Search Results for author:
Found 114 papers, 38 papers with code
CLIMB: CLustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training
We analyze the final data mixture, elucidating the characteristics of an optimal data mixture.
AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration
As large language models (LLMs) become increasingly capable, security and safety evaluation are crucial.
Dynamic Load Balancing for EV Charging Stations Using Reinforcement Learning and Demand Prediction
This paper presents a method for load balancing and dynamic pricing in electric vehicle (EV) charging networks, utilizing reinforcement learning (RL) to enhance network performance.
Demand Forecasting for Electric Vehicle Charging Stations using Multivariate Time-Series Analysis
As the number of electric vehicles (EVs) continues to grow, the demand for charging stations is also increasing, leading to challenges such as long wait times and insufficient infrastructure.
Modeling Behavior Change for Multi-model At-Risk Students Early Prediction (extended version)
In the educational domain, identifying students at risk of dropping out is essential for allowing educators to intervene effectively, improving both academic outcomes and overall student well-being.
Near-Optimal Online Learning for Multi-Agent Submodular Coordination: Tight Approximation and Communication Efficiency
Coordinating multiple agents to collaboratively maximize submodular functions in unpredictable environments is a critical task with numerous applications in machine learning, robot planning and control.
DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails
While substantial safety data exist in English, multilingual guardrail modeling remains underexplored due to the scarcity of open-source safety data in other languages.
Combinatorial Optimization Perspective based Framework for Multi-behavior Recommendation
To address these problems, we propose a novel multi-behavior recommendation framework based on the combinatorial optimization perspective, named COPF.
Data-Efficient Model for Psychological Resilience Prediction based on Neurological Data
In the test stage, a new noise-informed inference algorithm is proposed to address the low signal-to-noise ratio of the neurological data.
Pre-train and Fine-tune: Recommenders as Large Models
We first propose the theory of the information bottleneck for fine-tuning and present an explanation for the fine-tuning technique in recommenders.
Collaborative Imputation of Urban Time Series through Cross-city Meta-learning
We then introduce a cross-city collaborative learning scheme through model-agnostic meta learning, incorporating hierarchical modulation and normalization techniques to accommodate multiscale representations and reduce variance in response to heterogeneity.
FairTP: A Prolonged Fairness Framework for Traffic Prediction
Fairness in traffic prediction is not static; it varies over time and across regions.
AddrLLM: Address Rewriting via Large Language Model on Nationwide Logistics Data
Address rewriting has emerged as a solution to rectify these abnormal addresses.
AllRestorer: All-in-One Transformer for Image Restoration under Composite Degradations
Specifically, we introduce an All-in-One Transformer Block (AiOTB), which adaptively removes all degradations present in a given image by modeling the relationships between all degradations and the image embedding in latent space.
Mixture of Knowledge Minigraph Agents for Literature Review Generation
A novel prompt-based algorithm, the knowledge minigraph construction agent (KMCA), is designed to identify relations between concepts from academic literature and automatically constructs knowledge minigraphs.
WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning
Specifically, WebRL incorporates 1) a self-evolving curriculum that generates new tasks from unsuccessful attempts, 2) a robust outcome-supervised reward model (ORM), and 3) adaptive reinforcement learning strategies to ensure consistent improvements.
Return Augmented Decision Transformer for Off-Dynamics Reinforcement Learning
Previous works tackle the dynamics shift problem by augmenting the reward in the trajectory from the source domain to match the optimal trajectory in the target domain.
AutoGLM: Autonomous Foundation Agents for GUIs
This limitation underscores the importance of developing foundation agents capable of learning through autonomous environmental interactions by reinforcing existing models.
Personality Analysis from Online Short Video Platforms with Multi-domain Adaptation
Personality analysis from online short videos has gained prominence due to its applications in personalized recommendation systems, sentiment analysis, and human-computer interaction.
FastAttention: Extend FlashAttention2 to NPUs and Low-resource GPUs
In this work, we propose FastAttention which pioneers the adaptation of FlashAttention series for NPUs and low-resource GPUs to boost LLM inference efficiency.
Graph Neural Patching for Cold-Start Recommendations
To this end, we introduce Graph Neural Patching for Cold-Start Recommendations (GNP), a customized GNN framework with dual functionalities: GWarmer for modeling collaborative signal on existing warm users/items and Patching Networks for simulating and enhancing GWarmer's performance on cold-start recommendations.
SecCodePLT: A Unified Platform for Evaluating the Security of Code GenAI
Our methodology ensures the data quality while enabling large-scale generation.
Language-centered Human Activity Recognition
To address this, we propose LanHAR, a novel system that leverages Large Language Models (LLMs) to generate semantic interpretations of sensor readings and activity labels for cross-dataset HAR.
DreamForge: Motion-Aware Autoregressive Video Generation for Multi-View Driving Scenes
Recent advances in diffusion models have improved controllable streetscape generation and supported downstream perception and planning tasks.
DQFormer: Towards Unified LiDAR Panoptic Segmentation with Decoupled Queries
To this end, we propose a novel framework dubbed DQFormer to implement semantic and instance segmentation in a unified workflow.
Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving
Unlike the aforementioned prior works, we propose Drive-OccWorld, which adapts a vision-centric 4D forecasting world model to end-to-end planning for autonomous driving.
MalLight: Influence-Aware Coordinated Traffic Signal Control for Traffic Signal Malfunctions
Urban traffic is subject to disruptions that cause extended waiting time and safety issues at signalized intersections.
An Efficient Continuous Control Perspective for Reinforcement-Learning-based Sequential Recommendation
However, previous studies mainly focus on discrete action and policy spaces, which might have difficulties in handling dramatically growing items efficiently.
Experimental evaluation of offline reinforcement learning for HVAC control in buildings
In summary, this paper presents our well-structured investigations and new findings when applying offline reinforcement learning to building HVAC systems.
VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents
Large Multimodal Models (LMMs) have ushered in a new era in artificial intelligence, merging capabilities in both language and vision to form highly capable Visual Foundation Agents.
HMDN: Hierarchical Multi-Distribution Network for Click-Through Rate Prediction
As the recommendation service needs to address increasingly diverse distributions, such as multi-population, multi-scenario, multitarget, and multi-interest, more and more recent works have focused on multi-distribution modeling and achieved great progress.
Mini-batch Coresets for Memory-efficient Training of Large Language Models
However, this approach becomes infeasible and ineffective for LLMs, due to the highly imbalanced nature of the sources in language data, use of the Adam optimizer, and the very large gradient dimensionality of LLMs.
AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies
However, existing public benchmarks often define safety categories based on previous literature, intuitions, or common sense, leading to disjointed sets of categories for risks specified in recent regulations and policies, which makes it challenging to evaluate and compare FMs across these benchmarks.
Brevity is the soul of wit: Pruning long files for code generation
Specifically, many have shown that de-duplicating data, or sub-selecting higher quality data, can lead to efficiency or performance improvements.
Self-assessment, Exhibition, and Recognition: a Review of Personality in Large Language Models
By presenting a clear taxonomy, in-depth analysis, promising future directions, and extensive resource collections, we aim to provide a better understanding and facilitate further advancements in this emerging field.
AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies
We present a comprehensive AI risk taxonomy derived from eight government policies from the European Union, United States, and China and 16 company policies worldwide, making a significant step towards establishing a unified language for generative AI safety evaluation.
A Benchmark Study of Deep-RL Methods for Maximum Coverage Problems over Graphs
Our benchmark study sheds light on potential challenges in current deep reinforcement learning research for solving combinatorial optimization problems.
Urban-Focused Multi-Task Offline Reinforcement Learning with Contrastive Data Sharing
MODA addresses the challenges of data scarcity and heterogeneity in a multi-task urban setting through Contrastive Data Sharing among tasks.
Toward Structure Fairness in Dynamic Graph Embedding: A Trend-aware Dual Debiasing Approach
We first identify biased structural evolutions in a dynamic graph based on the evolving trend of vertex degree and then propose FairDGE, the first structurally Fair Dynamic Graph Embedding algorithm.
More Efficient Randomized Exploration for Reinforcement Learning via Approximate Sampling
Empirically, we show that in tasks where deep exploration is necessary, our proposed algorithms that combine FGTS and approximate sampling perform significantly better compared to other strong baselines.
GLINT-RU: Gated Lightweight Intelligent Recurrent Units for Sequential Recommender Systems
Meanwhile, existing efficient SRS approaches struggle to embed high-quality semantic and positional information into latent representations.
LLaMA-Reg: Using LLaMA 2 for Unsupervised Medical Image Registration
We find that using the pretrained large language model to encode deep features of the medical images in the registration model can effectively improve image registration accuracy, indicating the great potential of the large language model in medical image registration tasks.
Dual-Camera Smooth Zoom on Mobile Phones
In this work, we introduce a new task, ie, dual-camera smooth zoom (DCSZ) to achieve a smooth zoom preview.
Affective-NLI: Towards Accurate and Interpretable Personality Recognition in Conversation
To utilize affectivity within dialog content for accurate personality recognition, we fine-tuned a pre-trained language model specifically for emotion recognition in conversations, facilitating real-time affective annotations for utterances.
SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models
In clinical text summarization on the MIMIC-III dataset (Johnson et al., 2016), S2L again outperforms training on the full dataset using only 50% of the data.
Heterogeneity-aware Cross-school Electives Recommendation: a Hybrid Federated Approach
In response, we propose HFRec, a heterogeneity-aware hybrid federated recommender system designed for cross-school elective course recommendations.
Boosting Gradient Ascent for Continuous DR-submodular Maximization
The fundamental idea of our boosting technique is to exploit non-oblivious search to derive a novel auxiliary function $F$, whose stationary points are excellent approximations to the global maximum of the original DR-submodular objective $f$.
Attention Is Not the Only Choice: Counterfactual Reasoning for Path-Based Explainable Recommendation
Unfortunately, these attention weights are intentionally designed for model accuracy but not explainability.
Explore 3D Dance Generation via Reward Model from Automatically-Ranked Demonstrations
This paper presents an Exploratory 3D Dance generation framework, E3D2, designed to address the exploration capability deficiency in existing music-conditioned 3D dance generation models.
Camera-based 3D Semantic Scene Completion with Sparse Guidance Network
In this paper, we adopt the dense-sparse-dense design and propose a one-stage camera-based SSC framework, termed SGN, to propagate semantics from the semantic-aware seed voxels to the whole scene based on spatial geometry cues.
Decoding Data Quality via Synthetic Corruptions: Embedding-guided Pruning of Code Data
Armed with this knowledge, we devise novel pruning metrics that operate in embedding space to identify and remove low-quality entries in the Stack dataset.
Moving Sampling Physics-informed Neural Networks induced by Moving Mesh PDE
In this work, we propose an end-to-end adaptive sampling neural network (MMPDE-Net) based on the moving mesh method, which can adaptively generate new sampling points by solving the moving mesh PDE.
Training A Multi-stage Deep Classifier with Feedback Signals
Multi-Stage Classifier (MSC) - several classifiers working sequentially in an arranged order and classification decision is partially made at each step - is widely used in industrial applications for various resource limitation reasons.
Boosting Summarization with Normalizing Flows and Aggressive Training
This paper presents FlowSUM, a normalizing flows-based variational encoder-decoder framework for Transformer-based summarization.
Bayes-enhanced Multi-view Attention Networks for Robust POI Recommendation
To this end, we investigate a novel problem of robust POI recommendation by considering the uncertainty factors of the user check-ins, and proposes a Bayes-enhanced Multi-view Attention Network.
Optimal Batched Best Arm Identification
Based on Tri-BBAI, we further propose the almost optimal batched best arm identification (Opt-BBAI) algorithm, which is the first algorithm that achieves the near-optimal sample and batch complexity in the non-asymptotic setting (i. e., $\delta>0$ is arbitrarily fixed), while enjoying the same batch and sample complexity as Tri-BBAI when $\delta$ tends to zero.
Data Distillation Can Be Like Vodka: Distilling More Times For Better Quality
Dataset distillation aims to minimize the time and memory needed for training deep networks on large datasets, by creating a small set of synthetic images that has a similar generalization performance to that of the full dataset.
On the Stability of Expressive Positional Encodings for Graphs
Despite many attempts to address non-uniqueness, most methods overlook stability, leading to poor generalization on unseen graph structures.
Molecular Property Prediction
Out-of-Distribution Generalization
+1
Sieve: Multimodal Dataset Pruning Using Image Captioning Models
We propose a pruning signal, Sieve, that employs synthetic captions generated by image-captioning models pretrained on small, diverse, and well-aligned image-text pairs to evaluate the alignment of noisy image-text pairs.
Non-Uniform Sampling Reconstruction for Symmetrical NMR Spectroscopy by Exploiting Inherent Symmetry
Symmetrical NMR spectroscopy constitutes a vital branch of multidimensional NMR spectroscopy, providing a powerful tool for the structural elucidation of biological macromolecules.
Parallel Knowledge Enhancement based Framework for Multi-behavior Recommendation
In the fusion step, advanced neural networks are used to model the hierarchical correlations between user behaviors.
SSC-RS: Elevate LiDAR Semantic Scene Completion with Representation Separation and BEV Fusion
However, how to effectively exploit the relationships between the semantic context in semantic segmentation and geometric structure in scene completion remains under exploration.
PANet: LiDAR Panoptic Segmentation with Sparse Instance Proposal and Aggregation
Firstly, we propose a non-learning Sparse Instance Proposal (SIP) module with the ``sampling-shifting-grouping" scheme to directly group thing points into instances from the raw point cloud efficiently.
Challenges and Opportunities in Improving Worst-Group Generalization in Presence of Spurious Features
Through this, we highlight how existing group inference methods struggle in the presence of spurious features that are learned later in training.
Towards Sustainable Learning: Coresets for Data-efficient Deep Learning
To improve the efficiency and sustainability of learning deep models, we propose CREST, the first scalable framework with rigorous theoretical guarantees to identify the most valuable examples for training non-convex models, particularly deep networks.
Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias
In this work, we provide the first theoretical analysis of the effect of simplicity bias on learning spurious correlations.
Few-shot Adaptation to Distribution Shifts By Mixing Source and Target Embeddings
Pretrained machine learning models need to be adapted to distribution shifts when deployed in new target environments.
Mitigating Spurious Correlations in Multi-modal Models during Fine-tuning
Spurious correlations that degrade model generalization or lead the model to be right for the wrong reasons are one of the main robustness concerns for real-world deployments.
On the uncertainty analysis of the data-enabled physics-informed neural network for solving neutron diffusion eigenvalue problem
In practical engineering experiments, the data obtained through detectors are inevitably noisy.
CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning
Multimodal contrastive pretraining has been used to train multimodal representation models, such as CLIP, on large amounts of paired image-text data.
Battery Valuation and Management for Battery Swapping Station with an Intertemporal Framework
Battery swapping as a business model for battery energy storage (BES) has great potential in future integrated low-carbon energy and transportation systems.
Eff-3DPSeg: 3D organ-level plant shoot segmentation using annotation-efficient point clouds
Second, a weakly-supervised deep learning method was proposed for plant organ segmentation.
Machine Learning for Smart and Energy-Efficient Buildings
In this work, we review the ways in which machine learning has been leveraged to make buildings smart and energy-efficient.
ILSGAN: Independent Layer Synthesis for Unsupervised Foreground-Background Segmentation
Unsupervised foreground-background segmentation aims at extracting salient objects from cluttered backgrounds, where Generative Adversarial Network (GAN) approaches, especially layered GANs, show great promise.
Distilling Representations from GAN Generator via Squeeze and Span
In recent years, generative adversarial networks (GANs) have been an actively studied topic and shown to successfully produce high-quality realistic images in various domains.
Learning to Annotate Part Segmentation with Gradient Matching
The success of state-of-the-art deep neural networks heavily relies on the presence of large-scale labelled datasets, which are extremely expensive and time-consuming to annotate.
Local Manifold Augmentation for Multiview Semantic Consistency
Multiview self-supervised representation learning roots in exploring semantic consistency across data of complex intra-class variation.
Not All Poisons are Created Equal: Robust Training against Data Poisoning
Data poisoning causes misclassification of test time target examples by injecting maliciously crafted samples in the training data.
Neural Networks Based on Power Method and Inverse Power Method for Solving Linear Eigenvalue Problems
In this article, we propose two kinds of neural networks inspired by power method and inverse power method to solve linear eigenvalue problems.
Sequence-to-Set Generative Models
We present GRU2Set, which is an instance of our sequence-to-set method and employs the famous GRU model as the sequence generative model.
Deep Feature Selection for Anomaly Detection Based on Pretrained Network and Gaussian Discriminative Analysis
Deep learning neural network serves as a powerful tool for visual anomaly detection (AD) and fault diagnosis, attributed to its strong abstractive interpretation ability in the representation domain.
Ranked #79 on
Anomaly Detection
on MVTec AD
Communication-Efficient Decentralized Online Continuous DR-Submodular Maximization
Maximizing a monotone submodular function is a fundamental task in machine learning, economics, and statistics.
Online Learning for Non-monotone Submodular Maximization: From Full Information to Bandit Feedback
In this paper, we revisit the online non-monotone continuous DR-submodular maximization problem over a down-closed convex set, which finds wide real-world applications in the domain of machine learning, economics, and operations research.
Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attacks
We make the key observation that attacks introduce local sharp regions of high training loss, which when minimized, results in learning the adversarial perturbations and makes the attack successful.
Towards Better Dermoscopic Image Feature Representation Learning for Melanoma Classification
Deep learning-based melanoma classification with dermoscopic images has recently shown great potential in automatic early-stage melanoma diagnosis.
Time-aware Dynamic Graph Embedding for Asynchronous Structural Evolution
Meanwhile, we treat each edge sequence as a whole and embed its ToV of the first vertex to further encode the time-sensitive information.
MNL-Bandits under Inventory and Limited Switches Constraints
Optimizing the assortment of products to display to customers is a key to increasing revenue for both offline and online retailers.
Explaining Deep Convolutional Neural Networks via Latent Visual-Semantic Filter Attention
We also demonstrate a novel application of our method for unsupervised dataset bias analysis which allows us to automatically discover hidden biases in datasets or compare different subsets without using additional labels.
Feature Construction and Selection for PV Solar Power Modeling
A machine learning framework for 1-hour ahead solar power prediction is developed in this paper based on the historical data.
An Exact Method for the Daily Package Shipment Problem with Outsourcing
The package shipment problem requires to optimally co-design paths for both packages and a heterogeneous fleet in a transit center network (TCN).
Which Style Makes Me Attractive? Interpretable Control Discovery and Counterfactual Explanation on StyleGAN
First, we propose a novel approach to disentangle latent subspace semantics by exploiting existing face analysis models, e. g., face parsers and face landmark detectors.
Stochastic Continuous Submodular Maximization: Boosting via Non-oblivious Function
In the online setting, for the first time we consider the adversarial delays for stochastic gradient feedback, under which we propose a boosting online gradient algorithm with the same non-oblivious function $F$.
Towards Transactive Energy: An Analysis of Information-related Practical Issues
The development of distributed energy resources, such as rooftop photovoltaic (PV) panels, batteries, and electric vehicles (EVs), has decentralized our power system operation, where transactive energy markets empower local energy exchanges.
Value Activation for Bias Alleviation: Generalized-activated Deep Double Deterministic Policy Gradients
It is vital to accurately estimate the value function in Deep Reinforcement Learning (DRL) such that the agent could execute proper actions instead of suboptimal ones.
Improving Cooperative Game Theory-based Data Valuation via Data Utility Learning
The Shapley value (SV) and Least core (LC) are classic methods in cooperative game theory for cost/profit sharing problems.
Language Scaling for Universal Suggested Replies Model
Faced with increased compute requirements and low resources for language expansion, we build a single universal model for improving the quality and reducing run-time costs of our production system.
Reconstructing 3D Model from Single-View Sketch with Deep Neural Network
It creates the transformation representation of a sketch by extracting the shape features of an input sketch and transformation template samples.
A Dimension-Insensitive Algorithm for Stochastic Zeroth-Order Optimization
This paper concerns a convex, stochastic zeroth-order optimization (S-ZOO) problem.
Learning Foreground-Background Segmentation from Improved Layered GANs
Deep learning approaches heavily rely on high-quality human supervision which is nonetheless expensive, time-consuming, and error-prone, especially for image segmentation task.
Bias-reduced Multi-step Hindsight Experience Replay for Efficient Multi-goal Reinforcement Learning
Two main challenges in multi-goal reinforcement learning are sparse rewards and sample inefficiency.
Comprehensible Counterfactual Explanation on Kolmogorov-Smirnov Test
One challenge remained untouched is how we can obtain an explanation on why a test set fails the KS test.
Optimal Sharing and Fair Cost Allocation of Community Energy Storage
Further, we demonstrate both the building-wise and community-wise economic benefits are enhanced with the ES sharing model over the individual ES (IES) model.
Fairness
Computer Science and Game Theory
EPARS: Early Prediction of At-risk Students with Online and Offline Learning Behaviors
We propose a novel algorithm (EPARS) that could early predict STAR in a semester by modeling online and offline learning behaviors.
A Generative Model for Sampling High-Performance and Diverse Weights for Neural Networks
Recent work on mode connectivity in the loss landscape of deep neural networks has demonstrated that the locus of (sub-)optimal weight vectors lies on continuous paths.
Unsupervised Learning of Neural Networks to Explain Neural Networks (extended abstract)
This paper presents an unsupervised method to learn a neural network, namely an explainer, to interpret a pre-trained convolutional neural network (CNN), i. e., the explainer uses interpretable visual concepts to explain features in middle conv-layers of a CNN.
Network Transplanting (extended abstract)
This paper focuses on a new task, i. e., transplanting a category-and-task-specific neural network to a generic, modular network without strong supervision.
Explaining AlphaGo: Interpreting Contextual Effects in Neural Networks
In this paper, we propose to disentangle and interpret contextual effects that are encoded in a pre-trained deep neural network.
Unsupervised Learning of Neural Networks to Explain Neural Networks
Given feature maps of a certain conv-layer of the CNN, the explainer performs like an auto-encoder, which first disentangles the feature maps into object-part features and then inverts object-part features back to features of higher conv-layers of the CNN.
Network Transplanting
This paper focuses on a new task, i. e., transplanting a category-and-task-specific neural network to a generic, modular network without strong supervision.
Dynamic Filtering with Large Sampling Field for ConvNets
We propose a dynamic filtering strategy with large sampling field for ConvNets (LS-DFN), where the position-specific kernels learn from not only the identical position but also multiple sampled neighbor regions.
Accelerating E-Commerce Search Engine Ranking by Contextual Factor Selection
Solving the problem by reinforcement learning, we propose the RankCFS, which has been assessed in an off-line environment as well as a real-world on-line environment (Taobao. com).
Interpreting CNNs via Decision Trees
We propose to learn a decision tree, which clarifies the specific reason for each prediction made by the CNN at the semantic level.
Finding Theme Communities from Database Networks
Given a database network where each vertex is associated with a transaction database, we are interested in finding theme communities.
PIEFA: Personalized Incremental and Ensemble Face Alignment
Face alignment, especially on real-time or large-scale sequential images, is a challenging task with broad applications.
