Conversational Speech Synthesis (CSS) aims to express a target utterance with the proper speaking style in a user-agent conversation setting. Existing CSS methods employ effective multi-modal context modeling techniques to achieve empathy understanding and expression. However, they often need to design complex network architectures and meticulously optimize the modules within them. In addition, due to the limitations of small-scale datasets containing scripted recording styles, they often fail to simulate real natural conversational styles. To address the above issues, we propose a novel generative expressive CSS system, termed GPT-Talker.We transform the multimodal information of the multi-turn dialogue history into discrete token sequences and seamlessly integrate them to form a comprehensive user-agent dialogue context. Leveraging the power of GPT, we predict the token sequence, that includes both semantic and style knowledge, of response for the agent. After that, the expressive conversational speech is synthesized by the conversation-enriched VITS to deliver feedback to the user.Furthermore, we propose a large-scale Natural CSS Dataset called NCSSD, that includes both naturally recorded conversational speech in improvised styles and dialogues extracted from TV shows. It encompasses both Chinese and English languages, with a total duration of 236 hours.We conducted comprehensive experiments on the reliability of the NCSSD and the effectiveness of our GPT-Talker. Both subjective and objective evaluations demonstrate that our model outperforms other state-of-the-art CSS systems significantly in terms of naturalness and expressiveness. The Code, Dataset, and Pre-trained Model are available at: https://github.com/AI-S2-Lab/GPT-Talker.

Zero-shot dialogue state tracking (DST) seeks to enable dialogue systems to transition to unfamiliar domains without manual annotation or extensive retraining. Prior research has approached this objective by embedding prompts into language models (LMs). Common methodologies include integrating prompts at the input layer or introducing learnable variables at each transformer layer. Nonetheless, each strategy exhibits inherent limitations. Prompts integrated at the input layer risk underutilization, with their impact potentially diminishing across successive transformer layers. Conversely, the addition of learnable variables to each layer can complicate the training process and increase inference latency. To tackle the issues mentioned above, this paper proposes Dual Low-Rank Adaptation (DualLoRA), a plug-and-play architecture designed for zero-shot DST. DualLoRA incorporates two distinct Low-Rank Adaptation (LoRA) components, targeting both dialogue context processing and prompt optimization, to ensure the comprehensive influence of prompts throughout the transformer model layers. This is achieved without incurring additional inference latency, showcasing an efficient integration into existing architectures. Through rigorous evaluation on the MultiWOZ and SGD datasets, DualLoRA demonstrates notable improvements across multiple domains, outperforming traditional baseline methods in zero-shot settings. Our code is accessible at: \url{https://github.com/suntea233/DualLoRA}.

Ontologies are formal representations of knowledge in specific domains that provide a structured framework for organizing and understanding complex information. Creating ontologies, however, is a complex and time-consuming endeavor. ChEBI is a well-known ontology in the field of chemistry, which provides a comprehensive resource for defining chemical entities and their properties. However, it covers only a small fraction of the rapidly growing knowledge in chemistry and does not provide references to the scientific literature. To address this, we propose a methodology that involves augmenting existing annotated text corpora with knowledge from Chebi and fine-tuning a large language model (LLM) to recognize chemical entities and their roles in scientific text. Our experiments demonstrate the effectiveness of our approach. By combining ontological knowledge and the language understanding capabilities of LLMs, we achieve high precision and recall rates in identifying both the chemical entities and roles in scientific literature. Furthermore, we extract them from a set of 8,000 ChemRxiv articles, and apply a second LLM to create a knowledge graph (KG) of chemical entities and roles (CEAR), which provides complementary information to ChEBI, and can help to extend it.

Large language models (LLMs) have gained increasing popularity in robotic task planning due to their exceptional abilities in text analytics and generation, as well as their broad knowledge of the world. However, they fall short in decoding visual cues. LLMs have limited direct perception of the world, which leads to a deficient grasp of the current state of the world. By contrast, the emergence of visual language models (VLMs) fills this gap by integrating visual perception modules, which can enhance the autonomy of robotic task planning. Despite these advancements, VLMs still face challenges, such as the potential for task execution errors, even when provided with accurate instructions. To address such issues, this paper proposes a ReplanVLM framework for robotic task planning. In this study, we focus on error correction interventions. An internal error correction mechanism and an external error correction mechanism are presented to correct errors under corresponding phases. A replan strategy is developed to replan tasks or correct error codes when task execution fails. Experimental results on real robots and in simulation environments have demonstrated the superiority of the proposed framework, with higher success rates and robust error correction capabilities in open-world tasks. Videos of our experiments are available at https://youtu.be/NPk2pWKazJc.

Ophthalmology consultations are crucial for diagnosing, treating, and preventing eye diseases. However, the growing demand for consultations exceeds the availability of ophthalmologists. By leveraging large pre-trained language models, we can design effective dialogues for specific scenarios, aiding in consultations. Traditional fine-tuning strategies for question-answering tasks are impractical due to increasing model size and often ignoring patient-doctor role function during consultations. In this paper, we propose EyeDoctor, an ophthalmic medical questioning large language model that enhances accuracy through doctor-patient role perception guided and an augmented knowledge base with external disease information. Experimental results show EyeDoctor achieves higher question-answering precision in ophthalmology consultations. Notably, EyeDoctor demonstrated a 7.25% improvement in Rouge-1 scores and a 10.16% improvement in F1 scores on multi-round datasets compared to second best model ChatGPT, highlighting the importance of doctor-patient role differentiation and dynamic knowledge base expansion for intelligent medical consultations. EyeDoc also serves as a free available web based service and souce code is available at https://github.com/sperfu/EyeDoc.

Large Language Models (LLMs) have shown significant advances in the past year. In addition to new versions of GPT and Llama, several other LLMs have been introduced recently. Some of these are open models available for download and modification. Although multilingual large language models have been available for some time, their performance on low-resourced languages such as Sinhala has been poor. We evaluated four recent LLMs on their performance directly in the Sinhala language, and by translation to and from English. We also evaluated their fine-tunability with a small amount of fine-tuning data. Claude and GPT 4o perform well out-of-the-box and do significantly better than previous versions. Llama and Mistral perform poorly but show some promise of improvement with fine tuning.

Audio-visual semantic segmentation (AVSS) aims to segment and classify sounding objects in videos with acoustic cues. However, most approaches operate on the close-set assumption and only identify pre-defined categories from training data, lacking the generalization ability to detect novel categories in practical applications. In this paper, we introduce a new task: open-vocabulary audio-visual semantic segmentation, extending AVSS task to open-world scenarios beyond the annotated label space. This is a more challenging task that requires recognizing all categories, even those that have never been seen nor heard during training. Moreover, we propose the first open-vocabulary AVSS framework, OV-AVSS, which mainly consists of two parts: 1) a universal sound source localization module to perform audio-visual fusion and locate all potential sounding objects and 2) an open-vocabulary classification module to predict categories with the help of the prior knowledge from large-scale pre-trained vision-language models. To properly evaluate the open-vocabulary AVSS, we split zero-shot training and testing subsets based on the AVSBench-semantic benchmark, namely AVSBench-OV. Extensive experiments demonstrate the strong segmentation and zero-shot generalization ability of our model on all categories. On the AVSBench-OV dataset, OV-AVSS achieves 55.43% mIoU on base categories and 29.14% mIoU on novel categories, exceeding the state-of-the-art zero-shot method by 41.88%/20.61% and open-vocabulary method by 10.2%/11.6%. The code is available at https://github.com/ruohaoguo/ovavss.

OpenAI has started rolling out its advanced Voice Mode feature. Starting today, a small number of paying ChatGPT users will be able to have a tete-a-tete with the AI chatbot. All ChatGPT Plus members should receive access to the expanded toolset by the fall of this year. In an announcement on X, the company said this advanced version of its Voice Mode "offers more natural, real-time conversations, allows you to interrupt anytime, and senses and responds to your emotions." We're starting to roll out advanced Voice Mode to a small group of ChatGPT Plus users.

Last fall, Eric Klopfer decided to conduct an experiment in his undergraduate computer science class at the Massachusetts Institute of Technology (MIT). He divided the class into three groups and gave them a programming task to solve in the Fortran language, which none of them knew. One group was allowed to use ChatGPT to solve the problem, the second group was told to use Meta's Code Llama large language model (LLM), and the third group could only use Google. The group that used ChatGPT, predictably, solved the problem quickest, while it took the second group longer to solve it. It took the group using Google even longer, because they had to break the task down into components.

Google is running a new commercial during the Olympics. It's about a cute little girl--she's a runner, and she loves Team USA's Sydney McLaughlin-Levrone, a world-record-holding track star who won two Olympic gold medals in 2021. The little girl wants to write her a letter. "Help my daughter write a letter telling Sydney McLaughlin-Levrone how inspiring she is," he asks Google's Gemini. He instructs it to add a line about how his daughter plans to break McLaughlin-Levrone's world record one day (and to be sure to include the phrase sorry, not sorry.)