Search Results for author:
Found 76 papers, 41 papers with code
QSTS: A Question-Sensitive Text Similarity Measure for Question Generation
Indeed, QG models continue to be evaluated using traditional measures such as BLEU, METEOR, and ROUGE scores which were designed for other text generation problems.
NUS-IDS at CASE 2021 Task 1: Improving Multilingual Event Sentence Coreference Identification With Linguistic Information
Event Sentence Coreference Identification (ESCI) aims to cluster event sentences that refer to the same event together for information extraction.
Suicide Risk Prediction by Tracking Self-Harm Aspects in Tweets: NUS-IDS at the CLPsych 2021 Shared Task
We describe our system for identifying users at-risk for suicide based on their tweets developed for the CLPsych 2021 Shared Task.
Causal Augmentation for Causal Sentence Classification
Scarcity of annotated causal texts leads to poor robustness when training state-of-the-art language models for causal sentence classification.
On Generating Fact-Infused Question Variations
We study a double encoder-decoder model, Fact-Infused Question Generator (FIQG), for learning to generate fact-infused questions from a given question.
Ferret: Federated Full-Parameter Tuning at Scale for Large Language Models
To address these limitations, we propose federated full-parameter tuning at scale for LLMs (Ferret), the first first-order method with shared randomness to enable scalable full-parameter tuning of LLMs across decentralized data sources while maintaining competitive model accuracy.
LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models
Large language models (LLMs) face significant challenges in handling long-context tasks because of their limited effective context window size during pretraining, which restricts their ability to generalize over extended sequences.
Chain-of-Exemplar: Enhancing Distractor Generation for Multimodal Educational Question Generation
Multiple-choice questions (MCQs) are important in enhancing concept learning and student engagement for educational purposes.
Leveraging Weak Cross-Modal Guidance for Coherence Modelling via Iterative Learning
The iterative cross-modal boosting also functions in inference to further enhance coherence prediction in each modality.
GalleryGPT: Analyzing Paintings with Large Multimodal Models
Specifically, we first propose a task of composing paragraph analysis for artworks, i. e., painting in this paper, only focusing on visual characteristics to formulate more comprehensive understanding of artworks.
From 2D to 3D: AISG-SLA Visual Localization Challenge
To tackle these challenges, we organized the AISG-SLA Visual Localization Challenge (VLC) at IJCAI 2023 to explore how AI can accurately extract camera pose data from 2D images in 3D space.
TRACE: TRansformer-based Attribution using Contrastive Embeddings in LLMs
The rapid evolution of large language models (LLMs) represents a substantial leap forward in natural language understanding and generation.
Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning
Data quality stands at the forefront of deciding the effectiveness of video-language representation learning.
Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models
To bridge this gap, we address the lack of high-quality, diverse multimodal mathematical datasets by collecting 40K high-quality images with question-answer pairs from 24 existing datasets and synthesizing 320K new pairs, creating the MathV360K dataset, which enhances both the breadth and depth of multimodal mathematical questions.
On Newton's Method to Unlearn Neural Networks
With the widespread applications of neural networks (NNs) trained on personal data, machine unlearning has become increasingly important for enabling individuals to exercise their personal data ownership, particularly the "right to be forgotten" from trained NNs.
PetalView: Fine-grained Location and Orientation Extraction of Street-view Images via Cross-view Local Search with Supplementary Materials
Satellite-based street-view information extraction by cross-view matching refers to a task that extracts the location and orientation information of a given street-view image query by using one or multiple geo-referenced satellite images.
Ask-before-Plan: Proactive Language Agents for Real-World Planning
In this work, we introduce a new task, Proactive Agent Planning, which requires language agents to predict clarification needs based on user-agent conversation and agent-environment interaction, invoke external tools to collect valid information, and generate a plan to fulfill the user's demands.
Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives
Humans use multiple senses to comprehend the environment.
Encoding and Controlling Global Semantics for Long-form Video Question Answering
Seeking answers effectively for long videos is essential to build video question answering (videoQA) systems.
Prompt Optimization with Human Feedback
We apply our APOHF algorithm to various tasks, including optimizing user instructions, prompt optimization for text-to-image generative models, and response optimization with human feedback (i. e., further refining the response using a variant of our APOHF).
Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplars
On the other hand, the impact of the instruction, another essential component in the prompt given to the LLM, is often overlooked in existing exemplar selection methods.
Data-Free Federated Class Incremental Learning with Diffusion-Based Generative Memory
In this paper, we introduce a novel data-free federated class incremental learning framework with diffusion-based generative memory (DFedDGM) to mitigate catastrophic forgetting by generating stable, high-quality images through diffusion models.
Learnable Item Tokenization for Generative Recommendation
Utilizing powerful Large Language Models (LLMs) for generative recommendation has attracted much attention.
One-Shot Sequential Federated Learning for Non-IID Data by Enhancing Local Model Diversity
In this paper, we improve the one-shot sequential federated learning for non-IID data by proposing a local model diversity-enhancing strategy.
PINNACLE: PINN Adaptive ColLocation and Experimental points selection
Physics-Informed Neural Networks (PINNs), which incorporate PDEs as soft constraints, train with a composite loss function that contains multiple training point types: different types of collocation points chosen during training to enforce each PDE and initial/boundary conditions, and experimental points which are usually costly to obtain via experiments or simulations.
SemRoDe: Macro Adversarial Training to Learn Representations That are Robust to Word-Level Attacks
Language models (LMs) are indispensable tools for natural language processing tasks, but their vulnerability to adversarial attacks remains a concern.
Chain of Thought Explanation for Dialogue State Tracking
Dialogue state tracking (DST) aims to record user queries and goals during a conversational interaction achieved by maintaining a predefined set of slots and their corresponding values.
Localized Zeroth-Order Prompt Optimization
Existing methodologies usually prioritize a global optimization for finding the global optimum, which however will perform poorly in certain tasks.
CET2: Modelling Topic Transitions for Coherent and Engaging Knowledge-Grounded Conversations
Knowledge-grounded dialogue systems aim to generate coherent and engaging responses based on the dialogue contexts and selected external knowledge.
PHAnToM: Personality Has An Effect on Theory-of-Mind Reasoning in Large Language Models
Drawing inspiration from psychological research on the links between certain personality traits and Theory-of-Mind (ToM) reasoning, and from prompt engineering research on the hyper-sensitivity of prompts in affecting LLMs capabilities, this study investigates how inducing personalities in LLMs using prompts affects their ToM reasoning capabilities.
On the Multi-turn Instruction Following for Conversational Web Agents
Web agents powered by Large Language Models (LLMs) have demonstrated remarkable abilities in planning and executing multi-step interactions within complex web-based environments, fulfilling a wide range of web navigation tasks.
Don't Just Say "I don't know"! Self-aligning Large Language Models for Responding to Unknown Questions with Explanations
Despite the remarkable abilities of Large Language Models (LLMs) to answer questions, they often display a considerable level of overconfidence even when the question does not have a definitive answer.
Hint-before-Solving Prompting: Guiding LLMs to Effectively Utilize Encoded Knowledge
Large Language Models (LLMs) have recently showcased remarkable generalizability in various domains.
FGAD: Self-boosted Knowledge Distillation for An Effective Federated Graph Anomaly Detection Framework
Although federated learning offers a promising solution, the prevalent non-IID problems and high communication costs present significant challenges, particularly pronounced in collaborations with graph data distributed among different participants.
LLM-based Federated Recommendation
Nevertheless, applying Fed4Rec to LLM-based recommendation presents two main challenges: first, an increase in the imbalance of performance across clients, affecting the system's efficiency over time, and second, a high demand on clients' computational and storage resources for local training and inference of LLMs.
Mercury: A Code Efficiency Benchmark for Code Large Language Models
Based on the distribution, we introduce a new metric Beyond, which computes a runtime-percentile-weighted Pass score to reflect functional correctness and code efficiency simultaneously.
Topic Modeling as Multi-Objective Contrastive Optimization
Secondly, we explicitly cast contrastive topic modeling as a gradient-based multi-objective optimization problem, with the goal of achieving a Pareto stationary solution that balances the trade-off between the ELBO and the contrastive objective.
Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Models
In the face of uncertainty, the ability to *seek information* is of fundamental importance.
OmniDialog: An Omnipotent Pre-training Model for Task-Oriented Dialogue System
Furthermore, to glean a nuanced understanding of OmniDialog's strengths and potential pitfalls, we designed a fine-grained analysis framework for dialogue-centric tasks.
READ-PVLA: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in Low-Resource Video-Language Modeling
Fully fine-tuning pretrained large-scale transformer models has become a popular paradigm for video-language modeling tasks, such as temporal language grounding and video-language summarization.
DemaFormer: Damped Exponential Moving Average Transformer with Energy-Based Modeling for Temporal Language Grounding
Temporal Language Grounding seeks to localize video moments that semantically correspond to a natural language query.
Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents
Proactive dialogues serve as a practical yet challenging dialogue problem in the era of large language models (LLMs), where the dialogue policy planning is the key to improving the proactivity of LLMs.
From Static to Dynamic: A Continual Learning Framework for Large Language Models
The vast number of parameters in large language models (LLMs) endows them with remarkable capabilities, allowing them to excel in a variety of natural language processing tasks.
Solving Math Word Problems with Reexamination
Math word problem (MWP) solving aims to understand the descriptive math problem and calculate the result, for which previous efforts are mostly devoted to upgrade different technical modules.
Bridging Items and Language: A Transition Paradigm for Large Language Model-Based Recommendation
Harnessing Large Language Models (LLMs) for recommendation is rapidly emerging, which relies on two fundamental steps to bridge the recommendation item space and the language space: 1) item indexing utilizes identifiers to represent items in the language space, and 2) generation grounding associates LLMs' generated token sequences to in-corpus items.
Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers
This is mainly due to the limited expressive power of the Gaussian process (GP) which is used by BO as a surrogate to model the objective function.
Source Attribution for Large Language Model-Generated Data
The impressive performances of Large Language Models (LLMs) and their immense potential for commercialization have given rise to serious concerns over the Intellectual Property (IP) of their training data.
Enhancing Large Language Model Induced Task-Oriented Dialogue Systems Through Look-Forward Motivated Goals
Recently, the development of large language models (LLMs) has been significantly enhanced the question answering and dialogue generation, and makes them become increasingly popular in current practical scenarios.
Beyond Geo-localization: Fine-grained Orientation of Street-view Images by Cross-view Matching with Satellite Imagery with Supplementary Materials
Street-view imagery provides us with novel experiences to explore different places remotely.
Ranked #3 on
Image-Based Localization
on cvact
Fair yet Asymptotically Equal Collaborative Learning
In collaborative learning with streaming data, nodes (e. g., organizations) jointly and continuously learn a machine learning (ML) model by sharing the latest model updates computed from their latest streaming data.
Training-Free Neural Active Learning with Initialization-Robustness Guarantees
To this end, we introduce our expected variance with Gaussian processes (EV-GP) criterion for neural active learning, which is theoretically guaranteed to select data points which lead to trained NNs with both (a) good predictive performances and (b) initialization robustness.
A Comprehensive Survey of Sentence Representations: From the BERT Epoch to the ChatGPT Era and Beyond
In this paper, we provide an overview of the different methods for sentence representation learning, focusing mostly on deep learning models.
Constructing and Interpreting Causal Knowledge Graphs from News
In this work, we propose a methodology to construct causal knowledge graphs (KGs) from news using two steps: (1) Extraction of Causal Relations, and (2) Argument Clustering and Representation into KG.
Non-Autoregressive Math Word Problem Solver with Unified Tree Structure
For evaluating the possible expression variants, we design a path-based metric to evaluate the partial accuracy of expressions of a unified tree.
EasySpider: A No-Code Visual System for Crawling the Web
As such, web-crawling is an essential tool for both computational and non-computational scientists to conduct research.
Data-Free Diversity-Based Ensemble Selection For One-Shot Federated Learning in Machine Learning Model Market
The emerging availability of trained machine learning models has put forward the novel concept of Machine Learning Model Market in which one can harness the collective intelligence of multiple well-trained models to improve the performance of the resultant model through one-shot federated learning and ensemble learning in a data-free manner.
GPTScore: Evaluate as You Desire
Generative Artificial Intelligence (AI) has enabled the development of sophisticated models that are capable of producing high-caliber text, images, and other outputs through the utilization of large pre-trained models.
Fourier Sensitivity and Regularization of Computer Vision Models
Using this result, we propose a general measure of any differentiable model's Fourier-sensitivity using the unitary Fourier-transform of its input-gradient.
CorefDiffs: Co-referential and Differential Knowledge Flow in Document Grounded Conversations
Knowledge-grounded dialog systems need to incorporate smooth transitions among knowledge selected for generating responses, to ensure that dialog flows naturally.
Joint Triplet Loss Learning for Next New POI Recommendation
Sparsity of the User-POI matrix is a well established problem for next POI recommendation, which hinders effective learning of user preferences.
UniCausal: Unified Benchmark and Repository for Causal Text Mining
Current causal text mining datasets vary in objectives, data coverage, and annotation schemes.
Vision-and-Language Pretraining
Moreover, a list of training datasets and downstream tasks is supplied to further polish the perspective into V\&L pretraining.
Are All the Datasets in Benchmark Necessary? A Pilot Study of Dataset Evaluation for Text Classification
In this paper, we ask the research question of whether all the datasets in the benchmark are necessary.
Polyglot Prompt: Multilingual Multitask PrompTraining
This paper aims for a potential architectural improvement for multilingual learning and asks: Can different tasks from different languages be modeled in a monolithic framework, i. e. without any task/language-specific module?
COOL, a Context Outlooker, and its Application to Question Answering and other Natural Language Processing Tasks
We present an outlook attention mechanism, COOL, for natural language processing.
Syntax-informed Question Answering with Heterogeneous Graph Transformer
Large neural language models are steadily contributing state-of-the-art performance to question answering and other natural language and information processing tasks.
Trusted Media Challenge Dataset and User Study
To tackle the issue, we have organized the Trusted Media Challenge (TMC) to explore how Artificial Intelligence (AI) technologies could be leveraged to combat fake media.
NUS-IDS at FinCausal 2021: Dependency Tree in Graph Neural Network for Better Cause-Effect Span Detection
Automatic identification of cause-effect spans in financial documents is important for causality modelling and understanding reasons that lead to financial events.
Spatial Frequency Sensitivity Regularization for Robustness
The ability to generalize to out-of-distribution data is a major challenge for modern deep neural networks.
Electrocardiogram Classification and Visual Diagnosis of Atrial Fibrillation with DenseECG
We trained our model using the publicly available dataset from 2017 PhysioNet Computing in Cardiology(CinC) Challenge containing 8528 single-lead ECG recordings of short-term heart rhythms (9-61s).
Origin-Aware Next Destination Recommendation with Personalized Preference Attention
Next destination recommendation is an important task in the transportation domain of taxi and ride-hailing services, where users are recommended with personalized destinations given their current origin location.
ESTeR: Combining Word Co-occurrences and Word Associations for Unsupervised Emotion Detection
Accurate detection of emotions in user- generated text was shown to have several applications for e-commerce, public well-being, and disaster management.
STP-UDGAT: Spatial-Temporal-Preference User Dimensional Graph Attention Network for Next POI Recommendation
Next Point-of-Interest (POI) recommendation is a longstanding problem across the domains of Location-Based Social Networks (LBSN) and transportation.
Detecting and Diagnosing Incipient Building Faults Using Uncertainty Information from Deep Neural Networks
Early detection of incipient faults is of vital importance to reducing maintenance costs, saving energy, and enhancing occupant comfort in buildings.
MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks
The prevalence of networked sensors and actuators in many real-world systems such as smart buildings, factories, power plants, and data centers generate substantial amounts of multivariate time series data for these systems.
Anomaly Detection with Generative Adversarial Networks for Multivariate Time Series
We used LSTM-RNN in our GAN to capture the distribution of the multivariate time series of the sensors and actuators under normal working conditions of a CPS.
