Large language models have become multimodal, and many of them are said to integrate their modalities using common representations. If this were true, a drawing of a car as an image, for instance, should map to a similar area in the latent space as a textual description of the strokes that form the drawing. To explore this in a black-box access regime to these models, we propose the use of machine teaching, a theory that studies the minimal set of examples a teacher needs to choose so that the learner captures the concept. In this paper, we evaluate the complexity of teaching vision-language models a subset of objects in the Quick, Draw! dataset using two presentations: raw images as bitmaps and trace coordinates in TikZ format. The results indicate that image-based representations generally require fewer segments and achieve higher accuracy than coordinate-based representations. But, surprisingly, the teaching size usually ranks concepts similarly across both modalities, even when controlling for (a human proxy of) concept priors, suggesting that the simplicity of concepts may be an inherent property that transcends modality representations.

Free-text rationales play a pivotal role in explainable NLP, bridging the knowledge and reasoning gaps behind a model's decision-making. However, due to the diversity of potential reasoning paths and a corresponding lack of definitive ground truth, their evaluation remains a challenge. Existing evaluation metrics rely on the degree to which a rationale supports a target label, but we find these fall short in evaluating rationales that inadvertently leak the labels. To address this problem, we propose RORA, a Robust free-text Rationale evaluation against label leakage. RORA quantifies the new information supplied by a rationale to justify the label. This is achieved by assessing the conditional V-information \citep{hewitt-etal-2021-conditional} with a predictive family robust against leaky features that can be exploited by a small model. RORA consistently outperforms existing approaches in evaluating human-written, synthetic, or model-generated rationales, particularly demonstrating robustness against label leakage. We also show that RORA aligns well with human judgment, providing a more reliable and accurate measurement across diverse free-text rationales.

In this work, we present Vlogger, a generic AI system for generating a minute-level video blog (i.e., vlog) of user descriptions. Different from short videos with a few seconds, vlog often contains a complex storyline with diversified scenes, which is challenging for most existing video generation approaches. To break through this bottleneck, our Vlogger smartly leverages Large Language Model (LLM) as Director and decomposes a long video generation task of vlog into four key stages, where we invoke various foundation models to play the critical roles of vlog professionals, including (1) Script, (2) Actor, (3) ShowMaker, and (4) Voicer. With such a design of mimicking human beings, our Vlogger can generate vlogs through explainable cooperation of top-down planning and bottom-up shooting. Moreover, we introduce a novel video diffusion model, ShowMaker, which serves as a videographer in our Vlogger for generating the video snippet of each shooting scene. By incorporating Script and Actor attentively as textual and visual prompts, it can effectively enhance spatial-temporal coherence in the snippet. Besides, we design a concise mixed training paradigm for ShowMaker, boosting its capacity for both T2V generation and prediction. Finally, the extensive experiments show that our method achieves state-of-the-art performance on zero-shot T2V generation and prediction tasks. More importantly, Vlogger can generate over 5-minute vlogs from open-world descriptions, without loss of video coherence on script and actor. The code and model is all available at https://github.com/zhuangshaobin/Vlogger.

We present GLM-Dialog, a large-scale language model (LLM) with 10B parameters capable of knowledge-grounded conversation in Chinese using a search engine to access the Internet knowledge. GLM-Dialog offers a series of applicable techniques for exploiting various external knowledge including both helpful and noisy knowledge, enabling the creation of robust knowledge-grounded dialogue LLMs with limited proper datasets. To evaluate the GLM-Dialog more fairly, we also propose a novel evaluation method to allow humans to converse with multiple deployed bots simultaneously and compare their performance implicitly instead of explicitly rating using multidimensional metrics.Comprehensive evaluations from automatic to human perspective demonstrate the advantages of GLM-Dialog comparing with existing open source Chinese dialogue models. We release both the model checkpoint and source code, and also deploy it as a WeChat application to interact with users. We offer our evaluation platform online in an effort to prompt the development of open source models and reliable dialogue evaluation systems. The additional easy-to-use toolkit that consists of short text entity linking, query generation, and helpful knowledge classification is also released to enable diverse applications. All the source code is available on Github.

Though it's often talked about as if it's a single continuous structure, China's legendary Great Wall is actually a series of stone fortifications that crawl across the country's changing landscape from the Korean border to the Gobi desert. Thousands of miles long and more than 2,000 years old in some places, as much as 30 percent of the wall "lies crumbling into ruins" as it is slowly reclaimed by the natural world, according to National Geographic. To reach some of the most vulnerable sections of the ancient wall –– deteriorating portions that people have been completely cut off from or that remain too dangerous to traverse --Chinese authorities have deployed a new tool: drones. The drones have allowed Chinese authorities to map and measure sections of the wall, offering precise data that is already being used to rehabilitate a structure that is widely recognized as one of mankind's greatest feats of engineering, the BBC reported in a video published this week. Data collected by the drones has helped workers build support structures for vulnerable sections of the wall, the BBC reported.

Intel is contributing its intellectual capital--its innovative thinking and brightest minds and technology--to saving one of the greatest human-made creations on Earth, The Great Wall of China. The monument, which represents thousands of years of culture, is in danger of crumbling. To combat this nearly impossible challenge, Intel has partnered with the China Foundation for Cultural Heritage Conservation to launch an innovative new approach to its restoration, using artificial intelligence and drones (the project was announced in April). Intel's team set out on a mission to preserve one of the most iconic landmarks on earth, embarking on an expedition as they reimagined preservation work on this monument with new tools: Intel Drones and Al. "By talking about these products and combining the drone tech with AI, and having that solution built on the Xeon processor, I can tell a very technical story to people who would be interested in that, Then creatively, it's also a super-appealing human interest story that can elevate their perception of Intel outside of the PC," Intel's VP, global creative director Teresa Herd told Fast Company about the project, which bridges technology with cultural heritage, a brand-building exercise with an act of corporate responsibility.

The Great Wall of China, one of the Seven Wonders of the World is set to be restored with the drone assistance. Intel has teamed up with the China Foundation for Cultural Heritage Conservation in order to protect and restore this wonder. In the coming months, the drone will be deployed for aerial photography of the walls and help team gauge the Wall's current condition. "This partnership showcases how Intel's technology breakthroughs can benefit the restoration of Great Wall of China. It's a powerful example of how Intel's artificial intelligence and drone technology can positively impact the world," says Alyson Griffin, Intel's leader of global brand marketing.

At more than 2,000 years old, the Great Wall of China is getting a touch up thanks to technology. A link has been sent to your friend's email address. A link has been posted to your Facebook feed. At more than 2,000 years old, the Great Wall of China is getting a touch up thanks to technology.

Intel is deploying hi-tech drones to help spot parts of the Great Wall of China that have fallen into disrepair. The chipmaker is sending some Falcon 8 drones to shoot aerial photos of the famous Jiankou section of the wall, which is known for its steep climbs and scenic views. Due to its thick vegetation and centuries old materials, the areas has'naturally weathered' and requires repair -- a process that can be made easier by using drones, Intel said. Intel, which is partnering with the China Foundation for Cultural Heritage Conservation for the project, will send its Falcon drones to take aerial photos that will then be converted into high-definition images. Artificial intelligence will create a visual representation of the Great Wall to identify areas that are in need of repair and plan the safest way to restore them.

China plans to use artificial intelligence (AI) and drones to protect the Great Wall. Under an agreement between the government and the US tech giant Intel, the world's second largest manufacturer of semiconductors and microprocessors and the China Foundation For Cultural Heritage Conservation will explore ways to collaborate in the inspection, repair and preservation of the Great Wall, Xinhua news agency reported. To begin with, Intel drones will collect images from sections of the monument and use 3D modelling to identify damaged areas. "The use of the latest technologies, will provide a new perspective of the protection of the Great Wall, and show us the great potential of science and technology in cultural heritage protection," said Li Xiaojie, director of the China Foundation For Cultural Heritage Conservation. The Great Wall, a symbol of China, is actually not just one wall, but many interconnected walls built between the third century B.C. and the Ming Dynasty (1384-1644).