How do birds stay warm in winter? Puffing up is just the start. Breakthroughs, discoveries, and DIY tips sent six days a week. Then you notice a robin hopping from branch to branch. Nearby, ducks are calmly swimming in the pond and waddling around on the ice.

Metrics like FactScore and VeriScore that evaluate long-form factuality operate by decomposing an input response into atomic claims and then individually verifying each claim. While effective and interpretable, these methods incur numerous LLM calls and can take upwards of 100 seconds to evaluate a single response, limiting their practicality in large-scale evaluation and training scenarios. To address this, we propose VeriFastScore, which leverages synthetic data to fine-tune Llama3.1 8B for simultaneously extracting and verifying all verifiable claims within a given text based on evidence from Google Search. We show that this task cannot be solved via few-shot prompting with closed LLMs due to its complexity: the model receives ~4K tokens of evidence on average and needs to concurrently decompose claims, judge their verifiability, and verify them against noisy evidence. However, our fine-tuned VeriFastScore model demonstrates strong correlation with the original VeriScore pipeline at both the example level (r=0.80) and system level (r=0.94) while achieving an overall speedup of 6.6x (9.9x excluding evidence retrieval) over VeriScore. To facilitate future factuality research, we publicly release our VeriFastScore model and synthetic datasets.

We present a novel alignment-before-generation approach to tackle the challenging task of generating general 3D shapes based on 2D images or texts. Directly learning a conditional generative model from images or texts to 3D shapes is prone to producing inconsistent results with the conditions because 3D shapes have an additional dimension whose distribution significantly differs from that of 2D images and texts. To bridge the domain gap among the three modalities and facilitate multi-modal-conditioned 3D shape generation, we explore representing 3D shapes in a shape-image-text-aligned space. Our framework comprises two models: a Shape-Image-Text-Aligned Variational Auto-Encoder (SITA-VAE) and a conditional Aligned Shape Latent Diffusion Model (ASLDM). The former model encodes the 3D shapes into the shape latent space aligned to the image and text and reconstructs the fine-grained 3D neural fields corresponding to given shape embeddings via the transformer-based decoder.

We introduce Michelangelo: a minimal, synthetic, and unleaked long-context reasoning evaluation for large language models which is also easy to automatically score. This evaluation is derived via a novel, unifying framework for evaluations over arbitrarily long contexts which measure the model's ability to do more than retrieve a single piece of information from its context. The central idea of the \frameworkname framework (\frameworkshort) is to construct tasks which require a model to ``chisel away'' the irrelevant information in the context, revealing a latent structure in the context. To verify a model's understanding of this latent structure, we query the model for details of the structure. Using \frameworkshort, we produce three diagnostic long-context evaluations across code and natural-language domains intended to provide a stronger signal of long-context language model capabilities. We perform evaluations on several state-of-the-art models and demonstrate both that a) the proposed evaluations are high-signal and b) that there is significant room for improvement in synthesizing long-context information.

Machine learning can provide companies with a competitive advantage by using the data they're collecting -- for example, purchasing patterns -- to generate predictions that power revenue-generating products (e.g. But it's difficult for any one employee to keep up with -- much less manage -- the massive volumes of data being created. That poses a problem, given AI systems tend to deliver superior predictions when they're provided up-to-the-minute data. Systems that aren't regularly retrained on new data run the risk of becoming "stale" and less accurate over time. Fortunately, an emerging set of practices dubbed "MLOps" promises to simplify the process of feeding data to systems by abstracting away the complexities.

There is a famous story about Michelangelo and his masterful sculpture of Moses, which you can view at Rome's Basilica di San Pietro in Vincoli. After finishing Moses, the artist was so impressed with the life-like qualities of his work that he hit the statue on its knee and said "Parla!" -- Speak! To Michelangelo, such perfection of form had to do more than mimic life -- it had to live. Falling in love with the work is part of the creative process. The culmination of a masterpiece is to endow it with its own spirit.

A visit to DMart or Reliance Retail in India on any given day would make one think about Black Friday sales. The limited manpower in stores often falls short to tend to the swarm of shoppers in Indian retail stores. To solve the issue, Scribble Data strives to provide automated and customised solutions for retail businesses to tend to the demand and needs of every customer that walks in through their door. The startup offers retail chains real-time inventory management, identifies customer shopping trends, and provides personalised recommendations. Scribble Data helps businesses build machine learning (ML) applications for making their daily operations hassle free and for creating more market-worthy ML features.

One thing that we can do to mitigate those risks is to draw inspiration from some of the biggest companies in the world that are deploying machine learning at scale. Today, we would like to discuss some of the reference architectures used by AI powerhouses like Google, Facebook, LinkedIn, and Uber to enable their machine learning pipelines. One of the best-known efforts in this area, Uber's Michelangelo is the runtime powering hundreds of machine learning workflows at Uber. From experimentation to model serving, Michelangelo combines mainstream technologies to automate the lifecycle of machine learning applications. The architecture behind Michelangelo uses a modern but complex stack based on technologies such as HDFS, Spark, Samza, Cassandra, MLLib, XGBoost, and TensorFlow.

Today artificial intelligence (AI) driven digital technologies are giving us new pathways to always have your loved ones with you, 7x24. Not really, despite the eeriness from Black Mirror episodes, or Carrie Fisher digitally created to carry on as Princess Leia in Star Wars, and Microsoft securing a patent for software that could reincarnate people as a chat bot, opening the door to more uses of AI contemplating how to bring the dead back to life are rapidly accelerating. Are we ready for death resurrections? Is this the right thing for us to be doing? From my research, we don't have all the answers to this complex question yet, but what we have are many innovators, academics, researchers shaping the answer to this question that will enable richer immersive digital learning experiences – and others that bringing grandma back to life – and persisting forever – may feel positively therapeutic to ease a deep grief, or feel like you are immersed in a Stephen King movie.

Today artificial intelligence (AI) driven digital technologies are giving us new pathways to always have your loved ones with you, 7x24. Not really, despite the eeriness from Black Mirror episodes, or Carrie Fisher digitally created to carry on as Princess Leia in Star Wars, and Microsoft securing a patent for software that could reincarnate people as a chat bot, opening the door to more uses of AI contemplating how to bring the dead back to life are rapidly accelerating. Are we ready for death resurrections? Is this the right thing for us to be doing? From my research, we don't have all the answers to this complex question yet, but what we have are many innovators, academics, researchers shaping the answer to this question that will enable richer immersive digital learning experiences – and others that bringing grandma back to life – and persisting forever – may feel positively therapeutic to ease a deep grief, or feel like you are immersed in a Stephen King movie.