[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

手把手带你实战 Huggingface Transformers 课程视频同步更新在B站与YouTube

获取QQ空间发布的历史说说

⚡FlashRAG: A Python Toolkit for Efficient RAG Research

An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.

Tooling for the Common Objects In 3D dataset.

Official implementation of Reward Imputation with Sketching for Contextual Batched Bandits

PyTorch implementation of SketchSampler: Sketch-based 3D Reconstruction via View-dependent Depth Sampling, ECCV2022.

[IROS 2021] BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models

[IROS 2020] se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains

Code for "OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models" NeurIPS 2022

Code Release for RelPose++: Recovering 6D Poses from Sparse-view Observations

COLMAP - Structure-from-Motion and Multi-View Stereo

🪐 Objaverse-XL is a Universe of 10M+ 3D Objects. Contains API Scripts for Downloading and Processing!

PixelNeRF Official Repository

Code release for NeRF (Neural Radiance Fields)

NeRF (Neural Radiance Fields) and NeRF in the Wild using pytorch-lightning

WebUI extension for ControlNet

PyTorch implementation of the PoseCNN framework

[CVPR 2024 Highlight] FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects

Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion

A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes

[CVPR2019 Oral] Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation on Python3, Tensorflow, and Keras

Robust fine-tuning of zero-shot models

PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

中文命名实体识别（包括多种模型：HMM，CRF，BiLSTM，BiLSTM+CRF的具体实现）