Renrui Zhang

Personalize-SAM. Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds

Point-NN. [CVPR 2023] Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis

MonoDETR. [ICCV 2023] The first DETR model for monocular 3D object detection with depth-guided transformer

PointCLIP. [CVPR 2022] PointCLIP: Point Cloud Understanding by CLIP

I2P-MAE. [CVPR 2023] Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders

Point-M2AE. [NeurIPS 2022] Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training

MathVerse. [ECCV 2024] Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?

MAVIS. [ICLR 2025] Mathematical Visual Instruction Tuning for Multi-modal Large Language Models

LLaMA-Adapter. Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

CaFo. [CVPR 2023] Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners

MonoDETR-MV. The multi-view version of MonoDETR on nuScenes dataset

ZrrSkywalker.

CALIP. Enhancing Zero-shot CLIP with Cross-Modality Attention

MathVista. MathVista: data, code, and evaluation for Mathematical Reasoning in Visual Contexts

ZrrSkywalker.github.io. HTML