Symbolic models play a key role in cognitive science, expressing computationally precise hypotheses about how the brain implements a cognitive process. Identifying an appropriate model typically requires a great deal of effort and ingenuity on the part of a human scientist. Here, we adapt FunSearch (Romera-Paredes et al. 2024), a recently developed tool that uses Large Language Models (LLMs) in an evolutionary algorithm, to automatically discover symbolic cognitive models that accurately capture human and animal behavior. We consider datasets from three species performing a classic reward-learning task that has been the focus of substantial modeling effort, and find that the discovered programs outperform state-of-the-art cognitive models for each. The discovered programs can readily be interpreted as hypotheses about human and animal cognition, instantiating interpretable symbolic learning and decision-making algorithms. Broadly, these results demonstrate the viability of using LLM-powered program synthesis to propose novel scientific hypotheses regarding mechanisms of human and animal cognition.

We introduce SciSpace Copilot, an AI research assistant that helps in understanding and reading research papers faster by providing a plethora of features. Answering questions from a document has recently become popular using the Retrieval Augmented Generation (RAG) approach. Our tool uses an advanced question-answering pipeline to get accurate answers and also provide exact citations for the same. We provide many more valuable features on scientific text, including generating explanations, generating summaries, adding notes and highlights, and finding related papers from our 200 million corpus. Our tool supports 100+ languages, making research more accessible across language barriers. Thousands of users use SciSpace Copilot on a daily basis by uploading their articles to understand research faster and better. Our tool can be accessed at this link: https://typeset.io.

We present VIDIM, a generative model for video inter-polation, which creates short videos given a start and end frame. In order to achieve high fidelity and generate motions unseen in the input data, VIDIM uses cascaded diffusion models to first generate the target video at low resolution, and then generate the high-resolution video conditioned on the low-resolution generated video. We compare VIDIM to previous state-of-the-art methods on video interpolation, and demonstrate how such works fail in most settings where the underlying motion is complex, nonlinear, or ambiguous while VIDIM can easily handle such cases. We additionally demonstrate how classifier-free guidance on the start and end frame and conditioning the super-resolution model on the original high-resolution frames without additional parameters unlocks high-fidelity results. VIDIM is fast to sample from as it jointly denoises all the frames to be generated, requires less than a billion parameters per diffusion model to produce compelling results, and still enjoys scalability and improved quality at larger parameter counts. Please see our project page at vidim-interpolation.github.io.

Integrating traffic cameras with deep learning facilitates real-time multi-camera vehicle path reconstruction, benefiting smart city initiatives such as traffic management and public safety. The high demands on latency, bandwidth, and privacy underscore the necessity of edge computing platforms. However, the continuous operation of compute-intensive deep learning algorithms on round-the-clock camera streams can exceed the compute and power capacities of edge data centers. Therefore, it is critical to strategically deploy and activate camera streams to balance compute demands with performance requirements. Currently, there is a lack of tools to support this planning process. This paper presents Seer, a comprehensive suite of tools and algorithms that aids traffic planners in optimizing traffic camera placement and deep learning model deployment, considering compute and budgetary constraints. Seer encompasses (1) a graph-based algorithm for efficient camera placement incorporating road network topology, (2) a collaborative algorithm for vehicle path reconstruction that enables the use of less accurate but resource-efficient deep learning models, and (3) a scalable traffic simulation framework derived from open-source projects that model city road networks. Evaluations of Seer on two real-world road networks, each with thousands of intersections and simulated vehicle paths, show a 6.3x reduction in compute requirements. This is achieved through a combination of sparse camera deployment and the use of lightweight models, with an average 55% increase in the Hausdorff distance for the path reconstruction algorithm, translating to an absolute increase of 135 to 195 meters.

The popularity of High-Frequency Trading (HFT) or algorithmic trading has surged in the last ten years, largely due to the exponential increase in computing power. However, while software solutions for HFT have become increasingly optimized over time, they are still plagued by network stack, and kernel-user space separation overheads. Order book construction is a crucial step in any HFT system, as it provides a market snapshot on which trading decisions must be based and executed. This paper proposes a simple linear data structure for tracking the order book and a hybrid binary-linear search algorithm to maintain the top bid and ask offers corresponding to market depth, on FPGAs. Our approach takes into account that most trading activity occurs on the top of the bid and offer sides. Through design analysis and experimentation, we demonstrate that our simple approach is scalable and practical, outperforming previous methods.

In this paper we introduce a large-scale hand pose dataset, collected using a novel capture method. Existing datasets are either generated synthetically or captured using depth sensors: synthetic datasets exhibit a certain level of appearance difference from real depth images, and real datasets are limited in quantity and coverage, mainly due to the difficulty to annotate them. We propose a tracking system with six 6D magnetic sensors and inverse kinematics to automatically obtain 21-joints hand pose annotations of depth maps captured with minimal restriction on the range of motion. The capture protocol aims to fully cover the natural hand pose space. As shown in embedding plots, the new dataset exhibits a significantly wider and denser range of hand poses compared to existing benchmarks. Current state-of-the-art methods are evaluated on the dataset, and we demonstrate significant improvements in cross-benchmark performance. We also show significant improvements in egocentric hand pose estimation with a CNN trained on the new dataset.

A fuzzy match index for scale‐invariant feature transform (SIFT) features is proposed in this study that cumulatively involves all the test SIFT keypoints in the decision‐making process. The new fuzzy SIFT classifier is adapted successfully for robust face recognition from complex backgrounds without using any face cropping tools and using only a single training template. The further incorporation of entropy weights ensures that the facial features have a greater role in the soft decision‐making as compared with the background features. The highlights of the authors’ work are: (i) The development of a novel highly efficient fuzzy SIFT descriptor matching tool; (ii) incorporation of feature entropy weights to highlight the contribution of facial features; (iii) application to robust face recognition from uncropped images having diverse backgrounds with a single template for each subject. The authors thus allow for weak supervision of the face recognition experiment and obtain high accuracy for 20 subjects of the CALTECH‐256 face database, 133 subjects of the labelled faces for the wild dataset and 994 subjects of the FERET database, with state‐of‐the‐art comparisons indicating the supremacy of the authors’ approach.