Self-e beha Despite vior volution, curre, is essential nt the adv ability ancements for the of embodied agents in reinforcement to autonomously domain with fine-tuning long-horizon, improv (RFT) e their real-w sho reasoning wing orld strong tasks.

LLM-based agents have demonstrated great potential in generating and managing code within complex codebases. In this paper, we introduce WebGen-Bench, a novel benchmark designed to measure an LLM-based agent's ability to create multifile website codebases from scratch. It contains diverse instructions for website generation, created through the combined efforts of human annotators and GPT4o. These instructions span three major categories and thirteen minor categories, encompassing nearly all important types of web applications. To assess the quality of the generated websites, we generate test cases targeting each functionality described in the instructions. These test cases are then manually filtered, refined, and organized to ensure accuracy, resulting in a total of 647 test cases. Each test case specifies an operation to be performed on the website and the expected outcome of the operation. To automate testing and improve reproducibility, we employ a powerful web-navigation agent to execute test cases on the generated websites and determine whether the observed responses align with the expected results. We evaluate three high-performance code-agent frameworks--Bolt.diy,

Collaborative filtering methods based on implicit feedback (e.g., purchase records and browsing history) are widely used in recommender systems. Compared to explicit feedback (e.g., 1-5 star ratings), implicit feedback is more abundant and accessible in real-world applications. However, the missing data of implicit feedback also brings two challenges.

Inspired by the human ability to perform complex manipulation in the complete absence of vision (like retrieving an object from a pocket), the robotic manipulation field is motivated to develop new methods for tactile-based object interaction. However, tactile sensing presents the challenge of being an active sensing modality: a touch sensor provides sparse, local data, and must be used in conjunction with effective exploration strategies in order to collect information. In this work, we focus on the process of guiding tactile exploration, and its interplay with task-related decision making. We propose TANDEM (TActile exploration aNd DEcision Making), an architecture to learn efficient exploration strategies in conjunction with decision making. Our approach is based on separate but co-trained modules for exploration and discrimination. We demonstrate this method on a tactile object recognition task, where a robot equipped with a touch sensor must explore and identify an object from a known set based on binary contact signals alone. TANDEM achieves higher accuracy with fewer actions than alternative methods and is also shown to be more robust to sensor noise.

It was/is a lot material to cover in 90 minutes, and conceptual understanding / developing intuition was the main point. Of course, there is great online material to make use of, and you'll see my preferences in the cited sources;-). This year, having covered the basics, I hope to be developing use cases and practical applications showing applicability of Deep Learning even in non-Google-size (resp: Facebook, Baidu, Apple...) environments.

For many years, the idea of delivering robust personalization and relevance was aspirational, causing some marketers to pause. The recent Google I/O conference told us that it's time for those who hesitated to take another look. Google focused on artificial intelligence (AI), moving on from the mobile-first mentality. Whether it be through text, voice, or visual input, Google's strategy hinges on knowing everything it can at that exact moment for providing maximum context to the user. Simply put, enabling marketers to meet users where they are and with context to most accurately provide value.

We've seen AI-powered chat bots spread across different services, but Google is opening up a way for more companies to get in on the action. With "Actions on Google," you can stay in your app (or talking to an Assistant-enabled device like Google Home) to do something like order food just by having a conversation. On stage, the demo showed off ordering delivery from Panera, without needing to enter your home address or payment information, or even create a specialized account. Support for actions has been available since Google Home launched but only worked with a limited number of services. Now that it supports transactions, it's about to get a lot more useful.

This work compares two actions' concurrency and co-occurrence employed in temporal modeling languages, one with a PDDL-style action modeling languages used by the AI planning community, exclusion mechanism, and another with an explicit and argue that they explain why MILP or SMT have notion of resources, and investigates their seemed unattractive. Specifically, we observe that PDDL 2.1 implications on constraint-based search. The first [Fox and Long, 2003] induces temporal gaps between consecutive mechanism forces temporal gaps in action schedules interdependent actions, and these gaps often induce and have a high performance penalty. The second twice the number of steps in the plans than what is necessary, mechanism avoids the gaps, with dramatically with strong negative performance implications. The gaps are improved performance.

This paper describes Picat's planner, its implementation, and planning models for several domains used in International Planning Competition (IPC) 2014. Picat's planner is implemented by use of tabling. During search, every state encountered is tabled, and tabled states are used to effectively perform resource-bounded search. In Picat, structured data can be used to avoid enumerating all possible permutations of objects, and term sharing is used to avoid duplication of common state data. This paper presents several modeling techniques through the example models, ranging from designing state representations to facilitate data sharing and symmetry breaking, encoding actions with operations for efficient precondition checking and state updating, to incorporating domain knowledge and heuristics. Broadly, this paper demonstrates the effectiveness of tabled logic programming for planning, and argues the importance of modeling despite recent significant progress in domain-independent PDDL planners.