We introduce the Local Intersectional Visual Spaces (LIVS) dataset, a benchmark for multi-criteria alignment of text-to-image (T2I) models in inclusive urban planning. Developed through a two-year participatory process with 30 community organizations, LIVS encodes diverse spatial preferences across 634 initial concepts, consolidated into six core criteria: Accessibility, Safety, Comfort, Invitingness, Inclusivity, and Diversity, through 37,710 pairwise comparisons. Using Direct Preference Optimization (DPO) to fine-tune Stable Diffusion XL, we observed a measurable increase in alignment with community preferences, though a significant proportion of neutral ratings highlights the complexity of modeling intersectional needs. Additionally, as annotation volume increases, accuracy shifts further toward the DPO-tuned model, suggesting that larger-scale preference data enhances fine-tuning effectiveness. LIVS underscores the necessity of integrating context-specific, stakeholder-driven criteria into generative modeling and provides a resource for evaluating AI alignment methodologies across diverse socio-spatial contexts.

Meta has nuked a bunch of its AI-generated profiles from Facebook Instagram, the company confirmed, after the AI characters prompted widespread outrage and ridicule from users on social media. The AI-generated profiles, which were labeled as "AI managed by Meta," launched in September of 2023, rolling out alongside the company's celebrity-branded AI chatbots ( also discontinued). Meta doesn't seem to have updated any of these profiles for several months, and the pages seem to have been largely unnoticed until this week, following an interview published by the Financial Times with Meta's VP of Generative AI, Connor Hayes. In the interview, Hayes spoke about the company's goal to eventually fill its services with AI-generated profiles that can interact with people and function "kind of in the same way that accounts do." Those comments brought attention to the extant fMeta-created AI profiles and, well, users were not exactly impressed with what they found.

Iterative improvement of model architectures is fundamental to deep learning: Transformers first enabled scaling, and recent advances in model hybridization have pushed the quality-efficiency frontier. However, optimizing architectures remains challenging and expensive. Current automated or manual approaches fall short, largely due to limited progress in the design of search spaces and due to the simplicity of resulting patterns and heuristics. In this work, we propose a new approach for the synthesis of tailored architectures (STAR). Our approach combines a novel search space based on the theory of linear input-varying systems, supporting a hierarchical numerical encoding into architecture genomes. STAR genomes are automatically refined and recombined with gradient-free, evolutionary algorithms to optimize for multiple model quality and efficiency metrics. Using STAR, we optimize large populations of new architectures, leveraging diverse computational units and interconnection patterns, improving over highly-optimized Transformers and striped hybrid models on the frontier of quality, parameter size, and inference cache for autoregressive language modeling.

We present Language-Image Value learning (LIV), a unified objective for vision-language representation and reward learning from action-free videos with text annotations. Exploiting a novel connection between dual reinforcement learning and mutual information contrastive learning, the LIV objective trains a multi-modal representation that implicitly encodes a universal value function for tasks specified as language or image goals. We use LIV to pre-train the first control-centric vision-language representation from large human video datasets such as EpicKitchen. Given only a language or image goal, the pre-trained LIV model can assign dense rewards to each frame in videos of unseen robots or humans attempting that task in unseen environments. Further, when some target domain-specific data is available, the same objective can be used to fine-tune and improve LIV and even other pre-trained representations for robotic control and reward specification in that domain. In our experiments on several simulated and real-world robot environments, LIV models consistently outperform the best prior input state representations for imitation learning, as well as reward specification methods for policy synthesis. Our results validate the advantages of joint vision-language representation and reward learning within the unified, compact LIV framework.

Liv., the lifestyle digital bank by Emirates NBD and the fastest growing bank in the UAE, has partnered with US-based Kasisto, to introduce Olivia, an artificial intelligence-powered chatbot. It added that the chatbot can help customers get quick answers on a range of services and can also answer queries on how much customers have spent last month on groceries or in restaurants, helping them plan and manage their finances better. Olivia can also seamlessly hand over the conversation to the Liv. Chatbots are AI-enabled computer programs designed to simulate human communication, allowing them to answer customer queries in real time. "Virtual assistants are playing an increasingly important part in our daily lives and our new chatbot Olivia will offer millennial customers a new way to engage with and receive information and instant insights on their spending and finances," said Jayash Patel, head of Liv.

Walmart-backed Flipkart has just issued a challenge to Amazon's Alexa and Google Assistant. The home-grown e-commerce giant today announced that it has acquired Bengaluru-based artificial intelligence (AI) startup Liv.ai, which has developed a platform that converts speech-to-text in nine regional languages apart from English. With this move, the e-tailer hopes to soon offer an end-to-end conversational shopping experience for its users. "Given the complexities in typing on vernacular keyboards, voice will become a preferred interface for new shoppers. One does understand that building a voice interface is complex, and is especially challenging in Indian context given multiple languages and accents," Flipkart CEO Kalyan Krishnamurthy said in a statement.

We propose an approximation of the Possible Worlds Semantics (PWS) for action planning. A corresponding planning system is implemented by a transformation of the action specification to an Answer-Set Program. A novelty is support for postdiction wrt. (a) the plan existence problem in our framework can be solved in NP, as compared to $\Sigma_2^P$ for non-approximated PWS of Baral(2000); and (b) the planner generates optimal plans wrt. a minimal number of actions in $\Delta_2^P$. We demo the planning system with standard problems, and illustrate its integration in a larger software framework for robot control in a smart home.