Machine learning models exhibit strong performance on datasets with abundant labeled samples.

Large language models (LLMs) have achieved remarkable success in natural language tasks, but their inference incurs substantial computational and memory overhead. To improve efficiency, parallel decoding methods like Skeleton-of-Thought (SoT) decompose prompts into sub-problems for concurrent processing. However, these methods significantly compromise answer quality by treating semantically linked sub-problems as independent. We propose Plato, a novel approach that co-designs algorithms and systems for semantic-aware parallel decoding. Plato leverages LLMs to organize sub-problems into a dependency graph based on logical and causal relationships, enabling concurrent decoding of non-dependent nodes while preserving answer coherence and quality. To further enhance efficiency, Plato pipelines planning and node decoding stages, implements a global context cache, and carefully structures node inference prompts to maximize key-value cache reuse and minimize overhead. Our evaluations show that Plato improves throughput by 68% over autoregressive decoding while achieving a 40% net win rate in answer quality. Compared to SoT, Plato demonstrates a remarkable 90% quality net-win rate. Ablation studies reveal that our pipeline design improves speedup by 29%, while our KV cache reuse optimization reduces overhead by 75%.

Machine learning models exhibit strong performance on datasets with abundant labeled samples. Here, our key insight is that there is often abundant, auxiliary domain information describing input features which can be structured as a heterogeneous knowledge graph (KG). We propose PLATO, a method that achieves strong performance on tabular data with d \gg n by using an auxiliary KG describing input features to regularize a multilayer perceptron (MLP). PLATO is based on the inductive bias that two input features corresponding to similar nodes in the auxiliary KG should have similar weight vectors in the MLP's first layer. Across 6 d \gg n datasets, PLATO outperforms 13 state-of-the-art baselines by up to 10.19%.

Synthesizing novel view images from a few views is a challenging but practical problem. Existing methods often struggle with producing high-quality results or necessitate per-object optimization in such few-view settings due to the insufficient information provided. In this work, we explore leveraging the strong 2D priors in pre-trained diffusion models for synthesizing novel view images. To address these problems, we propose \textit{DreamSparse}, a framework that enables the frozen pre-trained diffusion model to generate geometry and identity-consistent novel view images. Specifically, DreamSparse incorporates a geometry module designed to capture features about spatial information from sparse views as a 3D prior. Subsequently, a spatial guidance model is introduced to convert rendered feature maps as spatial information for the generative process.

The Age of AI has also ushered in the Age of Debates About AI. And Yuval Noah Harari, author of Sapiens and Homo Deus, and one of our foremost big-picture thinkers about the grand sweep of humanity, history and the future, is now out with Nexus: A Brief History of Information Networks from the Stone Age to AI. Harari generally falls into the AI alarmist category, but his thinking pushes the conversation beyond the usual arguments. The book is a look at human history through the lens of how we gather and marshal information. For Harari, this is essential, because how we use--and misuse--information is central to how our history has unfolded and to our future with AI. In what Harari calls the "naïve view of information," humans have assumed that more information will necessarily lead to greater understanding and even wisdom about the world.

As robotic systems become increasingly integrated into complex real-world environments, there is a growing need for approaches that enable robots to understand and act upon natural language instructions without relying on extensive pre-programmed knowledge of their surroundings. This paper presents PLATO, an innovative system that addresses this challenge by leveraging specialized large language model agents to process natural language inputs, understand the environment, predict tool affordances, and generate executable actions for robotic systems. Unlike traditional systems that depend on hard-coded environmental information, PLATO employs a modular architecture of specialized agents to operate without any initial knowledge of the environment. These agents identify objects and their locations within the scene, generate a comprehensive high-level plan, translate this plan into a series of low-level actions, and verify the completion of each step. The system is particularly tested on challenging tool-use tasks, which involve handling diverse objects and require long-horizon planning. PLATO's design allows it to adapt to dynamic and unstructured settings, significantly enhancing its flexibility and robustness. By evaluating the system across various complex scenarios, we demonstrate its capability to tackle a diverse range of tasks and offer a novel solution to integrate LLMs with robotic platforms, advancing the state-of-the-art in autonomous robotic task execution. For videos and prompt details, please see our project website: https://sites.google.com/andrew.cmu.edu/plato

The Herculaneum Scrolls contain hugely significant philosophical and literary texts from ancient Greek and Roman scholars, but were turned to carbonized lumps by the catastrophic eruption of Mount Vesuvius in AD 79. Attempts to unroll the scrolls have damaged or destroyed them, turning the precious coal-like relics to dust. Now, scientists are using clever scanning techniques to identify the text written within – without having to unroll the fragile'papyrus' pages. The team has already read one of the scrolls to discover how Greek philosopher Plato spent his last evening 2,500 years ago - but say other huge revelations about Socrates could be in store. Graziano Ranocchia, a papyrologist from the University of Pisa in Italy, said: 'Plato is just the start'.

An Italian researcher has claimed to have found the long-lost burial place of the famed Greek philosopher Plato who died around 348 BC. Graziano Ranocchia used AI to decipher the Herculaneum scrolls, charred papyrus found buried by the Mount Vesuvius eruption in 79AD, revealing new text that pointed to an exact location in Athens. The analysis showed Plato was buried in'The Academy,' a famous school founded by the philosopher in 387 BC, near the so-called Museion - a small building sacred to the Muses that no longer stands among the ruins. Ranocchia and his team uncovered 1,000 words, corresponding to 30 percent of the text, using the'bionic eye' - and believe they will have the papyrus completely analyzed by 2026. The analysis showed Plato was buried in'The Academy,' a famous school founded by the philosopher in 387 BC, near the so-called Museion - a small building sacred to the Muses The team uncovered 1,000 words, corresponding to 30 percent of the text, using the'bionic eye' - and believe they will have the papyrus completely analyzed by 2026 'Compared to previous editions, there is now an almost radically changed text, implying a number of new and concrete facts about various academic philosophers,' Ranocchia said in a statement.

In real-life conversations, the content is diverse, and there exists the one-to-many problem that requires diverse generation. Previous studies attempted to introduce discrete or Gaussian-based continuous latent variables to address the one-to-many problem, but the diversity is limited. Recently, diffusion models have made breakthroughs in computer vision, and some attempts have been made in natural language processing. In this paper, we propose DiffusionDialog, a novel approach to enhance the diversity of dialogue generation with the help of diffusion model. In our approach, we introduce continuous latent variables into the diffusion model. The problem of using latent variables in the dialog task is how to build both an effective prior of the latent space and an inferring process to obtain the proper latent given the context. By combining the encoder and latent-based diffusion model, we encode the response's latent representation in a continuous space as the prior, instead of fixed Gaussian distribution or simply discrete ones. We then infer the latent by denoising step by step with the diffusion model. The experimental results show that our model greatly enhances the diversity of dialog responses while maintaining coherence. Furthermore, in further analysis, we find that our diffusion model achieves high inference efficiency, which is the main challenge of applying diffusion models in natural language processing.

We propose the concepts of philomatics and psychomatics as hybrid combinations of philosophy and psychology with mathematics. We explain four motivations for this combination which are fulfilling the desire of analytical philosophy, proposing science of philosophy, justifying mathematical algorithms by philosophy, and abstraction in both philosophy and mathematics. We enumerate various examples for philomatics and psychomatics, some of which are explained in more depth. The first example is the analysis of relation between the context principle, semantic holism, and the usage theory of meaning with the attention mechanism in mathematics. The other example is on the relations of Plato's theory of forms in philosophy with the holographic principle in string theory, object-oriented programming, and machine learning. Finally, the relation between Wittgenstein's family resemblance and clustering in mathematics is explained. This paper opens the door of research for combining philosophy and psychology with mathematics.