Open-domain dialogue systems aim to generate natural and engaging conversations, providing significant practical value in real applications such as social robotics and personal assistants. The advent of large language models (LLMs) has greatly advanced this field by improving context understanding and conversational fluency. However, existing LLM-based dialogue systems often fall short in proactively understanding the user's chatting preferences and guiding conversations toward user-centered topics. This lack of user-oriented proactivity can lead users to feel unappreciated, reducing their satisfaction and willingness to continue the conversation in human-computer interactions. To address this issue, we propose a User-oriented Proactive Chatbot (UPC) to enhance the user-oriented proactivity. Specifically, we first construct a critic to evaluate this proactivity inspired by the LLM-as-a-judge strategy. Given the scarcity of high-quality training data, we then employ the critic to guide dialogues between the chatbot and user agents, generating a corpus with enhanced user-oriented proactivity. To ensure the diversity of the user backgrounds, we introduce the ISCO-800, a diverse user background dataset for constructing user agents. Moreover, considering the communication difficulty varies among users, we propose an iterative curriculum learning method that trains the chatbot from easy-to-communicate users to more challenging ones, thereby gradually enhancing its performance. Experiments demonstrate that our proposed training method is applicable to different LLMs, improving user-oriented proactivity and attractiveness in open-domain dialogues.

Narrative systems, such as dialogue and storytelling systems, often utilize persona profiles to enhance personalized interactions. Existing persona profiles frequently exhibit biases, posing risks to system integrity and fairness. To address this, we introduce the UPCS framework, which categorizes character descriptions into eight dimensions, including bias mitigation strategies. Experimental results demonstrate UPCS's superiority in accuracy, diversity, bias elimination, and user satisfaction, marking a significant advancement in persona construction for reliable narrative systems.

The AI and Music S T ARTS Festival, organised by Sónar, Universitat Politècnica de Catalunya (UPC) and Betevé on 27-28 October comprised more than 100 activities that combined music and AI. The event gathered musicians, scientists and artists from across the world who gave exclusive live presentations of their work and experiments with AI. One of the main initiatives of the AI and Music S T ARTS Festival, and one which transcended the event, was the creation of Thinking Lab, an applied research lab where participants can explore the interrelation between AI and musical creativity, and, ultimately, the interaction between people and machines. The Thinking Lab is led by the Intelligent Data Science and Artificial Intelligence Research Centre (IDEAI-UPC) and the Centre for Image and Multimedia Technology (CITM), both at UPC, and coordinated together with Sónar. In this space of debate and co-creation, which has been in place since April, scientists, artists and other professionals exchange experiences and knowledge that has contributed to some of the presentations and performances at the festival.

HOW can a patent office seriously assert that it is serious about innovation when everyone who meets the officials comes from law firms and rarely has any scientific background? If this system's inception truly dates back to need to advance science, shouldn't these officials focus on actual scientists? This may sound like a shallow observation, but it perfectly describes the pattern we've been seeing at the European Patent Office (EPO) under António Campinos and his predecessor Battistelli (neither of whom has any background in the sciences). Seeing how the U.S. Patent and Trademark Office (USPTO) wants to work around 35 U.S.C. § 101, we're nowadays witnessing a similar trend in America too. A resurgence of software patents in Europe poses risk to US (case)law as well. We hope that American readers understand that. The EPO openly brags about objectives like spreading software patents to the whole world.