Search Results for author:
Found 27 papers, 23 papers with code
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1.
DeepSeek-V3 Technical Report
We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
We present DeepSeek-VL2, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL, through two key major upgrades.
Ranked #1 on
Referring Expression Comprehension
on RefCOCOg-test
JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation
To further improve the performance of our unified model, we adopt two key strategies: (i) decoupling the understanding and generation encoders, and (ii) aligning their representations during unified training.
Ranked #197 on
Visual Question Answering
on MM-Vet
Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation
In this paper, we introduce Janus, an autoregressive framework that unifies multimodal understanding and generation.
Ranked #164 on
Visual Question Answering
on MM-Vet
DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
Through this continued pre-training, DeepSeek-Coder-V2 substantially enhances the coding and mathematical reasoning capabilities of DeepSeek-V2, while maintaining comparable performance in general language tasks.
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
MLA guarantees efficient inference through significantly compressing the Key-Value (KV) cache into a latent vector, while DeepSeekMoE enables training strong models at an economical cost through sparse computation.
DeepSeek-VL: Towards Real-World Vision-Language Understanding
The DeepSeek-VL family (both 1. 3B and 7B models) showcases superior user experiences as a vision-language chatbot in real-world applications, achieving state-of-the-art or competitive performance across a wide range of visual-language benchmarks at the same model size while maintaining robust performance on language-centric benchmarks.
Ranked #99 on
Visual Question Answering
on MM-Vet
DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence
The rapid development of large language models has revolutionized code intelligence in software development.
Ranked #3 on
Code Generation
on APPS
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
Subsequently, we scale up DeepSeekMoE to 16B parameters and show that it achieves comparable performance with LLaMA2 7B, with only about 40% of computations.
DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
The rapid development of open-source large language models (LLMs) has been truly remarkable.
DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
The score distillation from this 3D-aware diffusion prior provides view-consistent guidance for the scene.
High speed free-space optical communication using standard fiber communication component without optical amplification
Free-space optical communication (FSO) can achieve fast, secure and license-free communication without need for physical cables, making it a cost-effective, energy-efficient and flexible solution when the fiber connection is unavailable.
Improving CLIP Fine-tuning Performance
Experiments suggest that the feature map distillation approach significantly boosts the fine-tuning performance of CLIP models on several typical downstream vision tasks.
iCLIP: Bridging Image Classification and Contrastive Language-Image Pre-Training for Visual Recognition
This paper presents a method that effectively combines two prevalent visual recognition methods, i. e., image classification and contrastive language-image pre-training, dubbed iCLIP.
On Data Scaling in Masked Image Modeling
Our study reveals that: (i) Masked image modeling is also demanding on larger data.
Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillation
These properties, which we aggregately refer to as optimization friendliness, are identified and analyzed by a set of attention- and optimization-related diagnosis tools.
Ranked #4 on
Instance Segmentation
on COCO test-dev
(using extra training data)
Revealing the Dark Secrets of Masked Image Modeling
In this paper, we compare MIM with the long-dominant supervised pre-trained models from two perspectives, the visualizations and the experiments, to uncover their key representational differences.
Ranked #3 on
Depth Estimation
on NYU-Depth V2
iCAR: Bridging Image Classification and Image-text Alignment for Visual Recognition
Second, we convert the image classification problem from learning parametric category classifier weights to learning a text encoder as a meta network to generate category classifier weights.
Swin Transformer V2: Scaling Up Capacity and Resolution
Three main techniques are proposed: 1) a residual-post-norm method combined with cosine attention to improve training stability; 2) A log-spaced continuous position bias method to effectively transfer models pre-trained using low-resolution images to downstream tasks with high-resolution inputs; 3) A self-supervised pre-training method, SimMIM, to reduce the needs of vast labeled images.
Ranked #4 on
Image Classification
on ImageNet V2
(using extra training data)
SimMIM: A Simple Framework for Masked Image Modeling
We also leverage this approach to facilitate the training of a 3B model (SwinV2-G), that by $40\times$ less data than that in previous practice, we achieve the state-of-the-art on four representative vision benchmarks.
Representation Learning
Self-Supervised Image Classification
+1
Breaking Shortcut: Exploring Fully Convolutional Cycle-Consistency for Video Correspondence Learning
Previous cycle-consistency correspondence learning methods usually leverage image patches for training.
Self-Supervised Learning with Swin Transformers
We are witnessing a modeling shift from CNN to Transformers in computer vision.
Ranked #77 on
Self-Supervised Image Classification
on ImageNet
Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning
We argue that the power of contrastive learning has yet to be fully unleashed, as current methods are trained only on instance-level pretext tasks, leading to representations that may be sub-optimal for downstream tasks requiring dense pixel predictions.
Parametric Instance Classification for Unsupervised Visual Feature Learning
This paper presents parametric instance classification (PIC) for unsupervised visual feature learning.
Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation
In the feature maps of CNNs, there commonly exists considerable spatial redundancy that leads to much repetitive processing.
Local Relation Networks for Image Recognition
The convolution layer has been the dominant feature extractor in computer vision for years.
Ranked #939 on
Image Classification
on ImageNet
