Search Results for author:
Found 39 papers, 12 papers with code
Conditional Image Repainting via Semantic Bridge and Piecewise Value Function
We study conditional image repainting where a model is trained to generate visual content conditioned on user inputs, and composite the generated content seamlessly onto a user provided image while preserving the semantics of users' inputs.
C^3KG: A Chinese Commonsense Conversation Knowledge Graph
Existing commonsense knowledge bases often organize tuples in an isolated manner, which is deficient for commonsense conversational models to plan the next steps.
Balancing Speciality and Versatility: a Coarse to Fine Framework for Supervised Fine-tuning Large Language Model
In an overall evaluation of both speciality and versatility, CoFiTune consistently outperforms baseline methods across diverse tasks and model scales.
READ: Improving Relation Extraction from an ADversarial Perspective
This strategy enables a larger attack budget for entities and coaxes the model to leverage relational patterns embedded in the context.
Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning
We conduct a series of experiments to prove LLMs can obtain benefits from mistakes in both directions.
A Question-centric Multi-experts Contrastive Learning Framework for Improving the Accuracy and Interpretability of Deep Sequential Knowledge Tracing Models
However, the inherent black-box nature of deep learning techniques often poses a hurdle for teachers to fully embrace the model's prediction results.
Contextualization Distillation from Large Language Model for Knowledge Graph Completion
While textual information significantly enhances the performance of pre-trained language models (PLMs) in knowledge graph completion (KGC), the static and noisy nature of existing corpora collected from Wikipedia articles or synsets definitions often limits the potential of PLM-based KGC models.
DAIL: Data Augmentation for In-Context Learning via Self-Paraphrase
DAIL leverages the intuition that large language models are more familiar with the content generated by themselves.
Multi-level Contrastive Learning for Script-based Character Understanding
In this work, we tackle the scenario of understanding characters in scripts, which aims to learn the characters' personalities and identities from their utterances.
Eliminating Reasoning via Inferring with Planning: A New Framework to Guide LLMs' Non-linear Thinking
Chain-of-Thought(CoT) prompting and its variants explore equipping large language models (LLMs) with high-level reasoning abilities by emulating human-like linear cognition and logic.
DiffuseIR:Diffusion Models For Isotropic Reconstruction of 3D Microscopic Images
Since the diffusion model learns the universal structural distribution of biological tissues, which is independent of the axial resolution, DiffuseIR can reconstruct authentic images with unseen low-axial resolutions into a high-axial resolution without requiring re-training.
Assisting Language Learners: Automated Trans-Lingual Definition Generation via Contrastive Prompt Learning
The standard definition generation task requires to automatically produce mono-lingual definitions (e. g., English definitions for English words), but ignores that the generated definitions may also consist of unfamiliar words for language learners.
TinyML Design Contest for Life-Threatening Ventricular Arrhythmia Detection
This paper concludes with the direction of improvement for the future TinyML design for health monitoring applications.
NTK-SAP: Improving neural network pruning by aligning training dynamics
Recent advances in neural tangent kernel (NTK) theory suggest that the training dynamics of large enough neural networks is closely related to the spectrum of the NTK.
Instance-wise Batch Label Restoration via Gradients in Federated Learning
Furthermore, we demonstrate that our method facilitates the existing gradient inversion attacks by exploiting the recovered labels, with an increase of 6-7 in PSNR on both MNIST and CIFAR100.
Fine-grained Contrastive Learning for Definition Generation
Recently, pre-trained transformer-based models have achieved great success in the task of definition generation (DG).
Robust Coordinated Longitudinal Control of MAV Based on Energy State
Fixed-wing Miniature Air Vehicle (MAV) is not only coupled with longitudinal motion, but also more susceptible to wind disturbance due to its lighter weight, which brings more challenges to its altitude and airspeed controller design.
C3KG: A Chinese Commonsense Conversation Knowledge Graph
Existing commonsense knowledge bases often organize tuples in an isolated manner, which is deficient for commonsense conversational models to plan the next steps.
Cyber Intrusion Detection by Using Deep Neural Networks with Attack-sharing Loss
To achieve high detection accuracy on imbalanced data, we design a novel attack-sharing loss function that can effectively move the decision boundary towards the attack classes and eliminates the bias towards the majority/benign class.
RMSprop can converge with proper hyper-parameter
Removing this assumption allows us to establish a phase transition from divergence to non-divergence for RMSProp.
On a Faster $R$-Linear Convergence Rate of the Barzilai-Borwein Method
The Barzilai-Borwein (BB) method has demonstrated great empirical success in nonlinear optimization.
A prognostic dynamic model applicable to infectious diseases providing easily visualized guides -- A case study of COVID-19 in the UK
A reasonable prediction of infectious diseases transmission process under different disease control strategies is an important reference point for policy makers.
The Global Landscape of Neural Networks: An Overview
Second, we discuss a few rigorous results on the geometric properties of wide networks such as "no bad basin", and some modifications that eliminate sub-optimal local minima and/or decreasing paths to infinity.
Sub-Optimal Local Minima Exist for Neural Networks with Almost All Non-Linear Activations
More specifically, we prove that for any multi-layer network with generic input data and non-linear activation functions, sub-optimal local minima can exist, no matter how wide the network is (as long as the last hidden layer has at least two neurons).
Customized OCT images compression scheme with deep neural network
We added customized skip connections between the compression CNNs and the reconstruction CNNs to reserve the detail information and trained the two nets together with the semantic segmented image patches from data preprocessing module.
Inverse Structural Design of Graphene/Boron Nitride Hybrids by Regressional GAN
A significant novelty of the proposed RGAN is that it combines the supervised and regressional convolutional neural network (CNN) with the traditional unsupervised GAN, thus overcoming the common technical barrier in the traditional GANs, which cannot generate data associated with given continuous quantitative labels.
Computational Physics Materials Science Applied Physics
An overlapping-free leaf segmentation method for plant point clouds
The proposed method can also facilitate the automatic traits estimation of each single leaf (such as the leaf area, length, and width), which has potential to become a highly effective tool for plant research and agricultural engineering.
An Integrated Image Filter for Enhancing Change Detection Results
In this paper, we present an integrated filter which comprises a weighted local guided image filter and a weighted spatiotemporal tree filter.
YUN-HPCC at SemEval-2019 Task 3: Multi-Step Ensemble Neural Network for Sentiment Analysis in Textual Conversation
This paper describes our approach to the sentiment analysis of Twitter textual conversations based on deep learning.
RILOD: Near Real-Time Incremental Learning for Object Detection at the Edge
The key component of RILOD is a novel incremental learning algorithm that trains end-to-end for one-stage deep object detection models only using training data of new object classes.
Regularize, Expand and Compress: Multi-task based Lifelong Learning via NonExpansive AutoML
Lifelong learning, the problem of continual learning where tasks arrive in sequence, has been lately attracting more attention in the computer vision community.
Class-incremental Learning via Deep Model Consolidation
The idea is to first train a separate model only for the new classes, and then combine the two individual models trained on data of two distinct set of classes (old classes and new classes) via a novel double distillation training objective.
MICIK: MIning Cross-Layer Inherent Similarity Knowledge for Deep Model Compression
State-of-the-art deep model compression methods exploit the low-rank approximation and sparsity pruning to remove redundant parameters from a learned hidden layer.
On the Benefit of Width for Neural Networks: Disappearance of Bad Basins
Wide networks are often believed to have a nice optimization landscape, but what rigorous results can we prove?
Dynamically Hierarchy Revolution: DirNet for Compressing Recurrent Neural Network on Mobile Devices
Recurrent neural networks (RNNs) achieve cutting-edge performance on a variety of problems.
Talking Face Generation by Conditional Recurrent Adversarial Network
Given an arbitrary face image and an arbitrary speech clip, the proposed work attempts to generating the talking face video with accurate lip synchronization while maintaining smooth transition of both lip and facial movement over the entire video clip.
LCANet: End-to-End Lipreading with Cascaded Attention-CTC
In this paper, we propose LCANet, an end-to-end deep neural network based lipreading system.
Ranked #2 on
Lipreading
on GRID corpus (mixed-speech)
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Boundary-sensitive Network for Portrait Segmentation
Compared to the general semantic segmentation problem, portrait segmentation has higher precision requirement on boundary area.
DeepRebirth: Accelerating Deep Neural Network Execution on Mobile Devices
As observed in the experiment, DeepRebirth achieves more than 3x speed-up and 2. 5x run-time memory saving on GoogLeNet with only 0. 4% drop of top-5 accuracy on ImageNet.
