搜索结果：thousand

The Thousand Brains Theory (TBT) and its open-source Monty framework model object recognition through sensorimotor inference -- identifying objects by actively moving a sensor across their surface and building evidence contact by contact. The current implementation encodes each contact as a dense floating-point vector. While Monty tracks inter-step displacement and accumulates evidence across contacts, it treats the feature activation pattern at each contact as an unordered set - the directional sequence in which features are encountered carries no representational weight. In TBT, the sequence of contacts carries spatial meaning: knowing that feature A was felt before feature B during a left-to-right sweep tells you something about where A and B sit on the object. Dense vectors discard this ordering. We propose replacing dense vectors with rank-order spike packets: each contact produces a brief burst of neural events where the most strongly activated neuron fires first. The time gap between successive bursts implicitly encodes sensor displacement without explicit coordinate calculations. A biologically motivated learning rule (STDP) encodes traversal direction into synaptic weights

We construct Pulsar Polarisation Arrays (PPA), using regular pulsars monitored in MeerKAT's Thousand Pulsar Array (TPA) Programme, to search for Axion-like Dark Matter (ALDM) within Milky Way. Specifically, from a catalogue of 1237 regular pulsars, we select the 50 ones with the highest signal-to-noise ratio and set upper limits on the ALDM Chern-Simons coupling. We find no signals with statistical significance over the mass range of $[10^{-23},10^{-20}]\,{\rm eV}$ in the six-year MeerKAT's data. By combining the high-quality TPA pulsars and the accurate ionospheric subtraction of spinifex, we establish the most sensitive upper limits to the date on the ALDM Chern-Simons coupling, namely $\lesssim 10^{-14} - 3\times 10^{-13}\,{\rm GeV}^{-1}$, for the mass range of $[10^{-23},10^{-21}]\,{\rm eV}$ except at $m_a \sim 1.3 \times 10^{-22}\,$eV. This study underscores the great potential of constructing regular-pulsar PPAs for scientific tasks.

Motivation: Modern bioinformatics workflows, particularly in imaging and representation learning, can generate thousands to tens of thousands of quantitative phenotypes from a single cohort. In such settings, running genome-wide association analyses trait by trait rapidly becomes a computational bottleneck. While established GWAS tools are highly effective for individual traits, they are not optimized for phenotype-rich screening workflows in which the same genotype matrix is reused across a large phenotype panel. Results: We present TorchGWAS, a framework for high-throughput association testing of large phenotype panels through hardware acceleration. The current public release provides stable Python and command-line workflows for linear GWAS and multivariate phenotype screening, supports NumPy, PLINK, and BGEN genotype inputs, aligns phenotype and covariate tables by sample identifier, and performs covariate adjustment internally. In a benchmark with 8.9 million markers and 23,000 samples, fastGWA required approximately 100 second per phenotype on an AMD EPYC 7763 64-core CPU, whereas TorchGWAS completed 2,048 phenotypes in 10 minute and 20,480 phenotypes in 20 minutes on a single

We propose an approach to generative quantum machine learning that overcomes the fundamental scaling issues of variational quantum circuits. The core idea is to use a class of generative models based on instantaneous quantum polynomial circuits, which we show can be trained efficiently on classical hardware. Although training is classically efficient, sampling from these circuits is widely believed to be classically hard, and so computational advantages are possible when sampling from the trained model on quantum hardware. By combining our approach with a data-dependent parameter initialisation strategy, we do not encounter issues of barren plateaus and successfully circumvent the poor scaling of gradient estimation that plagues traditional approaches to quantum circuit optimisation. We investigate and evaluate our approach on a number of real and synthetic datasets, training models with up to one thousand qubits and hundreds of thousands of parameters. We find that the quantum models can successfully learn from high dimensional data, and perform surprisingly well compared to simple energy-based classical generative models trained with a similar amount of hyperparameter optimisatio

The polarimetry of recent pulsar observations has provided a wealth of observational data with which to test physical theories of emission mechanisms, radiative transfer and even theories that extend beyond the Standard Model. In this work, we have outlined the data analysis of the polarisation time series data of a population of 513 pulsars from the Thousand Pulsar Array observing programme, laying the foundation for building the MeerKAT Thousand-Pulsar Polarization Array as a probe for ultralight Axion-Like Dark Matter (ALDM). From this large dataset we have focused on the temporal trends in the observed polarisation angle (PA) through a measure we call the PA offset, and characterised the trends due to the effects of Faraday Rotation within the interstellar medium and the Earth's ionosphere, as well as generic white and red noise models that are estimated within a Bayesian MCMC analysis. Then, motivated by potential extra contributions to the rotation of the PA that may not be Faraday-like, arising from the proposed ALDM field, we have investigated a derived time dependence for the rotation measure (RM) required to explain the observed PA offset. Comparison of these estimates to

Current AI systems achieve impressive performance on many tasks, yet they lack core attributes of biological intelligence, including rapid, continual learning, representations grounded in sensorimotor interactions, and structured knowledge that enables efficient generalization. Neuroscience theory suggests that mammals evolved flexible intelligence through the replication of a semi-independent, sensorimotor module, a functional unit known as a cortical column. To address the disparity between biological and artificial intelligence, thousand-brains systems were proposed as a means of mirroring the architecture of cortical columns and their interactions. In the current work, we evaluate the unique properties of Monty, the first implementation of a thousand-brains system. We focus on 3D object perception, and in particular, the combined task of object recognition and pose estimation. Utilizing the YCB dataset of household objects, we first assess Monty's use of sensorimotor learning to build structured representations, finding that these enable robust generalization. These representations include an emphasis on classifying objects by their global shape, as well as a natural ability to

It is now possible to directly measure the accelerations that arise from the distribution of (dark) matter in the Milky Way. These acceleration-based measurements of the local dark matter density are now becoming competitive with estimates obtained through traditional kinematic techniques such as Jeans modeling. While classical methods can now draw on the positions and velocities of many millions of stars, recent acceleration-based studies have used fewer than 100 sources, yet achieve comparable precision. A key limitation of kinematic approaches is their reliance on assumptions of dynamical equilibrium and symmetry; direct acceleration measurements do not inherently suffer from this constraint. We find that, for the specific problem of estimating the local dark matter density, a single direct acceleration measurement can provide information comparable to $\sim$10$^5$ stars. We test the theoretical performance of direct acceleration techniques and Jeans modeling in estimating the local dark matter density using hydrodynamical N-body simulations of a MW-like galaxy, both in isolation and including a Sagittarius-like dwarf to generate disequilibrium. In the equilibrium scenario, Jean

We present PORTAL, a novel framework for developing artificial intelligence agents capable of playing thousands of 3D video games through language-guided policy generation. By transforming decision-making problems into language modeling tasks, our approach leverages large language models (LLMs) to generate behavior trees represented in domain-specific language (DSL). This method eliminates the computational burden associated with traditional reinforcement learning approaches while preserving strategic depth and rapid adaptability. Our framework introduces a hybrid policy structure that combines rule-based nodes with neural network components, enabling both high-level strategic reasoning and precise low-level control. A dual-feedback mechanism incorporating quantitative game metrics and vision-language model analysis facilitates iterative policy improvement at both tactical and strategic levels. The resulting policies are instantaneously deployable, human-interpretable, and capable of generalizing across diverse gaming environments. Experimental results demonstrate PORTAL's effectiveness across thousands of first-person shooter (FPS) games, showcasing significant improvements in dev

British physicist Stephen Hawkings most important discovery was that black holes are not so black, as they possess a temperature and emit thermal radiation. In his popular science texts, Hawking offered a detailed explanation of this phenomenon. The aim of this work is to translate that explanation into mathematical language accessible to an advanced high school student, all within a thousand words.

The advancement of AI systems for mental health support is hindered by limited access to therapeutic conversation data, particularly for trauma treatment. We present Thousand Voices of Trauma, a synthetic benchmark dataset of 3,000 therapy conversations based on Prolonged Exposure therapy protocols for Post-traumatic Stress Disorder (PTSD). The dataset comprises 500 unique cases, each explored through six conversational perspectives that mirror the progression of therapy from initial anxiety to peak distress to emotional processing. We incorporated diverse demographic profiles (ages 18-80, M=49.3, 49.4% male, 44.4% female, 6.2% non-binary), 20 trauma types, and 10 trauma-related behaviors using deterministic and probabilistic generation methods. Analysis reveals realistic distributions of trauma types (witnessing violence 10.6%, bullying 10.2%) and symptoms (nightmares 23.4%, substance abuse 20.8%). Clinical experts validated the dataset's therapeutic fidelity, highlighting its emotional depth while suggesting refinements for greater authenticity. We also developed an emotional trajectory benchmark with standardized metrics for evaluating model responses. This privacy-preserving da

We present DISTRIBUTEDANN, a distributed vector search service that makes it possible to search over a single 50 billion vector graph index spread across over a thousand machines that offers 26ms median query latency and processes over 100,000 queries per second. This is 6x more efficient than existing partitioning and routing strategies that route the vector query to a subset of partitions in a scale out vector search system. DISTRIBUTEDANN is built using two well-understood components: a distributed key-value store and an in-memory ANN index. DISTRIBUTEDANN has replaced conventional scale-out architectures for serving the Bing search engine, and we share our experience from making this transition.

An image may convey a thousand words, but a video composed of hundreds or thousands of image frames tells a more intricate story. Despite significant progress in multimodal large language models (MLLMs), generating extended videos remains a formidable challenge. As of this writing, OpenAI's Sora, the current state-of-the-art system, is still limited to producing videos that are up to one minute in length. This limitation stems from the complexity of long video generation, which requires more than generative AI techniques for approximating density functions essential aspects such as planning, story development, and maintaining spatial and temporal consistency present additional hurdles. Integrating generative AI with a divide-and-conquer approach could improve scalability for longer videos while offering greater control. In this survey, we examine the current landscape of long video generation, covering foundational techniques like GANs and diffusion models, video generation strategies, large-scale training datasets, quality metrics for evaluating long videos, and future research areas to address the limitations of the existing video generation capabilities. We believe it would serv

As we become increasingly dependent on vision language models (VLMs) to answer questions about the world around us, there is a significant amount of research devoted to increasing both the difficulty of video question answering (VQA) datasets, and the context lengths of the models that they evaluate. The reliance on large language models as backbones has lead to concerns about potential text dominance, and the exploration of interactions between modalities is underdeveloped. How do we measure whether we're heading in the right direction, with the complexity that multi-modal models introduce? We propose a joint method of computing both feature attributions and modality scores based on Shapley values, where both the features and modalities are arbitrarily definable. Using these metrics, we compare $6$ VLM models of varying context lengths on $4$ representative datasets, focusing on multiple-choice VQA. In particular, we consider video frames and whole textual elements as equal features in the hierarchy, and the multiple-choice VQA task as an interaction between three modalities: video, question and answer. Our results demonstrate a dependence on text and show that the multiple-choice

Humans are remarkably efficient at learning tasks from demonstrations, but today's imitation learning methods for robot manipulation often require hundreds or thousands of demonstrations per task. We investigate two fundamental priors for improving learning efficiency: decomposing manipulation trajectories into sequential alignment and interaction phases, and retrieval-based generalisation. Through 3,450 real-world rollouts, we systematically study this decomposition. We compare different design choices for the alignment and interaction phases, and examine generalisation and scaling trends relative to today's dominant paradigm of behavioural cloning with a single-phase monolithic policy. In the few-demonstrations-per-task regime (<10 demonstrations), decomposition achieves an order of magnitude improvement in data efficiency over single-phase learning, with retrieval consistently outperforming behavioural cloning for both alignment and interaction. Building on these insights, we develop Multi-Task Trajectory Transfer (MT3), an imitation learning method based on decomposition and retrieval. MT3 learns everyday manipulation tasks from as little as a single demonstration each, whil

Artificial intelligence has advanced rapidly in the last decade, driven primarily by progress in the scale of deep-learning systems. Despite these advances, the creation of intelligent systems that can operate effectively in diverse, real-world environments remains a significant challenge. In this white paper, we outline the Thousand Brains Project, an ongoing research effort to develop an alternative, complementary form of AI, derived from the operating principles of the neocortex. We present an early version of a thousand-brains system, a sensorimotor agent that is uniquely suited to quickly learn a wide range of tasks and eventually implement any capabilities the human neocortex has. Core to its design is the use of a repeating computational unit, the learning module, modeled on the cortical columns found in mammalian brains. Each learning module operates as a semi-independent unit that can model entire objects, represents information through spatially structured reference frames, and both estimates and is able to effect movement in the world. Learning is a quick, associative process, similar to Hebbian learning in the brain, and leverages inductive biases around the spatial str

Battery technology is increasingly important for global electrification efforts. However, batteries are highly sensitive to small manufacturing variations that can induce reliability or safety issues. An important technology for battery quality control is computed tomography (CT) scanning, which is widely used for non-destructive 3D inspection across a variety of clinical and industrial applications. Historically, however, the utility of CT scanning for high-volume manufacturing has been limited by its low throughput as well as the difficulty of handling its large file sizes. In this work, we present a dataset of over one thousand CT scans of as-produced commercially available batteries. The dataset spans various chemistries (lithium-ion and sodium-ion) as well as various battery form factors (cylindrical, pouch, and prismatic). We evaluate seven different battery types in total. The manufacturing variability and the presence of battery defects can be observed via this dataset. This dataset may be of interest to scientists and engineers working on battery technology, computer vision, or both.

Fine-tuning large language models (LLMs) with low-rank adaptations (LoRAs) has become common practice, often yielding numerous copies of the same LLM differing only in their LoRA updates. This paradigm presents challenges for systems that serve real-time responses to queries that each involve a different LoRA. Prior works optimize the design of such systems but still require continuous loading and offloading of LoRAs, as it is infeasible to store thousands of LoRAs in GPU memory. To mitigate this issue, we investigate the efficacy of compression when serving LoRAs. We propose a method for the joint compression of LoRAs into a shared basis paired with LoRA-specific scaling matrices. We extend our algorithm to learn clusters of LoRAs that are amenable to joint compression, allowing it to scale gracefully to large LoRA collections. Our experiments with up to 1000 LoRAs demonstrate that compressed LoRAs preserve performance while offering major throughput gains in realistic serving scenarios with over a thousand LoRAs, maintaining 80% of the throughput of serving a single LoRA.

Quantum networks can enable various applications such as distributed quantum computing, long-distance quantum communication, and network-based quantum sensing with unprecedented performances. One of the most important building blocks for a quantum network is a photonic quantum memory which serves as the interface between the communication channel and the local functional unit. A programmable quantum memory which can process a large stream of flying qubits and fulfill the requirements of multiple core functions in a quantum network is still to-be-realized. Here we report a high-performance quantum memory which can simultaneously store 72 optical qubits carried by 144 spatially separated atomic ensembles and support up to a thousand consecutive write or read operations in a random access way, two orders of magnitude larger than the previous record. Due to the built-in programmability, this quantum memory can be adapted on-demand for several functions. As example applications, we realize quantum queue, stack, and buffer which closely resemble the counterpart devices for classical information processing. We further demonstrate the synchronization and reshuffle of 4 entangled pairs of p

By use of a special wave function derived from similarly transformed propagators, this work shows that the energy of a thousand spin-balanced fermions in a three-dimensional harmonic potential can be accurately computed using the Monte Carlo method.