This is your work, valued
Countably infinite
DisDiff. [NeurIPS 2023] code for "DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic Models
★ 77VCT. [NeurIPS 2022] code for "Visual Concepts Tokenization"
★ 23EncDiff. [NeurIPS 2024 Spotlight] code for "Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement"
★ 20ActivationFunctionDemo. [TCAD 2018] Code for “Design Space Exploration of Neural Network Activation Function Circuits”
★ 18Groupified-VAE. [ICLR 2022] code for "Towards building a group-based unsupervised representation disentanglement framework"
★ 15ASE-Pair-Programing-Project. How is the 26-letter frequency of English distributed in a novel? What are the words that often appear in a type of article? What is the most commonly used term for a writer? What is the most commonly used phrase in Harry Potter, and so on. We will write some procedures to solve this problem and satisfy our curiosity.
★ 13RF-VAE. Pytorch implementation of RF_VAE proposed in Relevance Factor VAE: Learning and Identifying Disentangled Factors, Kim et al.
★ 9ThomasNotes. This is a repository of my own learning notes, also could be a tutorial. I will I will continue to update this new repository, which may include machine learning, deep learning, probability theory, information theory, pytorch, tensorflow, and some learning materials from numpy, which may be partially non-original but could be useful.
★ 3DisCo. [ICLR2022] Code for "Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning View"
★ 3origin. This code is for generating the parameters before multi-value operation.
★ 2Poetic-Image. software engineering team project
★ 1CS-DisMo. Code for paper "Rethinking Content and Style: Exploring Bias for Unsupervised Disentanglement"
★ 1ternary-cnn. This code ternary the output of the neural networks.
★ 1DockerFile. The DockerFile of OpenPAI
★ 1binary-cov. This code binary the output of the convolution layer of CNN and train and prune the parameters.
★ 1Anotool. The "Anotool" is a demo for labeling multi-attribute object labels for images, with hierarchical attributes and objects, which is the anotation tool of the dataset and the paper:
★ 1SimFlow. Official implementation of SimFlow
★ 33SFD. [CVPR 2026] Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion
★ 153Awesome-Video-LMM-Post-Training. 🔥🔥🔥 Latest Papers, Codes and Datasets on Video-LMM Post-Training
★ 297ms-swift. Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).
★ 15kArinar. Python
★ 43gpt-oss. gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
★ 20kAudioCLIP. Source code for models described in the paper "AudioCLIP: Extending CLIP to Image, Text and Audio" (https://arxiv.org/abs/2106.13043)
★ 872DiffSynth-Studio. Enjoy the magic of Diffusion models!
★ 13kConceptExpress. [ECCV 2024 Oral] ConceptExpress: Harnessing Diffusion Models for Single-image Unsupervised Concept Extraction
★ 77trl. Train transformer language models with reinforcement learning.
★ 19kopen-infra-index. Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
★ 8kDiT-Visualization. Visualization of DiT self attention features
★ 236Wan2.1. Wan: Open and Advanced Large-Scale Video Generative Models
★ 17kawesome-deepseek-integration. Integrate the DeepSeek API into popular software
★ 38kAwesome-Diffusion-Flow-Samplers. Collecting research materials on neural samplers with diffusion/flow models
★ 59Embodied-AI-Guide. [Lumina具身智能社区] 具身智能技术指南 Embodied-AI-Guide
★ 15kEncDiff. [NeurIPS 2024 Spotlight] code for "Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement"
★ 20DeepSeek-R1.
★ 92kFollowYourPose. [AAAI 2024] Follow-Your-Pose: This repo is the official implementation of "Follow-Your-Pose : Pose-Guided Text-to-Video Generation using Pose-Free Videos"
★ 1.4kawesome-diffusion-categorized. collection of diffusion model papers categorized by their subareas
★ 2.2kGrounded-SAM-2. Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2
★ 3.7kDoRA. [ICML2024 (Oral)] Official PyTorch implementation of DoRA: Weight-Decomposed Low-Rank Adaptation
★ 986annotated_deep_learning_paper_implementations. 🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
★ 67kVAR. [NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!
★ 8.7kU-DiT. [NeurIPS 2024] The official code of "U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers"
★ 240InstructRAG. [ICLR 2025] InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales
★ 151Holistic-Motion2D. Data release of Holistic-Motion2D
★ 10video2game. Code release of Video2Game
★ 334VideoSys. VideoSys: An easy and efficient system for video generation
★ 2kdistrifuser. [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
★ 727SoraReview. The official GitHub page for the review paper "Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models".
★ 504DiT. Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"
★ 8.7kbaby-llama2-chinese. 用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库;24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
★ 2.9kLora-for-Diffusers. The most easy-to-understand tutorial for using LoRA (Low-Rank Adaptation) within diffusers framework for AI Generation Researchers🔥
★ 824CoT-Collection. [EMNLP 2023] The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning
★ 258Multimodal-Context-Reasoning. A multimodal context reasoning approach that introduce the multi-view semantic alignment information via prefix tuning.
★ 15SVD_Xtend. Stable Video Diffusion Training Code and Extensions.
★ 731DiffiT. [ECCV 2024] Official Repository for DiffiT: Diffusion Vision Transformers for Image Generation
★ 517Awesome-LLMs-for-Video-Understanding. 🔥🔥🔥 [IEEE TCSVT] Latest Papers, Codes and Datasets on Vid-LLMs.
★ 3.3kFastSAM. Fast Segment Anything
★ 8.4kAnyText. Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>
★ 4.9kTinyLlama. The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
★ 9kProText. [AAAI'25, CVPRW 2024] Official repository of paper titled "Learning to Prompt with Text Only Supervision for Vision-Language Models".
★ 128czsc. 缠中说禅技术分析工具;缠论;股票;期货;Quant;量化交易
★ 5.6kCogVLM. a state-of-the-art-level open visual language model | 多模态预训练模型
★ 6.7kFDAE. Implementation of "Factorized Diffusion Autoencoder for Unsupervised Disentangled Representation Learning" (AAAI 2024)
★ 17Disentanglement-Paper-List. disentanglement learning paper list
★ 3wangyanhui666.github.io. HTML
★ 1DecryptPrompt. 总结Prompt&LLM论文,开源数据&模型,AIGC应用
★ 3.4kDeepSeek-Coder. DeepSeek Coder: Let the Code Write Itself
★ 24kcaption-upsampling. This repository implements the idea of "caption upsampling" from DALL-E 3 with Zephyr-7B and gathers results with SDXL.
★ 158ALIA. Augmenting with Language-guided Image Augmentation (ALIA)
★ 78Mini-DALLE3. Mini-DALLE3: Interactive Text to Image by Prompting Large Language Models
★ 313Awesome-Text-to-3D.
★ 161Cola. [NeurIPS2023] Official implementation of the paper "Large Language Models are Visual Reasoning Coordinators"
★ 106latent-flow. NeurIPS23 "Flow Factorized Representation Learning"
★ 46RTD. [ICML 2022] Representation Topology Divergence: A Method for Comparing Neural Network Representations
★ 27letta. Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.
★ 24kDisDiff. [NeurIPS 2023] code for "DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic Models
★ 77MarineGPT. The official implementation of MarineGPT
★ 45Look-Outside-Room. [CVPR 2022] Look Outside the Room: Synthesizing A Consistent Long-Term 3D Scene Video from A Single Image
★ 82DPM-Solver-v3. Official code for "DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics" (NeurIPS 2023)
★ 135EVA. EVA Series: Visual Representation Fantasies from BAAI
★ 2.7klynx-llm. paper: https://arxiv.org/abs/2307.02469 page: https://lynx-llm.github.io/
★ 272Linguistic-Binding-in-Diffusion-Models. Jupyter Notebook
★ 82PDAE. Official PyTorch implementation of PDAE (NeurIPS 2022)
★ 225nashae-beamsynthesis. Published code for the ECCV '22 paper NashAE: Disentangling Representations through Adversarial Covariance Minimization and data for the Beamsynthesis disentanglement dataset
★ 6NeuralOptimalTransport. PyTorch implementation of "Neural Optimal Transport" (ICLR 2023 Spotlight)
★ 233Video-ChatGPT. [ACL 2024 🔥] Video-ChatGPT is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrained visual encoder adapted for spatiotemporal video representation. We also introduce a rigorous 'Quantitative Evaluation Benchmarking' for video-based conversational models.
★ 1.5kflash-attention. Fast and memory-efficient exact attention
★ 25kgrokking-squared. Jupyter Notebook
★ 28grokking. Implementation of OpenAI's 'Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets' paper.
★ 44grokking. unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"
★ 90MeZO. [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333
★ 1.2kNeTI. Official Implementation for "A Neural Space-Time Representation for Text-to-Image Personalization" (SIGGRAPH Asia 2023)
★ 182NKSR. [CVPR 2023 Highlight] Neural Kernel Surface Reconstruction
★ 982DDPM_inversion. Official pytorch implementation of the paper: "An Edit Friendly DDPM Noise Space: Inversion and Manipulations". CVPR 2024.
★ 368diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
★ 34ksort-google-scholar. Ranking Google Scholar search results based on the number of citations
★ 992ContextDET. Contextual Object Detection with Multimodal Large Language Models
★ 261Uni-ControlNet. [NeurIPS 2023] Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models
★ 670UniControl. Unified Controllable Visual Generation Model
★ 662Awesome-LLM. Awesome-LLM: a curated list of Large Language Model
★ 27kHa-NeRF. [CVPR 2022] Ha-NeRF😆: Hallucinated Neural Radiance Fields in the Wild
★ 160MindVideo. Official code base for MinD-Video
★ 389CLIPA. [NeurIPS 2023] This repository includes the official implementation of our paper "An Inverse Scaling Law for CLIP Training"
★ 322guidance. A guidance language for controlling large language models.
★ 22kllm-numbers. Numbers every LLM developer should know
★ 4.3kleetcode-master. 《代码随想录》LeetCode 刷题攻略:200道经典题目刷题顺序,共60w字的详细图解,视频难点剖析,50余张思维导图,支持C++,Java,Python,Go,JavaScript等多语言版本,从此算法学习不再迷茫!🔥🔥 来看看,你会发现相见恨晚!🚀
★ 62kDragGAN. Implementation of DragGAN: Interactive Point-based Manipulation on the Generative Image Manifold
★ 2.1kIF. Python
★ 7.8kMUSE-Pytorch. An in-context conditioning version of MUSE with pre-trained checkpoints.
★ 115so-vits-svc. SoftVC VITS Singing Voice Conversion
★ 28kAsk-Anything. [CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
★ 3.3kCompositional-Generalization. [NeurIPS 2022] Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Language
★ 13s2p. Code repository for On the interaction between supervision and self-play in emergent communication (ICLR 2020)
★ 15Inpaint-Anything. Inpaint anything using Segment Anything and inpainting models.
★ 7.7kAwesome-ComposableAI. A curated list of Composable AI methods: Building AI system by composing modules.
★ 199LoRA. Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
★ 14kAwesome-Anything. General AI methods for Anything: AnyObject, AnyGeneration, AnyModel, AnyTask, AnyX
★ 1.9kEditAnything. Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)
★ 3.4kconsistency_models. Official repo for consistency models.
★ 6.5kImageReward. [NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation
★ 1.7kOpenAGI. OpenAGI: When LLM Meets Domain Experts
★ 2.3ksegment-anything. The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
★ 55kInjectFusion_official. Python
★ 127gpt_academic. 为GPT/GLM等LLM大语言模型提供实用化交互接口,特别优化论文阅读/润色/写作体验,模块化设计,支持自定义快捷按钮&函数插件,支持Python和C++等项目剖析&自译解功能,PDF/LaTex论文翻译&总结功能,支持并行问询多种LLM模型,支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。
★ 71kvisual_token_matching. [ICLR'23 Oral] Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching
★ 257dino. PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
★ 7.6kcustom-diffusion. Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)
★ 2kT2I-Adapter. T2I-Adapter
★ 3.8kself-instruct. Aligning pretrained language models with instruction data generated by themselves.
★ 4.6kviper. Code for the paper "ViperGPT: Visual Inference via Python Execution for Reasoning"
★ 1.7kplug-and-play. Official Pytorch Implementation for “Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation” (CVPR 2023)
★ 1kdreambooth.
★ 1kAsyrp_official. official repo for Asyrp : Diffusion Models already have a Semantic Latent Space (ICLR2023)
★ 289ELITE. ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation (ICCV 2023, Oral)
★ 541unidiffuser. Code and models for the paper "One Transformer Fits All Distributions in Multi-Modal Diffusion"
★ 1.5kUNINEXT. [CVPR'23] Universal Instance Perception as Object Discovery and Retrieval
★ 1.3kprismer. The implementation of "Prismer: A Vision-Language Model with Multi-Task Experts".
★ 1.3kTaskMatrix. Python
★ 34kVPD. [ICCV 2023] VPD is a framework that leverages the high-level and low-level knowledge of a pre-trained text-to-image diffusion model to downstream visual perception tasks.
★ 540llama. Inference code for Llama models
★ 60kunilm. Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
★ 22kimg2dataset. Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
★ 4.4kstylegan2-projecting-images. Projecting images to latent space with StyleGAN2.
★ 300laion-prepro. Get hundred of million of image+url from the crawling at home dataset and preprocess them
★ 222sysbinder. Official Code for Neural Systematic Binder
★ 34FlexLLMGen. Running large language models on a single GPU for throughput-oriented scenarios.
★ 9.4kControlNet. Let us control diffusion models!
★ 34kparti-pytorch. Implementation of Parti, Google's pure attention-based text-to-image neural network, in Pytorch
★ 537SAR. Code for ICLR 2023 paper (Oral) — Towards Stable Test-Time Adaptation in Dynamic Wild World
★ 214Imagen-pytorch. Python
★ 274Uni-Perceiver. Python
★ 291ICL_PaperList. Paper List for In-context Learning 🌷
★ 876language-quantized-autoencoders. Language Quantized AutoEncoders
★ 115ChatGPT. ❄️ ChatGPT Desktop Application (Mac, Windows and Linux)
★ 54kinstruct-pix2pix. Python
★ 6.9kblobgan. Official PyTorch implementation of BlobGAN: Spatially Disentangled Scene Representations
★ 173Tune-A-Video. [ICCV 2023] Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
★ 4.4kawesome-cv-writing. 该仓库包含了计算机视觉论文中写作常用的句式、短语、缩写等。
★ 56slate. This is the official source code for SLATE. We provide the code for the model, the training code, and a dataset loader for the 3D Shapes dataset. This code is implemented in Pytorch.
★ 89Self-supervised-Video-Concept. Code for Static and Dynamic Concepts for Self-supervised Video Representation Learning.
★ 11Open-Assistant. OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
★ 37kVCT. [NeurIPS 2022] code for "Visual Concepts Tokenization"
★ 23LAVIS. LAVIS - A One-stop Library for Language-Vision Intelligence
★ 11kdisentanglement_lib_med. [NeurIPS 2022] disentanglement evaluation robust to model dimension variance.
★ 10dpm-solver. Official code for "DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps" (Neurips 2022 Oral)
★ 1.9knerf-pytorch. A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.
★ 6.1kiclr2023_stats. ICLR2023 statistics
★ 60Paper-Picture-Writing-Code. MLNLP: Paper Picture Writing Code
★ 1.2kdiffae. Official implementation of Diffusion Autoencoders
★ 968DiffuseIT. Official repository of "Diffusion-based Image Translation using Disentangled Style and Content Representation" ( ICLR 2023 )
★ 305guided-diffusion. Python
★ 7.4kDALLE-pytorch. Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch
★ 5.6kmixstyle-release. Domain Generalization with MixStyle (ICLR'21)
★ 334StyleMix. Python
★ 33deep-vector-quantization. VQVAEs, GumbelSoftmaxes and friends
★ 654stable-diffusion. A latent text-to-image diffusion model
★ 73kCrossAttentionControl. Unofficial implementation of "Prompt-to-Prompt Image Editing with Cross Attention Control" with Stable Diffusion
★ 1.3kDreambooth-Stable-Diffusion. Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion
★ 7.7kGLIP. Grounded Language-Image Pre-training
★ 2.6kPromptPapers. Must-read papers on prompt-based tuning for pre-trained language models.
★ 4.3ktextual_inversion. Jupyter Notebook
★ 3.1kAwesome-Diffusion-Models. A collection of resources and papers on Diffusion Models
★ 12kText2All. A curated list of text-guided generative models resources
★ 159stable-dreamfusion. Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.
★ 8.8kimagen-pytorch. Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch
★ 8.4kGroupified-VAE. [ICLR 2022] code for "Towards building a group-based unsupervised representation disentanglement framework"
★ 15latent-diffusion. High-Resolution Image Synthesis with Latent Diffusion Models
★ 14kclip-gen. CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP
★ 147EA-VQ-VAE. This repo provides the code for the ACL 2020 paper "Evidence-Aware Inferential Text Generation with Vector Quantised Variational AutoEncoder"
★ 57Distributional-Generalization-in-Natural-Language-Processing. Distributional Generalization in NLP. A roadmap.
★ 86google-research. Google Research
★ 38kcomet. [NeurIPS 2021] Code for Unsupervised Learning of Compositional Energy Concepts
★ 60IODINE. PyTorch re-implementation of Multi-Object Representation Learning with Iterative Variational Inference
★ 59cook. 🍲 好的,今天我们来做菜!OK, Let's Cook!
★ 6.5kMAE. PyTorch implementation of Masked Autoencoder
★ 289mae. PyTorch implementation of MAE https//arxiv.org/abs/2111.06377
★ 8.4kDALI. A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.
★ 5.7ktfrecord. Standalone TFRecord reader/writer with PyTorch data loaders
★ 902SCOPS. SCOPS: Self-Supervised Co-Part Segmentation (CVPR'19)
★ 219taming-transformers. Taming Transformers for High-Resolution Image Synthesis
★ 6.5kconvit. Code for the Convolutional Vision Transformer (ConViT)
★ 474SingleSampleGeneralization-ICLR2022. Python
★ 23DSU. [ICLR 2022] Official pytorch implementation of "Uncertainty Modeling for Out-of-Distribution Generalization" in International Conference on Learning Representations (ICLR) 2022.
★ 165DDG. [CVPR 2022 Oral] Towards Principled Disentanglement for Domain Generalization
★ 64Generalization-Causality. 关于domain generalization,domain adaptation,causality,robutness,prompt,optimization,generative model各式各样研究的阅读笔记
★ 1.2kswad. Official Implementation of SWAD (NeurIPS 2021)
★ 174AI_Blog. AI Blog with Markdown
★ 36tent. ICLR21 Tent: Fully Test-Time Adaptation by Entropy Minimization
★ 472deepmind-research. This repository contains implementations and illustrative code to accompany DeepMind publications
★ 15kColossalAI. Making large AI models cheaper, faster and more accessible
★ 41kperceiver-pytorch. Implementation of Perceiver, General Perception with Iterative Attention, in Pytorch
★ 1.2kDiffFlow. [Neurips 2021]Diffusion Normalizing Flow (DiffFlow)
★ 120EADA. [AAAI 2022] Code release for "Active Learning for Domain Adaptation: An Energy-based Approach". https://arxiv.org/abs/2112.01406
★ 1iclr2022_stats. HTML
★ 47DisentanglementMetrics. This repository contains the full code for our paper "Theory and evaluation metrics for learning disentangled representations"
★ 15Taming-VAEs. Jupyter Notebook
★ 28lightning-hydra-template. PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡
★ 5.3k