Enhancing Zero-shot CLIP with Cross-Modality Attention

The multi-view version of MonoDETR on nuScenes dataset

[CVPR 2022] PointCLIP: Point Cloud Understanding by CLIP

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

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

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

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

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

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

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

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

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

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

TRI-ML Monocular Depth Estimation Repository

Vectornet for trajectory prediction, implemented in PyTorch/Torch_geometric (WIP)

Waymo Open Dataset

OpenMMLab Detection Toolbox and Benchmark

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures

Official repository of T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT

[AAAI 2023] Zero-Shot Enhancement of CLIP with Parameter-free Attention

Reading list for research topics in Masked Image Modeling

Awesome List of Masked Image Modeling (MIM) Papers for Self-supervised Visual Representation Learning

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

✨✨Latest Papers and Datasets on Multimodal Large Language Models, and Their Evaluation.

Align 3D Point Cloud with Multi-modalities for Large Language Models