Search Results for author:
Found 32 papers, 23 papers with code
Quantifying the Capability Boundary of DeepSeek Models: An Application-Driven Performance Analysis
DeepSeek-R1, known for its low training cost and exceptional reasoning capabilities, has achieved state-of-the-art performance on various benchmarks.
Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
In this work, we introduce Janus-Pro, an advanced version of the previous work Janus.
Ranked #4 on
Text-to-Image Generation
on GenEval
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1.
Ranked #2 on
Mathematical Reasoning
on AIME24
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 #17 on
Text-to-Image Generation
on GenEval
CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM
This paper aims to design a unified Computer-Aided Design (CAD) generation system that can easily generate CAD models based on the user's inputs in the form of textual description, images, point clouds, or even a combination of them.
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 #11 on
on WISE
MagicID: Flexible ID Fidelity Generation System
Portrait Fidelity Generation is a prominent research area in generative models, with a primary focus on enhancing both controllability and fidelity.
P/D-Serve: Serving Disaggregated Large Language Model at Scale
To overcome previous problems, this paper proposes an end-to-end system P/D-Serve, complying with the paradigm of MLOps (machine learning operations), which models end-to-end (E2E) P/D performance and enables: 1) fine-grained P/D organization, mapping the service with RoCE (RDMA over converged ethernet) as needed, to facilitate similar processing and dynamic adjustments on P/D ratios; 2) on-demand forwarding upon rejections for idle prefill, decoupling the scheduler from regular inaccurate reports and local queues, to avoid timeouts in prefill; and 3) efficient KVCache transfer via optimized D2D access.
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 #101 on
Visual Question Answering
on MM-Vet
DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
The rapid development of open-source large language models (LLMs) has been truly remarkable.
Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models
This paper presents Paint3D, a novel coarse-to-fine generative framework that is capable of producing high-resolution, lighting-less, and diverse 2K UV texture maps for untextured 3D meshes conditioned on text or image inputs.
DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
The score distillation from this 3D-aware diffusion prior provides view-consistent guidance for the scene.
Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation
We present a novel alignment-before-generation approach to tackle the challenging task of generating general 3D shapes based on 2D images or texts.
MotionGPT: Human Motion as a Foreign Language
Building upon this "motion vocabulary", we perform language modeling on both motion and text in a unified manner, treating human motion as a specific language.
Ranked #4 on
Motion Captioning
on HumanML3D
A New Paradigm for Device-free Indoor Localization: Deep Learning with Error Vector Spectrum in Wi-Fi Systems
The demand for device-free indoor localization using commercial Wi-Fi devices has rapidly increased in various fields due to its convenience and versatile applications.
Executing your Commands via Motion Diffusion in Latent Space
We study a challenging task, conditional human motion generation, which produces plausible human motion sequences according to various conditional inputs, such as action classes or textual descriptors.
Ranked #2 on
Motion Synthesis
on HumanAct12
Coordinates Are NOT Lonely -- Codebook Prior Helps Implicit Neural 3D Representations
Implicit neural 3D representation has achieved impressive results in surface or scene reconstruction and novel view synthesis, which typically uses the coordinate-based multi-layer perceptrons (MLPs) to learn a continuous scene representation.
Speech Drives Templates: Co-Speech Gesture Synthesis with Learned Templates
Co-speech gesture generation is to synthesize a gesture sequence that not only looks real but also matches with the input speech audio.
Prior Based Human Completion
One is a structure prior, it uses a human parsing map to represent the human body structure.
Liquid Warping GAN with Attention: A Unified Framework for Human Image Synthesis
Also, we build a new dataset, namely iPER dataset, for the evaluation of human motion imitation, appearance transfer, and novel view synthesis.
Learning from Multimodal and Multitemporal Earth Observation Data for Building Damage Mapping
In this study, we have developed a global multisensor and multitemporal dataset for building damage mapping.
Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images
In the end, we further utilize the reconstructed image to extract the structure and measure the difference between structure extracted from original and the reconstructed image.
Channel Distillation: Channel-Wise Attention for Knowledge Distillation
Knowledge distillation is to transfer the knowledge from the data learned by the teacher network to the student network, so that the student has the advantage of less parameters and less calculations, and the accuracy is close to the teacher.
Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis
In this paper, we propose to use a 3D body mesh recovery module to disentangle the pose and shape, which can not only model the joint location and rotation but also characterize the personalized body shape.
Multi-Cell Multi-Task Convolutional Neural Networks for Diabetic Retinopathy Grading
To considering the relationships of images with different stages, we propose a \textbf{Multi-Task} learning strategy which predicts the label with both classification and regression.
Future Frame Prediction for Anomaly Detection â A New Baseline
To predict a future frame with higher quality for normal events, other than the commonly used appearance (spatial) constraints on intensity and gradient, we also introduce a motion (temporal) constraint in video prediction by enforcing the optical flow between predicted frames and ground truth frames to be consistent, and this is the first work that introduces a temporal constraint into the video prediction task.
Future Frame Prediction for Anomaly Detection -- A New Baseline
To predict a future frame with higher quality for normal events, other than the commonly used appearance (spatial) constraints on intensity and gradient, we also introduce a motion (temporal) constraint in video prediction by enforcing the optical flow between predicted frames and ground truth frames to be consistent, and this is the first work that introduces a temporal constraint into the video prediction task.
Ranked #2 on
Traffic Accident Detection
on SA
A Revisit of Sparse Coding Based Anomaly Detection in Stacked RNN Framework
Motivated by the capability of sparse coding based anomaly detection, we propose a Temporally-coherent Sparse Coding (TSC) where we enforce similar neighbouring frames be encoded with similar reconstruction coefficients.
Ranked #29 on
Anomaly Detection
on ShanghaiTech
