Search Results for author:
Found 116 papers, 31 papers with code
SeqDialN: Sequential Visual Dialog Network in Joint Visual-Linguistic Representation Space
In this work, we formulate a visual dialog as an information flow in which each piece of information is encoded with the joint visual-linguistic representation of a single dialog round.
Annotating Interruption in Dyadic Human Interaction
Integrating the existing interruption and turn switch classification methods, we propose a new annotation schema to annotate different types of interruptions through timeliness, switch accomplishment and speech content level.
DH-RAG: A Dynamic Historical Context-Powered Retrieval-Augmented Generation Method for Multi-Turn Dialogue
Retrieval-Augmented Generation (RAG) systems have shown substantial benefits in applications such as question answering and multi-turn dialogue \citep{lewis2020retrieval}.
A Multimodal PDE Foundation Model for Prediction and Scientific Text Descriptions
PDE foundation models utilize neural networks to train approximations to multiple differential equations simultaneously and are thus a general purpose solver that can be adapted to downstream tasks.
Task Vectors in In-Context Learning: Emergence, Formation, and Benefit
In-context learning is a remarkable capability of transformers, referring to their ability to adapt to specific tasks based on a short history or context.
HarmonyIQA: Pioneering Benchmark and Model for Image Harmonization Quality Assessment
To address the issue and facilitate the advancement of IHAs, we introduce the first Image Quality Assessment Database for image Harmony evaluation (HarmonyIQAD), which consists of 1, 350 harmonized images generated by 9 different IHAs, and the corresponding human visual preference scores.
ESVQA: Perceptual Quality Assessment of Egocentric Spatial Videos
With the rapid development of eXtended Reality (XR), egocentric spatial shooting and display technologies have further enhanced immersion and engagement for users.
Xmodel-2 Technical Report
Xmodel-2 is a 1. 2-billion-parameter large language model designed specifically for reasoning tasks.
FineVQ: Fine-Grained User Generated Content Video Quality Assessment
The rapid growth of user-generated content (UGC) videos has produced an urgent need for effective video quality assessment (VQA) algorithms to monitor video quality and guide optimization and recommendation procedures.
EasyTime: Time Series Forecasting Made Easy
First, EasyTime enables one-click evaluation, enabling researchers to evaluate new forecasting methods using the suite of diverse time series datasets collected in the preexisting time series forecasting benchmark (TFB).
F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration
The FaceQ database comprises 12, 255 images generated by 29 models across three tasks: (1) face generation, (2) face customization, and (3) face restoration.
Preference Discerning with LLM-Enhanced Generative Retrieval
We assess current state-of-the-art methods using our benchmark and show that they struggle to accurately discern user preferences.
Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models
The multimodal risk distribution strategy is used to segment harmful instructions across multiple modalities to effectively circumvent MLLMs' security protection.
Unifying Generative and Dense Retrieval for Sequential Recommendation
This hybrid approach provides insights into the trade-offs between these approaches and demonstrates improvements in efficiency and effectiveness for recommendation systems in small-scale benchmarks.
VICON: A Foundation Model for Multi-Physics Fluid Dynamics via Vision In-Context Operator Networks
In-Context Operator Networks (ICONs) are models that learn operators across different types of PDEs using a few-shot, in-context approach.
Xmodel-1.5: An 1B-scale Multilingual LLM
We introduce Xmodel-1. 5, a 1-billion-parameter multilingual large language model pretrained on 2 trillion tokens, designed for balanced performance and scalability.
Domain Generalization for Cross-Receiver Radio Frequency Fingerprint Identification
Radio Frequency Fingerprint Identification (RFFI) technology uniquely identifies emitters by analyzing unique distortions in the transmitted signal caused by non-ideal hardware.
MultiBalance: Multi-Objective Gradient Balancing in Industrial-Scale Multi-Task Recommendation System
In industrial recommendation systems, multi-task learning (learning multiple tasks simultaneously on a single model) is a predominant approach to save training/serving resources and improve recommendation performance via knowledge transfer between the joint learning tasks.
Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition
In this study, we explore a surprising phenomenon related to ICL: LLMs can perform multiple, computationally distinct ICL tasks simultaneously, during a single inference call, a capability we term "task superposition".
ESIQA: Perceptual Quality Assessment of Vision-Pro-based Egocentric Spatial Images
In this paper, we establish the Egocentric Spatial Images Quality Assessment Database (ESIQAD), the first IQA database dedicated for egocentric spatial images as far as we know.
LongSkywork: A Training Recipe for Efficiently Extending Context Length in Large Language Models
We introduce LongSkywork, a long-context Large Language Model (LLM) capable of processing up to 200, 000 tokens.
PackVFL: Efficient HE Packing for Vertical Federated Learning
To this core, we propose PackVFL, an efficient VFL framework based on packed HE (PackedHE), to accelerate the existing HE-based VFL algorithms.
Offline Trajectory Generalization for Offline Reinforcement Learning
Then we propose four strategies to use World Transformers to generate high-rewarded trajectory simulation by perturbing the offline data.
Mitigating Receiver Impact on Radio Frequency Fingerprint Identification via Domain Adaptation
To address this issue, we formulate the cross-receiver RFFI as a model adaptation problem, which adapts the trained model to unlabeled signals from a new receiver.
AIGCOIQA2024: Perceptual Quality Assessment of AI Generated Omnidirectional Images
Finally, we conduct a benchmark experiment to evaluate the performance of state-of-the-art IQA models on our database.
TransLandSeg: A Transfer Learning Approach for Landslide Semantic Segmentation Based on Vision Foundation Model
We propose TransLandSeg, which is a transfer learning approach for landslide semantic segmentation based on a vision foundation model (VFM).
How Well Can Transformers Emulate In-context Newton's Method?
Recent studies have suggested that Transformers can implement first-order optimization algorithms for in-context learning and even second order ones for the case of linear regression.
RS-DPO: A Hybrid Rejection Sampling and Direct Preference Optimization Method for Alignment of Large Language Models
Finally, we apply DPO with the contrastive samples to align the model to human preference.
Future Prediction Can be a Strong Evidence of Good History Representation in Partially Observable Environments
Then, our main contributions are two-fold: (a) we demonstrate that the performance of reinforcement learning is strongly correlated with the prediction accuracy of future observations in partially observable environments, and (b) our approach can significantly improve the overall end-to-end approach by preventing high-variance noisy signals from reinforcement learning objectives to influence the representation learning.
Learning Dynamics from Multicellular Graphs with Deep Neural Networks
Multicellular self-assembly into functional structures is a dynamic process that is critical in the development and diseases, including embryo development, organ formation, tumor invasion, and others.
PDE Generalization of In-Context Operator Networks: A Study on 1D Scalar Nonlinear Conservation Laws
We show the positive evidence to the second question, i. e., ICON can generalize well to some PDEs with new forms without any fine-tuning.
On the Effectiveness of Unlearning in Session-Based Recommendation
On the one hand, these approaches cannot achieve satisfying unlearning effects due to the collaborative correlations and sequential connections between the unlearning item and the remaining items in the session.
MetaDefa: Meta-learning based on Domain Enhancement and Feature Alignment for Single Domain Generalization
The single domain generalization(SDG) based on meta-learning has emerged as an effective technique for solving the domain-shift problem.
Dual-stream contrastive predictive network with joint handcrafted feature view for SAR ship classification
Most existing synthetic aperture radar (SAR) ship classification technologies heavily rely on correctly labeled data, ignoring the discriminative features of unlabeled SAR ship images.
Double Reverse Regularization Network Based on Self-Knowledge Distillation for SAR Object Classification
In current synthetic aperture radar (SAR) object classification, one of the major challenges is the severe overfitting issue due to the limited dataset (few-shot) and noisy data.
Looped Transformers are Better at Learning Learning Algorithms
Transformers have demonstrated effectiveness in in-context solving data-fitting problems from various (latent) models, as reported by Garg et al.
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.
SkyMath: Technical Report
Large language models (LLMs) have shown great potential to solve varieties of natural language processing (NLP) tasks, including mathematical reasoning.
A Survey for Federated Learning Evaluations: Goals and Measures
Evaluation is a systematic approach to assessing how well a system achieves its intended purpose.
Fine-Tune Language Models as Multi-Modal Differential Equation Solvers
In the growing domain of scientific machine learning, in-context operator learning has shown notable potential in building foundation models, as in this framework the model is trained to learn operators and solve differential equations using prompted data, during the inference stage without weight updates.
In-Context Operator Learning with Data Prompts for Differential Equation Problems
This paper introduces a new neural-network-based approach, namely In-Context Operator Networks (ICON), to simultaneously learn operators from the prompted data and apply it to new questions during the inference stage, without any weight update.
Both Efficiency and Effectiveness! A Large Scale Pre-ranking Framework in Search System
In the realm of search systems, multi-stage cascade architecture is a prevalent method, typically consisting of sequential modules such as matching, pre-ranking, and ranking.
A Survey on Vertical Federated Learning: From a Layered Perspective
From the hardware layer to the vertical federated system layer, researchers contribute to various aspects of VFL.
GP-NAS-ensemble: a model for NAS Performance Prediction
It is of great significance to estimate the performance of a given model architecture without training in the application of Neural Architecture Search (NAS) as it may take a lot of time to evaluate the performance of an architecture.
Reliable and Interpretable Personalized Federated Learning
When there are large differences in data distribution among clients, it is crucial for federated learning to design a reliable client selection strategy and an interpretable client communication framework to better utilize group knowledge.
Generative Adversarial Learning for Trusted and Secure Clustering in Industrial Wireless Sensor Networks
Traditional machine learning techniques have been widely used to establish the trust management systems.
PathProx: A Proximal Gradient Algorithm for Weight Decay Regularized Deep Neural Networks
Weight decay is one of the most widely used forms of regularization in deep learning, and has been shown to improve generalization and robustness.
Generative Adversarial Learning for Intelligent Trust Management in 6G Wireless Networks
Next, the integration of AI and trust management is developed to optimize the intelligence and security.
An Evolutionary Game based Secure Clustering Protocol with Fuzzy Trust Evaluation and Outlier Detection for Wireless Sensor Networks
To acquire secured data delivery and address the conflict between security and energy, in this paper we present an evolutionary game based secure clustering protocol with fuzzy trust evaluation and outlier detection for WSNs.
A Secure Clustering Protocol with Fuzzy Trust Evaluation and Outlier Detection for Industrial Wireless Sensor Networks
And then a density based outlier detection mechanism is introduced to acquire an adaptive trust threshold used to isolate the malicious nodes from being cluster heads.
An Intelligent Trust Cloud Management Method for Secure Clustering in 5G enabled Internet of Medical Things
To assure secure and reliable communication in 5G edge computing and D2D enabled IoMT systems, this paper presents an intelligent trust cloud management method.
An Intelligent Deterministic Scheduling Method for Ultra-Low Latency Communication in Edge Enabled Industrial Internet of Things
Then a non-collision theory based deterministic scheduling (NDS) method is proposed to achieve ultra-low latency communication for the time-sensitive flows.
Secure Forward Aggregation for Vertical Federated Neural Networks
In this paper, we focus on SplitNN, a well-known neural network framework in VFL, and identify a trade-off between data security and model performance in SplitNN.
Rare Gems: Finding Lottery Tickets at Initialization
Frankle & Carbin conjecture that we can avoid this by training "lottery tickets", i. e., special sparse subnetworks found at initialization, that can be trained to high accuracy.
Practical and Secure Federated Recommendation with Personalized Masks
In this paper, we proposed federated masked matrix factorization (FedMMF) to protect the data privacy in federated recommender systems without sacrificing efficiency and effectiveness.
The Threat of Offensive AI to Organizations
Although offensive AI has been discussed in the past, there is a need to analyze and understand the threat in the context of organizations.
Learning Functional Priors and Posteriors from Data and Physics
In summary, the proposed method is capable of learning flexible functional priors, and can be extended to big data problems using stochastic HMC or normalizing flows since the latent space is generally characterized as low dimensional.
Passage Retrieval for Outside-Knowledge Visual Question Answering
We first conduct sparse retrieval with BM25 and study expanding the question with object names and image captions.
Natural Language Understanding with Privacy-Preserving BERT
We investigate the privacy and utility implications of applying dx-privacy, a variant of Local Differential Privacy, to BERT fine-tuning in NLU applications.
Weakly-Supervised Open-Retrieval Conversational Question Answering
Our method is more flexible as it can handle both span answers and freeform answers.
Measure-conditional Discriminator with Stationary Optimum for GANs and Statistical Distance Surrogates
We propose a simple but effective modification of the discriminators, namely measure-conditional discriminators, as a plug-and-play module for different GANs.
Long Range Arena : A Benchmark for Efficient Transformers
Transformers do not scale very well to long sequence lengths largely because of quadratic self-attention complexity.
Flow-based Generative Models for Learning Manifold to Manifold Mappings
Partly due to this gap, there are also no modality transfer/translation models for manifold-valued data whereas numerous such methods based on generative models are available for natural images.
Learning to Expand: Reinforced Pseudo-relevance Feedback Selection for Information-seeking Conversations
More specifically, we propose a reinforced selector to extract useful PRF terms to enhance response candidates and a BERT-based response ranker to rank the PRF-enhanced responses.
FedEval: A Holistic Evaluation Framework for Federated Learning
In this paper, we propose a holistic evaluation framework for FL called FedEval, and present a benchmarking study on seven state-of-the-art FL algorithms.
Long Range Arena: A Benchmark for Efficient Transformers
In the recent months, a wide spectrum of efficient, fast Transformers have been proposed to tackle this problem, more often than not claiming superior or comparable model quality to vanilla Transformer models.
Ranked #4 on
ListOps
on ListOps
DiPair: Fast and Accurate Distillation for Trillion-Scale Text Matching and Pair Modeling
Pre-trained models like BERT (Devlin et al., 2018) have dominated NLP / IR applications such as single sentence classification, text pair classification, and question answering.
Solving Inverse Stochastic Problems from Discrete Particle Observations Using the Fokker-Planck Equation and Physics-informed Neural Networks
The Fokker-Planck (FP) equation governing the evolution of the probability density function (PDF) is applicable to many disciplines but it requires specification of the coefficients for each case, which can be functions of space-time and not just constants, hence requiring the development of a data-driven modeling approach.
Generative Ensemble Regression: Learning Particle Dynamics from Observations of Ensembles with Physics-Informed Deep Generative Models
Particle coordinates at a single time instant, possibly noisy or truncated, are recorded in each snapshot but are unpaired across the snapshots.
SeqDialN: Sequential Visual Dialog Networks in Joint Visual-Linguistic Representation Space
IP based SeqDialN is our baseline with a simple 2-layer LSTM design that achieves decent performance.
DS-Sync: Addressing Network Bottlenecks with Divide-and-Shuffle Synchronization for Distributed DNN Training
However, due to the global synchronization nature, its performance can be significantly influenced by network bottlenecks caused by either static topology heterogeneity or dynamic bandwidth contentions.
Match$^2$: A Matching over Matching Model for Similar Question Identification
However, it has long been a challenge to properly measure the similarity between two questions due to the inherent variation of natural language, i. e., there could be different ways to ask a same question or different questions sharing similar expressions.
Open-Retrieval Conversational Question Answering
We build an end-to-end system for ORConvQA, featuring a retriever, a reranker, and a reader that are all based on Transformers.
Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder for Long-Form Document Matching
In order to better capture sentence level semantic relations within a document, we pre-train the model with a novel masked sentence block language modeling task in addition to the masked word language modeling task used by BERT.
B-PINNs: Bayesian Physics-Informed Neural Networks for Forward and Inverse PDE Problems with Noisy Data
In this Bayesian framework, the Bayesian neural network (BNN) combined with a PINN for PDEs serves as the prior while the Hamiltonian Monte Carlo (HMC) or the variational inference (VI) could serve as an estimator of the posterior.
Reinforcement Learning for Active Flow Control in Experiments
We demonstrate experimentally the feasibility of applying reinforcement learning (RL) in flow control problems by automatically discovering active control strategies without any prior knowledge of the flow physics.
Fluid Dynamics Robotics
Sparse Sinkhorn Attention
We propose Sparse Sinkhorn Attention, a new efficient and sparse method for learning to attend.
APTER: Aggregated Prognosis Through Exponential Reweighting
This paper considers the task of learning how to make a prognosis of a patient based on his/her micro-array expression levels.
IART: Intent-aware Response Ranking with Transformers in Information-seeking Conversation Systems
We also perform case studies and analysis of learned user intent and its impact on response ranking in information-seeking conversations to provide interpretation of results.
An "augmentation-free" rotation invariant classification scheme on point-cloud and its application to neuroimaging
Though in the medical imaging community, 3D point-cloud processing is not a "go-to" choice, it is a canonical way to preserve rotation invariance.
A GMM based algorithm to generate point-cloud and its application to neuroimaging
Experimental validation has been performed to show that the proposed scheme can generate new 3D structures using interpolation techniques, i. e., given two 3D structures represented as point-clouds, we can generate point-clouds in between.
POIRot: A rotation invariant omni-directional pointnet
Our proposed model is rotationally invariant and can preserve geometric shape of a 3D point-cloud.
Highly-scalable, physics-informed GANs for learning solutions of stochastic PDEs
Uncertainty quantification for forward and inverse problems is a central challenge across physical and biomedical disciplines.
Potential Flow Generator with $L_2$ Optimal Transport Regularity for Generative Models
We propose a potential flow generator with $L_2$ optimal transport regularity, which can be easily integrated into a wide range of generative models including different versions of GANs and flow-based models.
Attentive History Selection for Conversational Question Answering
First, we propose a positional history answer embedding method to encode conversation history with position information using BERT in a natural way.
BERT with History Answer Embedding for Conversational Question Answering
One of the major challenges to multi-turn conversational search is to model the conversation history to answer the current question.
Contextual Aware Joint Probability Model Towards Question Answering System
In this paper, we address the question answering challenge with the SQuAD 2. 0 dataset.
A Deep Look into Neural Ranking Models for Information Retrieval
Ranking models lie at the heart of research on information retrieval (IR).
Answer Interaction in Non-factoid Question Answering Systems
Information retrieval systems are evolving from document retrieval to answer retrieval.
User Intent Prediction in Information-seeking Conversations
Due to the limited communication bandwidth in conversational search, it is important for conversational assistants to accurately detect and predict user intent in information-seeking conversations.
Learning to Selectively Transfer: Reinforced Transfer Learning for Deep Text Matching
Specifically, the data selector "acts" on the source domain data to find a subset for optimization of the TL model, and the performance of the TL model can provide "rewards" in turn to update the selector.
Physics-Informed Generative Adversarial Networks for Stochastic Differential Equations
We developed a new class of physics-informed generative adversarial networks (PI-GANs) to solve in a unified manner forward, inverse and mixed stochastic problems based on a limited number of scattered measurements.
Transfer Learning for Context-Aware Question Matching in Information-seeking Conversations in E-commerce
Building multi-turn information-seeking conversation systems is an important and challenging research topic.
Response Ranking with Deep Matching Networks and External Knowledge in Information-seeking Conversation Systems
Our models and research findings provide new insights on how to utilize external knowledge with deep neural models for response selection and have implications for the design of the next generation of information-seeking conversation systems.
Analyzing and Characterizing User Intent in Information-seeking Conversations
Understanding and characterizing how people interact in information-seeking conversations is crucial in developing conversational search systems.
aNMM: Ranking Short Answer Texts with Attention-Based Neural Matching Model
As an alternative to question answering methods based on feature engineering, deep learning approaches such as convolutional neural networks (CNNs) and Long Short-Term Memory Models (LSTMs) have recently been proposed for semantic matching of questions and answers.
Ranked #12 on
Question Answering
on TrecQA
Characterizing and Predicting Enterprise Email Reply Behavior
Email is still among the most popular online activities.
Neural Matching Models for Question Retrieval and Next Question Prediction in Conversation
We further evaluate the neural matching models in the next question prediction task in conversations.
Testing Piecewise Functions
We also identify the optimal dependence on the number of pieces in the query complexity of passive testing in the special case of piecewise constant functions.
Learning with Changing Features
In particular, we propose an approach to provably determine the time instant from which the new/changed features start becoming relevant with respect to an output variable in an agnostic (supervised) learning setting.
Adaptive and Scalable Android Malware Detection through Online Learning
In order to perform scalable detection and to adapt to the drift and evolution in malware population, an online passive-aggressive classifier is used.
Contextual Weisfeiler-Lehman Graph Kernel For Malware Detection
To address this, we develop the Contextual Weisfeiler-Lehman kernel (CWLK) which is capable of capturing both these types of information.
Dynamic matrix factorization with social influence
Matrix factorization is a key component of collaborative filtering-based recommendation systems because it allows us to complete sparse user-by-item ratings matrices under a low-rank assumption that encodes the belief that similar users give similar ratings and that similar items garner similar ratings.
Statistical Learning under Nonstationary Mixing Processes
Under these conditions, we propose a learning method, and establish that for bounded VC subgraph classes, the cumulative excess risk grows sublinearly in the number of predictions, at a quantified rate.
Semi-Supervised Low-Rank Mapping Learning for Multi-Label Classification
SLRM model takes advantage of the nuclear norm regularization on mapping to effectively capture the label correlations.
Learning with a Drifting Target Concept
Some of the results also describe an active learning variant of this setting, and provide bounds on the number of queries for the labels of points in the sequence sufficient to obtain the stated bounds on the error rates.
Bounds on the Minimax Rate for Estimating a Prior over a VC Class from Independent Learning Tasks
We study the optimal rates of convergence for estimating a prior distribution over a VC class from a sequence of independent data sets respectively labeled by independent target functions sampled from the prior.
Minimax Analysis of Active Learning
This work establishes distribution-free upper and lower bounds on the minimax label complexity of active learning with general hypothesis classes, under various noise models.
Buy-in-Bulk Active Learning
We additionally study the total cost sufficient for learning, for an abstract notion of the cost of requesting the labels of a given number of examples at once.
Surrogate Losses in Passive and Active Learning
Specifically, it presents an active learning algorithm based on an arbitrary classification-calibrated surrogate loss function, along with an analysis of the number of label requests sufficient for the classifier returned by the algorithm to achieve a given risk under the 0-1 loss.
Active Learning with a Drifting Distribution
We study the problem of active learning in a stream-based setting, allowing the distribution of the examples to change over time.
Semi-supervised Learning with Weakly-Related Unlabeled Data : Towards Better Text Categorization
For empirical evaluation, we present a direct comparison with a number of state-of-the-art methods for inductive semi-supervised learning and text categorization; and we show that SSLW results in a significant improvement in categorization accuracy, equipped with a small training set and an unlabeled resource that is weakly related to the test beds."
