Disentangling shared network-level dynamics from region-specific activity is a central challenge in modeling multi-region neural data. We introduce SPIRE (Shared-Private Inter-Regional Encoder), a deep multi-encoder autoencoder that factorizes recordings into shared and private latent subspaces with novel alignment and disentanglement losses. Trained solely on baseline data, SPIRE robustly recovers cross-regional structure and reveals how external perturbations reorganize it. On synthetic benchmarks with ground-truth latents, SPIRE outperforms classical probabilistic models under nonlinear distortions and temporal misalignments. Applied to intracranial deep brain stimulation (DBS) recordings, SPIRE shows that shared latents reliably encode stimulation-specific signatures that generalize across sites and frequencies. These results establish SPIRE as a practical, reproducible tool for analyzing multi-region neural dynamics under stimulation. Understanding how distributed brain regions coordinate--and how this coordination is reorganized by interventions such as deep brain stimulation (DBS)--remains a major challenge. Disorders like dystonia and Parkinson's involve dysfunction in basal ganglia-thalamo-cortical circuits (Galvan et al., 2015; Jinnah & Hess, 2006; Obeso et al., 2008; Zhuang et al., 2004), and while DBS of targets such as globus pallidus internus (GPi) and subthalamic nucleus (STN) is clinically effective (Ben-abid, 2003; Lozano et al., 2019; Larsh et al., 2021) its network-level mechanisms remain poorly understood. Latent variable models can capture such effects by reducing neural activity to low-dimensional subspaces, but existing methods have key limitations. Classical models such as Gaussian Process Factor Analysis (GPFA) (Y u et al., 2008) and Canonical Correlation Analysis (CCA) (Bach & Jordan, 2005) assume linearity. DLAG (Delayed Latents Across Groups) (Gokcen et al., 2022) disentangles shared vs. private dynamics but is restricted to linear-Gaussian structure and spiking data. Multimodal models (SharedAE (Yi et al.), MMV AE (Shi et al., 2019)) align shared spaces but are not designed for intracranial recordings under stimulation. Critically, none of these frameworks provide a nonlinear, disentangling model that can separate shared versus private dynamics in human local field potential (LFP) data under external perturbation. Addressing this gap is essential: understanding how stimulation reorganizes intrinsic cross-regional coordination could reveal circuit-level mechanisms of DBS that remain invisible to local analyses.

Recent advances in diffusion models have revolutionized generative AI, but their sheer size makes on device personalization, and thus effective federated learning (FL), infeasible. We propose Shared Backbone Personal Identity Representation Embeddings (SPIRE), a framework that casts per client diffusion based generation as conditional generation in FL. SPIRE factorizes the network into (i) a high capacity global backbone that learns a population level score function and (ii) lightweight, learnable client embeddings that encode local data statistics. This separation enables parameter efficient finetuning that touches $\leq 0.01\%$ of weights. We provide the first theoretical bridge between conditional diffusion training and maximum likelihood estimation in Gaussian mixture models. For a two component mixture we prove that gradient descent on the DDPM with respect to mixing weights loss recovers the optimal mixing weights and enjoys dimension free error bounds. Our analysis also hints at how client embeddings act as biases that steer a shared score network toward personalized distributions. Empirically, SPIRE matches or surpasses strong baselines during collaborative pretraining, and vastly outperforms them when adapting to unseen clients, reducing Kernel Inception Distance while updating only hundreds of parameters. SPIRE further mitigates catastrophic forgetting and remains robust across finetuning learning rate and epoch choices.

Speculative decoding (SD) has been shown to reduce the latency of autoregressive decoding (AD) by 2-3x for small batch sizes. However, increasing throughput and therefore reducing the cost per token requires decoding with large batch sizes. Recent work shows that SD can accelerate decoding with large batch sizes too if the context is sufficiently long and the draft model's KV cache is sparse. We introduce SPIRe, a draft model that combines static sparse attention, pruned initialization, and feedback memory to increase the modeled throughput of speculative decoding by over 100% compared to speculation with a much smaller draft model and by over 35% compared to the strong baseline of sparse self-speculation. Our approach is particularly effective when context lengths vary significantly across requests.

Robot learning has proven to be a general and effective technique for programming manipulators. Imitation learning is able to teach robots solely from human demonstrations but is bottlenecked by the capabilities of the demonstrations. Reinforcement learning uses exploration to discover better behaviors; however, the space of possible improvements can be too large to start from scratch. And for both techniques, the learning difficulty increases proportional to the length of the manipulation task. Accounting for this, we propose SPIRE, a system that first uses Task and Motion Planning (TAMP) to decompose tasks into smaller learning subproblems and second combines imitation and reinforcement learning to maximize their strengths. We develop novel strategies to train learning agents when deployed in the context of a planning system. We evaluate SPIRE on a suite of long-horizon and contact-rich robot manipulation problems. We find that SPIRE outperforms prior approaches that integrate imitation learning, reinforcement learning, and planning by 35% to 50% in average task performance, is 6 times more data efficient in the number of human demonstrations needed to train proficient agents, and learns to complete tasks nearly twice as efficiently. View https://sites.google.com/view/spire-corl-2024 for more details.

Creating knowledge bases and ontologies is a time consuming task that relies on a manual curation. AI/NLP approaches can assist expert curators in populating these knowledge bases, but current approaches rely on extensive training data, and are not able to populate arbitrary complex nested knowledge schemas. Here we present Structured Prompt Interrogation and Recursive Extraction of Semantics (SPIRES), a Knowledge Extraction approach that relies on the ability of Large Language Models (LLMs) to perform zero-shot learning (ZSL) and general-purpose query answering from flexible prompts and return information conforming to a specified schema. Given a detailed, user-defined knowledge schema and an input text, SPIRES recursively performs prompt interrogation against GPT-3+ to obtain a set of responses matching the provided schema. SPIRES uses existing ontologies and vocabularies to provide identifiers for all matched elements. We present examples of use of SPIRES in different domains, including extraction of food recipes, multi-species cellular signaling pathways, disease treatments, multi-step drug mechanisms, and chemical to disease causation graphs. Current SPIRES accuracy is comparable to the mid-range of existing Relation Extraction (RE) methods, but has the advantage of easy customization, flexibility, and, crucially, the ability to perform new tasks in the absence of any training data. This method supports a general strategy of leveraging the language interpreting capabilities of LLMs to assemble knowledge bases, assisting manual knowledge curation and acquisition while supporting validation with publicly-available databases and ontologies external to the LLM. SPIRES is available as part of the open source OntoGPT package: https://github.com/ monarch-initiative/ontogpt.

Apple has revealed the games that are coming to Apple Arcade in July and the company has a stacked lineup in store for subscribers. A trifecta of classic indies are on the way to the service very soon in the form of Stardew Valley, Slay the Spire and Ridiculous Fishing. The latter is particularly intriguing, as Apple says it's "a full and expanded remaster" of the original game, which was an Apple Design Award winner. Ridiculous Fishing EX, to give the new version its full name, is now in 3D. You'll use unusual fishing gear such as chainsaws and toasters to try and land fish in an open sea.

Image classifiers often use spurious patterns, such as "relying on the presence of a person to detect a tennis racket, which do not generalize. In this work, we present an end-to-end pipeline for identifying and mitigating spurious patterns for such models, under the assumption that we have access to pixel-wise object-annotations. We start by identifying patterns such as "the model's prediction for tennis racket changes 63% of the time if we hide the people." Then, if a pattern is spurious, we mitigate it via a novel form of data augmentation. We demonstrate that our method identifies a diverse set of spurious patterns and that it mitigates them by producing a model that is both more accurate on a distribution where the spurious pattern is not helpful and more robust to distribution shift.

This is not a representation of what 2020 felt like -- it's a screen shot from Dead Cells. This is not a representation of what 2020 felt like -- it's a screen shot from Dead Cells. And thank goodness for that, right? Amid worldwide shutdowns, strenuous conversations about police reform, and an endless election cycle, we could all use a break. Do what I do: Pick up your Switch (or whatever console you use) and give yourself a well-deserved, news-free distraction.

Spire is all about helping our customers know what is next, so they can make better decisions. This month we are moving this forward by launching a true super-computer into orbit – 1-2 teraflops!

University teaching is under the microscope as institutions brace themselves for the first Teaching Excellence Framework, which will accord them gold, silver and bronze status. The biggest developments in university teaching are being driven by technology. The old techniques of talk and chalk are being challenged by lecture capture, flipped learning and decision-making based on data analysis. But technology can have worrying consequences. One (unnamed) university was recently brought under attack by its smart devices – a network including vending machines and light sensors was hacked, wreaking havoc with internet speeds across campus. And then there are the concerns about privacy raised by such developments.