Search

Artificial Expert Intelligence (AEI) seeks to transcend the limitations of both Artificial General Intelligence (AGI) and narrow AI by integrating domain-specific expertise with critical, precise reasoning capabilities akin to those of top human experts. Existing AI systems often excel at predefined tasks but struggle with adaptability and precision in novel problem-solving. To overcome this, AEI introduces a framework for ``Probably Approximately Correct (PAC) Reasoning". This paradigm provides robust theoretical guarantees for reliably decomposing complex problems, with a practical mechanism for controlling reasoning precision. In reference to the division of human thought into System 1 for intuitive thinking and System 2 for reflective reasoning~\citep{tversky1974judgment}, we refer to this new type of reasoning as System 3 for precise reasoning, inspired by the rigor of the scientific method. AEI thus establishes a foundation for error-bounded, inference-time learning.

The Caravan large-sample hydrology dataset (Kratzert et al., 2023) was created to standardize and harmonize streamflow data from various regional datasets, combined with globally available meteorological forcing and catchment attributes. This community-driven project also allows researchers to conveniently extend the dataset for additional basins, as done 6 times to date (see https://github.com/kratzert/Caravan/discussions/10). We present a novel extension to Caravan, focusing on enriching the meteorological forcing data. Our extension adds three precipitation nowcast products (CPC, IMERG v07 Early, and CHIRPS) and three weather forecast products (ECMWF IFS HRES, GraphCast, and CHIRPS-GEFS) to the existing ERA5-Land reanalysis data. The inclusion of diverse data sources, particularly weather forecasts, enables more robust evaluation and benchmarking of hydrological models, especially for real-time forecasting scenarios. To the best of our knowledge, this extension makes Caravan the first large-sample hydrology dataset to incorporate weather forecast data, significantly enhancing its capabilities and fostering advancements in hydrological research, benchmarking, and real-time hydrologic forecasting. The data is publicly available under a CC-BY-4.0 license on Zenodo in two parts (https://zenodo.org/records/14161235, https://zenodo.org/records/14161281) and on Google Cloud Platform (GCP) - see more under the Data Availability chapter.

We study the quantum-classical polynomial hierarchy, QCPH, which is the class of languages solvable by a constant number of alternating classical quantifiers followed by a quantum verifier. Our main result is that QCPH is infinite relative to a random oracle (previously, this was not even known relative to any oracle). We further prove that higher levels of PH are not contained in lower levels of QCPH relative to a random oracle; this is a strengthening of the somewhat recent result that PH is infinite relative to a random oracle (Rossman, Servedio, and Tan 2016). The oracle separation requires lower bounding a certain type of low-depth alternating circuit with some quantum gates. To establish this, we give a new switching lemma for quantum algorithms which may be of independent interest. Our lemma says that for any $d$, if we apply a random restriction to a function $f$ with quantum query complexity $\mathrm{Q}(f)\le n^{1/3}$, the restricted function becomes exponentially close (in terms of $d$) to a depth-$d$ decision tree. Our switching lemma works even in a "worst-case" sense, in that only the indices to be restricted are random; the values they are restricted to are chosen adversarially. Moreover, the switching lemma also works for polynomial degree in place of quantum query complexity., Comment: 40 pages

We study the query complexity analogue of the class TFNP of total search problems. We give a way to convert partial functions to total search problems under certain settings; we also give a way to convert search problems back into partial functions. As an application, we give new separations for degree-like measures. We give an exponential separation between quantum query complexity and approximate degree for a total search problem. We also give an exponential separation between approximate degree and the positive quantum adversary for a total search problem. We then strengthen the former separation to upper bound a larger measure: the two-sided approximate non-negative degree, also called the conical junta degree. This measure is often larger than quantum query complexity and even a separation from randomized query complexity was not known. We extend our results to communication complexity, and obtain an exponential separation between quantum information complexity and the relaxed partition bound for a total search problem. Even a weaker separation between randomized communication complexity and the relaxed partition bound was not known for total search problems (or even for partial functions). Most of our separations for total search problems can be converted to separations for partial functions. Using this, we reprove the recent exponential separation between quantum query complexity and approximate degree for a partial function by Ambainis and Belovs (2023), among other new results.

We study the quantum query algorithms for simplex finding, a generalization of triangle finding to hypergraphs. This problem satisfies a rank-reduction property: a quantum query algorithm for finding simplices in rank-$r$ hypergraphs can be turned into a faster algorithm for finding simplices in rank-$(r-1)$ hypergraphs. We then show that every nested Johnson graph quantum walk (with any constant number of nested levels) can be converted into an adaptive learning graph. Then, we introduce the concept of $\alpha$-symmetric learning graphs, which is a useful framework for designing and analyzing complex quantum search algorithms. Inspired by the work of Le Gall, Nishimura, and Tani (2016) on $3$-simplex finding, we use our new technique to obtain an algorithm for $4$-simplex finding in rank-$4$ hypergraphs with $O(n^{2.46})$ quantum query cost, improving the trivial $O(n^{2.5})$ algorithm., Comment: 31 pages

We present a novel approach for test-time adaptation via online self-training, consisting of two components. First, we introduce a statistical framework that detects distribution shifts in the classifier's entropy values obtained on a stream of unlabeled samples. Second, we devise an online adaptation mechanism that utilizes the evidence of distribution shifts captured by the detection tool to dynamically update the classifier's parameters. The resulting adaptation process drives the distribution of test entropy values obtained from the self-trained classifier to match those of the source domain, building invariance to distribution shifts. This approach departs from the conventional self-training method, which focuses on minimizing the classifier's entropy. Our approach combines concepts in betting martingales and online learning to form a detection tool capable of quickly reacting to distribution shifts. We then reveal a tight relation between our adaptation scheme and optimal transport, which forms the basis of our novel self-supervised loss. Experimental results demonstrate that our approach improves test-time accuracy under distribution shifts while maintaining accuracy and calibration in their absence, outperforming leading entropy minimization methods across various scenarios.

Diffusion-based generative models have recently shown remarkable image and video editing capabilities. However, local video editing, particularly removal of small attributes like glasses, remains a challenge. Existing methods either alter the videos excessively, generate unrealistic artifacts, or fail to perform the requested edit consistently throughout the video. In this work, we focus on consistent and identity-preserving removal of glasses in videos, using it as a case study for consistent local attribute removal in videos. Due to the lack of paired data, we adopt a weakly supervised approach and generate synthetic imperfect data, using an adjusted pretrained diffusion model. We show that despite data imperfection, by learning from our generated data and leveraging the prior of pretrained diffusion models, our model is able to perform the desired edit consistently while preserving the original video content. Furthermore, we exemplify the generalization ability of our method to other local video editing tasks by applying it successfully to facial sticker-removal. Our approach demonstrates significant improvement over existing methods, showcasing the potential of leveraging synthetic data and strong video priors for local video editing tasks.

Large language models (LLMs) have shown an impressive ability to perform tasks believed to require thought processes. When the model does not document an explicit thought process, it becomes difficult to understand the processes occurring within its hidden layers and to determine if these processes can be referred to as reasoning. We introduce a novel and interpretable analysis of internal multi-hop reasoning processes in LLMs. We demonstrate that the prediction process for compositional reasoning questions can be modeled using a simple linear transformation between two semantic category spaces. We show that during inference, the middle layers of the network generate highly interpretable embeddings that represent a set of potential intermediate answers for the multi-hop question. We use statistical analyses to show that a corresponding subset of tokens is activated in the model's output, implying the existence of parallel reasoning paths. These observations hold true even when the model lacks the necessary knowledge to solve the task. Our findings can help uncover the strategies that LLMs use to solve reasoning tasks, offering insights into the types of thought processes that can emerge from artificial intelligence. Finally, we also discuss the implication of cognitive modeling of these results.

Given the remarkable results of motion synthesis with diffusion models, a natural question arises: how can we effectively leverage these models for motion editing? Existing diffusion-based motion editing methods overlook the profound potential of the prior embedded within the weights of pre-trained models, which enables manipulating the latent feature space; hence, they primarily center on handling the motion space. In this work, we explore the attention mechanism of pre-trained motion diffusion models. We uncover the roles and interactions of attention elements in capturing and representing intricate human motion patterns, and carefully integrate these elements to transfer a leader motion to a follower one while maintaining the nuanced characteristics of the follower, resulting in zero-shot motion transfer. Editing features associated with selected motions allows us to confront a challenge observed in prior motion diffusion approaches, which use general directives (e.g., text, music) for editing, ultimately failing to convey subtle nuances effectively. Our work is inspired by how a monkey closely imitates what it sees while maintaining its unique motion patterns; hence we call it Monkey See, Monkey Do, and dub it MoMo. Employing our technique enables accomplishing tasks such as synthesizing out-of-distribution motions, style transfer, and spatial editing. Furthermore, diffusion inversion is seldom employed for motions; as a result, editing efforts focus on generated motions, limiting the editability of real ones. MoMo harnesses motion inversion, extending its application to both real and generated motions. Experimental results show the advantage of our approach over the current art. In particular, unlike methods tailored for specific applications through training, our approach is applied at inference time, requiring no training. Our webpage is at https://monkeyseedocg.github.io., Comment: Video: https://www.youtube.com/watch?v=s5oo3sKV0YU, Project page: https://monkeyseedocg.github.io, Code: https://github.com/MonkeySeeDoCG/MoMo-code

Clinical problem-solving requires processing of semantic medical knowledge such as illness scripts and numerical medical knowledge of diagnostic tests for evidence-based decision-making. As large language models (LLMs) show promising results in many aspects of language-based clinical practice, their ability to generate non-language evidence-based answers to clinical questions is inherently limited by tokenization. Therefore, we evaluated LLMs' performance on two question types: numeric (correlating findings) and semantic (differentiating entities) while examining differences within and between LLMs in medical aspects and comparing their performance to humans. To generate straightforward multi-choice questions and answers (QAs) based on evidence-based medicine (EBM), we used a comprehensive medical knowledge graph (encompassed data from more than 50,00 peer-reviewed articles) and created the "EBMQA". EBMQA contains 105,000 QAs labeled with medical and non-medical topics and classified into numerical or semantic questions. We benchmarked this dataset using more than 24,500 QAs on two state-of-the-art LLMs: Chat-GPT4 and Claude3-Opus. We evaluated the LLMs accuracy on semantic and numerical question types and according to sub-labeled topics. For validation, six medical experts were tested on 100 numerical EBMQA questions. We found that both LLMs excelled more in semantic than numerical QAs, with Claude3 surpassing GPT4 in numerical QAs. However, both LLMs showed inter and intra gaps in different medical aspects and remained inferior to humans. Thus, their medical advice should be addressed carefully.

The task of Visual Place Recognition (VPR) is to predict the location of a query image from a database of geo-tagged images. Recent studies in VPR have highlighted the significant advantage of employing pre-trained foundation models like DINOv2 for the VPR task. However, these models are often deemed inadequate for VPR without further fine-tuning on task-specific data. In this paper, we propose a simple yet powerful approach to better exploit the potential of a foundation model for VPR. We first demonstrate that features extracted from self-attention layers can serve as a powerful re-ranker for VPR. Utilizing these features in a zero-shot manner, our method surpasses previous zero-shot methods and achieves competitive results compared to supervised methods across multiple datasets. Subsequently, we demonstrate that a single-stage method leveraging internal ViT layers for pooling can generate global features that achieve state-of-the-art results, even when reduced to a dimensionality as low as 128D. Nevertheless, incorporating our local foundation features for re-ranking, expands this gap. Our approach further demonstrates remarkable robustness and generalization, achieving state-of-the-art results, with a significant gap, in challenging scenarios, involving occlusion, day-night variations, and seasonal changes.

We describe a novel subgradient following apparatus for calculating the optimum of convex problems with variational penalties. In this setting, we receive a sequence $y_i,\ldots,y_n$ and seek a smooth sequence $x_1,\ldots,x_n$. The smooth sequence attains the minimum Bregman divergence to an input sequence with additive variational penalties in the general form of $\sum_i g_i(x_{i+1}-x_i)$. We derive, as special cases of our apparatus, known algorithms for the fused lasso and isotonic regression. Our approach also facilitates new variational penalties such as non-smooth barrier functions. We next derive and analyze multivariate problems in which $\mathbf{x}_i,\mathbf{y}_i\in\mathbb{R}^d$ and variational penalties that depend on $\|\mathbf{x}_{i+1}-\mathbf{x}_i\|$. The norms we consider are $\ell_2$ and $\ell_\infty$ which promote group sparsity. Last but not least, we derive a lattice-based subgradient following for variational penalties characterized through the output of arbitrary convolutional filters. This paradigm yields efficient solvers for problems in which sparse high-order discrete derivatives such as acceleration and jerk are desirable.

We present Jamba, a new base large language model based on a novel hybrid Transformer-Mamba mixture-of-experts (MoE) architecture. Specifically, Jamba interleaves blocks of Transformer and Mamba layers, enjoying the benefits of both model families. MoE is added in some of these layers to increase model capacity while keeping active parameter usage manageable. This flexible architecture allows resource- and objective-specific configurations. In the particular configuration we have implemented, we end up with a powerful model that fits in a single 80GB GPU. Built at large scale, Jamba provides high throughput and small memory footprint compared to vanilla Transformers, and at the same time state-of-the-art performance on standard language model benchmarks and long-context evaluations. Remarkably, the model presents strong results for up to 256K tokens context length. We study various architectural decisions, such as how to combine Transformer and Mamba layers, and how to mix experts, and show that some of them are crucial in large scale modeling. We also describe several interesting properties of these architectures which the training and evaluation of Jamba have revealed, and plan to release checkpoints from various ablation runs, to encourage further exploration of this novel architecture. We make the weights of our implementation of Jamba publicly available under a permissive license., Comment: Webpage: https://www.ai21.com/jamba

In this paper we introduce a new model of random spanning trees that we call choice spanning trees, constructed from so-called choice random walks. These are random walks for which each step is chosen from a subset of random options, according to some pre-defined rule. The choice spanning trees are constructed by running a choice modified version of Wilson's algorithm or the Aldous-Broder algorithm on the complete graph. We show that the scaling limits of these choice spanning trees are slight variants of random aggregation trees previously considered by Curien and Haas (2017). Moreover, we show that the loop-erasure of a choice random walk run on the complete graph converges after rescaling to a generalized Rayleigh process, extending a result of Evans, Pitman and Winter (2006). These are all natural extensions of similar results for uniform spanning trees., Comment: 36 pages

We present here Multem 3, an updated and revised version of Multem 2, which syntax has been upgraded to Fortran 2018, with the source code being divided into modules. Multem 3 is equipped with LAPACK, the state-of-the art Faddeeva complex error function routine, and the Bessel function package AMOS. The amendments significantly improve both the speed, convergence, and precision of Multem 2. Increased stability allows to freely increase the cut-off value LMAX on the number of spherical vector wave functions and the cut-off value RMAX controlling the maximal length of reciprocal vectors taken into consideration. An immediate bonus is that Multem 3 can be reliably used to describe bound states in the continuum (BICs). To ensure convergence of the layer coupling scheme, it appears that appreciably larger values of convergence paramaters LMAX and RMAX are required than those reported in numerous published work in the past using Multem 2. We hope that Multem 3 will become a reliable and fast alternative to generic commercial software, such as COMSOL Multiphysics, CST Microwave Studio, or Ansys HFSS, and that it will become the code of choice for various optimization tasks for a large number of research groups. The improvements concern the core part of Multem 2, which is common to the extensions of Multem 2 for acoustic and elastic multiple scattering and to the original layer-Kohn-Korringa-Rostocker (LKKR) code. Therefore, the enhancements presented here can be readily applied to the above codes as well.

We give an oracle separation between QMA and QCMA for quantum algorithms that have bounded adaptivity in their oracle queries; that is, the number of rounds of oracle calls is small, though each round may involve polynomially many queries in parallel. Our oracle construction is a simplified version of the construction used recently by Li, Liu, Pelecanos, and Yamakawa (2023), who showed an oracle separation between QMA and QCMA when the quantum algorithms are only allowed to access the oracle classically. To prove our results, we introduce a property of relations called \emph{slipperiness}, which may be useful for getting a fully general classical oracle separation between QMA and QCMA.

Assuming an instance of the Brodsky-Rinot proxy principle holding at a regular uncountable cardinal $\kappa$, we construct $2^\kappa$-many pairwise non-embeddable minimal non-$\sigma$-scattered linear orders of size $\kappa$. In particular, in G\"odel's constructible universe $L$, these linear orders exist for any regular uncountable cardinal $\kappa$ that is not weakly compact. This extends a recent result of Cummings, Eisworth and Moore that takes care of all the successor cardinals of $L$. At the level of $\aleph_1$, their work answered an old question of Baumgartner by constructing from $\diamondsuit$ a minimal Aronszajn line that is not Souslin. Our use of the proxy principle yields the same conclusion from a weaker assumption which holds for instance in the generic extension after adding a single Cohen real to a model of $CH$., Comment: 22 pages, comments are welcome

We show that the union of two or more independent uniform spanning forests (USF) on $\mathbb{Z}^d$ with $d\geq 3$ almost surely forms a connected transient graph. In fact, this also holds when taking the union of a deterministic everywhere percolating set and an independent $\epsilon$-Bernoulli percolation on a single USF sample., Comment: 10 pages

Artificial Intelligence (AI) is progressing rapidly, and companies are shifting their focus to developing generalist AI systems that can autonomously act and pursue goals. Increases in capabilities and autonomy may soon massively amplify AI's impact, with risks that include large-scale social harms, malicious uses, and an irreversible loss of human control over autonomous AI systems. Although researchers have warned of extreme risks from AI, there is a lack of consensus about how exactly such risks arise, and how to manage them. Society's response, despite promising first steps, is incommensurate with the possibility of rapid, transformative progress that is expected by many experts. AI safety research is lagging. Present governance initiatives lack the mechanisms and institutions to prevent misuse and recklessness, and barely address autonomous systems. In this short consensus paper, we describe extreme risks from upcoming, advanced AI systems. Drawing on lessons learned from other safety-critical technologies, we then outline a comprehensive plan combining technical research and development with proactive, adaptive governance mechanisms for a more commensurate preparation., Comment: Published in Science: https://www.science.org/doi/10.1126/science.adn0117

When using Stochastic Gradient Descent (SGD) for training machine learning models, it is often crucial to provide the model with examples sampled at random from the dataset. However, for large datasets stored in the cloud, random access to individual examples is often costly and inefficient. A recent work \cite{corgi}, proposed an online shuffling algorithm called CorgiPile, which greatly improves efficiency of data access, at the cost some performance loss, which is particularly apparent for large datasets stored in homogeneous shards (e.g., video datasets). In this paper, we introduce a novel two-step partial data shuffling strategy for SGD which combines an offline iteration of the CorgiPile method with a subsequent online iteration. Our approach enjoys the best of both worlds: it performs similarly to SGD with random access (even for homogenous data) without compromising the data access efficiency of CorgiPile. We provide a comprehensive theoretical analysis of the convergence properties of our method and demonstrate its practical advantages through experimental results., Comment: 19 pages, 5 figures

Floods are one of the most common natural disasters, with a disproportionate impact in developing countries that often lack dense streamflow gauge networks. Accurate and timely warnings are critical for mitigating flood risks, but hydrological simulation models typically must be calibrated to long data records in each watershed. Using AI, we achieve reliability in predicting extreme riverine events in ungauged watersheds at up to a 5-day lead time that is similar to or better than the reliability of nowcasts (0-day lead time) from a current state of the art global modeling system (the Copernicus Emergency Management Service Global Flood Awareness System). Additionally, we achieve accuracies over 5-year return period events that are similar to or better than current accuracies over 1-year return period events. This means that AI can provide flood warnings earlier and over larger and more impactful events in ungauged basins. The model developed in this paper was incorporated into an operational early warning system that produces publicly available (free and open) forecasts in real time in over 80 countries. This work highlights a need for increasing the availability of hydrological data to continue to improve global access to reliable flood warnings.

Research has shown educators' implicit biases to be a key factor in creating and perpetuating disparities in students' experiences of schooling, learning, and longer-term outcomes, including job opportunities, wealth, and health. Current school reform and transformation efforts are aimed at addressing institutionalized racism in school policies, practices, and cultural systems by implementing implicit bias training for teachers and staff. In this paper, we explain how a school home visits program, Parent Teacher Home Visits (PTHV), is a promising intervention for counteracting implicit biases and improving outcomes for families and students. The PTHV "relational" home visit model focuses on promoting mutually supportive and accountable relationships between educators and families. We present data from a study examining the experiences of 107 educators and 68 family members who participated in PTHV, showing how educators shifted their deficit assumptions about families and students. Although the PTHV model was not created to address implicit biases, we found that the key components of these home visits align with strategies that psychological research has demonstrated effectively counteracting implicit biases and reducing discriminatory behaviors.