for Vision-Language Pre-training

Edit360: 2D Image Edits to 3D Assets from Any Angle

VisionZip: Longer is Better but Not Necessary in Vision Language Models

OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation

Mitigating Object Hallucinations via Sentence-Level Early Intervention

DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception

Enhancing Spatial Reasoning in Multimodal Large Language Models through Reasoning-based Segmentation

RefDetector: A Simple Yet Effective Matching-based Method for Referring Expression Comprehension