Diffusion language models have recently emerged as a competitive alternative to autoregressive language models. Beyond next-token generation, they are more efficient and flexible by enabling parallel and any-order token generation. However, despite empirical successes, their computational power and fundamental limitations remain poorly understood. In this paper, we formally study whether non-autoregressive generation in Masked Diffusion Models (MDM) enables solving problems beyond the reach of Auto-Regressive Models (ARM). Our results show that MDM with sufficiently large context length is computationally universal with decoding steps matching the optimal parallel time complexity in PRAM. However, when controlling for other factors, MDM's flexibility to generate in any-order does not expand what ARM can already solve. To address this, we propose a new form of generation called any-process generation, which extends MDM with capabilities to remask, insert and delete tokens, allowing self-correction, length-variable editing, and adaptive parallelism. Theoretically and empirically, we demonstrate these capabilities enable scalability to significantly harder reasoning problems that are otherwise intractable for ARM and vanilla MDM. Additionally, they prove essential for generation tasks where objects naturally evolve through non-sequential processes, crucial for extending current LLMs beyond natural language to domains such as coding and science.

Humans localize themselves efficiently in known environments by first recognizing landmarks defined on certain objects and their spatial relationships, and then verifying the location by aligning detailed structures of recognized objects with those in the memory. Inspired by this, we propose the place recognition anywhere model (PRAM) to perform visual localization as efficiently as humans do. PRAM consists of two main components - recognition and registration. In detail, first of all, a self-supervised map-centric landmark definition strategy is adopted, making places in either indoor or outdoor scenes act as unique landmarks. Then, sparse keypoints extracted from images, are utilized as the input to a transformer-based deep neural network for landmark recognition; these keypoints enable PRAM to recognize hundreds of landmarks with high time and memory efficiency. Keypoints along with recognized landmark labels are further used for registration between query images and the 3D landmark map. Different from previous hierarchical methods, PRAM discards global and local descriptors, and reduces over 90% storage. Since PRAM utilizes recognition and landmark-wise verification to replace global reference search and exhaustive matching respectively, it runs 2.4 times faster than prior state-of-the-art approaches. Moreover, PRAM opens new directions for visual localization including multi-modality localization, map-centric feature learning, and hierarchical scene coordinate regression.

Non-parents may not believe it, but pushing a pram around can be a fairly strenuous task, especially when the train gets rough. It's a full body workout to push two kids under four in my old Uppababy Vista, which weighed the same as an iceberg and had the turning circle of the Titanic. To remedy this, Canadian startup GlüxKind has developed an electrically-assisted stroller that'll make pushing easier, and can even drive itself, albeit only when your kid isn't on board. The GlüxKind Ella is the brainchild of Anne Hunger and Kevin Huang, a couple who were less than whelmed when looking for a stroller for their own daughter. They decided to build their own device by strapping an electric skateboard to a regular stroller, and started developing their product from there. The device has three modes, the first of which is to add electric assist to the wheels as you're pushing it around.

Andy Grove (Intel's business leader until 2004) termed "software spiral" the exceptionally resilient business model behind general-purpose CPUs. Application software is the defining component of SWS: Code written once could yet benefit from performance scaling of later CPU generations. SWS is comprised of several abstraction levels. The random access machine, or model (RAM) is most relevant for the current Counterpoint Viewpoint (CPV): each serial step of an algorithm features a basic operation taking unit time ("uniform cost" criterion). The RAM has long been the gold standard for algorithms and data structures.

Redistribution systems iteratively redistribute mass between groups under the control of rules. PRAM is a framework for building redistribution systems. We discuss the relationships between redistribution systems, agent-based systems, compartmental models and Bayesian models. PRAM puts agent-based models on a sound probabilistic footing by reformulating them as redistribution systems. This provides a basis for integrating agent-based and probabilistic models. \pram/ extends the themes of probabilistic relational models and lifted inference to incorporate dynamical models and simulation. We illustrate PRAM with an epidemiological example.

In agent-based models (ABMs, e.g., [4, 3]) agents probabilistically change state. State can be represented as attribute values such as health status, monthly income, age, political orientation, location and so on. A population of agents has a joint state that is typically a joint distribution; for example, a population has a joint distribution over income levels and political beliefs. ABMs are a popular method for exploring the dynamics of joint states, which can be hard to estimate when attribute values depend on each other, and populations are heterogeneous in the sense that not everyone has the same distribution of attribute values, and the principal mechanism for changing attribute values is interactions between agents. For example, suppose all agents have a flu status attribute that changes conditionally - given other attributes such as age, income, and vaccination status - when agents interact. The dynamics of flu - how it moves through heterogeneous populations - can be difficult or impossible to solve, but ABMs can simulate the interactions of agents, and the flu status of these agents can be tracked over time. ABMs are no doubt engines of probabilistic inference, but it is difficult to say anything about the models that underlie the inference. This paper presents pram - Probabilistic Relational Agentbased Models - a new kind of ABM with design influences from compartmental models (e.g., [1]) and probabilistic relational models (PRMs; e.g., [2]).