MAIDCRL: Semi-centralized Multi-Agent Influence Dense-CNN Reinforcement Learning
The study introduces MAIDCRL (Multi-Agent Dense-CNN Reinforcement Learning), a reinforcement learning algorithm that incorporates convolutional layers into…
Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous Driving and Zero-Shot Instruction Following
The paper introduces a new method, Diffusion-ES, that combines gradient-free optimization with trajectory denoising to optimize non-differentiable…
What is Hiding in Medicine’s Dark Matter? Learning with Missing Data in Medical Practices
This research paper discusses the issue of missing data in electronic patient records (EPRs) and its impact…
G-SciEdBERT: A Contextualized LLM for Science Assessment Tasks in German
The article introduces ‘G-SciEdBERT’, a contextualized German Science Education BERT developed for scoring written responses to science…
On the Out-Of-Distribution Generalization of Multimodal Large Language Models
The article investigates the generalization capabilities of Multimodal Large Language Models (MLLMs) under out-of-distribution scenarios and domain-specific…
RQP-SGD: Differential Private Machine Learning through Noisy SGD and Randomized Quantization
The article introduces a new approach, RQP-SGD, for privacy-preserving machine learning. The rise of IoT devices necessitates…
TIC: Translate-Infer-Compile for accurate ‘text to plan’ using LLMs and logical intermediate representations
The article presents a study on the problem of generating plans for given natural language planning task…
Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning
The paper discusses the creation of the Aya Dataset, a multilingual instruction-following dataset spanning 65 languages. The…
Feedback Loops With Language Models Drive In-Context Reward Hacking
The article presents a study on how feedback loops in language models can cause in-context reward hacking…
Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning
The article discusses a computational model designed to mimic how humans infer hidden rules by conducting experiments….