Search Results for author:
Found 68 papers, 22 papers with code
LookCloser: Frequency-aware Radiance Field for Tiny-Detail Scene
Humans perceive and comprehend their surroundings through information spanning multiple frequencies.
Exposing Product Bias in LLM Investment Recommendation
In this paper, we reveal a novel product bias in LLM investment recommendation, where LLMs exhibit systematic preferences for specific products.
Mitigating Data Scarcity in Time Series Analysis: A Foundation Model with Series-Symbol Data Generation
Building on this concept, we introduce a series-symbol (S2) dual-modulity data generation mechanism, enabling the unrestricted creation of high-quality time series data paired with corresponding symbolic representations.
Time Series Treatment Effects Analysis with Always-Missing Controls
Estimating treatment effects in time series data presents a significant challenge, especially when the control group is always unobservable.
TSS GAZ PTP: Towards Improving Gumbel AlphaZero with Two-stage Self-play for Multi-constrained Electric Vehicle Routing Problems
Recently, Gumbel AlphaZero~(GAZ) was proposed to solve classic combinatorial optimization problems such as TSP and JSSP by creating a carefully designed competition model~(consisting of a learning player and a competitor player), which leverages the idea of self-play.
Beyond English: Unveiling Multilingual Bias in LLM Copyright Compliance
To explore these questions, we construct a dataset of popular song lyrics in English, French, Chinese, and Korean and systematically probe seven LLMs using prompts in these languages.
Unveiling Provider Bias in Large Language Models for Code Generation
Large Language Models (LLMs) have emerged as the new recommendation engines, outperforming traditional methods in both capability and scope, particularly in code generation applications.
A Backdoor Attack Scheme with Invisible Triggers Based on Model Architecture Modification
Machine learning systems are vulnerable to backdoor attacks, where attackers manipulate model behavior through data tampering or architectural modifications.
GeoTexDensifier: Geometry-Texture-Aware Densification for High-Quality Photorealistic 3D Gaussian Splatting
3D Gaussian Splatting (3DGS) has recently attracted wide attentions in various areas such as 3D navigation, Virtual Reality (VR) and 3D simulation, due to its photorealistic and efficient rendering performance.
PanoLlama: Generating Endless and Coherent Panoramas with Next-Token-Prediction LLMs
In this paper, we introduce PanoLlama, a novel framework that redefines panoramic image generation as a next-token prediction task.
Interpret the Internal States of Recommendation Model with Sparse Autoencoder
Firstly, we train an autoencoder with sparsity constraints to reconstruct internal activations of recommendation models, making the RecSAE latents more interpretable and monosemantic than the original neuron activations.
Multi-Scale Diffusion: Enhancing Spatial Layout in High-Resolution Panoramic Image Generation
Diffusion models have recently gained recognition for generating diverse and high-quality content, especially in the domain of image synthesis.
Machine Unlearning in Forgettability Sequence
Machine unlearning (MU) is becoming a promising paradigm to achieve the "right to be forgotten", where the training trace of any chosen data points could be eliminated, while maintaining the model utility on general testing samples after unlearning.
Cognitive Biases in Large Language Models for News Recommendation
Despite large language models (LLMs) increasingly becoming important components of news recommender systems, employing LLMs in such systems introduces new risks, such as the influence of cognitive biases in LLMs.
Speculative Coreset Selection for Task-Specific Fine-tuning
Task-specific fine-tuning is essential for the deployment of large language models (LLMs), but it requires significant computational resources and time.
EditBoard: Towards a Comprehensive Evaluation Benchmark for Text-Based Video Editing Models
To address this gap, we propose EditBoard, the first comprehensive evaluation benchmark for text-based video editing models.
Enhancing Vectorized Map Perception with Historical Rasterized Maps
To fully exploit a historical map, we propose two novel modules to enhance BEV features and map element queries.
GSpect: Spectral Filtering for Cross-Scale Graph Classification
Compared with other methods, we use graph wavelet neural networks for the convolution layer of the model, which aggregates multi-scale messages to generate graph representations.
Towards Empathetic Conversational Recommender Systems
With empathy we refer to a system's ability to capture and express emotions.
How to Engage Your Readers? Generating Guiding Questions to Promote Active Reading
However, what makes an active reading question good, what the linguistic role of these questions is, and what is their impact on human reading remains understudied.
Efficient DNN-Powered Software with Fair Sparse Models
With the emergence of the Software 3. 0 era, there is a growing trend of compressing and integrating large models into software systems, with significant societal implications.
Large Language Models as Evaluators for Recommendation Explanations
We also provide further insights into combining human labels with the LLM evaluation process and utilizing ensembles of multiple heterogeneous LLM evaluators to enhance the accuracy and stability of evaluations.
Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models
In this technical report, we introduce the training methodologies implemented in the development of Skywork-MoE, a high-performance mixture-of-experts (MoE) large language model (LLM) with 146 billion parameters and 16 experts.
Automated Loss function Search for Class-imbalanced Node Classification
Class-imbalanced node classification tasks are prevalent in real-world scenarios.
Pretrained Optimization Model for Zero-Shot Black Box Optimization
Zero-shot optimization involves optimizing a target task that was not seen during training, aiming to provide the optimal solution without or with minimal adjustments to the optimizer.
Deep Learning Library Testing: Definition, Methods and Challenges
This paper provides an overview of the testing research related to various DL libraries, discusses the strengths and weaknesses of existing methods, and provides guidance and reference for the application of the DL library.
Network Structure Governs Drosophila Brain Functionality
The results revealed that even with rudimentary neuronal activation mechanisms, models grounded in real neural network structures can generate activation patterns strikingly similar to those observed in the actual brain.
In silico bioactivity prediction of proteins interacting with graphene-based nanomaterials guides rational design of biosensor
Graphene based nanomaterials have attracted significant attention for their potentials in biomedical and biotechnology applications in recent years, owing to the outstanding physical and chemical properties.
Sculpting Molecules in Text-3D Space: A Flexible Substructure Aware Framework for Text-Oriented Molecular Optimization
This work not only holds general significance for the advancement of deep learning methodologies but also paves the way for a transformative shift in molecular design strategies.
Diffusion Meets DAgger: Supercharging Eye-in-hand Imitation Learning
The Dataset Aggregation, or DAgger approach to this problem simply collects more data to cover these failure states.
Leveraging Enhanced Queries of Point Sets for Vectorized Map Construction
In autonomous driving, the high-definition (HD) map plays a crucial role in localization and planning.
Chu-ko-nu: A Reliable, Efficient, and Anonymously Authentication-Enabled Realization for Multi-Round Secure Aggregation in Federated Learning
Specifically, in terms of share transfer, Chu-ko-nu breaks the probability P barrier by supplementing a redistribution process of secret key components (the sum of all components is the secret key), thus ensuring the reusability of the secret key.
Chain-of-History Reasoning for Temporal Knowledge Graph Forecasting
Temporal Knowledge Graph (TKG) forecasting aims to predict future facts based on given histories.
Your Large Language Model is Secretly a Fairness Proponent and You Should Prompt it Like One
Building on this insight and observation, we develop FairThinking, a pipeline designed to automatically generate roles that enable LLMs to articulate diverse perspectives for fair expressions.
Multi-target Detection for Reconfigurable Holographic Surfaces Enabled Radar
Multi-target detection is one of the primary tasks in radar-based localization and sensing, typically built on phased array antennas.
Modeling Spoof Noise by De-spoofing Diffusion and its Application in Face Anti-spoofing
Face anti-spoofing is crucial for ensuring the security and reliability of face recognition systems.
DREAM: Debugging and Repairing AutoML Pipelines
In response to the challenge of model design, researchers proposed Automated Machine Learning (AutoML) systems, which automatically search for model architecture and hyperparameters for a given task.
Automatic Implementation of Neural Networks through Reaction Networks -- Part I: Circuit Design and Convergence Analysis
Information processing relying on biochemical interactions in the cellular environment is essential for biological organisms.
Skywork: A More Open Bilingual Foundation Model
In this technical report, we present Skywork-13B, a family of large language models (LLMs) trained on a corpus of over 3. 2 trillion tokens drawn from both English and Chinese texts.
Push Past Green: Learning to Look Behind Plant Foliage by Moving It
We use self-supervision to train SRPNet, a neural network that predicts what space is revealed on execution of a candidate action on a given plant.
SIFTER: A Task-specific Alignment Strategy for Enhancing Sentence Embeddings
This indicates that different downstream tasks have different levels of sensitivity to sentence components.
A Peer-to-peer Federated Continual Learning Network for Improving CT Imaging from Multiple Institutions
In this work, we propose a novel peer-to-peer federated continual learning strategy to improve low-dose CT imaging performance from multiple institutions.
Rapid Plug-in Defenders
To address this challenge, this paper focuses on the Rapid Plug-in Defender (RaPiD) problem, aiming to rapidly counter adversarial perturbations without altering the deployed model.
SimHaze: game engine simulated data for real-world dehazing
Using a modern game engine, our approach renders crisp clean images and their precise depth maps, based on which high-quality hazy images can be synthesized for training dehazing models.
B2Opt: Learning to Optimize Black-box Optimization with Little Budget
To achieve this, 1) drawing on the mechanism of genetic algorithm, we propose a deep neural network framework called B2Opt, which has a stronger representation of optimization strategies based on survival of the fittest; 2) B2Opt can utilize the cheap surrogate functions of the target task to guide the design of the efficient optimization strategies.
Efficient Map Sparsification Based on 2D and 3D Discretized Grids
Furthermore, to reduce the influence of different spatial distributions between the mapping and query sequences, which is not considered in previous methods, we also introduce a space constraint term based on 3D discretized grids.
ERM-KTP: Knowledge-Level Machine Unlearning via Knowledge Transfer
When receiving the unlearning requests, we transfer the knowledge of the non-target data points from the original model to the unlearned model and meanwhile prohibit the knowledge of the target data points via our proposed knowledge transfer and prohibition (KTP) method.
Explaining Adversarial Robustness of Neural Networks from Clustering Effect Perspective
The experimental evaluations manifest the superiority of SAT over other state-of-the-art AT mechanisms in defending against adversarial attacks against both output and intermediate layers.
MUter: Machine Unlearning on Adversarially Trained Models
However, existing methods focus exclusively on unlearning from standard training models and do not apply to adversarial training models (ATMs) despite their popularity as effective defenses against adversarial examples.
Variational Reasoning over Incomplete Knowledge Graphs for Conversational Recommendation
We propose a variational Bayesian method to approximate posterior distributions over dialogue-specific subgraphs, which not only leverages the dialogue corpus for restructuring missing entity relations but also dynamically selects knowledge based on the dialogue context.
rPPG-Toolbox: Deep Remote PPG Toolbox
Camera-based physiological measurement is a fast growing field of computer vision.
MobilePhys: Personalized Mobile Camera-Based Contactless Physiological Sensing
Camera-based contactless photoplethysmography refers to a set of popular techniques for contactless physiological measurement.
OmiTrans: generative adversarial networks based omics-to-omics translation framework
With the rapid development of high-throughput experimental technologies, different types of omics (e. g., genomics, epigenomics, transcriptomics, proteomics, and metabolomics) data can be produced from clinical samples.
Consensus-Based Decentralized Energy Trading for Distributed Energy Resources
In smart grids, distributed energy resources (DERs) have penetrated residential zones to provide a new form of electricity supply, mainly from renewable energy.
VAC-CNN: A Visual Analytics System for Comparative Studies of Deep Convolutional Neural Networks
The rapid development of Convolutional Neural Networks (CNNs) in recent years has triggered significant breakthroughs in many machine learning (ML) applications.
SO-SLAM: Semantic Object SLAM with Scale Proportional and Symmetrical Texture Constraints
Object SLAM introduces the concept of objects into Simultaneous Localization and Mapping (SLAM) and helps understand indoor scenes for mobile robots and object-level interactive applications.
Method for making multi-attribute decisions in wargames by combining intuitionistic fuzzy numbers with reinforcement learning
Researchers are increasingly focusing on intelligent games as a hot research area. The article proposes an algorithm that combines the multi-attribute management and reinforcement learning methods, and that combined their effect on wargaming, it solves the problem of the agent's low rate of winning against specific rules and its inability to quickly converge during intelligent wargame training. At the same time, this paper studied a multi-attribute decision making and reinforcement learning algorithm in a wargame simulation environment, and obtained data on red and blue conflict. Calculate the weight of each attribute based on the intuitionistic fuzzy number weight calculations.
Modal-Adaptive Gated Recoding Network for RGB-D Salient Object Detection
Then, a modal-adaptive gate unit (MGU) is proposed to suppress the invalid information and transfer the effective modal features to the recoding mixer and the hybrid branch decoder.
Perception-and-Regulation Network for Salient Object Detection
Effective fusion of different types of features is the key to salient object detection.
XOmiVAE: an interpretable deep learning model for cancer classification using high-dimensional omics data
To the best of our knowledge, XOmiVAE is one of the first activation level-based interpretable deep learning models explaining novel clusters generated by VAE.
GraphFM: Graph Factorization Machines for Feature Interaction Modeling
To solve the problems, we propose a novel approach, Graph Factorization Machine (GraphFM), by naturally representing features in the graph structure.
Privacy Inference Attacks and Defenses in Cloud-based Deep Neural Network: A Survey
This survey presents the most recent findings of privacy attacks and defenses appeared in cloud-based neural network services.
NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results
This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with a focus on the proposed methods and results.
DyGCN: Dynamic Graph Embedding with Graph Convolutional Network
We naturally generalizes the embedding propagation scheme of GCN to dynamic setting in an efficient manner, which is to propagate the change along the graph to update node embeddings.
OmiEmbed: a unified multi-task deep learning framework for multi-omics data
To tackle this problem and pave the way for machine learning aided precision medicine, we proposed a unified multi-task deep learning framework named OmiEmbed to capture biomedical information from high-dimensional omics data with the deep embedding and downstream task modules.
Flow-Sensory Contact Electrification of Graphene
All-electronic interrogation of biofluid flow velocity by sensors incorporated in ultra-low-power or self-sustained systems offers the promise of enabling multifarious emerging research and applications.
Applied Physics
Heterogeneous Graph Collaborative Filtering
In this work, we propose to model user-item interactions as a heterogeneous graph which consists of not only user-item edges indicating their interaction but also user-user edges indicating their similarity.
Unsupervised Visual Representation Learning with Increasing Object Shape Bias
(Very early draft)Traditional supervised learning keeps pushing convolution neural network(CNN) achieving state-of-art performance.
