Latent dynamical systems have been widely used to characterize the dynamics of neural population activity in the brain. However, these models typically ignore the fact that the brain contains multiple cell types. This limits their ability to capture the functional roles of distinct cell classes, and to predict the effects of cell-specific perturbations on neural activity or behavior. To overcome these limitations, we introduce the `cell-type dynamical systems (CTDS) model. This model extends latent linear dynamical systems to contain distinct latent variables for each cell class, with biologically inspired constraints on both dynamics and emissions.

Neural Algorithmic Reasoning (NAR) research has demonstrated that graph neural networks (GNNs) could learn to execute classical algorithms. However, most previous approaches have always used a recurrent architecture, where each iteration of the GNN matches an iteration of the algorithm. In this paper we study neurally solving algorithms from a different perspective: since the algorithm's solution is often an equilibrium, it is possible to find the solution directly by solving an equilibrium equation. Our approach requires no information on the ground-truth number of steps of the algorithm, both during train and test time. Furthermore, the proposed method improves the performance of GNNs on executing algorithms and is a step towards speeding up existing NAR models. Our empirical evidence, leveraging algorithms from the CLRS-30 benchmark, validates that one can train a network to solve algorithmic problems by directly finding the equilibrium. We discuss the practical implementation of such models and propose regularisations to improve the performance of these equilibrium reasoners.

There is a rapidly growing interest in controlling consistency across multiple generated images using diffusion models. Among various methods, recent works have found that simply manipulating attention modules by concatenating features from multiple reference images provides an efficient approach to enhancing consistency without fine-tuning. Despite its popularity and success, few studies have elucidated the underlying mechanisms that contribute to its effectiveness. In this work, we reveal that the popular approach is a linear interpolation of image self-attention and cross-attention between synthesized content and reference features, with a constant rank-1 coefficient. Motivated by this observation, we find that a rank-1 coefficient is not necessary and simplifies the controllable generation mechanism. The resulting algorithm, which we coin as RefDrop, allows users to control the influence of reference context in a direct and precise manner. Besides further enhancing consistency in single-subject image generation, our method also enables more interesting applications, such as the consistent generation of multiple subjects, suppressing specific features to encourage more diverse content, and high-quality personalized video generation by boosting temporal consistency. Even compared with state-of-the-art image-prompt-based generators, such as IP-Adapter, RefDrop is competitive in terms of controllability and quality while avoiding the need to train a separate image encoder for feature injection from reference images, making it a versatile plug-and-play solution for any image or video diffusion model.

We propose a novel neural networks based approach to efficiently answer arbitrary Most Probable Explanation (MPE) queries--a well-known NP-hard task--in large probabilistic models such as Bayesian and Markov networks, probabilistic circuits, and neural auto-regressive models. By arbitrary MPE queries, we mean that there is no predefined partition of variables into evidence and non-evidence variables. The key idea is to distill all MPE queries over a given probabilistic model into a neural network and then use the latter for answering queries, eliminating the need for time-consuming inference algorithms that operate directly on the probabilistic model. We improve upon this idea by incorporating inference-time optimization with self-supervised loss to iteratively improve the solutions and employ a teacher-student framework that provides a better initial network, which in turn, helps reduce the number of inference-time optimization steps. The teacher network utilizes a self-supervised loss function optimized for getting the exact MPE solution, while the student network learns from the teacher's near-optimal outputs through supervised loss. We demonstrate the efficacy and scalability of our approach on various datasets and a broad class of probabilistic models, showcasing its practical effectiveness.

We explore how generating a chain of thought---a series of intermediate reasoning steps---significantly improves the ability of large language models to perform complex reasoning. In particular, we show how such reasoning abilities emerge naturally in sufficiently large language models via a simple method called chain of thought prompting, where a few chain of thought demonstrations are provided as exemplars in prompting. Experiments on three large language models show that chain of thought prompting improves performance on a range of arithmetic, commonsense, and symbolic reasoning tasks. The empirical gains can be striking. For instance, prompting a 540B-parameter language model with just eight chain of thought exemplars achieves state of the art accuracy on the GSM8K benchmark of math word problems, surpassing even finetuned GPT-3 with a verifier.

We study the sample complexity of learning an $\varepsilon$-optimal policy in an average-reward Markov decision process (MDP) under a generative model. For weakly communicating MDPs, we establish the complexity bound $\widetilde{O}\left(SA\frac{\mathsf{H}}{\varepsilon^2} \right)$, where $\mathsf{H}$ is the span of the bias function of the optimal policy and $SA$ is the cardinality of the state-action space. Our result is the first that is minimax optimal (up to log factors) in all parameters $S,A,\mathsf{H}$, and $\varepsilon$, improving on existing work that either assumes uniformly bounded mixing times for all policies or has suboptimal dependence on the parameters. We also initiate the study of sample complexity in general (multichain) average-reward MDPs.

Humans can picture a sound scene given an imprecise natural language description. For example, it is easy to imagine an acoustic environment given a phrase like the lion roar came from right behind me!. For a machine to have the same degree of comprehension, the machine must know what a lion is (semantic attribute), what the concept of behind is (spatial attribute) and how these pieces of linguistic information align with the semantic and spatial attributes of the sound (what a roar sounds like when its coming from behind). State-of-the-art audio foundation models, such as CLAP, which learn to map between audio scenes and natural textual descriptions, are trained on non-spatial audio and text pairs, and hence lack spatial awareness. In contrast, sound event localization and detection models are limited to recognizing sounds from a fixed number of classes, and they localize the source to absolute position (e.g., 0.2m) rather than a position described using natural language (e.g., next to me).

PCWorld reports that Nvidia's DLSS 5 announcement caught major game developers from Ubisoft and Capcom off-guard, who were unaware their games would be featured in demonstrations. The generative AI technology faces significant backlash from gamers who criticize it as an "AI filter" that potentially devalues game aesthetics and may require two high-end GPUs. Despite being planned for fall 2026 release, DLSS 5 already raises concerns about artistic control and whether developers want this AI-enhanced visual processing in their games. Nvidia DLSS 5 is coming later this year, adding generative "AI" features to the performance-enhancing tech . Gamers are calling the tool an "Instagram yaas filter" and "AI slop," among other, less kind terms. The way that it adds detail to faces and seems to hijack -- or replace?

Rivian will provide 50,000 robotaxis to Uber in a deal worth $1.25 billion Initial deployments will start in San Francisco and Miami. Rivian and Uber, with the former to provide the latter with 50,000 robotaxis in funding. This starts with Uber purchasing 10,000 Rivian R2 robotaxis, which will be deployed in San Francisco and Miami by 2028. If all goes well, Uber will scoop up 40,000 more robotaxis by 2030. The company plans to scale the initiative to 25 major cities by 2031.

Black, white, Muslim, or Christian: Players found common ground across the board. A black chess player about to win against a light-skinned cleric. Breakthroughs, discoveries, and DIY tips sent six days a week. Chess is widely seen as a great equalizer. Players from every social, racial, and economic class have squared off across the board for nearly 1,500 years, with victories determined solely by skill and strategy.