Search Results for author:
Found 20 papers, 10 papers with code
MILE: A Mutation Testing Framework of In-Context Learning Systems
In this work, inspired by the foundations of adopting testing techniques in machine learning (ML) systems, we propose a mutation testing framework designed to characterize the quality and effectiveness of test data for ICL systems.
ShapeICP: Iterative Category-level Object Pose and Shape Estimation from Depth
The task is particularly challenging because the three unknowns, object pose, object shape, and model-to-measurement correspondences, are compounded together but only a single view of depth measurements is provided.
Automata Extraction from Transformers
To improve the transparency of ML systems, automata extraction methods, which interpret stateful ML models as automata typically through formal languages, have proven effective for explaining the mechanism of recurrent neural networks (RNNs).
Boosting Jailbreak Attack with Momentum
Recently, the Greedy Coordinate Gradient (GCG) attack has demonstrated efficacy in exploiting this vulnerability by optimizing adversarial prompts through a combination of gradient heuristics and greedy search.
Exploring the Robustness of In-Context Learning with Noisy Labels
In this paper, inspired by prior research that studies ICL ability using simple function classes, we take a closer look at this problem by investigating the robustness of Transformers against noisy labels.
Towards General Conceptual Model Editing via Adversarial Representation Engineering
Since the development of Large Language Models (LLMs) has achieved remarkable success, understanding and controlling their internal complex mechanisms has become an urgent problem.
Heuristic Optimization of Amplifier Reconfiguration Process for Autonomous Driving Optical Networks
We propose a heuristic-based optimization scheme for reliable optical amplifier reconfiguration process in ADON.
On the Duality Between Sharpness-Aware Minimization and Adversarial Training
Instead of perturbing the samples, Sharpness-Aware Minimization (SAM) perturbs the model weights during training to find a more flat loss landscape and improve generalization.
Building a digital twin of EDFA: a grey-box modeling approach
To enable intelligent and self-driving optical networks, high-accuracy physical layer models are required.
Weighted Automata Extraction and Explanation of Recurrent Neural Networks for Natural Language Tasks
In this paper, we propose a novel framework of Weighted Finite Automata (WFA) extraction and explanation to tackle the limitations for natural language tasks.
Sharpness-Aware Minimization Alone can Improve Adversarial Robustness
In this paper, we explore SAM in the context of adversarial robustness.
Using Z3 for Formal Modeling and Verification of FNN Global Robustness
To evaluate the effectiveness of our implementation and improvements, we conduct extensive experiments on a set of benchmark datasets.
A Grey-box Launch-profile Aware Model for C+L Band Raman Amplification
Based on the physical features of Raman amplification, we propose a three-step modelling scheme based on neural networks (NN) and linear regression.
Physics-informed EDFA Gain Model Based on Active Learning
We propose a physics-informed EDFA gain model based on the active learning method.
A Front-End for Dense Monocular SLAM using a Learned Outlier Mask Prior
Recent achievements in depth prediction from a single RGB image have powered the new research area of combining convolutional neural networks (CNNs) with classical simultaneous localization and mapping (SLAM) algorithms.
Bootstrapped Self-Supervised Training with Monocular Video for Semantic Segmentation and Depth Estimation
For a robot deployed in the world, it is desirable to have the ability of autonomous learning to improve its initial pre-set knowledge.
Deep reinforcement learning with a particle dynamics environment applied to emergency evacuation of a room with obstacles
Overall, we show that our model can efficiently simulate emergency evacuation in complex environments with multiple room exits and obstacles where it is difficult to obtain an intuitive rule for fast evacuation.
FasterRCNN Monitoring of Road Damages: Competition and Deployment
Maintaining aging infrastructure is a challenge currently faced by local and national administrators all around the world.
A deep reinforcement learning model based on deterministic policy gradient for collective neural crest cell migration
Because of the different migration mechanisms of leader and follower neural crest cells, we train two types of agents (leaders and followers) to learn the collective cell migration behavior.
Local Contrast Learning
We focus on one-shot classification by deep learning approach based on a small quantity of training samples.
