AI
-
AI-Generated Content in Cross-Domain Applications: Research Trends, Challenges and Propositions
Source: arXiv AI PapersRead more: AI-Generated Content in Cross-Domain Applications: Research Trends, Challenges and PropositionsThis paper discusses the rapid evolution of Artificial Intelligence Generated Content (AIGC) across various sectors. It provides insights into its…
-
VideoAgent: Personalized Synthesis of Scientific Videos
Source: arXiv AI PapersRead more: VideoAgent: Personalized Synthesis of Scientific VideosVideoAgent introduces a new method for automating the creation of personalized scientific videos. It utilizes a conversational interface to parse…
-
MAPGD: Multi-Agent Prompt Gradient Descent for Collaborative Prompt Optimization
Source: arXiv AI PapersRead more: MAPGD: Multi-Agent Prompt Gradient Descent for Collaborative Prompt OptimizationMAPGD is a novel framework aimed at enhancing prompt optimization for large language models. By integrating multi-agent collaboration, it improves…
-
Task Decoding based on Eye Movements using Synthetic Data Augmentation
Source: arXiv AI PapersRead more: Task Decoding based on Eye Movements using Synthetic Data AugmentationThis paper explores the integration of synthetic data in eye-tracking research to boost task decoding accuracy. By employing popular synthetic…
-
A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models
Source: arXiv AI PapersRead more: A Survey of Reasoning and Agentic Systems in Time Series with Large Language ModelsThis survey defines and organizes the literature on time series reasoning into distinct topologies. It evaluates methods based on their…
-
HeLoFusion: An Efficient and Scalable Encoder for Modeling Heterogeneous and Multi-Scale Interactions in Trajectory Prediction
Source: arXiv AI PapersRead more: HeLoFusion: An Efficient and Scalable Encoder for Modeling Heterogeneous and Multi-Scale Interactions in Trajectory PredictionHeLoFusion introduces a new method for modeling multi-agent trajectory prediction in autonomous driving. The approach focuses on local, multi-scale interactions,…
-
Learning Representations in Video Game Agents with Supervised Contrastive Imitation Learning
Source: arXiv AI PapersRead more: Learning Representations in Video Game Agents with Supervised Contrastive Imitation LearningThis paper presents a novel approach using Supervised Contrastive Learning (SupCon) within the context of Imitation Learning (IL) for video…
-
EgoMem: Lifelong Memory Agent for Full-duplex Omnimodal Models
Source: arXiv AI PapersRead more: EgoMem: Lifelong Memory Agent for Full-duplex Omnimodal ModelsEgoMem is the first lifelong memory agent designed for full-duplex models that process real-time audiovisual streams. It enables the recognition…
-
BuildingGym: An open-source toolbox for AI-based building energy management using reinforcement learning
Source: arXiv AI PapersRead more: BuildingGym: An open-source toolbox for AI-based building energy management using reinforcement learningBuildingGym is an innovative open-source tool designed for training reinforcement learning (RL) control strategies in building energy management. It integrates…
-
Neuromorphic Intelligence
Source: arXiv AI PapersRead more: Neuromorphic IntelligenceNeuromorphic computing aims to achieve energy efficiency similar to the human brain by leveraging insights from various scientific fields. This…