initial collection
SurveyAgent: A Conversational System for Personalized and Efficient Research Survey
Wang, Xintao, Chen, Jiangjie, Li, Nianqi, Chen, Lida, Yuan, Xinfeng, Shi, Wei, Ge, Xuyang, Xu, Rui, Xiao, Yanghua
In the rapidly advancing research fields such as AI, managing and staying abreast of the latest scientific literature has become a significant challenge for researchers. Although previous efforts have leveraged AI to assist with literature searches, paper recommendations, and question-answering, a comprehensive support system that addresses the holistic needs of researchers has been lacking. This paper introduces SurveyAgent, a novel conversational system designed to provide personalized and efficient research survey assistance to researchers. SurveyAgent integrates three key modules: Knowledge Management for organizing papers, Recommendation for discovering relevant literature, and Query Answering for engaging with content on a deeper level. This system stands out by offering a unified platform that supports researchers through various stages of their literature review process, facilitated by a conversational interface that prioritizes user interaction and personalization. Our evaluation demonstrates SurveyAgent's effectiveness in streamlining research activities, showcasing its capability to facilitate how researchers interact with scientific literature.
The Morning After: Connected dumbbells that Amazon's Alexa can adjust
WFH didn't just mean working from home. For those with the drive, it also stood for workouts from home. Many companies boomed as they adjusted to many of us shifting our training and exercise from gym to living room / spare room / that corner of the bedroom. Now, the pendulum is swinging back as some gyms tentatively reopen, and we return to the squat rack that didn't quite fit into our tiny studio apartment. But that won't stop fitness companies from introducing new blends of gear with tech tricks, hoping you'll be willing to upgrade your gear.
Dreamstime Leverages Machine Learning to Launch Megapixl.com - Site Uses Dreamstime's Artificial
The initial collection on Megapixl.com is curated based on editor's feedback and customer behaviors that rate images and place them within certain ranks in the collection. Once the site is launched, the machine learning platform will take gathered user data into account and offer refinements to the Dreamstime.com Content on the site includes photos, vector art, and video content representing several categories including abstract, business, people, editorial, 2D & 3D Animation, Video Production Elements, Technology, and Travel. "By launching MegaPixl we give users access to an incredible collection that is curated by humans and then further improved and customized by machine learning tools that learn past behaviors to make dynamic recommendations," said Serban Enache, CEO and co-founder, Dreamstime. "The initial collection on Megapixl is already curated because we've accounted for user's actions so we know how images will be rated and placed within the collection. Megapixl is designed as a first stop for designers because we are effectively using the designer community to help itself by basing the collection on designer behaviors. Users will come to the site to find the right image quickly – giving them more time to focus on their designs."
A Complete Algorithm for Generating Landmarks
Bonet, Blai (Universidad Simon Bolivar) | Castillo, Julio (Universidad Simon Bolivar)
A collection of landmarks is complete if the cost of a minimum-cost hitting set equals h + and there is a minimum-cost hitting set that is an optimal relaxed plan. We present an algorithm for generating a complete collection of landmarks and we show that this algorithm can be extended into effective polytime heuristics for optimal and satisficing planning. The new admissible heuristics are compared with current state-of-the-art heuristics for optimal planning on benchmark problems from the IPC.