Search Results for author:
Found 68 papers, 22 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.
CAD-GPT: Synthesising CAD Construction Sequence with Spatial Reasoning-Enhanced Multimodal LLMs
Computer-aided design (CAD) significantly enhances the efficiency, accuracy, and innovation of design processes by enabling precise 2D and 3D modeling, extensive analysis, and optimization.
LogBabylon: A Unified Framework for Cross-Log File Integration and Analysis
Logs are critical resources that record events, activities, or messages produced by software applications, operating systems, servers, and network devices.
Conformal Prediction on Quantifying Uncertainty of Dynamic Systems
Our motivation is to introduce conformal prediction into the uncertainty assessment of dynamical systems, providing a method supported by theoretical guarantees.
Beyond Surface Structure: A Causal Assessment of LLMs' Comprehension Ability
We further apply the ADCE to evaluate a series of mainstream LLMs, showing that most of them exhibit deep structure comprehension ability, which grows along with the prediction accuracy.
Beyond correlation: The impact of human uncertainty in measuring the effectiveness of automatic evaluation and LLM-as-a-judge
Specifically, we demonstrate that when the proportion of samples with variation or uncertainty in human labels (gathered during human evaluation) is relatively high, machine labels (generated by automatic evaluation methods) may superficially appear to have similar or better correlation with the human majority label compared to human-to-human (HH) correlation.
Salient Information Prompting to Steer Content in Prompt-based Abstractive Summarization
We show that adding keyphrases in prompts can improve ROUGE F1 and recall, making the generated summaries more similar to the reference and more complete.
Ranked #2 on
Text Summarization
on MeetingBank
CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text Generation
However, these approaches are suboptimal for generative tasks, which require more nuanced guidance beyond a single numeric metric to improve the prompt and optimize multiple aspects of the generated text.
Ranked #1 on
Text Summarization
on ACI-Bench
MedDet: Generative Adversarial Distillation for Efficient Cervical Disc Herniation Detection
Additionally, we customize the second-order nmODE to improve the model's resistance to noise in MRI.
Towards Generalizable Reinforcement Learning via Causality-Guided Self-Adaptive Representations
General intelligence requires quick adaption across tasks.
Boosting Efficiency in Task-Agnostic Exploration through Causal Knowledge
We demonstrate that causal exploration aids in learning accurate world models using fewer data and provide theoretical guarantees for its convergence.
Harnessing the Power of LLMs: Automating Unit Test Generation for High-Performance Computing
To address this, we propose an automated method for generating unit tests for such software, considering their unique features like complex logic and parallel processing.
When Swarm Learning meets energy series data: A decentralized collaborative learning design based on blockchain
Notably, as the number of data volume and the count of local epochs increases within a threshold, there is an improvement in model performance accompanied by a reduction in the variance of performance errors.
ConSiDERS-The-Human Evaluation Framework: Rethinking Human Evaluation for Generative Large Language Models
In this position paper, we argue that human evaluation of generative large language models (LLMs) should be a multidisciplinary undertaking that draws upon insights from disciplines such as user experience research and human behavioral psychology to ensure that the experimental design and results are reliable.
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.
Teaching Machines to Code: Smart Contract Translation with LLMs
The advent of large language models (LLMs) has marked a significant milestone in the realm of artificial intelligence, with their capabilities often matching or surpassing human expertise in various domains.
Revisiting Generative Adversarial Networks for Binary Semantic Segmentation on Imbalanced Datasets
In particular, the proposed framework containing a cGANs and a novel auxiliary network is developed to enhance and stabilize the generator's performance under two alternative training stages, when estimating a multiscale probability feature map from heterogeneous and imbalanced inputs iteratively.
Single Word Change is All You Need: Designing Attacks and Defenses for Text Classifiers
Experimental results on 4 datasets and BERT and distilBERT classifiers show that SP-Defense improves \r{ho} by 14. 6% and 13. 9% and decreases the attack success rate of SP-Attack by 30. 4% and 21. 2% on two classifiers respectively, and decreases the attack success rate of existing attack methods that involve multiple-word perturbations.
Dropout Concrete Autoencoder for Band Selection on HSI Scenes
Deep learning-based informative band selection methods on hyperspectral images (HSI) recently have gained intense attention to eliminate spectral correlation and redundancies.
Data and Physics driven Deep Learning Models for Fast MRI Reconstruction: Fundamentals and Methodologies
Magnetic Resonance Imaging (MRI) is a pivotal clinical diagnostic tool, yet its extended scanning times often compromise patient comfort and image quality, especially in volumetric, temporal and quantitative scans.
Integrating Chemical Language and Molecular Graph in Multimodal Fused Deep Learning for Drug Property Prediction
The advantage of the multimodal model lies in its ability to process diverse sources of data using proper models and suitable fusion methods, which would enhance the noise resistance of the model while obtaining data diversity.
A cyclical route linking fundamental mechanism and AI algorithm: An example from tuning Poisson's ratio in amorphous networks
"AI for science" is widely recognized as a future trend in the development of scientific research.
Automatic nodule identification and differentiation in ultrasound videos to facilitate per-nodule examination
Ultrasound is a vital diagnostic technique in health screening, with the advantages of non-invasive, cost-effective, and radiation free, and therefore is widely applied in the diagnosis of nodules.
An Empirical Study of AI-based Smart Contract Creation
The main objective of this study is to assess the quality of generated code provided by LLMs for smart contracts.
PFB-Diff: Progressive Feature Blending Diffusion for Text-driven Image Editing
Diffusion models have showcased their remarkable capability to synthesize diverse and high-quality images, sparking interest in their application for real image editing.
Linking Sketch Patches by Learning Synonymous Proximity for Graphic Sketch Representation
The cropped sketch patches are linked according to their global semantics or local geometric shapes, namely the synonymous proximity, by computing the cosine similarity between the captured patch embeddings.
Audit and Improve Robustness of Private Neural Networks on Encrypted Data
(ii) How to design a robust PNet given the encrypted input without decryption?
Exploring the Universal Vulnerability of Prompt-based Learning Paradigm
Prompt-based learning paradigm bridges the gap between pre-training and fine-tuning, and works effectively under the few-shot setting.
Towards Explainable Meta-Learning for DDoS Detection
With the ever increasing of new intrusions, intrusion detection task rely on Artificial Intelligence more and more.
IA-FaceS: A Bidirectional Method for Semantic Face Editing
To strike a balance between the reconstruction capacity and the control flexibility, the encoder is designed as a multi-head structure to yield embeddings for reconstruction and control, respectively: a high-dimensional tensor with spatial properties for consistent reconstruction and four low-dimensional facial component embeddings for semantic face editing.
Accelerating Integrated Task and Motion Planning with Neural Feasibility Checking
Task and Motion Planning (TAMP) provides a hierarchical framework to handle the sequential nature of manipulation tasks by interleaving a symbolic task planner that generates a possible action sequence, with a motion planner that checks the kinematic feasibility in the geometric world, generating robot trajectories if several constraints are satisfied, e. g., a collision-free trajectory from one state to another.
The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining
Existing machine unlearning techniques focus on centralized training, where access to all holders' training data is a must for the server to conduct the unlearning process.
HDL: Hybrid Deep Learning for the Synthesis of Myocardial Velocity Maps in Digital Twins for Cardiac Analysis
A core part of digital healthcare twins is model-based data synthesis, which permits the generation of realistic medical signals without requiring to cope with the modelling complexity of anatomical and biochemical phenomena producing them in reality.
D^2ETR: Decoder-Only DETR with Computationally Efficient Cross-Scale Attention
DETR is the first fully end-to-end detector that predicts a final set of predictions without post-processing.
ARSC-Net: Adventitious Respiratory Sound Classification Network Using Parallel Paths with Channel-Spatial Attention
The two types of features are entered into the parallel encoders paths with residual attention for extracting feature representation, and then fused into a channel-spatial attention module to adaptively focus on the important features between channel and spatial part for the classification task.
Ranked #14 on
Audio Classification
on ICBHI Respiratory Sound Database
(using extra training data)
D$^2$ETR: Decoder-Only DETR with Computationally Efficient Cross-Scale Attention
DETR is the first fully end-to-end detector that predicts a final set of predictions without post-processing.
Deep Rival Penalized Competitive Learning for Low-resolution Face Recognition
Current face recognition tasks are usually carried out on high-quality face images, but in reality, most face images are captured under unconstrained or poor conditions, e. g., by video surveillance.
DeceFL: A Principled Decentralized Federated Learning Framework
Although there has been a joint effort in tackling such a critical issue by proposing privacy-preserving machine learning frameworks, such as federated learning, most state-of-the-art frameworks are built still in a centralized way, in which a central client is needed for collecting and distributing model information (instead of data itself) from every other client, leading to high communication pressure and high vulnerability when there exists a failure at or attack on the central client.
A Photonic-Circuits-Inspired Compact Network: Toward Real-Time Wireless Signal Classification at the Edge
In addition, compact and integratable hardware platforms which can implement ML models at the chip scale will find much broader application to wireless communication networks.
IA-GM: A Deep Bidirectional Learning Method for Graph Matching
Existing deep learning methods for graph matching(GM) problems usually considered affinity learningto assist combinatorial optimization in a feedforward pipeline, and parameter learning is executed by back-propagating the gradients of the matching loss.
Ranked #18 on
Graph Matching
on PASCAL VOC
(matching accuracy metric)
Multi-Scale Hourglass Hierarchical Fusion Network for Single Image Deraining
Rain streaks bring serious blurring and visual quality degradation, which often vary in size, direction and density.
R&R: Metric-guided Adversarial Sentence Generation
It improves the quality of adversarial examples by optimizing a critique score which combines the fluency, similarity, and misclassification metrics.
EDSC: An Event-Driven Smart Contract Platform
This paper presents EDSC, a novel smart contract platform design based on the event-driven execution model as opposed to the traditionally employed transaction-driven execution model.
Distributed, Parallel, and Cluster Computing
Planar narrow-band-pass filter based on Si resonant metasurface
Optically resonant dielectric metasurfaces offer unique capability to fully control the wavefront, polarisation, intensity or spectral content of light based on the excitation and interference of different electric and magnetic Mie multipolar resonances.
Optics
Rewriting Meaningful Sentences via Conditional BERT Sampling and an application on fooling text classifiers
Most adversarial attack methods that are designed to deceive a text classifier change the text classifier's prediction by modifying a few words or characters.
AutoML to Date and Beyond: Challenges and Opportunities
AutoML tools aim to make machine learning accessible for non-machine learning experts (domain experts), to improve the efficiency of machine learning, and to accelerate machine learning research.
Black-box Adversarial Sample Generation Based on Differential Evolution
The technique does not require any knowledge of the structure or weights of the target DNN.
Solve Traveling Salesman Problem by Monte Carlo Tree Search and Deep Neural Network
We present a self-learning approach that combines deep reinforcement learning and Monte Carlo tree search to solve the traveling salesman problem.
Saliency-based Weighted Multi-label Linear Discriminant Analysis
The proposed method is based on a probabilistic model for defining the weights of individual samples in a weighted multi-label LDA approach.
Simultaneous Left Atrium Anatomy and Scar Segmentations via Deep Learning in Multiview Information with Attention
Using our MVTT recursive attention model, both the LA anatomy and scar can be segmented accurately (mean Dice score of 93% for the LA anatomy and 87% for the scar segmentations) and efficiently (~0. 27 seconds to simultaneously segment the LA anatomy and scars directly from the 3D LGE CMR dataset with 60-68 2D slices).
Defense against Adversarial Examples by Encoder-Assisted Search in the Latent Coding Space
In the inference time, when given an input, we will start a search process in the latent space which aims to find the closest reconstruction to the given image on the distribution of normal data.
Robust Invisible Video Watermarking with Attention
The goal of video watermarking is to embed a message within a video file in a way such that it minimally impacts the viewing experience but can be recovered even if the video is redistributed and modified, allowing media producers to assert ownership over their content.
Multi-owner Secure Encrypted Search Using Searching Adversarial Networks
To address this, this paper proposes secure and efficient multi-keyword ranked search over encrypted cloud data for multi-owner model based on searching adversarial networks.
Modeling Tabular data using Conditional GAN
Tabular data usually contains a mix of discrete and continuous columns.
Ranked #1 on
Tabular Data Generation
on California Housing Prices
MLFriend: Interactive Prediction Task Recommendation for Event-Driven Time-Series Data
In this paper, we tackle the challenge of defining useful prediction problems on event-driven time-series data.
Revisit Lmser and its further development based on convolutional layers
Proposed in 1991, Least Mean Square Error Reconstruction for self-organizing network, shortly Lmser, was a further development of the traditional auto-encoder (AE) by folding the architecture with respect to the central coding layer and thus leading to the features of symmetric weights and neurons, as well as jointly supervised and unsupervised learning.
SteganoGAN: High Capacity Image Steganography with GANs
Image steganography is a procedure for hiding messages inside pictures.
A* Tree Search for Portfolio Management
By uniting the advantages in A* search algorithm with Monte Carlo tree search, we come up with a new algorithm named A* tree search in which best information is returned to guide next search.
Synthesizing Tabular Data using Generative Adversarial Networks
Generative adversarial networks (GANs) implicitly learn the probability distribution of a dataset and can draw samples from the distribution.
Computational Decomposition of Style for Controllable and Enhanced Style Transfer
Neural style transfer has been demonstrated to be powerful in creating artistic image with help of Convolutional Neural Networks (CNN).
Election with Bribed Voter Uncertainty: Hardness and Approximation Algorithm
In this paper, we introduce a novel variant of the bribery problem, "Election with Bribed Voter Uncertainty" or BVU for short, accommodating the uncertainty that the vote of a bribed voter may or may not be counted.
Lightweight (Reverse) Fuzzy Extractor with Multiple Referenced PUF Responses
A Physical unclonable functions (PUF), alike a fingerprint, exploits manufacturing randomness to endow each physical item with a unique identifier.
Cryptography and Security
Weighted Linear Discriminant Analysis based on Class Saliency Information
In this paper, we propose a new variant of Linear Discriminant Analysis to overcome underlying drawbacks of traditional LDA and other LDA variants targeting problems involving imbalanced classes.
Sketch-pix2seq: a Model to Generate Sketches of Multiple Categories
Moreover, the combination of CNN encoder and removal of KL-divergence, i. e., the sketch-pix2seq model, had better performance in learning and generating sketches of multiple categories and showed promising results in creativity tasks.
Direct detection of pixel-level myocardial infarction areas via a deep-learning algorithm
Accurate detection of the myocardial infarction (MI) area is crucial for early diagnosis planning and follow-up management.
Input Convex Neural Networks
We show that many existing neural network architectures can be made input-convex with a minor modification, and develop specialized optimization algorithms tailored to this setting.
Topic Sensitive Neural Headline Generation
Neural models have recently been used in text summarization including headline generation.
Structuring Causal Tree Models with Continuous Variables
This paper considers the problem of invoking auxiliary, unobservable variables to facilitate the structuring of causal tree models for a given set of continuous variables.
