Search Results for author:
Found 28 papers, 16 papers with code
Extract and Merge: Superpixel Segmentation with Regional Attributes
For a certain object in an image, the relationship between its central region and the peripheral region is not well utilized in existing superpixel segmentation methods.
Towards Trustworthy GUI Agents: A Survey
GUI agents, powered by large foundation models, can interact with digital interfaces, enabling various applications in web automation, mobile navigation, and software testing.
Correctness Learning: Deductive Verification Guided Learning for Human-AI Collaboration
Despite significant progress in AI and decision-making technologies in safety-critical fields, challenges remain in verifying the correctness of decision output schemes and verification-result driven design.
Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data
Large multimodal models (LMMs) have shown impressive capabilities in a wide range of visual tasks.
Ranked #1 on
Pneumonia Detection
on Chest X-ray images
SearchRAG: Can Search Engines Be Helpful for LLM-based Medical Question Answering?
Large Language Models (LLMs) have shown remarkable capabilities in general domains but often struggle with tasks requiring specialized knowledge.
Applying Neural Monte Carlo Tree Search to Unsignalized Multi-intersection Scheduling for Autonomous Vehicles
In this paper, we apply Neural Monte Carlo Tree Search (NMCTS) to the challenging task of scheduling platoons of vehicles crossing unsignalized intersections.
Drama: Mamba-Enabled Model-Based Reinforcement Learning Is Sample and Parameter Efficient
Transformers, on the other hand, suffer from the quadratic memory and computational complexity of self-attention mechanisms, scaling as $O(n^2)$, where $n$ is the sequence length.
ECHOPulse: ECG controlled echocardio-grams video generation
Echocardiography (ECHO) is essential for cardiac assessments, but its video quality and interpretation heavily relies on manual expertise, leading to inconsistent results from clinical and portable devices.
MGH Radiology Llama: A Llama 3 70B Model for Radiology
In recent years, the field of radiology has increasingly harnessed the power of artificial intelligence (AI) to enhance diagnostic accuracy, streamline workflows, and improve patient care.
Leveraging Large Language Models with Chain-of-Thought and Prompt Engineering for Traffic Crash Severity Analysis and Inference
The LLMs were tasked with crash severity inference to: (1) evaluate the models' capabilities in crash severity analysis, (2) assess the effectiveness of CoT and domain-informed prompt engineering, and (3) examine the reasoning abilities with the CoT framework.
UCB-driven Utility Function Search for Multi-objective Reinforcement Learning
In Multi-objective Reinforcement Learning (MORL) agents are tasked with optimising decision-making behaviours that trade-off between multiple, possibly conflicting, objectives.
Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages
Besides, the experiments show that there is a strong correlation between the LLM's performance in different languages and the proportion of those languages in its pre-training corpus.
Retrieval-enhanced Knowledge Editing in Language Models for Multi-Hop Question Answering
To tackle the problem, we propose the Retrieval-Augmented model Editing (RAE) framework for multi-hop question answering.
Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era
Therefore, in this paper, we introduce Usable XAI in the context of LLMs by analyzing (1) how XAI can benefit LLMs and AI systems, and (2) how LLMs can contribute to the advancement of XAI.
Automated Natural Language Explanation of Deep Visual Neurons with Large Models
Deep neural networks have exhibited remarkable performance across a wide range of real-world tasks.
MKRAG: Medical Knowledge Retrieval Augmented Generation for Medical Question Answering
Focusing on medical QA, we evaluate the impact of different retrieval models and the number of facts on LLM performance using the MedQA-SMILE dataset.
GiGaMAE: Generalizable Graph Masked Autoencoder via Collaborative Latent Space Reconstruction
By considering embeddings encompassing graph topology and attribute information as reconstruction targets, our model could capture more generalized and comprehensive knowledge.
ENGAGE: Explanation Guided Data Augmentation for Graph Representation Learning
Then, we design two data augmentation schemes on graphs for perturbing structural and feature information, respectively.
Could Small Language Models Serve as Recommenders? Towards Data-centric Cold-start Recommendations
To evaluate our approach, we introduce a cold-start recommendation benchmark, and the results demonstrate that the enhanced small language models can achieve comparable cold-start recommendation performance to that of large models with only $17\%$ of the inference time.
Interpretation of Time-Series Deep Models: A Survey
Deep learning models developed for time-series associated tasks have become more widely researched nowadays.
ChatGraph: Interpretable Text Classification by Converting ChatGPT Knowledge to Graphs
To tackle these limitations, we propose a novel framework that leverages the power of ChatGPT for specific tasks, such as text classification, while improving its interpretability.
Black-box Backdoor Defense via Zero-shot Image Purification
Defending against such attacks is challenging, especially for real-world black-box models where only query access is permitted.
Co-supervised learning paradigm with conditional generative adversarial networks for sample-efficient classification
Classification using supervised learning requires annotating a large amount of classes-balanced data for model training and testing.
Decision-based Black-box Attack Against Vision Transformers via Patch-wise Adversarial Removal
On the other hand, the neglect of noise sensitivity differences between image regions by existing decision-based attacks further compromises the efficiency of noise compression, especially for ViTs.
Domain Adaptation without Model Transferring
Existing unsupervised domain adaptation (UDA) methods can achieve promising performance without transferring data from source domain to target domain.
Exploring Uncertainty in Deep Learning for Construction of Prediction Intervals
In this paper, We explore the uncertainty in deep learning to construct the prediction intervals.
Polishing Decision-Based Adversarial Noise With a Customized Sampling
We propose Customized Adversarial Boundary (CAB) attack that uses the current noise to model the sensitivity of each pixel and polish adversarial noise of each image with a customized sampling setting.
Curls & Whey: Boosting Black-Box Adversarial Attacks
On the one hand, existing iterative attacks add noises monotonically along the direction of gradient ascent, resulting in a lack of diversity and adaptability of the generated iterative trajectories.
