It is the subfield of computer science that focuses on creating systems capable of intelligent behavior, including problem solving, learning, adaptation, perception, and language understanding.
This academic paper discusses the challenge of integrating multiple robotic and Artificial Intelligence (AI) techniques to model complex robot behaviour. The authors propose using a formal framework to map the…
Continue readingThe authors of this paper delve into the reasoning capabilities of Large Language Models (LLMs), particularly GPT-4. Initially, there was optimism that reasoning might automatically emerge with scale, but this…
Continue readingThis research paper presents Safety-Gymnasium, an environment suite for safety-critical tasks in both single and multi-agent scenarios in AI learning. It also introduces a library called Safe Policy Optimization, which…
Continue readingThe paper presents a neuro-symbolic framework, PSYCHIC, developed for the Scholarly Question Answering over Linked Data (Scholarly QALD) challenge at The International Semantic Web Conference 2023. This challenge focuses on…
Continue readingThe researchers from Peking University have proposed a novel algorithm, Safe Reinforcement Learning from Human Feedback (Safe RLHF), aimed at enhancing the safety and performance of Large Language Models (LLMs)….
Continue readingThe research paper presents a solution for complex planning problem-solving that ensures completeness. The authors propose a hybrid search method that combines high-level and low-level actions, called a complete subgoal…
Continue readingThis research paper introduces a U-Net-based network that uses spatio-temporal features with cross-attention transformers to extract information from historical maps. This method addresses the challenges of data-dependent uncertainty in the…
Continue readingThe paper focuses on the detection of heart disease through ECG images using advanced technologies, specifically vision transformer models. These models include Google-Vit, Microsoft-Beit, and Swin-Tiny. The study emphasizes the…
Continue readingThis research presents a Multimodal Interlaced Transformer (MIT) for weakly supervised point cloud segmentation that jointly considers 2D and 3D data. Current methods require extra 2D annotations to achieve 2D-3D…
Continue readingThis research paper reveals that Large Language Models (LLMs), despite being trained solely on textual data, are surprisingly effective encoders for purely visual tasks. This is achieved by using a…
Continue readingLooks like you're using an ad blocker. Please support us by disabling these ad blocker.
