Search Results for author:
Found 18 papers, 11 papers with code
MoMa: A Modular Deep Learning Framework for Material Property Prediction
Deep learning methods for material property prediction have been widely explored to advance materials discovery.
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.
DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark
We believe that the GenVideo dataset and the DeMamba module will significantly advance the field of AI-generated video detection.
Dual-Adapter: Training-free Dual Adaptation for Few-shot Out-of-Distribution Detection
We study the problem of few-shot out-of-distribution (OOD) detection, which aims to detect OOD samples from unseen categories during inference time with only a few labeled in-domain (ID) samples.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
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.
NTIRE 2024 Quality Assessment of AI-Generated Content Challenge
A total of 196 participants have registered in the video track.
Conditional Prototype Rectification Prompt Learning
Recent advancements in efficient transfer learning (ETL) have shown remarkable success in fine-tuning VLMs within the scenario of limited data, introducing only a few parameters to harness task-specific insights from VLMs.
The Devil is in the Few Shots: Iterative Visual Knowledge Completion for Few-shot Learning
Few-shot learning aims to further enhance the transfer capability of CLIP by giving few images in each class, aka 'few shots'.
Segment Anything Model Meets Image Harmonization
Image harmonization is a crucial technique in image composition that aims to seamlessly match the background by adjusting the foreground of composite images.
Boosting Audio-visual Zero-shot Learning with Large Language Models
Recent methods mainly focus on learning multi-modal features aligned with class names to enhance the generalization ability to unseen categories.
Ranked #1 on
GZSL Video Classification
on ActivityNet-GZSL (cls)
DiffUTE: Universal Text Editing Diffusion Model
Specifically, we build our model on a diffusion model and carefully modify the network structure to enable the model for drawing multilingual characters with the help of glyph and position information.
Hierarchical Dynamic Image Harmonization
The MGD effectively applies distinct convolution to the foreground and background, learning the representations of foreground and background regions as well as their correlations to the global harmonization, facilitating local visual consistency for the images much more efficiently.
Ranked #2 on
Image Harmonization
on HAdobe5k(1024$\times$1024)
Shaping Visual Representations with Attributes for Few-Shot Recognition
Under the guidance of attribute modality, our method can learn enhanced semantic-aware representation for classification.
Sparse Spatial Transformers for Few-Shot Learning
Finally, we propose using an image patch-matching module to calculate the distance between dense local representations, thus determining which category the query image belongs to in the support set.
Ranked #17 on
Few-Shot Image Classification
on FC100 5-way (1-shot)
Hierarchical Representation based Query-Specific Prototypical Network for Few-Shot Image Classification
Few-shot image classification aims at recognizing unseen categories with a small number of labeled training data.
Multi-level Metric Learning for Few-shot Image Recognition
Moreover, a Multi-level Metric Learning (MML) method is proposed, which not only calculates the pixel-level similarity but also considers the similarity of part-level features and global-level features.
Multi-scale Adaptive Task Attention Network for Few-Shot Learning
Then, an adaptive task attention module is proposed to select the most important LRs among the entire task.
