Search Results for author:
Found 11 papers, 5 papers with code
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
Visual-Semantic Graph Matching Net for Zero-Shot Learning
However, methods trained under this paradigm often struggle to learn robust embedding space because they align the two modalities in an isolated manner among classes, which ignore the crucial class relationship during the alignment process.
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
3D-CT-GPT: Generating 3D Radiology Reports through Integration of Large Vision-Language Models
Medical image analysis is crucial in modern radiological diagnostics, especially given the exponential growth in medical imaging data.
HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments
Recent advances in high-fidelity virtual environments serve as one of the major driving forces for building intelligent embodied agents to perceive, reason and interact with the physical world.
ChatRadio-Valuer: A Chat Large Language Model for Generalizable Radiology Report Generation Based on Multi-institution and Multi-system Data
Radiology report generation, as a key step in medical image analysis, is critical to the quantitative analysis of clinically informed decision-making levels.
Quantum and Translation Embedding for Knowledge Graph Completion
The insight of this work enlightens the notion of dense feature model design for KGC which is a new alternative to Deep Neural networks (DNN) in this task or even a better choice.
On Sufficient and Necessary Conditions in Bounded CTL: A Forgetting Approach
To address such a scenario in a principled way, we introduce a forgetting-based approach in CTL and show that it can be used to compute SNC and WSC of a property under a given model and over a given signature.
Semi-supervised Feature Learning For Improving Writer Identification
In this study, a semi-supervised feature learning pipeline was proposed to improve the performance of writer identification by training with extra unlabeled data and the original labeled data simultaneously.
On Forgetting in Tractable Propositional Fragments
Distilling from a knowledge base only the part that is relevant to a subset of alphabet, which is recognized as forgetting, has attracted extensive interests in AI community.
