华特迪士尼公司

Animated characters often move in non-physical ways and have proportions that are far from a typical walking robot. This provides an ideal platform for innovation in both mechanical design and stylized motion control. In this letter, we bring Olaf to life in the physical world, relying on reinforcement learning guided by animation references for control. To create the illusion of Olaf's feet moving along his body, we hide two asymmetric legs under a soft foam skirt. To fit actuators inside the character, we use spherical and planar linkages in the arms, mouth, and eyes. Because the walk cycle results in harsh contact sounds, we introduce additional rewards that noticeably reduce impact noise. The large head, driven by small actuators in the character's slim neck, creates a risk of overheating, amplified by the costume. To keep actuators from overheating, we feed temperature values as additional inputs to policies, introducing new rewards to keep them within bounds. We validate the efficacy of our modeling in simulation and through experiments on the robot.

How and why does a recommender system fail the users it serves? Oftentimes, practitioners are left to improve their algorithms based on a combination of feedback from stakeholder teams, domain expertise, and insights from data analyses. Yet the nuances of how and where recommendations perform well or poorly for end users are difficult to discern from aggregate quantitative metrics. Whereas these metrics provide a high-level and incomplete picture, further granularity into the quality of recommendations and their patterns requires reasoning with domain understanding and objectivity, at scale. We contemplate this complex conundrum and describe a method and implementation that uses the latest AI agentic advances to provide actionable diagnoses and improvements for production recommender systems. We present AURA (Agentic Understanding and Refinement of recommender Algorithms), an end-to-end agentic system that performs qualitative evaluation at scale and can then generate improvements to our algorithms at the code level. Specialized agents read production engagement logs, from thousands of sessions to millions, and surface patterns and examples of how the recommender fails real users. The next step uses those diagnoses and context about the recommender's own code, data, and training pipeline to propose and implement refinements grounded in that codebase. We report the system design, initial tests on production data from two large consumer platforms at a major media-streaming company, safeguards, operational learnings, and early results toward a self-improving recommender system. Finally, the diagnostic gap AURA closes is not specific to streaming. The architecture is built to transfer: every domain-specific element enters through the configuration layer that already ported it between our two platforms. We map it concretely to e-commerce and online-retail recommendation.

Deep Learning (DL) is well-suited for handling big data challenges and future issues in IoT. Advanced image processing techniques are pivotal in addressing security challenges in medical imaging. Anonymization techniques, encryption, watermarking, and Federated Learning (FL) are crucial for securing data and protecting privacy. AI-driven Clinical Decision Support Systems (CDSS) are increasingly used in clinical medicine, integrating Machine Learning (ML) capabilities into expert systems to enhance performance. The Unlearning Technique has recently become a way to implement the concept of “the right to be forgotten” in FL. Current research on effective retraining or approximate unlearning methods often overlooks the information leakage risks tied to model differences before and after unlearning.

Generative image codecs aim to optimize perceptual quality, producing realistic and detailed reconstructions. However, they often overlook a key property of human vision: our tendency to focus on particular aspects of a visual scene (e.g., salient objects) while giving less importance to other regions. An ideal perceptual codec should be able to exploit this property by allocating more representational capacity to perceptually important areas. To this end, we propose a region-adaptive diffusion-based image codec that supports non-uniform bit allocation within an image. We design a novel spatially varying diffusion model capable of denoising varying amounts of noise per pixel according to arbitrary importance maps. We further identify that these maps can serve as effective priors on the latent representation, and integrate them into our entropy model, improving rate-distortion performance. Built on these contributions, our spatially-adaptive diffusion-based codec outperforms state-of-the-art ROI-controllable baselines in both full-image and ROI-masked perceptual quality.

Modern DevOps practices are increasingly emphasizing Developer Experience metrics as critical factors influencing the efficacy of software delivery. However, despite significant advancements in this direction, the challenge of constructing a causal model that elucidates the impact of Developer Experience metrics on the speed of releases remains unresolved. This study aims to formalize and empirically evaluate the causal relationship between various indicators of development experience (such as cognitive load and technical frustration) and the speed of the release cycle within DevOps environments. A simulation model was developed for this analysis, embodying a prototypical CI/CD infrastructure characterized by either a microservices or serverless architecture within a cloud framework. Bayesian Causal Modeling was employed, facilitating the exploration of how Developer Experience variables influence the time parameters of the release cycle. The model encompasses seven variables, comprising five key Developer Experience metrics alongside two control parameters (architectural and organizational levels). Within the simulation framework, data was generated based on the principles of Web Application Architecture, incorporating contemporary methodologies of Full Stack Development and RESTful API interfaces. The findings reveal a statistically significant causal relationship between cognitive load and technical frustration and an increase in the duration of the deployment cycle. For instance, the probability of exceeding a release duration of 14 days increases from 21% to 83% in case of slow CI/CD integration, and accordingly from 18% to 72% when utilizing low-quality tools. This underscores the feasibility of integrating Developer Experience metrics into Engineering Decision Support Systems within DevOps processes. The results obtained from this study can be leveraged to enhance DevOps monitoring strategies, prioritize interventions within development workflows, and further advance analytical platforms aimed at managing the quality of the developer experience.