Search Results for author:
Found 14 papers, 3 papers with code
Reinforcement Learning of Self Enhancing Camera Image and Signal Processing
Our \textit{Recursive Self Enhancement Reinforcement Learning}(RSE-RL) model views the identification and correction of artifacts as a recursive self-learning and self-improvement exercise and consists of two major sub-modules: (i) The latent feature sub-space clustering/grouping obtained through variational auto-encoders enabling rapid identification of the correspondence and discrepancy between noisy and clean image patches.
Deep Contrastive Patch-Based Subspace Learning for Camera Image Signal Processing
Camera Image Signal Processing (ISP) pipelines can get appealing results in different image signal processing tasks.
A Survey on Reinforcement Learning for Combinatorial Optimization
This paper gives a detailed review of reinforcement learning (RL) in combinatorial optimization, introduces the history of combinatorial optimization starting in the 1950s, and compares it with the RL algorithms of recent years.
Identifying Mislabeled Images in Supervised Learning Utilizing Autoencoder
Supervised learning is based on the assumption that the ground truth in the training data is accurate.
Training Heterogeneous Features in Sequence to Sequence Tasks: Latent Enhanced Multi-filter Seq2Seq Model
A latent space transformation is applied for enhancing the quality of the representations.
Self-Enhancing Multi-filter Sequence-to-Sequence Model
As for the main contribution, we design a self-enhancing mechanism that uses a reinforcement learning algorithm to optimize the clustering algorithm without additional training data.
On the Privacy Risks of Deploying Recurrent Neural Networks in Machine Learning Models
Additionally, we study the effectiveness of two prominent mitigation methods for preempting MIAs, namely weight regularization and differential privacy.
Additive Logistic Mechanism for Privacy-Preserving Self-Supervised Learning
We study the privacy risks that are associated with training a neural network's weights with self-supervised learning algorithms.
Automaton-Based Representations of Task Knowledge from Generative Language Models
However, the textual outputs from GLMs cannot be formally verified or used for sequential decision-making.
Multimodal Pretrained Models for Sequential Decision-Making: Synthesis, Verification, Grounding, and Perception
We develop an algorithm that utilizes the knowledge from pretrained models to construct and verify controllers for sequential decision-making tasks, and to ground these controllers to task environments through visual observations.
On the Planning, Search, and Memorization Capabilities of Large Language Models
The rapid advancement of large language models, such as the Generative Pre-trained Transformer (GPT) series, has had significant implications across various disciplines.
Specification-Driven Video Search via Foundation Models and Formal Verification
The increasing abundance of video data enables users to search for events of interest, e. g., emergency incidents.
Fine-Tuning Language Models Using Formal Methods Feedback
Although pre-trained language models encode generic knowledge beneficial for planning and control, they may fail to generate appropriate control policies for domain-specific tasks.
Neuro-Symbolic Video Search
The unprecedented surge in video data production in recent years necessitates efficient tools to extract meaningful frames from videos for downstream tasks.
