Search Results for author:
Found 342 papers, 122 papers with code
Cross-Lingual Training of Dense Retrievers for Document Retrieval
Dense retrieval has shown great success for passage ranking in English.
Grouped-Attention for Content-Selection and Content-Plan Generation
A key component of the GSC-attention is grouped-attention, which is token-level attention constrained within each input attribute that enables our proposed model captures both local and global context.
Contrastive Data and Learning for Natural Language Processing
We then survey the benefits and the best practices of contrastive learning for various downstream NLP applications including Text Classification, Question Answering, Summarization, Text Generation, Interpretability and Explainability, Commonsense Knowledge and Reasoning, Vision-and-Language. This tutorial intends to help researchers in the NLP and computational linguistics community to understand this emerging topic and promote future research directions of using contrastive learning for NLP applications.
An Exploratory Study on Long Dialogue Summarization: What Works and What’s Next
Dialogue summarization helps readers capture salient information from long conversations in meetings, interviews, and TV series.
Talk Too Much: Poisoning Large Language Models under Token Limit
To enhance the stealthiness of the trigger, we present a poisoning attack against LLMs that is triggered by a generation/output condition-token limitation, which is a commonly adopted strategy by users for reducing costs.
Intelligent Reflecting Surface-Enabled Anti-Detection for Secure Sensing and Communications
The ever-increasing reliance on wireless communication and sensing has led to growing concerns over the vulnerability of sensitive information to unauthorized detection and interception.
On Unified Prompt Tuning for Request Quality Assurance in Public Code Review
Public Code Review (PCR) can be implemented through a Software Question Answering (SQA) community, which facilitates high knowledge dissemination.
PMG : Personalized Multimodal Generation with Large Language Models
Such user preferences are then fed into a generator, such as a multimodal LLM or diffusion model, to produce personalized content.
Evaluating LLMs at Detecting Errors in LLM Responses
This work introduces ReaLMistake, the first error detection benchmark consisting of objective, realistic, and diverse errors made by LLMs.
RAT: Retrieval-Augmented Transformer for Click-Through Rate Prediction
Predicting click-through rates (CTR) is a fundamental task for Web applications, where a key issue is to devise effective models for feature interactions.
Multimodal Pretraining, Adaptation, and Generation for Recommendation: A Survey
The recent advancements in pretrained multimodal models offer new opportunities and challenges in developing content-aware recommender systems.
A Survey on Self-Supervised Pre-Training of Graph Foundation Models: A Knowledge-Based Perspective
Graph self-supervised learning is now a go-to method for pre-training graph foundation models, including graph neural networks, graph transformers, and more recent large language model (LLM)-based graph models.
Visual Foundation Models Boost Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation
Then, another VFM trained on fine-grained 2D masks is adopted to guide the generation of semantically augmented images and point clouds to enhance the performance of neural networks, which mix the data from source and target domains like view frustums (FrustumMixing).
Generation is better than Modification: Combating High Class Homophily Variance in Graph Anomaly Detection
We find that in graph anomaly detection, the homophily distribution differences between different classes are significantly greater than those in homophilic and heterophilic graphs.
Predictive Clustering of Vessel Behavior Based on Hierarchical Trajectory Representation
To resolve this problem, we propose a Predictive Clustering of Hierarchical Vessel Behavior (PC-HiV).
EXACT-Net:EHR-guided lung tumor auto-segmentation for non-small cell lung cancer radiotherapy
Lung cancer is a devastating disease with the highest mortality rate among cancer types.
A Condensed Transition Graph Framework for Zero-shot Link Prediction with Large Language Models
To address this, in this work, we introduce a Condensed Transition Graph Framework for Zero-Shot Link Prediction (CTLP), which encodes all the paths' information in linear time complexity to predict unseen relations between entities, attaining both efficiency and information preservation.
Rapid Adoption, Hidden Risks: The Dual Impact of Large Language Model Customization
The increasing demand for customized Large Language Models (LLMs) has led to the development of solutions like GPTs.
3D Gaussian as a New Vision Era: A Survey
3D Gaussian Splatting (3D-GS) has emerged as a significant advancement in the field of Computer Graphics, offering explicit scene representation and novel view synthesis without the reliance on neural networks, such as Neural Radiance Fields (NeRF).
Large Language Models for Mathematical Reasoning: Progresses and Challenges
Mathematical reasoning serves as a cornerstone for assessing the fundamental cognitive capabilities of human intelligence.
MT-Ranker: Reference-free machine translation evaluation by inter-system ranking
Traditionally, Machine Translation (MT) Evaluation has been treated as a regression problem -- producing an absolute translation-quality score.
Optimal Sparse Survival Trees
Interpretability is crucial for doctors, hospitals, pharmaceutical companies and biotechnology corporations to analyze and make decisions for high stakes problems that involve human health.
EL-VIT: Probing Vision Transformer with Interactive Visualization
Therefore, a visualization system is needed to assist ViT users in understanding its functionality.
Assessing and Understanding Creativity in Large Language Models
This paper aims to establish an efficient framework for assessing the level of creativity in LLMs.
Generalized Reference Signals Design for Integrated Communication and Sensing with High-Resolution Algorithms
Delay and Doppler ambiguities of comb reference signal patterns are investigated through time delay and Doppler shift detection using high-resolution sensing algorithms.
Comb Reference Signal Pattern Design for Integrated Communication and Sensing
Ambiguity performances of reference signal patterns for integrated communication and sensing are studied via time delay and Doppler shift detection.
Rethinking Spectral Graph Neural Networks with Spatially Adaptive Filtering
Whilst spectral Graph Neural Networks (GNNs) are theoretically well-founded in the spectral domain, their practical reliance on polynomial approximation implies a profound linkage to the spatial domain.
Diff-Oracle: Diffusion Model for Oracle Character Generation with Controllable Styles and Contents
To train Diff-Oracle effectively, we propose to obtain pixel-level paired oracle character images (i. e., style and content images) by a pre-trained image-to-image translation model.
Graph Neural Networks with Diverse Spectral Filtering
Spectral Graph Neural Networks (GNNs) have achieved tremendous success in graph machine learning, with polynomial filters applied for graph convolutions, where all nodes share the identical filter weights to mine their local contexts.
Debiasing Sequential Recommenders through Distributionally Robust Optimization over System Exposure
Then, we introduce a penalty to items with high exposure probability to avoid the overestimation of user preference for biased samples.
Open-Pose 3D Zero-Shot Learning: Benchmark and Challenges
To this end, we propose a more realistic and challenging scenario named open-pose 3D zero-shot classification, focusing on the recognition of 3D objects regardless of their orientation.
Intelligent Reflecting Surface-Aided Electromagnetic Stealth Against Radar Detection
While traditional electromagnetic stealth materials/metasurfaces can render a target virtually invisible to some extent, they lack flexibility and adaptability, and can only operate within a limited frequency and angle/direction range, making it challenging to ensure the expected stealth performance.
TCP:Textual-based Class-aware Prompt tuning for Visual-Language Model
However, those textual tokens have a limited generalization ability regarding unseen domains, as they cannot dynamically adjust to the distribution of testing classes.
Deciphering and integrating invariants for neural operator learning with various physical mechanisms
To this end, we propose Physical Invariant Attention Neural Operator (PIANO) to decipher and integrate the physical invariants (PI) for operator learning from the PDE series with various physical mechanisms.
DocMath-Eval: Evaluating Numerical Reasoning Capabilities of LLMs in Understanding Long Documents with Tabular Data
This paper introduces DocMath-Eval, a comprehensive benchmark specifically designed to evaluate the numerical reasoning and problem-solving capabilities of LLMs in the context of understanding and analyzing financial documents containing both text and tables.
KnowledgeMath: Knowledge-Intensive Math Word Problem Solving in Finance Domains
We introduce KnowledgeMath, a novel benchmark designed to evaluate LLMs' capabilities in applying financial knowledge to solve complex math word problems.
Fair Abstractive Summarization of Diverse Perspectives
However, current work in summarization metrics and Large Language Models (LLMs) evaluation has not explored fair abstractive summarization.
Context Shift Reduction for Offline Meta-Reinforcement Learning
In this paper, we propose a novel approach called Context Shift Reduction for OMRL (CSRO) to address the context shift problem with only offline datasets.
Unified Low-Resource Sequence Labeling by Sample-Aware Dynamic Sparse Finetuning
Unfortunately, this requires formatting them into specialized augmented format unknown to the base pretrained language model (PLMs) necessitating finetuning to the target format.
FaMeSumm: Investigating and Improving Faithfulness of Medical Summarization
In this paper, we investigate and improve faithfulness in summarization on a broad range of medical summarization tasks.
Benchingmaking Large Langage Models in Biomedical Triple Extraction
Biomedical triple extraction systems aim to automatically extract biomedical entities and relations between entities.
A Review of Reinforcement Learning for Natural Language Processing, and Applications in Healthcare
It has gained significant attention in the field of Natural Language Processing (NLP) due to its ability to learn optimal strategies for tasks such as dialogue systems, machine translation, and question-answering.
Exploring the Potential of Large Language Models in Generating Code-Tracing Questions for Introductory Programming Courses
In this paper, we explore the application of large language models (LLMs) for generating code-tracing questions in introductory programming courses.
Channel Autocorrelation Estimation for IRS-Aided Wireless Communications Based on Power Measurements
Intelligent reflecting surface (IRS) can bring significant performance enhancement for wireless communication systems by reconfiguring wireless channels via passive signal reflection.
Hermes: Unlocking Security Analysis of Cellular Network Protocols by Synthesizing Finite State Machines from Natural Language Specifications
In this paper, we present Hermes, an end-to-end framework to automatically generate formal representations from natural language cellular specifications.
Multi-Functional Reconfigurable Intelligent Surface: System Modeling and Performance Optimization
In this paper, we propose and study a multi-functional reconfigurable intelligent surface (MF-RIS) architecture.
Multiple Satellites Collaboration for Joint Code-aided CFOs and CPOs Estimation
Low Earth Orbit (LEO) satellites are being extensively researched in the development of secure Internet of Remote Things (IoRT).
Multi-Passive/Active-IRS Enhanced Wireless Coverage: Deployment Optimization and Cost-Performance Trade-off
To reconcile these trade-offs, we formulate a joint multi-PIRS/AIRS deployment problem to select an optimal subset of all candidate locations for deploying IRS and also optimize the number of passive/active reflecting elements deployed at each selected location to satisfy a given SNR target over all cells, such that the total deployment cost is minimized.
Making the Full Model Adaptive: Multi-level Domain Adaptation for Multi-Domain CTR Prediction
We then select them in a domain-aware way to promote informative features for different domains.
An Anchor Learning Approach for Citation Field Learning
CIFAL leverages the anchor learning, which is model-agnostic for any Pre-trained Language Model, to help capture citation patterns from the data of different citation styles.
Self-driven Grounding: Large Language Model Agents with Automatical Language-aligned Skill Learning
Large language models (LLMs) show their powerful automatic reasoning and planning capability with a wealth of semantic knowledge about the human world.
UMMAFormer: A Universal Multimodal-adaptive Transformer Framework for Temporal Forgery Localization
Our approach introduces a Temporal Feature Abnormal Attention (TFAA) module based on temporal feature reconstruction to enhance the detection of temporal differences.
Ranked #1 on
Temporal Forgery Localization
on LAV-DF
MISSRec: Pre-training and Transferring Multi-modal Interest-aware Sequence Representation for Recommendation
We propose MISSRec, a multi-modal pre-training and transfer learning framework for SR. On the user side, we design a Transformer-based encoder-decoder model, where the contextual encoder learns to capture the sequence-level multi-modal user interests while a novel interest-aware decoder is developed to grasp item-modality-interest relations for better sequence representation.
Multi-domain Recommendation with Embedding Disentangling and Domain Alignment
We propose a new MDR method named EDDA with two key components, i. e., embedding disentangling recommender and domain alignment, to tackle the two challenges respectively.
Relational Contrastive Learning for Scene Text Recognition
We argue that such prior contextual information can be interpreted as the relations of textual primitives due to the heterogeneous text and background, which can provide effective self-supervised labels for representation learning.
MESED: A Multi-modal Entity Set Expansion Dataset with Fine-grained Semantic Classes and Hard Negative Entities
The Entity Set Expansion (ESE) task aims to expand a handful of seed entities with new entities belonging to the same semantic class.
An In-Depth Evaluation of Federated Learning on Biomedical Natural Language Processing
Language models (LMs) such as BERT and GPT have revolutionized natural language processing (NLP).
AutoAlign: Fully Automatic and Effective Knowledge Graph Alignment enabled by Large Language Models
In this paper, we propose the first fully automatic alignment method named AutoAlign, which does not require any manually crafted seed alignments.
Energy Beamforming for RF Wireless Power Transfer with Dynamic Metasurface Antennas
Radio frequency (RF) wireless power transfer (WPT) is a promising technology for charging the Internet of Things.
How far is Language Model from 100% Few-shot Named Entity Recognition in Medical Domain
Recent advancements in language models (LMs) have led to the emergence of powerful models such as Small LMs (e. g., T5) and Large LMs (e. g., GPT-4).
Cramér-Rao Bound Minimization for IRS-Enabled Multiuser Integrated Sensing and Communications
Accordingly, we model two types of CU receivers, namely Type-I and Type-II CU receivers, which do not have and have the capability of canceling the interference from the sensing signals, respectively.
RF-Based Simultaneous Localization and Source Seeking for Multi-Robot Systems
This paper considers a radio-frequency (RF)-based simultaneous localization and source-seeking (SLASS) problem in multi-robot systems, where multiple robots jointly localize themselves and an RF source using distance-only measurements extracted from RF signals and then control themselves to approach the source.
Pushing the Limits of Machine Design: Automated CPU Design with AI
By efficiently exploring a search space of unprecedented size 10^{10^{540}}, which is the largest one of all machine-designed objects to our best knowledge, and thus pushing the limits of machine design, our approach generates an industrial-scale RISC-V CPU within only 5 hours.
Towards Open-World Recommendation with Knowledge Augmentation from Large Language Models
In this work, we propose an Open-World Knowledge Augmented Recommendation Framework with Large Language Models, dubbed KAR, to acquire two types of external knowledge from LLMs -- the reasoning knowledge on user preferences and the factual knowledge on items.
FewSAR: A Few-shot SAR Image Classification Benchmark
Motivated by this observation, we propose a novel few-shot SAR image classification benchmark (FewSAR) to address this issue.
Equitable Multi-task Learning
To solve the issue, we in-depth investigate the equity problem for MTL and find that regularizing relative contribution of different tasks (i. e. value of task-specific loss divides its raw gradient norm) in updating shared parameter can improve generalization performance of MTL.
Online Prototype Alignment for Few-shot Policy Transfer
Domain adaptation in reinforcement learning (RL) mainly deals with the changes of observation when transferring the policy to a new environment.
XSemPLR: Cross-Lingual Semantic Parsing in Multiple Natural Languages and Meaning Representations
However, existing CLSP models are separately proposed and evaluated on datasets of limited tasks and applications, impeding a comprehensive and unified evaluation of CLSP on a diverse range of NLs and MRs. To this end, we present XSemPLR, a unified benchmark for cross-lingual semantic parsing featured with 22 natural languages and 8 meaning representations by examining and selecting 9 existing datasets to cover 5 tasks and 164 domains.
Flew Over Learning Trap: Learn Unlearnable Samples by Progressive Staged Training
Unlearning techniques are proposed to prevent third parties from exploiting unauthorized data, which generate unlearnable samples by adding imperceptible perturbations to data for public publishing.
A Comprehensive Survey on Deep Learning for Relation Extraction: Recent Advances and New Frontiers
This survey is expected to facilitate researchers' collaborative efforts to tackle the challenges of real-life RE systems.
JEPOO: Highly Accurate Joint Estimation of Pitch, Onset and Offset for Music Information Retrieval
In this paper, we propose a highly accurate method for joint estimation of pitch, onset and offset, named JEPOO.
Unlearnable Examples for Diffusion Models: Protect Data from Unauthorized Exploitation
This imperceptible protective noise makes the data almost unlearnable for diffusion models, i. e., diffusion models trained or fine-tuned on the protected data cannot generate high-quality and diverse images related to the protected training data.
W-procer: Weighted Prototypical Contrastive Learning for Medical Few-Shot Named Entity Recognition
Contrastive learning has become a popular solution for few-shot Name Entity Recognization (NER).
ANPL: Towards Natural Programming with Interactive Decomposition
We deploy ANPL on the Abstraction and Reasoning Corpus (ARC), a set of unique tasks that are challenging for state-of-the-art AI systems, showing it outperforms baseline programming systems that (a) without the ability to decompose tasks interactively and (b) without the guarantee that the modules can be correctly composed together.
Ranked #4 on
Code Generation
on HumanEval
Complementary and Integrative Health Lexicon (CIHLex) and Entity Recognition in the Literature
Results: From the 198 unique concepts in CIHLex, 62. 1% could be matched to at least one term in the UMLS.
Large language models in biomedical natural language processing: benchmarks, baselines, and recommendations
Biomedical literature is growing rapidly, making it challenging to curate and extract knowledge manually.
PLM-GNN: A Webpage Classification Method based on Joint Pre-trained Language Model and Graph Neural Network
It is based on the joint encoding of text and HTML DOM trees in the web pages.
Deep Graph Neural Networks via Flexible Subgraph Aggregation
Based on this, we propose a sampling-based node-level residual module (SNR) that can achieve a more flexible utilization of different hops of subgraph aggregation by introducing node-level parameters sampled from a learnable distribution.
Self-supervised Learning for Pre-Training 3D Point Clouds: A Survey
Finally, we share our thoughts on some of the challenges and potential issues that future research in self-supervised learning for pre-training 3D point clouds may encounter.
CSGCL: Community-Strength-Enhanced Graph Contrastive Learning
Graph Contrastive Learning (GCL) is an effective way to learn generalized graph representations in a self-supervised manner, and has grown rapidly in recent years.
Denoising Multi-modal Sequential Recommenders with Contrastive Learning
In contrast, modalities that do not cause users' behaviors are potential noises and might mislead the learning of a recommendation model.
Accurate and Efficient Event-based Semantic Segmentation Using Adaptive Spiking Encoder-Decoder Network
Leveraging the low-power, event-driven computation and the inherent temporal dynamics, spiking neural networks (SNNs) are potentially ideal solutions for processing dynamic and asynchronous signals from event-based sensors.
Joint Beam Scheduling and Power Allocation for SWIPT in Mixed Near- and Far-Field Channels
Extremely large-scale array (XL-array) has emerged as a promising technology to enhance the spectrum efficiency and spatial resolution in future wireless networks, leading to a fundamental paradigm shift from conventional far-field communications towards the new near-field communications.
False Claims against Model Ownership Resolution
Our core idea is that a malicious accuser can deviate (without detection) from the specified MOR process by finding (transferable) adversarial examples that successfully serve as evidence against independent suspect models.
Fair-CDA: Continuous and Directional Augmentation for Group Fairness
By adjusting the perturbation strength in the direction of the paths, our proposed augmentation is controllable and auditable.
Knowledge-augmented Frame Semantic Parsing with Hybrid Prompt-tuning
We propose a novel Knowledge-Augmented Frame Semantic Parsing Architecture (KAF-SPA) to enhance semantic representation by incorporating accurate frame knowledge into PLMs during frame semantic parsing.
Visual-Language Prompt Tuning with Knowledge-guided Context Optimization
Representative CoOp-based work combines the learnable textual tokens with the class tokens to obtain specific textual knowledge.
Bounding System-Induced Biases in Recommender Systems with A Randomized Dataset
To bridge this gap, we study the debiasing problem from a new perspective and propose to directly minimize the upper bound of an ideal objective function, which facilitates a better potential solution to the system-induced biases.
A Cross-institutional Evaluation on Breast Cancer Phenotyping NLP Algorithms on Electronic Health Records
We developed three types of NLP models (i. e., conditional random field, bi-directional long short-term memory and CancerBERT) to extract cancer phenotypes from clinical texts.
Conceptual Reinforcement Learning for Language-Conditioned Tasks
Recently, the language-conditioned policy is proposed to facilitate policy transfer through learning the joint representation of observation and text that catches the compact and invariant information across environments.
Compressed Interaction Graph based Framework for Multi-behavior Recommendation
However, it is challenging to explore multi-behavior data due to the unbalanced data distribution and sparse target behavior, which lead to the inadequate modeling of high-order relations when treating multi-behavior data ''as features'' and gradient conflict in multitask learning when treating multi-behavior data ''as labels''.
REASONER: An Explainable Recommendation Dataset with Multi-aspect Real User Labeled Ground Truths Towards more Measurable Explainable Recommendation
To alleviate the above problems, we propose to build an explainable recommendation dataset with multi-aspect real user labeled ground truths.
Ultra-low Precision Multiplication-free Training for Deep Neural Networks
The energy-efficient works try to decrease the precision of multiplication or replace the multiplication with energy-efficient operations such as addition or bitwise shift, to reduce the energy consumption of FP32 multiplications.
Dirichlet-based Uncertainty Calibration for Active Domain Adaptation
Active domain adaptation (DA) aims to maximally boost the model adaptation on a new target domain by actively selecting limited target data to annotate, whereas traditional active learning methods may be less effective since they do not consider the domain shift issue.
Online Symbolic Regression with Informative Query
Symbolic regression, the task of extracting mathematical expressions from the observed data $\{ \vx_i, y_i \}$, plays a crucial role in scientific discovery.
A method for incremental discovery of financial event types based on anomaly detection
Event datasets in the financial domain are often constructed based on actual application scenarios, and their event types are weakly reusable due to scenario constraints; at the same time, the massive and diverse new financial big data cannot be limited to the event types defined for specific scenarios.
Intelligent Reflecting Surface Aided Wireless Sensing: Applications and Design Issues
Intelligent reflecting surface (IRS) is an emerging technology that is able to significantly improve the performance of wireless communications, by smartly tuning signal reflections at a large number of passive reflecting elements.
Artificial Intelligence System for Detection and Screening of Cardiac Abnormalities using Electrocardiogram Images
In this study, we present an AI system developed to detect and screen cardiac abnormalities (CAs) from real-world ECG images.
Monte Carlo Neural PDE Solver for Learning PDEs via Probabilistic Representation
To address these limitations, we propose the Monte Carlo Neural PDE Solver (MCNP Solver) for training unsupervised neural solvers via the PDEs' probabilistic representation, which regards macroscopic phenomena as ensembles of random particles.
Target-Mounted Intelligent Reflecting Surface for Joint Location and Orientation Estimation
In this paper, we propose a new application of IRS for device-free target sensing via joint location and orientation estimation.
Adaptive Depth Graph Attention Networks
As one of the most popular GNN architectures, the graph attention networks (GAT) is considered the most advanced learning architecture for graph representation and has been widely used in various graph mining tasks with impressive results.
Towards Better Robustness against Common Corruptions for Unsupervised Domain Adaptation
Recent studies have investigated how to achieve robustness for unsupervised domain adaptation (UDA).
Exploring a multi_stage feedback teaching mode for graduate students of software engineering discipline based on project_driven competition
Aiming at the current problems of theory-oriented, practice-light, and lack of innovation ability in the teaching of postgraduate software engineering courses, a multi-stage feedback teaching mode for software engineering postgraduates based on competition project_driven is proposed.
Adaptive Low-Precision Training for Embeddings in Click-Through Rate Prediction
To this end, we formulate a novel quantization training paradigm to compress the embeddings from the training stage, termed low-precision training (LPT).
Electromagnetic Environment Analysis of High-Power Wireless Charging Device
Conclusion This paper explores the radiation level and distribution of the electromagnetic field around this type of charging equipment.
Research on Early Warning and NB-IoT Real-time Monitoring System for Radiation Source Shedding of Gamma Flaw Detection Machine
In conclusion, radiation source can be found timely when it falls off, to avoid radiation accident.
Optimal Sparse Regression Trees
Regression trees are one of the oldest forms of AI models, and their predictions can be made without a calculator, which makes them broadly useful, particularly for high-stakes applications.
3-D Positioning and Resource Allocation for Multi-UAV Base Stations Under Blockage-Aware Channel Model
Based on the proposed channel model, we formulate the joint optimization problem of UAV three-dimensional (3-D) positioning and resource allocation, by power allocation, user association, and subcarrier allocation, to maximize the minimum achievable rate among users.
A Bird's-eye View of Reranking: from List Level to Page Level
Moreover, simply applying a shared network for all the lists fails to capture the commonalities and distinctions in user behaviors on different lists.
A Generalized Doubly Robust Learning Framework for Debiasing Post-Click Conversion Rate Prediction
However, in this paper, by theoretically analyzing the bias, variance and generalization bounds of DR methods, we find that existing DR approaches may have poor generalization caused by inaccurate estimation of propensity scores and imputation errors, which often occur in practice.
MACSum: Controllable Summarization with Mixed Attributes
We propose two simple and effective parameter-efficient approaches for the new task of mixed controllable summarization based on hard prompt tuning and soft prefix tuning.
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions.
XRICL: Cross-lingual Retrieval-Augmented In-Context Learning for Cross-lingual Text-to-SQL Semantic Parsing
We also include global translation exemplars for a target language to facilitate the translation process for large language models.
On the Robustness of Dataset Inference
However, in a subspace of the same setting, we prove that DI suffers from high false positives (FPs) -- it can incorrectly identify an independent model trained with non-overlapping data from the same distribution as stolen.
ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples
Reasoning over tabular data requires both table structure understanding and a broad set of table reasoning skills.
Ranked #3 on
Semantic Parsing
on WikiSQL
(Denotation accuracy (test) metric)
Strategic Decisions Survey, Taxonomy, and Future Directions from Artificial Intelligence Perspective
Strategic Decision-Making is always challenging because it is inherently uncertain, ambiguous, risky, and complex.
Imbalanced Classification in Medical Imaging via Regrouping
We propose performing imbalanced classification by regrouping majority classes into small classes so that we turn the problem into balanced multiclass classification.
TransAlign: Fully Automatic and Effective Entity Alignment for Knowledge Graphs
The task of entity alignment between knowledge graphs (KGs) aims to identify every pair of entities from two different KGs that represent the same entity.
ConEntail: An Entailment-based Framework for Universal Zero and Few Shot Classification with Supervised Contrastive Pretraining
To fill these gaps, we propose ConEntail, a new framework for universal zero and few shot classification with supervised contrastive pretraining.
Object-Category Aware Reinforcement Learning
Object-oriented reinforcement learning (OORL) is a promising way to improve the sample efficiency and generalization ability over standard RL.
Causality-driven Hierarchical Structure Discovery for Reinforcement Learning
To address this issue, we propose CDHRL, a causality-driven hierarchical reinforcement learning framework, leveraging a causality-driven discovery instead of a randomness-driven exploration to effectively build high-quality hierarchical structures in complicated environments.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
Active and Passive IRS Jointly Aided Communication: Deployment Design and Achievable Rate
In this letter, we study the wireless point-to-point communication from a transmitter (Tx) to a receiver (Rx), which is jointly aided by an active intelligent reflecting surface (AIRS) and a passive IRS (PIRS).
Selective Annotation Makes Language Models Better Few-Shot Learners
Departing from recent in-context learning methods, we formulate an annotation-efficient, two-step framework: selective annotation that chooses a pool of examples to annotate from unlabeled data in advance, followed by prompt retrieval that retrieves task examples from the annotated pool at test time.
FOLIO: Natural Language Reasoning with First-Order Logic
We present FOLIO, a human-annotated, open-domain, and logically complex and diverse dataset for reasoning in natural language (NL), equipped with first order logic (FOL) annotations.
A Novel SCA-Based Method for Beamforming Optimization in IRS/RIS-Assisted MU-MISO Downlink
In this letter, we consider the fundamental problem of jointly designing the transmit beamformers and the phase-shifts of the intelligent reflecting surface (IRS) / reconfigurable intelligent surface (RIS) to minimize the transmit power, subject to quality-of-service constraints at individual users in an IRS-assisted multiuser multiple-input single-output downlink communication system.
EgPDE-Net: Building Continuous Neural Networks for Time Series Prediction with Exogenous Variables
While exogenous variables have a major impact on performance improvement in time series analysis, inter-series correlation and time dependence among them are rarely considered in the present continuous methods.
Code Comment Inconsistency Detection with BERT and Longformer
Comments, or natural language descriptions of source code, are standard practice among software developers.
FRIB: Low-poisoning Rate Invisible Backdoor Attack based on Feature Repair
To solve the above problems, we propose the idea of feature repair for the first time and introduce the blind watermark technique to repair the poisoned features lost during the generation of poisoned data.
LEO Satellite Access Network (LEO-SAN) Towards 6G: Challenges and Approaches
With the rapid development of satellite communication technologies, the space-based access network has been envisioned as a promising complementary part of the future 6G network.
SepLUT: Separable Image-adaptive Lookup Tables for Real-time Image Enhancement
Image-adaptive lookup tables (LUTs) have achieved great success in real-time image enhancement tasks due to their high efficiency for modeling color transforms.
Ranked #5 on
Image Enhancement
on MIT-Adobe 5k
(PSNR on proRGB metric)
Deep Manifold Learning with Graph Mining
Admittedly, Graph Convolution Network (GCN) has achieved excellent results on graph datasets such as social networks, citation networks, etc.
Outpainting by Queries
Image outpainting, which is well studied with Convolution Neural Network (CNN) based framework, has recently drawn more attention in computer vision.
MIA 2022 Shared Task: Evaluating Cross-lingual Open-Retrieval Question Answering for 16 Diverse Languages
We present the results of the Workshop on Multilingual Information Access (MIA) 2022 Shared Task, evaluating cross-lingual open-retrieval question answering (QA) systems in 16 typologically diverse languages.
Detecting Arbitrary Order Beneficial Feature Interactions for Recommender Systems
Detecting beneficial feature interactions is essential in recommender systems, and existing approaches achieve this by examining all the possible feature interactions.
SSMI: How to Make Objects of Interest Disappear without Accessing Object Detectors?
Most black-box adversarial attack schemes for object detectors mainly face two shortcomings: requiring access to the target model and generating inefficient adversarial examples (failing to make objects disappear in large numbers).
AdvSmo: Black-box Adversarial Attack by Smoothing Linear Structure of Texture
We construct the adversarial examples without relying on any internal information to the target model and design the imperceptible-high attack success rate constraint to guide the Gabor filter to select appropriate angles and scales to smooth the linear texture from the input images to generate adversarial examples.
Deep Random Vortex Method for Simulation and Inference of Navier-Stokes Equations
To this end, we propose the \emph{Deep Random Vortex Method} (DRVM), which combines the neural network with a random vortex dynamics system equivalent to the Navier-Stokes equation.
An F-shape Click Model for Information Retrieval on Multi-block Mobile Pages
However, with the development of user interface (UI) design, the layout of displayed items on a result page tends to be multi-block (i. e., multi-list) style instead of a single list, which requires different assumptions to model user behaviors more accurately.
A Survey on Gradient Inversion: Attacks, Defenses and Future Directions
In particular, we dig out some critical ingredients from the iteration-based attacks, including data initialization, model training and gradient matching.
Regularization Penalty Optimization for Addressing Data Quality Variance in OoD Algorithms
Due to the poor generalization performance of traditional empirical risk minimization (ERM) in the case of distributional shift, Out-of-Distribution (OoD) generalization algorithms receive increasing attention.
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models.
MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data
Numerical reasoning over hybrid data containing both textual and tabular content (e. g., financial reports) has recently attracted much attention in the NLP community.
QoE-Aware Resource Allocation for Semantic Communication Networks
Specifically, an approximate measure of semantic entropy is first developed to quantify the semantic information for different tasks, based on which a novel quality-of-experience (QoE) model is proposed.
ES-GNN: Generalizing Graph Neural Networks Beyond Homophily with Edge Splitting
While Graph Neural Networks (GNNs) have achieved enormous success in multiple graph analytical tasks, modern variants mostly rely on the strong inductive bias of homophily.
BARS: Towards Open Benchmarking for Recommender Systems
Despite significant progress made in both research and practice of recommender systems, to date, there is a lack of a widely-recognized benchmarking standard in this field.
Neural Program Synthesis with Query
In this work, we propose a query-based framework that trains a query neural network to generate informative input-output examples automatically and interactively from a large query space.
Improving Transferability for Domain Adaptive Detection Transformers
We implement the findings and the alignment modules into our adaptation method, and it benchmarks the DETR-style detector on the domain shift settings.
ReLoop: A Self-Correction Continual Learning Loop for Recommender Systems
Deep learning-based recommendation has become a widely adopted technique in various online applications.
Solving The Long-Tailed Problem via Intra- and Inter-Category Balance
Benchmark datasets for visual recognition assume that data is uniformly distributed, while real-world datasets obey long-tailed distribution.
Multi-Level Interaction Reranking with User Behavior History
MIR combines low-level cross-item interaction and high-level set-to-list interaction, where we view the candidate items to be reranked as a set and the users' behavior history in chronological order as a list.
Self Supervised Lesion Recognition For Breast Ultrasound Diagnosis
Since an ultrasound image only describes a partial 2D projection of a 3D lesion, such paradigm ignores the semantic relationship between different views of a lesion, which is inconsistent with the traditional diagnosis where sonographers analyze a lesion from at least two views.
From 2D Images to 3D Model:Weakly Supervised Multi-View Face Reconstruction with Deep Fusion
While weakly supervised multi-view face reconstruction (MVR) is garnering increased attention, one critical issue still remains open: how to effectively fuse multiple image information to reconstruct high-precision 3D models.
Towards Better Understanding of User Satisfaction in Open-Domain Conversational Search
This raises the question of how to accurately model user satisfaction in conversational search scenarios.
Contrastive Learning with Positive-Negative Frame Mask for Music Representation
We devise a novel contrastive learning objective to accommodate both self-augmented positives/negatives sampled from the same music.
An Interpretable Neuro-Symbolic Reasoning Framework for Task-Oriented Dialogue Generation
To obtain a transparent reasoning process, we introduce neuro-symbolic to perform explicit reasoning that justifies model decisions by reasoning chains.
Matrix Completion via Non-Convex Relaxation and Adaptive Correlation Learning
We theoretically validate that it is equivalent to the existing matrix completion models.
Bridge the Gap between Supervised and Unsupervised Learning for Fine-Grained Classification
Unsupervised learning technology has caught up with or even surpassed supervised learning technology in general object classification (GOC) and person re-identification (re-ID).
Mining On Alzheimer's Diseases Related Knowledge Graph to Identity Potential AD-related Semantic Triples for Drug Repurposing
The 1, 672, 110 filtered triples were used to train with knowledge graph completion algorithms (i. e., TransE, DistMult, and ComplEx) to predict candidates that might be helpful for AD treatment or prevention.
Neural Re-ranking in Multi-stage Recommender Systems: A Review
As the final stage of the multi-stage recommender system (MRS), re-ranking directly affects user experience and satisfaction by rearranging the input ranking lists, and thereby plays a critical role in MRS. With the advances in deep learning, neural re-ranking has become a trending topic and been widely applied in industrial applications.
Predicting Cancer Treatments Induced Cardiotoxicity of Breast Cancer Patients
After adjusting for baseline differences in cardiovascular health, patients who received chemotherapy or targeted therapy appeared to have higher risk of cardiotoxicity than patients who received radiation therapy.
Generalised Image Outpainting with U-Transformer
In this paper, we develop a novel transformer-based generative adversarial neural network called U-Transformer for generalised image outpainting problem.
Target Sensing with Intelligent Reflecting Surface: Architecture and Performance
Intelligent reflecting surface (IRS) has emerged as a promising technology to reconfigure the radio propagation environment by dynamically controlling wireless signal's amplitude and/or phase via a large number of reflecting elements.
On the Opportunity of Causal Learning in Recommendation Systems: Foundation, Estimation, Prediction and Challenges
Recently, recommender system (RS) based on causal inference has gained much attention in the industrial community, as well as the states of the art performance in many prediction and debiasing tasks.
Resource allocation for text semantic communications
Semantic communications have shown its great potential to improve the transmission reliability, especially in the low signal-to-noise regime.
UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models
Structured knowledge grounding (SKG) leverages structured knowledge to complete user requests, such as semantic parsing over databases and question answering over knowledge bases.
Ranked #1 on
Task-Oriented Dialogue Systems
on KVRET
Phase Turbulence Prediction Method for Line-of-Sight Multiple-Input–Multiple-Output Links Caused by Atmospheric Environment
In the method, the tropospheric refractivity profile was predicted using a mesoscale NWP model, and then MIMO phase was predicted by the parabolic equation model.
ISNet: Shape Matters for Infrared Small Target Detection
TOAA block calculates the low-level information with attention mechanism in both row and column directions and fuses it with the high-level information to capture the shape characteristic of targets and suppress noises.
AutoDES: AutoML Pipeline Generation of Classification with Dynamic Ensemble Strategy Selection
Ablation experiments on our framework validate the effectiveness of our proposed method.
Rethinking Influence Functions of Neural Networks in the Over-parameterized Regime
However, the classic implicit Hessian-vector product (IHVP) method for calculating IF is fragile, and theoretical analysis of IF in the context of neural networks is still lacking.
An Overview of Signal Processing Techniques for RIS/IRS-aided Wireless Systems
In the past as well as present wireless communication systems, the wireless propagation environment is regarded as an uncontrollable black box that impairs the received signal quality, and its negative impacts are compensated for by relying on the design of various sophisticated transmission/reception schemes.
Feature-based Recognition Framework for Super-resolution Images
In practical application, the performance of recognition network usually decreases when being applied on super-resolution images.
MISS: Multi-Interest Self-Supervised Learning Framework for Click-Through Rate Prediction
With the help of two novel CNN-based multi-interest extractors, self-supervision signals are discovered with full considerations of different interest representations (point-wise and union-wise), interest dependencies (short-range and long-range), and interest correlations (inter-item and intra-item).
AnchorGAE: General Data Clustering via $O(n)$ Bipartite Graph Convolution
The core problems mainly come from two aspects: (1) the graph is unavailable in the most clustering scenes so that how to construct high-quality graphs on the non-graph data is usually the most important part; (2) given n samples, the graph-based clustering methods usually consume at least $\mathcal O(n^2)$ time to build graphs and the graph convolution requires nearly $\mathcal O(n^2)$ for a dense graph and $\mathcal O(|\mathcal{E}|)$ for a sparse one with $|\mathcal{E}|$ edges.
Distilling Object Detectors with Feature Richness
Second, these methods imitate some features which are mistakenly regarded as the background by the teacher detector.
An Open Natural Language Processing Development Framework for EHR-based Clinical Research: A case demonstration using the National COVID Cohort Collaborative (N3C)
Although we use COVID-19 as a use case in this effort, our framework is general enough to be applied to other domains of interest in clinical NLP.
Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents
To the best of our knowledge, Summ$^N$ is the first multi-stage split-then-summarize framework for long input summarization.
DYLE: Dynamic Latent Extraction for Abstractive Long-Input Summarization
Transformer-based models have achieved state-of-the-art performance on short-input summarization.
Learning Controllable Elements Oriented Representations for Reinforcement Learning
Deep Reinforcement Learning (deep RL) has been successfully applied to solve various decision-making problems in recent years.
TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation
Recent progress in generative language models has enabled machines to generate astonishingly realistic texts.
Multi View Spatial-Temporal Model for Travel Time Estimation
Specifically, we use graph2vec to model the spatial view, dual-channel temporal module to model the trajectory view, and structural embedding to model traffic semantics.
Prefix-to-SQL: Text-to-SQL Generation from Incomplete User Questions
Existing text-to-SQL research only considers complete questions as the input, but lay-users might strive to formulate a complete question.
CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning
Named Entity Recognition (NER) in Few-Shot setting is imperative for entity tagging in low resource domains.
Ranked #7 on
Few-shot NER
on Few-NERD (INTRA)
(using extra training data)
EVOQUER: Enhancing Temporal Grounding with Video-Pivoted BackQuery Generation
Given a query and an untrimmed video, the temporal grounding model predicts the target interval, and the predicted video clip is fed into a video translation task by generating a simplified version of the input query.
An Exploratory Study on Long Dialogue Summarization: What Works and What's Next
Dialogue summarization helps readers capture salient information from long conversations in meetings, interviews, and TV series.
Eden: A Unified Environment Framework for Booming Reinforcement Learning Algorithms
In this framework, the environment can be easily configured to realize all kinds of RL tasks in the mainstream research.
Cross-Lingual Training with Dense Retrieval for Document Retrieval
Dense retrieval has shown great success in passage ranking in English.
CancerBERT: a BERT model for Extracting Breast Cancer Phenotypes from Electronic Health Records
This data used in the study included 21, 291 breast cancer patients diagnosed from 2010 to 2020, patients' clinical notes and pathology reports were collected from the University of Minnesota Clinical Data Repository (UMN).
"Adversarial Examples" for Proof-of-Learning
Jia et al. claimed that an adversary merely knowing the final model and training dataset cannot efficiently find a set of intermediate models with correct data points.
Memorize, Factorize, or be Naïve: Learning Optimal Feature Interaction Methods for CTR Prediction
As feature interactions bring in non-linearity, they are widely adopted to improve the performance of CTR prediction models.
Ranked #1 on
Click-Through Rate Prediction
on Avazu
Logic-Consistency Text Generation from Semantic Parses
Text generation from semantic parses is to generate textual descriptions for formal representation inputs such as logic forms and SQL queries.
Hindsight Value Function for Variance Reduction in Stochastic Dynamic Environment
In this paper, we propose to replace the state value function with a novel hindsight value function, which leverages the information from the future to reduce the variance of the gradient estimate for stochastic dynamic environments.
Video Crowd Localization with Multi-focus Gaussian Neighborhood Attention and a Large-Scale Benchmark
Video crowd localization is a crucial yet challenging task, which aims to estimate exact locations of human heads in the given crowded videos.
Improving Model Robustness with Latent Distribution Locally and Globally
The proposed adversarial training with latent distribution (ATLD) method defends against adversarial attacks by crafting LMAEs with the latent manifold in an unsupervised manner.
Discovering novel drug-supplement interactions using a dietary supplements knowledge graph generated from the biomedical literature
MATERIALS AND METHODS: We created SemRepDS (an extension of SemRep), capable of extracting semantic relations from abstracts by leveraging a DS-specific terminology (iDISK) containing 28, 884 DS terms not found in the UMLS.
Structured in Space, Randomized in Time: Leveraging Dropout in RNNs for Efficient Training
Recurrent Neural Networks (RNNs), more specifically their Long Short-Term Memory (LSTM) variants, have been widely used as a deep learning tool for tackling sequence-based learning tasks in text and speech.
Deep Learning Models in Detection of Dietary Supplement Adverse Event Signals from Twitter
We chose the best performing models in each task to assemble an end-to-end deep learning pipeline to detect DS AE signals and compared the results to the known DS AEs from a DS knowledge base (i. e., iDISK).
Deep Contrastive Graph Representation via Adaptive Homotopy Learning
In particular, in this paper, we apply AH to contrastive learning (AHCL) such that it can be effectively transferred from weak-supervised learning (given label priori) to unsupervised learning, where soft labels of contrastive learning are directly and adaptively learned.
Shuffle Transformer with Feature Alignment for Video Face Parsing
This is a short technical report introducing the solution of the Team TCParser for Short-video Face Parsing Track of The 3rd Person in Context (PIC) Workshop and Challenge at CVPR 2021.
Non-Gradient Manifold Neural Network
Moreover, by unifying the flexible Stiefel manifold and adaptive support vector machine, we devise the novel decision layer which efficiently fits the manifold structure of the data and label information.
