Despite the remarkable capabilities of large language models (LLMs) in various reasoning tasks, they still struggle with table reasoning tasks, particularly in maintaining consistency throughout multi-step reasoning processes. While existing approaches have explored various decomposition strategies, they often lack effective mechanisms to identify and correct errors in intermediate reasoning steps, leading to cascading error propagation. To address these issues, we propose Table-Critic, a novel multi-agent framework that facilitates collaborative criticism and iterative refinement of the reasoning process until convergence to correct solutions. Our framework consists of four specialized agents: a Judge for error identification, a Critic for comprehensive critiques, a Refiner for process improvement, and a Curator for pattern distillation. To effectively deal with diverse and unpredictable error types, we introduce a self-evolving template tree that systematically accumulates critique knowledge through experience-driven learning and guides future reflections. Extensive experiments have demonstrated that Table-Critic achieves substantial improvements over existing methods, achieving superior accuracy and error correction rates while maintaining computational efficiency and lower solution degradation rate.

In this work, we propose Table-LLM-Specialist, or Table-Specialist for short, as a new self-trained fine-tuning paradigm specifically designed for table tasks. Our insight is that for each table task, there often exist two dual versions of the same task, one generative and one classification in nature. Leveraging their duality, we propose a Generator-Validator paradigm, to iteratively generate-then-validate training data from language-models, to fine-tune stronger \sys models that can specialize in a given task, without requiring manually-labeled data. Our extensive evaluations suggest that our Table-Specialist has (1) \textit{strong performance} on diverse table tasks over vanilla language-models -- for example, Table-Specialist fine-tuned on GPT-3.5 not only outperforms vanilla GPT-3.5, but can often match or surpass GPT-4 level quality, (2) \textit{lower cost} to deploy, because when Table-Specialist fine-tuned on GPT-3.5 achieve GPT-4 level quality, it becomes possible to deploy smaller models with lower latency and inference cost, with comparable quality, and (3) \textit{better generalizability} when evaluated across multiple benchmarks, since \sys is fine-tuned on a broad range of training data systematically generated from diverse real tables. Our code and data will be available at https://github.com/microsoft/Table-LLM-Specialist.

Vascular anastomosis, the surgical connection of blood vessels, is essential in procedures such as organ transplants and reconstructive surgeries. The precision required limits accessibility due to the extensive training needed, with manual suturing leading to variable outcomes and revision rates up to 7.9%. Existing robotic systems, while promising, are either fully teleoperated or lack the capabilities necessary for autonomous vascular anastomosis. We present the Micro Smart Tissue Autonomous Robot (micro-STAR), an autonomous robotic system designed to perform vascular anastomosis on small-diameter vessels. The micro-STAR system integrates a novel suturing tool equipped with Optical Coherence Tomography (OCT) fiber-optic sensor and a microcamera, enabling real-time tissue detection and classification. Our system autonomously places sutures and manipulates tissue with minimal human intervention. In an ex vivo study, micro-STAR achieved outcomes competitive with experienced surgeons in terms of leak pressure, lumen reduction, and suture placement variation, completing 90% of sutures without human intervention. This represents the first instance of a robotic system autonomously performing vascular anastomosis on real tissue, offering significant potential for improving surgical precision and expanding access to high-quality care.

An eccentric inventor has created a bizarre four-legged robot that allows snakes to'walk'. Allen Pan, a Los Angeles-based engineer and YouTuber, created the device out of a long tube and four plastic legs connected to a controller board. Footage shows a snake curiously poking its head out the end of the device as it's serenely transported around the room. Pan, who posted a video blog of his project to YouTube, said he wanted to'give snakes back their legs'. Around 150 million years ago, snakes had visible legs, but they evolved to lose them, thought to be due to a genetic mutation.

As a CIO, regardless of the industry you are in, you share common opportunities and potential for advancements with other CIOs when it comes to technology. These might include theft of materials, physical security of staff and customers, doing more with fewer employees and contributing to the profitability of your company. In this column, we are going to examine some hospitality technology experiments with emphasis in the casino area. The first one is biometrics, the technical term for body measurements and calculations. It has long been used as a form of identification and access control. But with the proliferation of voice recognition devices (think Amazon Alexa, Apple Siri, and Google Assistant), biometric technology has moved into guest services and the Wynn Las Vegas Casino is currently attempting to use this as a big competitive advantage.

Amazon's Echo devices are powered by its Alexa artificial intelligence. LOS ANGELES -- Hey, Alexa, which of the seven Echo speakers should I buy, and what's the difference between them? And OK Google, the new Home Mini is so affordable at $29 for the holidays. How does it stack up to the entry level Echo, Amazon's Dot? If you're shopping for a smart speaker, here's how to decide which model and brand fits your needs and some advice on what to do once you own one.

We present a system that produces emotionally rich poetry inspired by personalized and empathic interpretation of text, particularly Internet blogs. Our implemented system is based on the blackboard architecture, and generates poetry from a theme that it considers the most inspiring. It also incorporates a model of emotions with an individual optimism rate that defines an affective state. The poems produced by the system contain emotional expressions that describe these feelings. We explain how the system re-conceptualizes the text by the empathic interpretation of its content. We also present how the blackboard architecture may support divergent problem solving in the field of computational creativity.We describe the system architecture and the generation algorithm followed by some illustrative results. Finally, we mention possible continuation of this work by incorporating other language generating systems as well as human experts in the blackboard architecture.