Search Results for author:
Found 16 papers, 9 papers with code
MHAF-YOLO: Multi-Branch Heterogeneous Auxiliary Fusion YOLO for accurate object detection
Due to the effective multi-scale feature fusion capabilities of the Path Aggregation FPN (PAFPN), it has become a widely adopted component in YOLO-based detectors.
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1.
Ranked #1 on
Multi-task Language Understanding
on MMLU
(using extra training data)
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.
EdgeOAR: Real-time Online Action Recognition On Edge Devices
To address this, we designed EdgeOAR, a novel framework specifically designed for OAR on edge devices.
The Evolution and Future Perspectives of Artificial Intelligence Generated Content
Artificial intelligence generated content (AIGC), a rapidly advancing technology, is transforming content creation across domains, such as text, images, audio, and video.
Autogenic Language Embedding for Coherent Point Tracking
Point tracking is a challenging task in computer vision, aiming to establish point-wise correspondence across long video sequences.
Ontology-driven Reinforcement Learning for Personalized Student Support
In the search for more effective education, there is a widespread effort to develop better approaches to personalize student education.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Multi-Branch Auxiliary Fusion YOLO with Re-parameterization Heterogeneous Convolutional for accurate object detection
Meanwhile, the Advanced Assisted Fusion (AAF) module deeply embedded within the neck conveys a more diverse range of gradient information to the output layer.
Ranked #50 on
Real-Time Object Detection
on MS COCO
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.
TIDE: Test Time Few Shot Object Detection
Few-shot object detection (FSOD) aims to extract semantic knowledge from limited object instances of novel categories within a target domain.
Learning noise-induced transitions by multi-scaling reservoir computing
To capture such stochastic transitions from data, we find that leveraging a machine learning model, reservoir computing as a type of recurrent neural network, can learn noise-induced transitions.
Multi-Agent Reinforcement Learning: Methods, Applications, Visionary Prospects, and Challenges
This paper aims to review methods and applications and point out research trends and visionary prospects for the next decade.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Neural-network solutions to stochastic reaction networks
The stochastic reaction network in which chemical species evolve through a set of reactions is widely used to model stochastic processes in physics, chemistry and biology.
SHREC'22 Track: Sketch-Based 3D Shape Retrieval in the Wild
We define two SBSR tasks and construct two benchmarks consisting of more than 46, 000 CAD models, 1, 700 realistic models, and 145, 000 sketches in total.
Two-Hop Walks Indicate PageRank Order
This paper shows that pairwise PageRank orders emerge from two-hop walks.
A Single-shot-per-pose Camera-Projector Calibration System For Imperfect Planar Targets
Existing camera-projector calibration methods typically warp feature points from a camera image to a projector image using estimated homographies, and often suffer from errors in camera parameters and noise due to imperfect planarity of the calibration target.
