As social media becomes increasingly popular, more and more activities related to public health emerge. Current techniques for public health analysis involve popular models such as BERT and large language models (LLMs). However, the costs of training in-domain LLMs for public health are especially expensive. Furthermore, such kinds of in-domain datasets from social media are generally imbalanced. To tackle these challenges, the data imbalance issue can be overcome by data augmentation and balanced training. Moreover, the ability of the LLMs can be effectively utilized by prompting the model properly. In this paper, a novel ALEX framework is proposed to improve the performance of public health analysis on social media by adopting an LLMs explanation mechanism. Results show that our ALEX model got the best performance among all submissions in both Task 2 and Task 4 with a high score in Task 1 in Social Media Mining for Health 2023 (SMM4H)[1]. Our code has been released at https:// github.com/YanJiangJerry/ALEX.

Large Language Models (LLMs) have significantly impacted numerous domains, including Software Engineering (SE). Many recent publications have explored LLMs applied to various SE tasks. Nevertheless, a comprehensive understanding of the application, effects, and possible limitations of LLMs on SE is still in its early stages. To bridge this gap, we conducted a systematic literature review on LLM4SE, with a particular focus on understanding how LLMs can be exploited to optimize processes and outcomes. We collect and analyze 229 research papers from 2017 to 2023 to answer four key research questions (RQs). In RQ1, we categorize different LLMs that have been employed in SE tasks, characterizing their distinctive features and uses. In RQ2, we analyze the methods used in data collection, preprocessing, and application highlighting the role of well-curated datasets for successful LLM for SE implementation. RQ3 investigates the strategies employed to optimize and evaluate the performance of LLMs in SE. Finally, RQ4 examines the specific SE tasks where LLMs have shown success to date, illustrating their practical contributions to the field. From the answers to these RQs, we discuss the current state-of-the-art and trends, identifying gaps in existing research, and flagging promising areas for future study.

While code-mixing is a common linguistic practice in many parts of the world, collecting high-quality and low-cost code-mixed data remains a challenge for natural language processing (NLP) research. The recent proliferation of Large Language Models (LLMs) compels one to ask: how capable are these systems in generating code-mixed data? In this paper, we explore prompting multilingual LLMs in a zero-shot manner to generate code-mixed data for seven languages in South East Asia (SEA), namely Indonesian, Malay, Chinese, Tagalog, Vietnamese, Tamil, and Singlish. We find that publicly available multilingual instruction-tuned models such as BLOOMZ and Flan-T5-XXL are incapable of producing texts with phrases or clauses from different languages. ChatGPT exhibits inconsistent capabilities in generating code-mixed texts, wherein its performance varies depending on the prompt template and language pairing. For instance, ChatGPT generates fluent and natural Singlish texts (an English-based creole spoken in Singapore), but for English-Tamil language pair, the system mostly produces grammatically incorrect or semantically meaningless utterances. Furthermore, it may erroneously introduce languages not specified in the prompt. Based on our investigation, existing multilingual LLMs exhibit a wide range of proficiency in code-mixed data generation for SEA languages. As such, we advise against using LLMs in this context without extensive human checks.

This paper investigates task-oriented communication for multi-device cooperative edge inference, where a group of distributed low-end edge devices transmit the extracted features of local samples to a powerful edge server for inference. While cooperative edge inference can overcome the limited sensing capability of a single device, it substantially increases the communication overhead and may incur excessive latency. To enable low-latency cooperative inference, we propose a learning-based communication scheme that optimizes local feature extraction and distributed feature encoding in a task-oriented manner, i.e., to remove data redundancy and transmit information that is essential for the downstream inference task rather than reconstructing the data samples at the edge server. Specifically, we leverage an information bottleneck (IB) principle to extract the task-relevant feature at each edge device and adopt a distributed information bottleneck (DIB) framework to formalize a single-letter characterization of the optimal rate-relevance tradeoff for distributed feature encoding. To admit flexible control of the communication overhead, we extend the DIB framework to a distributed deterministic information bottleneck (DDIB) objective that explicitly incorporates the representational costs of the encoded features. As the IB-based objectives are computationally prohibitive for high-dimensional data, we adopt variational approximations to make the optimization problems tractable. To compensate the potential performance loss due to the variational approximations, we also develop a selective retransmission (SR) mechanism to identify the redundancy in the encoded features of multiple edge devices to attain additional communication overhead reduction. Extensive experiments evidence that the proposed task-oriented communication scheme achieves a better rate-relevance tradeoff than baseline methods.

Researchers have trained computer algorithms to analyse underwater audio recordings and can detect patterns that indicate how healthy a reef is. In Australia, AIMS is taking that a step further, through research project Reef Song, where underwater loudspeakers placed on damaged reefs play healthy sounds to help attract fish and boost reef replenishment.

Elon Musk is "wired for war." At least, that's what Musk has told Walter Isaacson, whose thick biography of the mercurial mega-billionaire, Elon Musk, is out this week. When Musk says this, he's not talking about Ukraine, where his Starlink internet service has played a central role. Civilization, Warcraft: Orcs & Humans, The Battle of Polytopia, Elden Ring--Musk has spent much of his life in fantasy worlds. Isaacson's biography includes many astonishing details and relatively few pages focused on Musk's gaming obsession. But the video-game detail is telling. Musk doesn't seem to inhabit our reality, exactly, even as he profoundly shapes it.

Sharifa Alghowinem, a research scientist in the Media Lab's Personal Robots Group, poses with Jibo, a friendly robot companion developed by Professor Cynthia Breazeal. "As a child, I wished for a robot that would explain others' emotions to me" says Sharifa Alghowinem, a research scientist in the Media Lab's Personal Robots Group (PRG). Growing up in Saudi Arabia, Alghowinem says she dreamed of coming to MIT one day to develop Arabic-based technologies, and of creating a robot that could help herself and others navigate a complex world. In her early life, Alghowinem faced difficulties with understanding social cues and never scored well on standardized tests, but her dreams carried her through. She earned an undergraduate degree in computing before leaving home to pursue graduate education in Australia.

Recent years have seen significant progress in the realm of robot autonomy, accompanied by the expanding reach of robotic technologies. However, the emergence of new deployment domains brings unprecedented challenges in ensuring safe operation of these systems, which remains as crucial as ever. While traditional model-based safe control methods struggle with generalizability and scalability, emerging data-driven approaches tend to lack well-understood guarantees, which can result in unpredictable catastrophic failures. Successful deployment of the next generation of autonomous robots will require integrating the strengths of both paradigms. This article provides a review of safety filter approaches, highlighting important connections between existing techniques and proposing a unified technical framework to understand, compare, and combine them. The new unified view exposes a shared modular structure across a range of seemingly disparate safety filter classes and naturally suggests directions for future progress towards more scalable synthesis, robust monitoring, and efficient intervention.

This paper describes a system developed for the GENEA (Generation and Evaluation of Non-verbal Behaviour for Embodied Agents) Challenge 2023. Our solution builds on an existing diffusion-based motion synthesis model. We propose a contrastive speech and motion pretraining (CSMP) module, which learns a joint embedding for speech and gesture with the aim to learn a semantic coupling between these modalities. The output of the CSMP module is used as a conditioning signal in the diffusion-based gesture synthesis model in order to achieve semantically-aware co-speech gesture generation. Our entry achieved highest human-likeness and highest speech appropriateness rating among the submitted entries. This indicates that our system is a promising approach to achieve human-like co-speech gestures in agents that carry semantic meaning.

Recent years have witnessed rapid progress in observations of the Epoch of Reionization (EoR). These have enabled high-dimensional inference of galaxy and intergalactic medium (IGM) properties during the first billion years of our Universe. However, even using efficient, semi-numerical simulations, traditional inference approaches that compute 3D lightcones on-the-fly can take $10^5$ core hours. Here we present 21cmEMU: an emulator of several summary observables from the popular 21cmFAST simulation code. 21cmEMU takes as input nine parameters characterizing EoR galaxies, and outputs the following summary statistics: (i) the IGM mean neutral fraction; (ii) the 21-cm power spectrum; (iii) the mean 21-cm spin temperature; (iv) the sky-averaged (global) 21-cm signal; (vi) the ultraviolet (UV) luminosity functions (LFs); and (vii) the Thomson scattering optical depth to the cosmic microwave background (CMB). All observables are predicted with sub-percent median accuracy, with a reduction of the computational cost by a factor of over 10$^4$. After validating inference results, we showcase a few applications, including: (i) quantifying the relative constraining power of different observational datasets; (ii) seeing how recent claims of a late EoR impact previous inferences; and (iii) forecasting upcoming constraints from the sixth observing season of the Hydrogen Epoch of Reionization Array (HERA) telescope. 21cmEMU is publicly-available, and is included as an alternative simulator in the public 21CMMC sampler.