As people become more aware of their food choices, food computation models have become increasingly popular in assisting people in maintaining healthy eating habits. For example, food recommendation systems analyze recipe instructions to assess nutritional contents and provide recipe recommendations. The recent and remarkable successes of generative AI methods, such as auto-regressive large language models, can lead to robust methods for a more comprehensive understanding of recipes for healthy food recommendations beyond surface-level nutrition content assessments. In this study, we explore the use of generative AI methods to extend current food computation models, primarily involving the analysis of nutrition and ingredients, to also incorporate cooking actions (e.g., add salt, fry the meat, boil the vegetables, etc.). Cooking actions are notoriously hard to model using statistical learning methods due to irregular data patterns - significantly varying natural language descriptions for the same action (e.g., marinate the meat vs. marinate the meat and leave overnight) and infrequently occurring patterns (e.g., add salt occurs far more frequently than marinating the meat). The prototypical approach to handling irregular data patterns is to increase the volume of data that the model ingests by orders of magnitude. Unfortunately, in the cooking domain, these problems are further compounded with larger data volumes presenting a unique challenge that is not easily handled by simply scaling up. In this work, we propose novel aggregation-based generative AI methods, Cook-Gen, that reliably generate cooking actions from recipes, despite difficulties with irregular data patterns, while also outperforming Large Language Models and other strong baselines.

AI models have shown promise in many medical imaging tasks. However, our ability to explain what signals these models have learned is severely lacking. Explanations are needed in order to increase the trust in AI-based models, and could enable novel scientific discovery by uncovering signals in the data that are not yet known to experts. In this paper, we present a method for automatic visual explanations leveraging team-based expertise by generating hypotheses of what visual signals in the images are correlated with the task. We propose the following 4 steps: (i) Train a classifier to perform a given task (ii) Train a classifier guided StyleGAN-based image generator (StylEx) (iii) Automatically detect and visualize the top visual attributes that the classifier is sensitive towards (iv) Formulate hypotheses for the underlying mechanisms, to stimulate future research. Specifically, we present the discovered attributes to an interdisciplinary panel of experts so that hypotheses can account for social and structural determinants of health. We demonstrate results on eight prediction tasks across three medical imaging modalities: retinal fundus photographs, external eye photographs, and chest radiographs. We showcase examples of attributes that capture clinically known features, confounders that arise from factors beyond physiological mechanisms, and reveal a number of physiologically plausible novel attributes. Our approach has the potential to enable researchers to better understand, improve their assessment, and extract new knowledge from AI-based models. Importantly, we highlight that attributes generated by our framework can capture phenomena beyond physiology or pathophysiology, reflecting the real world nature of healthcare delivery and socio-cultural factors. Finally, we intend to release code to enable researchers to train their own StylEx models and analyze their predictive tasks.

Warning: This paper contains several contents that may be toxic, harmful, or offensive. In the last few years, text-to-image generative models have gained remarkable success in generating images with unprecedented quality accompanied by a breakthrough of inference speed. Despite their rapid progress, human biases that manifest in the training examples, particularly with regard to common stereotypical biases, like gender and skin tone, still have been found in these generative models. In this work, we seek to measure more complex human biases exist in the task of text-to-image generations. Inspired by the well-known Implicit Association Test (IAT) from social psychology, we propose a novel Text-to-Image Association Test (T2IAT) framework that quantifies the implicit stereotypes between concepts and valence, and those in the images. We replicate the previously documented bias tests on generative models, including morally neutral tests on flowers and insects as well as demographic stereotypical tests on diverse social attributes. The results of these experiments demonstrate the presence of complex stereotypical behaviors in image generations.

Conversational generative AI has demonstrated remarkable promise for empowering biomedical practitioners, but current investigations focus on unimodal text. Multimodal conversational AI has seen rapid progress by leveraging billions of image-text pairs from the public web, but such general-domain vision-language models still lack sophistication in understanding and conversing about biomedical images. In this paper, we propose a cost-efficient approach for training a visionlanguage conversational assistant that can answer open-ended research questions of biomedical images. The key idea is to leverage a large-scale, broad-coverage biomedical figure-caption dataset extracted from PubMed Central, use GPT-4 to self-instruct open-ended instruction-following data from the captions, and then fine-tune a large general-domain vision-language model using a novel curriculum learning method. Specifically, the model first learns to align biomedical vocabulary using the figure-caption pairs as is, then learns to master open-ended conversational semantics using GPT-4 generated instruction-following data, broadly mimicking how a layperson gradually acquires biomedical knowledge. This enables us to train a Large Language and Vision Assistant for BioMedicine (LLaVA-Med) in less than 15 hours (with eight A100s). LLaVA-Med exhibits excellent multimodal conversational capability and can follow open-ended instruction to assist with inquiries about a biomedical image. On three standard biomedical visual question answering datasets, fine-tuning LLaVA-Med outperforms previous supervised state-of-the-art on certain metrics. To facilitate biomedical multimodal research, we will release our instruction-following data and the LLaVA-Med model.

Artificial Intelligence Generated Content (AIGC) is one of the latest achievements in AI development. The content generated by related applications, such as text, images and audio, has sparked a heated discussion. Various derived AIGC applications are also gradually entering all walks of life, bringing unimaginable impact to people's daily lives. However, the rapid development of such generative tools has also raised concerns about privacy and security issues, and even copyright issues in AIGC. We note that advanced technologies such as blockchain and privacy computing can be combined with AIGC tools, but no work has yet been done to investigate their relevance and prospect in a systematic and detailed way. Therefore it is necessary to investigate how they can be used to protect the privacy and security of data in AIGC by fully exploring the aforementioned technologies. In this paper, we first systematically review the concept, classification and underlying technologies of AIGC. Then, we discuss the privacy and security challenges faced by AIGC from multiple perspectives and purposefully list the countermeasures that currently exist. We hope our survey will help researchers and industry to build a more secure and robust AIGC system.

Generative neural models hold great promise in enhancing programming education by synthesizing new content for students. We seek to design neural models that can automatically generate programming tasks for a given specification in the context of visual programming domains. Despite the recent successes of large generative models like GPT-4, our initial results show that these models are ineffective in synthesizing visual programming tasks and struggle with logical and spatial reasoning. We propose a novel neuro-symbolic technique, NeurTaskSyn, that can synthesize programming tasks for a specification given in the form of desired programming concepts exercised by its solution code and constraints on the visual task. NeurTaskSyn has two components: the first component is trained via imitation learning procedure to generate possible solution codes, and the second component is trained via reinforcement learning procedure to guide an underlying symbolic execution engine that generates visual tasks for these codes. We demonstrate the effectiveness of NeurTaskSyn through an extensive empirical evaluation and a qualitative study on reference tasks taken from the Hour of Code: Classic Maze challenge by Code-dot-org and the Intro to Programming with Karel course by CodeHS-dot-com.

In the paradigm of AI-generated content (AIGC), there has been increasing attention in extending pre-trained text-to-image (T2I) models to text-to-video (T2V) generation. Despite their effectiveness, these frameworks face challenges in maintaining consistent narratives and handling rapid shifts in scene composition or object placement from a single user prompt. This paper introduces a new framework, dubbed DirecT2V, which leverages instruction-tuned large language models (LLMs) to generate frame-by-frame descriptions from a single abstract user prompt. DirecT2V utilizes LLM directors to divide user inputs into separate prompts for each frame, enabling the inclusion of time-varying content and facilitating consistent video generation. To maintain temporal consistency and prevent object collapse, we propose a novel value mapping method and dual-softmax filtering. Extensive experimental results validate the effectiveness of the DirecT2V framework in producing visually coherent and consistent videos from abstract user prompts, addressing the challenges of zero-shot video generation.

Center for A.I. Safety Director Dan Hendrycks explains concerns about how the rapid growth of artificial intelligence could impact society. Secretary of State Antony Blinken said Wednesday that the United States is working with its European allies to develop a conduct code for artificial intelligence. Blinken is in Sweden for a meeting of the EU-U.S. Trade and Technology Council, which is jointly led by American and European officials. "We need accountable artificial intelligence. Generative AI is a complete game changer," European Commission Vice President Margrethe Vestager said at a press conference after the meeting, saying a draft of a voluntary code of conduct for artificial intelligence would be ready within a matter of weeks.

Almost 60% of people would like to see the UK government regulate the use of generative AI technologies such as ChatGPT in the workplace to help safeguard jobs, according to a survey. As leading figures in the tech industry call for restrictions on the rapid development of AI, research by the Prospect trade union suggests strong public support for regulation. In a survey of more than 1,000 people last month, 58% agreed that "the government should set rules around the use of generative AI to protect workers' jobs". Just 12% said the government should not interfere because "the benefits are likely to outweigh any costs". Employers have used various forms of AI for some time – including in target-setting, and hiring and firing decisions – but the salience of the technologies has increased dramatically since the release of ChatGPT, which hit 100 million users within two months of launch.

Last week, I went on the CBC News podcast "Nothing Is Foreign" to talk about the draft regulation--and what it means for the Chinese government to take such quick action on a still-very-new technology. As I said in the podcast, I see the draft regulation as a mixture of sensible restrictions on AI risks and a continuation of China's strong government tradition of aggressive intervention in the tech industry. Many of the clauses in the draft regulation are principles that AI critics are advocating for in the West: data used to train generative AI models shouldn't infringe on intellectual property or privacy; algorithms shouldn't discriminate against users on the basis of race, ethnicity, age, gender, and other attributes; AI companies should be transparent about how they obtained training data and how they hired humans to label the data. At the same time, there are rules that other countries would likely balk at. The government is asking that people who use these generative AI tools register with their real identity--just as on any social platform in China.