Harvard University Figure 1: T o visualize how topics evolve in real time, we create a rotatable embedding space where time is encoded along the Z-axis. We provide three preset views to help users explore topic clusters from different perspectives: (A) Front View (overall clusters), (B) Iso View (clusters over time), and (C) Side View (clusters over time). Here, each point represents an image from a dataset of Picasso's paintings, batched into 5-year intervals. Many real-world datasets - from an artist's body of work to a person's social media history - exhibit meaningful semantic changes over time that are difficult to capture with existing dimensionality reduction methods. To address this gap, we introduce a visualization technique that combines force-based projection and streaming clustering methods to build a spatial-temporal map of embeddings. We demonstrate the utility of our approach through use cases on text and image data, showing how it offers a new lens for understanding the aesthetics and semantics of temporal datasets.

AI is comprised of two ingredients: algorithms and data, and "Both of these are man-made," said Tony Fernandes, founder of HumanFocused.AI and CEO of UEGroup, a design company that employs artists. "People are fascinated to see what happens when both are allowed to run on their own and to look at what they generated,'' Fernandes said, adding that creating art requires inherent human influence. "To say that AI creates art is to say that anyone can replicate the work of Picasso," he said. "What makes Picasso's work relevant is the human spirit, imagination, and desire for expression. Picasso experimented with cubism to achieve something new.

His hands-off approach to the production of his famous balloon dogs and stainless steel rabbits has been criticised in the past but Jeff Koons, the world's most expensive artist, has drawn a red-line: "I wouldn't – for my own base work – be looking at AI to be developing my work." The potential and the risks of artificial intelligence is perhaps the hottest topic in the artistic world, with deep-learning models now able to replicate styles and produce unique compositions on request. It would appear to be a heaven-sent development for Koons, who was speaking to the Guardian at the launch of Reflections, a joint exhibition of his works alongside those of Pablo Picasso at the Alhambra in Granada. Koons's reliance on teams of craftspeople and cutting-edge technology in the making of his pieces prompted the Collector magazine last year to ask: "Is Jeff Koons an actual artist?" Exploiting technological advances is what he does.

Security concerns surrounding text-to-image diffusion models have driven researchers to unlearn inappropriate concepts through fine-tuning. Recent fine-tuning methods typically align the prediction distributions of unsafe prompts with those of predefined text anchors. However, these techniques exhibit a considerable performance trade-off between eliminating undesirable concepts and preserving other concepts. In this paper, we systematically analyze the impact of diverse text anchors on unlearning performance. Guided by this analysis, we propose AdvAnchor, a novel approach that generates adversarial anchors to alleviate the trade-off issue. These adversarial anchors are crafted to closely resemble the embeddings of undesirable concepts to maintain overall model performance, while selectively excluding defining attributes of these concepts for effective erasure. Extensive experiments demonstrate that AdvAnchor outperforms state-of-the-art methods. Our code is publicly available at https://anonymous.4open.science/r/AdvAnchor.

This paper addresses the contentious issue of copyright infringement in images generated by text-to-image models, sparking debates among AI developers, content creators, and legal entities. State-of-the-art models create high-quality content without crediting original creators, causing concern in the artistic community. To mitigate this, we propose the \copyright Plug-in Authorization framework, introducing three operations: addition, extraction, and combination. Addition involves training a \copyright plug-in for specific copyright, facilitating proper credit attribution. Extraction allows creators to reclaim copyright from infringing models, and combination enables users to merge different \copyright plug-ins. These operations act as permits, incentivizing fair use and providing flexibility in authorization. We present innovative approaches,"Reverse LoRA" for extraction and "EasyMerge" for seamless combination. Experiments in artist-style replication and cartoon IP recreation demonstrate \copyright plug-ins' effectiveness, offering a valuable solution for human copyright protection in the age of generative AIs.

Large-scale diffusion models, known for their impressive image generation capabilities, have raised concerns among researchers regarding social impacts, such as the imitation of copyrighted artistic styles. In response, existing approaches turn to machine unlearning techniques to eliminate unsafe concepts from pre-trained models. However, these methods compromise the generative performance and neglect the coupling among multi-concept erasures, as well as the concept restoration problem. To address these issues, we propose a Separable Multi-concept Eraser (SepME), which mainly includes two parts: the generation of concept-irrelevant representations and the weight decoupling. The former aims to avoid unlearning substantial information that is irrelevant to forgotten concepts. The latter separates optimizable model weights, making each weight increment correspond to a specific concept erasure without affecting generative performance on other concepts. Specifically, the weight increment for erasing a specified concept is formulated as a linear combination of solutions calculated based on other known undesirable concepts. Extensive experiments indicate the efficacy of our approach in eliminating concepts, preserving model performance, and offering flexibility in the erasure or recovery of various concepts.

Greg Rutkowski is among the artists calling for more protection from artificial intelligence tools.

The recent advances of AI technology, particularly in AI-Generated Content (AIGC), have enabled everyone to easily generate beautiful paintings with simple text description. With the stunning quality of AI paintings, it is widely questioned whether there still exists difference between human and AI paintings and whether human artists will be replaced by AI. To answer these questions, we develop a computational framework combining neural latent space and aesthetics features with visual analytics to investigate the difference between human and AI paintings. First, with categorical comparison of human and AI painting collections, we find that AI artworks show distributional difference from human artworks in both latent space and some aesthetic features like strokes and sharpness, while in other aesthetic features like color and composition there is less difference. Second, with individual artist analysis of Picasso, we show human artists' strength in evolving new styles compared to AI. Our findings provide concrete evidence for the existing discrepancies between human and AI paintings and further suggest improvements of AI art with more consideration of aesthetics and human artists' involvement.

The age of enterprise AI has come crashing down upon us in recent months. Public infatuation with ChatGPT since its release last November has opened the floodgates of corporate interest and set off an industry-wide land grab with every major tech entity vying to stake their claim in this burgeoning market by incorporating generative AI features into their existing products. Heavyweights including Google, Microsoft, Meta, and Baidu are already jockeying their Large Language Models (LLMs) for market dominance, while everybody else, from Adobe and AT&T to BMW and BYD, scrambles to find uses for the revolutionary technology. NVIDIA's newest cloud services offering, AI Foundations, will allow businesses lacking the time and money to develop their own models from scratch to "to build, refine and operate custom large language models and generative AI models that are trained with their own proprietary data and created for their unique domain-specific tasks." These models include NeMo, NVIDIA's text-to-image generation engine and DALL-E 2 competitor; BioNemo, a drug and molecule discovery-focused fork of the NeMo model built for the medical research community; and Picasso, an AI capable of generating images, video and "3D applications… to supercharge productivity for creativity, design and digital simulation," according to Tuesday's release.

On July the 13th the company that developed the generative AI art tool Midjourney opened its closed beta. To access it, you just need to enter the discord channel. Playing with this model immediately gives the feeling of something very powerful with a wide comprehension of text prompts. It works especially well with environments and characters, and from what I have seen, by default it has a bias towards artistic paintings. For example, with the prompt "enchanted jungle" you get: To thoroughly understand its power, I decided to test it by mixing in various ways two things that never existed at the same time: Pokémon and pre-1990 art movements.