Search Results for author:
Found 51 papers, 18 papers with code
ER-TEST Evaluating Explanation Regularization Methods for NLP Models
For the latter, explanation regularization (ER) aims to improve NLM generalization by pushing the machine rationales to align with human rationales.
AI Agent Behavioral Science
Recent advances in large language models (LLMs) have enabled the development of AI agents that exhibit increasingly human-like behaviors, including planning, adaptation, and social dynamics across diverse, interactive, and open-ended scenarios.
anyECG-chat: A Generalist ECG-MLLM for Flexible ECG Input and Multi-Task Understanding
However, existing ECG-focused MLLMs primarily focus on report generation tasks, often limited to single 12-lead, short-duration (10s) ECG inputs, thereby underutilizing the potential of MLLMs.
Discovering Pathology Rationale and Token Allocation for Efficient Multimodal Pathology Reasoning
Multimodal pathological image understanding has garnered widespread interest due to its potential to improve diagnostic accuracy and enable personalized treatment through integrated visual and textual data.
Fine-Grained ECG-Text Contrastive Learning via Waveform Understanding Enhancement
Electrocardiograms (ECGs) are essential for diagnosing cardiovascular diseases.
Improving Random Forests by Smoothing
Gaussian process regression is a popular model in the small data regime due to its sound uncertainty quantification and the exploitation of the smoothness of the regression function that is encountered in a wide range of practical problems.
Bridge the Gap: From Weak to Full Supervision for Temporal Action Localization with PseudoFormer
While recent approaches employ pseudo labels for training, three key challenges: generating high-quality pseudo labels, making full use of different priors, and optimizing training methods with noisy labels remain unresolved.
Can LLMs Grasp Implicit Cultural Values? Benchmarking LLMs' Metacognitive Cultural Intelligence with CQ-Bench
To address this gap, we introduce CQ-Bench, a benchmark specifically designed to assess LLMs' capability to infer implicit cultural values from natural conversational contexts.
Make the Most of Everything: Further Considerations on Disrupting Diffusion-based Customization
We propose Dual Anti-Diffusion (DADiff), a two-stage adversarial attack targeting diffusion customization, which, for the first time, integrates the adversarial prompt-level attack into the generation process of image-level adversarial examples.
Improving Interactive Diagnostic Ability of a Large Language Model Agent Through Clinical Experience Learning
The experimental results indicate that the PPME LLM achieved over 30% improvement compared to baselines.
VLMs as GeoGuessr Masters: Exceptional Performance, Hidden Biases, and Privacy Risks
Evaluating four VLMs, we find that while these models demonstrate the ability to recognize geographic information from images, achieving up to 53. 8% accuracy in city prediction, they exhibit significant biases.
ErasableMask: A Robust and Erasable Privacy Protection Scheme against Black-box Face Recognition Models
Moreover, ErasableMask also exhibits outstanding perturbation erasion performance, achieving over 90% erasion success rate.
De-biased Multimodal Electrocardiogram Analysis
We analyzed this phenomenon from a causal perspective in the context of ECG MLLMs and discovered that the confounder, severity of illness, introduces a spurious correlation between the question and answer, leading the model to rely on this spurious correlation and ignore the ECG input.
Translating Electrocardiograms to Cardiac Magnetic Resonance Imaging Useful for Cardiac Assessment and Disease Screening: A Multi-Center Study AI for ECG to CMR Translation Study
Trained on 159, 819 samples from five cohorts, including the UK Biobank (n=42, 483) and MIMIC-IV-ECG (n=164, 550), and externally validated on independent clinical datasets (n=3, 767), CardioNets achieved strong performance across disease screening and phenotype estimation tasks.
Causal Interventions on Causal Paths: Mapping GPT-2's Reasoning From Syntax to Semantics
While interpretability research has shed light on some internal algorithms utilized by transformer-based LLMs, reasoning in natural language, with its deep contextuality and ambiguity, defies easy categorization.
An Efficient System for Automatic Map Storytelling -- A Case Study on Historical Maps
Despite the recent advance of GPT-4 in text recognition and map captioning, it still has a limited understanding of maps, as its performance wanes when texts (e. g., titles and legends) in maps are missing or inaccurate.
Sequential Probability Assignment with Contexts: Minimax Regret, Contextual Shtarkov Sums, and Contextual Normalized Maximum Likelihood
Inspired by the seminal work of Shtarkov (1987) and Rakhlin, Sridharan, and Tewari (2010), we introduce a novel complexity measure, the \emph{contextual Shtarkov sum}, corresponding to the Shtarkov sum after projection onto a multiary context tree, and show that the worst case log contextual Shtarkov sum equals the minimax regret.
TEAM: Temporal Adversarial Examples Attack Model against Network Intrusion Detection System Applied to RNN
With the development of artificial intelligence, neural networks play a key role in network intrusion detection systems (NIDS).
Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals
In this work, we investigate the problem of adapting to the presence or absence of causal structure in multi-armed bandit problems.
InterIntent: Investigating Social Intelligence of LLMs via Intention Understanding in an Interactive Game Context
In this paper, we developed a novel framework, InterIntent, to assess LLMs' social intelligence by mapping their ability to understand and manage intentions in a game setting.
DIP-Watermark: A Double Identity Protection Method Based on Robust Adversarial Watermark
This strategy enhances the representation of universal carrier features, mitigating multi-objective optimization conflicts in watermarking.
STAT: Towards Generalizable Temporal Action Localization
To address this problem, we propose the Generalizable Temporal Action Localization task (GTAL), which focuses on improving the generalizability of action localization methods.
Conversational Disease Diagnosis via External Planner-Controlled Large Language Models
We demonstrated that our system obtained impressive performance in both disease screening and differential diagnoses tasks.
Self-Contradictory Reasoning Evaluation and Detection
For 2), we task the state-of-the-art model GPT-4 with identifying Self-Contra reasoning and finer-grained fallacies.
Dual Defense: Adversarial, Traceable, and Invisible Robust Watermarking against Face Swapping
Dual Defense invisibly embeds a single robust watermark within the target face to actively respond to sudden cases of malicious face swapping.
Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidance
Instead, our approach BOSS (BOotStrapping your own Skills) learns to accomplish new tasks by performing "skill bootstrapping," where an agent with a set of primitive skills interacts with the environment to practice new skills without receiving reward feedback for tasks outside of the initial skill set.
SOAR: Scene-debiasing Open-set Action Recognition
The former prevents the decoder from reconstructing the video background given video features, and thus helps reduce the background information in feature learning.
Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-Text Rationales
Existing metrics like task performance of the LM generating the rationales, or similarity between generated and gold rationales are not good indicators of their human utility.
Handling Concept Drift in Global Time Series Forecasting
Handling concept drift in forecasting is essential for many ML methods in use nowadays, however, the prior work only proposes methods to handle concept drift in the classification domain.
Clustered Federated Learning based on Nonconvex Pairwise Fusion
We propose a clustered FL framework that incorporates a nonconvex penalty to pairwise differences of parameters.
XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models
Explanation-based model debugging aims to resolve spurious biases by showing human users explanations of model behavior, asking users to give feedback on the behavior, then using the feedback to update the model.
Correlation Information Bottleneck: Towards Adapting Pretrained Multimodal Models for Robust Visual Question Answering
In this paper, we aim to improve input robustness from an information bottleneck perspective when adapting pretrained VLMs to the downstream VQA task.
AiM: Taking Answers in Mind to Correct Chinese Cloze Tests in Educational Applications
To automatically correct handwritten assignments, the traditional approach is to use an OCR model to recognize characters and compare them to answers.
ER-Test: Evaluating Explanation Regularization Methods for Language Models
to align with human rationales (Which input tokens would humans focus on?).
Multi-Marginal Contrastive Learning for Multi-Label Subcellular Protein Localization
In this paper, we propose a deep protein subcellular localization method with multi-marginal contrastive learning to perceive the same PSLs in different tissue images and different PSLs within the same tissue image.
LiVLR: A Lightweight Visual-Linguistic Reasoning Framework for Video Question Answering
Video Question Answering (VideoQA), aiming to correctly answer the given question based on understanding multi-modal video content, is challenging due to the rich video content.
Machine Learning for Multimodal Electronic Health Records-based Research: Challenges and Perspectives
Background: Electronic Health Records (EHRs) contain rich information of patients' health history, which usually include both structured and unstructured data.
SGEN: Single-cell Sequencing Graph Self-supervised Embedding Network
This method constructs the graph by the similarity relationship between cells and adopts GCN to analyze the neighbor embedding information of samples, which makes the similar cell closer to each other on the 2D scatter plot.
X-GGM: Graph Generative Modeling for Out-of-Distribution Generalization in Visual Question Answering
In this paper, we formulate OOD generalization in VQA as a compositional generalization problem and propose a graph generative modeling-based training scheme (X-GGM) to implicitly model the problem.
LightFuse: Lightweight CNN based Dual-exposure Fusion
Embedded systems have a huge market, and utilizing DCNNs' powerful functionality into them will further reduce human intervention.
Weakly Supervised Temporal Action Localization Through Learning Explicit Subspaces for Action and Context
To address this challenge, we introduce a framework that learns two feature subspaces respectively for actions and their context.
ACSNet: Action-Context Separation Network for Weakly Supervised Temporal Action Localization
In this paper, we introduce an Action-Context Separation Network (ACSNet) that explicitly takes into account context for accurate action localization.
Ranked #8 on
Weakly Supervised Action Localization
on THUMOS’14
Video Polyp Segmentation
Weakly Supervised Action Localization
Mobile-end Tone Mapping based on Integral Image and Integral Histogram
It is especially crucial for mobile devices because most of the images taken today are from mobile phones, hence such technology is highly demanded in the consumer market of mobile devices and is essential for a good customer experience.
Deep Reformulated Laplacian Tone Mapping
The reformulated Laplacian pyramid always decompose a WDR image into two frequency bands where the low-frequency band is global feature-oriented, and the high-frequency band is local feature-oriented.
Tone Mapping Based on Multi-scale Histogram Synthesis
HVS perceives luminance differently when under different adaptation levels, and therefore our algorithm uses functions built upon different scales to tone map pixels to different values.
WDR FACE: The First Database for Studying Face Detection in Wide Dynamic Range
Furthermore, we show the effect of different face detection procedures on the WDRIs in our database.
A review for Tone-mapping Operators on Wide Dynamic Range Image
The dynamic range of our normal life can exceeds 120 dB, however, the smart-phone cameras and the conventional digital cameras can only capture a dynamic range of 90 dB, which sometimes leads to loss of details for the recorded image.
Detecting Foodborne Illness Complaints in Multiple Languages Using English Annotations Only
To improve performance without extra annotations, we create artificial training documents in the target language through machine translation and train mBERT jointly for the source (English) and target language.
Weakly Supervised Temporal Action Localization Through Contrast Based Evaluation Networks
To address this challenge, we propose the Contrast-based Localization EvaluAtioN Network (CleanNet) with our new action proposal evaluator, which provides pseudo-supervision by leveraging the temporal contrast in snippet-level action classification predictions.
Ranked #15 on
Weakly Supervised Action Localization
on ActivityNet-1.2
(mAP@0.5 metric)
Attention-based Temporal Weighted Convolutional Neural Network for Action Recognition
Research in human action recognition has accelerated significantly since the introduction of powerful machine learning tools such as Convolutional Neural Networks (CNNs).
Detecting Drivable Area for Self-driving Cars: An Unsupervised Approach
Experiments show that our unsupervised approach is efficient and robust for detecting drivable area for self-driving cars.
