Search Results for author:
Found 52 papers, 26 papers with code
COVID-19 Claim Radar: A Structured Claim Extraction and Tracking System
To tackle the challenge of accurate and timely communication regarding the COVID-19 pandemic, we present a COVID-19 Claim Radar to automatically extract supporting and refuting claims on a daily basis.
RESIN-11: Schema-guided Event Prediction for 11 Newsworthy Scenarios
We introduce RESIN-11, a new schema-guided event extraction&prediction framework that can be applied to a large variety of newsworthy scenarios.
Eliminating Position Bias of Language Models: A Mechanistic Approach
Our mechanistic analysis attributes the position bias to two components employed in nearly all state-of-the-art LMs: causal attention and relative positional encodings.
Is GPT-4 conscious?
GPT-4 is often heralded as a leading commercial AI offering, sparking debates over its potential as a steppingstone toward artificial general intelligence.
LFMamba: Light Field Image Super-Resolution with State Space Model
We expect that our LFMamba shed light on effective representation learning of LFs with state space models.
Federated Incomplete Multi-View Clustering with Heterogeneous Graph Neural Networks
In the proposed FIM-GNNs, autoencoders built on heterogeneous graph neural network models are employed for feature extraction of multi-view data at each client site.
FlexLoc: Conditional Neural Networks for Zero-Shot Sensor Perspective Invariance in Object Localization with Distributed Multimodal Sensors
Localization is a critical technology for various applications ranging from navigation and surveillance to assisted living.
Weak-to-Strong Extrapolation Expedites Alignment
Through experiments with twelve open-source LLMs on HuggingFace, we demonstrate that ExPO consistently improves off-the-shelf DPO/RLHF models, as evaluated on the mainstream LLM benchmarks AlpacaEval 2. 0 and MT-Bench.
GDTM: An Indoor Geospatial Tracking Dataset with Distributed Multimodal Sensors
Constantly locating moving objects, i. e., geospatial tracking, is essential for autonomous building infrastructure.
FedADMM-InSa: An Inexact and Self-Adaptive ADMM for Federated Learning
First, we design an inexactness criterion for the clients' local updates to eliminate the need for empirically setting the local training accuracy.
Chinese MentalBERT: Domain-Adaptive Pre-training on Social Media for Chinese Mental Health Text Analysis
There is a recognized need for models capable of efficient analysis.
Dimensionality reduction can be used as a surrogate model for high-dimensional forward uncertainty quantification
The proposed method also diverges from the Probabilistic Learning on Manifold, as a reconstruction mapping from the feature space to the input-output space is circumvented.
Data-Free Quantization via Pseudo-label Filtering
Quantization for model compression can efficiently reduce the network complexity and storage requirement but the original training data is necessary to remedy the performance loss caused by quantization.
Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint
We investigate its behavior in three distinct settings -- offline, online, and hybrid -- and propose efficient algorithms with finite-sample theoretical guarantees.
The impact of Hong Kong's anti-ELAB movement on political related firms
Using the number of protestors as the measurement of daily protesting intensity from 2019/6/6 to 2020/1/17, this paper documents that the stock price of listed companies associated with the pan-democratic parties were more negatively affected by protesting than other companies.
PACIT: Unlocking the Power of Examples for Better In-Context Instruction Tuning
Instruction tuning enhances the instruction following ability of large language models by finetuning with supervised instruction data.
Enabling Language Models to Implicitly Learn Self-Improvement
Specifically, we reformulate the training objective of reinforcement learning from human feedback (RLHF) -- instead of maximizing response quality for a given input, we maximize the quality gap of the response conditioned on a reference response.
Parameter-Efficient Tuning Helps Language Model Alignment
To this end, prior works incorporate controllable generations for alignment to make language models learn multiple preferences and provide outputs with different preferences during inference if asked.
Enabling Resource-efficient AIoT System with Cross-level Optimization: A survey
Accordingly, the accuracy and responsiveness of DL models are bounded by resource availability.
Approximate and Weighted Data Reconstruction Attack in Federated Learning
Federated Learning (FL) is a distributed learning paradigm that enables multiple clients to collaborate on building a machine learning model without sharing their private data.
Psy-LLM: Scaling up Global Mental Health Psychological Services with AI-based Large Language Models
The demand for psychological counselling has grown significantly in recent years, particularly with the global outbreak of COVID-19, which has heightened the need for timely and professional mental health support.
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.
Heteroskedastic Geospatial Tracking with Distributed Camera Networks
Visual object tracking has seen significant progress in recent years.
Explaining Emergent In-Context Learning as Kernel Regression
Then, we empirically investigate the in-context behaviors of language models.
Understanding the Effect of Data Augmentation on Knowledge Distillation
However, such data augmentation methods are sub-optimal for knowledge distillation since the teacher model could provide label distributions and is more tolerant to semantic shifts.
RCOT: Detecting and Rectifying Factual Inconsistency in Reasoning by Reversing Chain-of-Thought
To detect factual inconsistency, RCoT first asks LLMs to reconstruct the problem based on generated solutions.
Games for Artificial Intelligence Research: A Review and Perspectives
Those platforms provide ideal benchmarks for exploring and comparing artificial intelligence ideas and techniques.
SmartBook: AI-Assisted Situation Report Generation for Intelligence Analysts
Timely and comprehensive understanding of emerging events is crucial for effective decision-making; automating situation report generation can significantly reduce the time, effort, and cost for intelligence analysts.
Learning Long-Range Information with Dual-Scale Transformers for Indoor Scene Completion
Due to the limited resolution of 3D sensors and the inevitable mutual occlusion between objects, 3D scans of real scenes are commonly incomplete.
State Space Closure: Revisiting Endless Online Level Generation via Reinforcement Learning
Concluding our outcomes and analysis, future work on endless online level generation via reinforcement learning should address the issue of diversity while assuring the occurrence of state space closure and quality.
Recognizing Object by Components with Human Prior Knowledge Enhances Adversarial Robustness of Deep Neural Networks
The first stage of ROCK corresponds to the process of decomposing objects into parts in human vision.
Augmentation with Projection: Towards an Effective and Efficient Data Augmentation Paradigm for Distillation
However, these data augmentation methods either potentially cause shifts in decision boundaries (representation interpolation), are not expressive enough (token replacement), or introduce too much computational overhead (augmentation with models).
Online Game Level Generation from Music
Game consists of multiple types of content, while the harmony of different content types play an essential role in game design.
FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations
We present a meta-learning framework for learning new visual concepts quickly, from just one or a few examples, guided by multiple naturally occurring data streams: simultaneously looking at images, reading sentences that describe the objects in the scene, and interpreting supplemental sentences that relate the novel concept with other concepts.
Enhancing Classifier Conservativeness and Robustness by Polynomiality
We illustrate the detrimental effect, such as overconfident decisions, that exponential behavior can have in methods like classical LDA and logistic regression.
Derivative-free Alternating Projection Algorithms for General Nonconvex-Concave Minimax Problems
In this paper, we study zeroth-order algorithms for nonconvex-concave minimax problems, which have attracted widely attention in machine learning, signal processing and many other fields in recent years.
Keiki: Towards Realistic Danmaku Generation via Sequential GANs
Search-based procedural content generation methods have recently been introduced for the autonomous creation of bullet hell games.
CLEVE: Contrastive Pre-training for Event Extraction
Event extraction (EE) has considerably benefited from pre-trained language models (PLMs) by fine-tuning.
Ice front shaping by upward convective current
We propose a boundary-layer model and a buoyancy-intensity model which account for the main features of the ice morphology.
Fluid Dynamics Geophysics
Reinforcement Learning with Dual-Observation for General Video Game Playing
Our proposed technique is implemented with three state-of-the-art reinforcement learning algorithms and tested on the game set of the 2020 General Video Game AI Learning Competition.
Respecting Domain Relations: Hypothesis Invariance for Domain Generalization
In this work, we define DIRs employed by existing works in probabilistic terms and show that by learning DIRs, overly strict requirements are imposed concerning the invariance.
Black Magic in Deep Learning: How Human Skill Impacts Network Training
Our study investigates the subjective human factor in comparisons of state of the art results and scientific reproducibility in deep learning.
A Novel CNet-assisted Evolutionary Level Repairer and Its Applications to Super Mario Bros
However, defective levels with illegal patterns may be generated due to the violation of constraints for level design.
MAVEN: A Massive General Domain Event Detection Dataset
Most existing datasets exhibit the following issues that limit further development of ED: (1) Data scarcity.
Probabilistic Performance-Pattern Decomposition (PPPD): analysis framework and applications to stochastic mechanical systems
Since the early 1900s, numerous research efforts have been devoted to developing quantitative solutions to stochastic mechanical systems.
Learning from Explanations with Neural Execution Tree
While deep neural networks have achieved impressive performance on a range of NLP tasks, these data-hungry models heavily rely on labeled data, which restricts their applications in scenarios where data annotation is expensive.
HMEAE: Hierarchical Modular Event Argument Extraction
Existing event extraction methods classify each argument role independently, ignoring the conceptual correlations between different argument roles.
Attention-Aware Age-Agnostic Visual Place Recognition
Different from conventional VPR settings where the query images and gallery images come from the same domain, we propose a more common but challenging setup where the query images are collected under a new unseen condition.
NERO: A Neural Rule Grounding Framework for Label-Efficient Relation Extraction
The soft matching module learns to match rules with semantically similar sentences such that raw corpora can be automatically labeled and leveraged by the RE module (in a much better coverage) as augmented supervision, in addition to the exactly matched sentences.
A novel active learning-based Gaussian process metamodelling strategy for estimating the full probability distribution in forward UQ analysis
This paper proposes an active learning-based Gaussian process (AL-GP) metamodelling method to estimate the cumulative as well as complementary cumulative distribution function (CDF/CCDF) for forward uncertainty quantification (UQ) problems.
How to Manipulate CNNs to Make Them Lie: the GradCAM Case
This illustrates that GradCAM cannot explain the decision of every CNN and provides a proof of concept showing that it is possible to obfuscate the inner workings of a CNN.
Deep Residual Neural Networks for Audio Spoofing Detection
Additionally, replay attacks where the attacker uses a speaker to replay a previously recorded genuine human speech are also possible.
