搜索结果：Discover animals

People often see animal shapes in clouds, a phenomenon known as pareidolia. We propose an AI-based method that aims to predict which animals people are likely to perceive in clouds, even though state-of-the-art recognition methods typically fail to detect such animals. Additionally, we introduce a method to assist individuals in perceiving specific pareidolic animals, even if they did not recognize them initially. Our approach uses a diffusion model to transform cloud segments into an animal shape that visually resemble the original cloud. This diffusion technique is inspired by the observation that the diffusion process succeeds only when the target animal resembles the shape of the cloud, and that subtle visual hints often suffice to help individuals recognize specific pareidolic animals. A generated image, successfully derived from the diffusion model, is then used to predict the pareidolic animal. Additionally, a short morphing video transitioning from the generated image back to the original cloud segment is employed to further enhance the human's perception of the pareidolic animals.

Reconstructing the 3D geometry, pose, and motion of animals is a long-standing problem, which has a wide range of applications, from biology, livestock management, and animal conservation and welfare to content creation in digital entertainment and Virtual/Augmented Reality (VR/AR). Traditionally, 3D models of real animals are obtained using 3D scanners. These, however, are intrusive, often prohibitively expensive, and difficult to deploy in the natural environment of the animals. In recent years, we have seen a significant surge in deep learning-based techniques that enable the 3D reconstruction, in a non-intrusive manner, of the shape and motion of dynamic objects just from their RGB image and/or video observations. Several papers have explored their application and extension to various types of animals. This paper surveys the latest developments in this emerging and growing field of research. It categorizes and discusses the state-of-the-art methods based on their input modalities, the way the 3D geometry and motion of animals are represented, the type of reconstruction techniques they use, and the training mechanisms they adopt. It also analyzes the performance of some key meth

How can we use AI to discover a new state of the art for a scientific problem? Prior work in test-time scaling, such as AlphaEvolve, performs search by prompting a frozen LLM. We perform reinforcement learning at test time, so the LLM can continue to train, but now with experience specific to the test problem. This form of continual learning is quite special, because its goal is to produce one great solution rather than many good ones on average, and to solve this very problem rather than generalize to other problems. Therefore, our learning objective and search subroutine are designed to prioritize the most promising solutions. We call this method Test-Time Training to Discover (TTT-Discover). Following prior work, we focus on problems with continuous rewards. We report results for every problem we attempted, across mathematics, GPU kernel engineering, algorithm design, and biology. TTT-Discover sets the new state of the art in almost all of them: (i) Erdős' minimum overlap problem and an autocorrelation inequality; (ii) a GPUMode kernel competition (up to $2\times$ faster than prior art); (iii) past AtCoder algorithm competitions; and (iv) denoising problem in single-cell analysi

The COVID-19 pandemic is spreading rapidly around the world, causing countries to impose lockdowns and efforts to develop vaccines on a global scale. However, human-to-animal and animal-to-human transmission cannot be ignored, as severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) can spread rapidly in farmed and wild animals. This could create a worrying cycle of SARS-CoV-2 spillover from humans to animals and spillback of new strains back into humans, rendering vaccines ineffective. This study provides a key indicator of animals that may be potential susceptible hosts for SARS-CoV-2 and coronavirus infections by analysing the phylogenetic distance between host angiotensin-converting enzyme 2 and the coronavirus spike protein. Crucially, our analysis identifies animals that are at elevated risk from a spillover and spillback incident. One group of animals has been identified as potentially susceptible to SARS-CoV-2 by harbouring a parasitic coronavirus spike protein similar to the SARS-CoV-2 spike protein. These animals may serve as amplification hosts in spillover events from zoonotic reservoirs. Tracing interspecies transmission in multi-host environments based solely o

Existing methods for reconstructing animatable 3D animals from videos typically rely on sparse semantic keypoints to fit parametric models. However, obtaining such keypoints is labor-intensive, and keypoint detectors trained on limited animal data are often unreliable. To address this, we propose 4D-Animal, a novel framework that reconstructs animatable 3D animals from videos without requiring sparse keypoint annotations. Our approach introduces a dense feature network that maps 2D representations to SMAL parameters, enhancing both the efficiency and stability of the fitting process. Furthermore, we develop a hierarchical alignment strategy that integrates silhouette, part-level, pixel-level, and temporal cues from pre-trained 2D visual models to produce accurate and temporally coherent reconstructions across frames. Extensive experiments demonstrate that 4D-Animal outperforms both model-based and model-free baselines. Moreover, the high-quality 3D assets generated by our method can benefit other 3D tasks, underscoring its potential for large-scale applications. The code is released at https://github.com/zhongshsh/4D-Animal.

Animal learning has interested ecologists and psychologists for over a century. Mathematical models that explain how animals store and recall information have gained attention recently. Central to this work is statistical decision theory (SDT), which relates information uptake in animals to Bayesian inference. SDT effectively explains many learning tasks in animals, but extending this theory to predict how animals will learn in changing environments still poses a challenge for ecologists. We addressed this shortcoming with a novel implementation of Bayesian Markov Chain Monte Carlo (MCMC) sampling to simulate how animals sample environmental information and learn as a result. We applied our framework to an individual-based model simulating complex foraging tasks encountered by wild animals. Simulated ``animals" learned behavioral strategies that optimized foraging returns simply by following the principles of an MCMC sampler. In these simulations, behavioral plasticity was most conducive to efficient foraging in unpredictable and uncertain environments. Our model suggests that animals prioritize highly concentrated resources even when these resources are less available overall, in

3D generation guided by text-to-image diffusion models enables the creation of visually compelling assets. However previous methods explore generation based on image or text. The boundaries of creativity are limited by what can be expressed through words or the images that can be sourced. We present YouDream, a method to generate high-quality anatomically controllable animals. YouDream is guided using a text-to-image diffusion model controlled by 2D views of a 3D pose prior. Our method generates 3D animals that are not possible to create using previous text-to-3D generative methods. Additionally, our method is capable of preserving anatomic consistency in the generated animals, an area where prior text-to-3D approaches often struggle. Moreover, we design a fully automated pipeline for generating commonly found animals. To circumvent the need for human intervention to create a 3D pose, we propose a multi-agent LLM that adapts poses from a limited library of animal 3D poses to represent the desired animal. A user study conducted on the outcomes of YouDream demonstrates the preference of the animal models generated by our method over others. Turntable results and code are released at

An animal is a planar shape formed by attaching congruent regular polygons, known as tiles, along their edges. In this paper, we study extremal animals defined on regular tessellations of the plane. In 1976, Harary and Harborth studied animals in the Euclidean cases, finding extremal values for their vertices, edges, and tiles, when any one of these parameters is fixed. Here, we generalize their results to hyperbolic animals. For each hyperbolic tessellation, we exhibit a sequence of spiral animals and prove that they attain the minimal numbers of edges and vertices within the class of animals with $n$ tiles. In their conclusions, Harary and Harborth also proposed the question of enumerating extremal animals with a fixed number of tiles. This question has previously only been considered for Euclidean animals. As a first step in solving this problem, we find special sequences of extremal animals that are unique extremal animals, in the sense that any animal with the same number of tiles which is distinct up to isometries can't be extremal.

Rises in the number of animal abuse cases are reported around the world. While chatbots have been effective in influencing their users' perceptions and behaviors, little if any research has hitherto explored the design of chatbots that embody animal identities for the purpose of eliciting empathy toward animals. We therefore conducted a mixed-methods experiment to investigate how specific design cues in such chatbots can shape their users' perceptions of both the chatbots' identities and the type of animal they represent. Our findings indicate that such chatbots can significantly increase empathy, improve attitudes, and promote prosocial behavioral intentions toward animals, particularly when they incorporate emotional verbal expressions and authentic details of such animals' lives. These results expand our understanding of chatbots with non-human identities and highlight their potential for use in conservation initiatives, suggesting a promising avenue whereby technology could foster a more informed and empathetic society.

Here we introduce simple structures for the analysis of complex hypergraphs, hypergraph animals. These structures are designed to describe the local node neighbourhoods of nodes in hypergraphs. We establish their relationships to lattice animals and network motifs, and we develop their combinatorial properties for sparse and uncorrelated hypergraphs. We make use of the tight link of hypergraph animals to partition numbers, which opens up a vast mathematical framework for the analysis of hypergraph animals. We then study their abundances in random hypergraphs. Two transferable insights result from this analysis: (i) it establishes the importance of high-cardinality edges in ensembles of random hypergraphs that are inspired by the classical Erdös-Renyí random graphs; and (ii) there is a close connection between degree and hyperedge cardinality in random hypergraphs that shapes animal abundances and spectra profoundly. Both findings imply that hypergraph animals can have the potential to affect information flow and processing in complex systems. Our analysis of also suggests that we need to spend more effort on investigating and developing suitable conditional ensembles of random hype

The idea of 3D reconstruction as scene understanding is foundational in computer vision. Reconstructing 3D scenes from 2D visual observations requires strong priors to disambiguate structure. Much work has been focused on the anthropocentric, which, characterized by smooth surfaces, coherent normals, and regular edges, allows for the integration of strong geometric inductive biases. Here, we consider a more challenging problem where such assumptions do not hold: the reconstruction of natural scenes containing trees, bushes, boulders, and animals. While numerous works have attempted to tackle the problem of reconstructing animals in the wild, they have focused solely on the animal, neglecting environmental context. This limits their usefulness for analysis tasks, as animals exist inherently within the 3D world, and information is lost when environmental factors are disregarded. We propose a method to reconstruct natural scenes from single images. We base our approach on recent advances leveraging the strong world priors ingrained in Large Language Models and train an autoregressive model to decode a CLIP embedding into a structured compositional scene representation, encompassing bo

We present a framework for generating music-synchronized, choreography aware animal dance videos. Our framework introduces choreography patterns -- structured sequences of motion beats that define the long-range structure of a dance -- as a novel high-level control signal for dance video generation. These patterns can be automatically estimated from human dance videos. Starting from a few keyframes representing distinct animal poses, generated via text-to-image prompting or GPT-4o, we formulate dance synthesis as a graph optimization problem that seeks the optimal keyframe structure to satisfy a specified choreography pattern of beats. We also introduce an approach for mirrored pose image generation, essential for capturing symmetry in dance. In-between frames are synthesized using an video diffusion model. With as few as six input keyframes, our method can produce up to 30 seconds dance videos across a wide range of animals and music tracks.

Animals capable of powered flight range in wingspan from a few hundred microns to a few meters. The inertial turbulence to which these animals are exposed features vortices ranging from a few hundred micrometers to hundreds of kilometers in size. Yet, the impact of ambient turbulence on animal flight is virtually uncharted and most studies on animal flight are conducted in still air or under laminar conditions. Here, we propose a novel parameterization that links animal flight with turbulence, through a proxy for the energy injected into the atmosphere, $E_{sp}=b^3 f^2$, with $f$ the animal's flapping frequency and $b$ the wingspan. We model this parameter using a scaling relation in the shape of a power law $E_{sp} \propto k^α$, with $k=1/b$ the wavenumber corresponding to the animal inverse wingspan. Literature provides four theoretical predictions on the exponent $α$: two connected to aerodynamic and energetic aspects of flight, $α_{aero}=-2$ and $α_{power}=-5/3$, and two linked to physiological limits. Drawing from experimental data of over 400 species spanning 13 insect orders and two vertebrate classes, we recover $α_{power}=-5/3$ as the best scaling relation across the anima

We consider the local limit of finite uniformly distributed directed animals on the square lattice viewed from the root. Two constructions of the resulting uniform infinite directed animal are given: one as a heap of dominoes, constructed by letting gravity act on a right-continuous random walk and one as a Markov process, obtained by slicing the animal horizontally. We look at geometric properties of this local limit and prove, in particular, that it consists of a single vertex at infinitely many (random) levels. Several martingales are found in connection with the confinement of the infinite directed animal on the non-negative coordinates.

An animal is a planar shape formed by attaching congruent regular polygons along their edges. In 1976, Harary and Harborth gave closed isoperimetric formulas for Euclidean animals. Here, we provide analogous formulas for hyperbolic animals. We do this by proving a connection between Sturmian words and the parameters of a discrete analogue of balls in the graph determined by hyperbolic tessellations. This reveals a complexity in hyperbolic animals that is not present in Euclidean animals.

We consider minimal-perimeter lattice animals, providing a set of conditions which are sufficient for a lattice to have the property that inflating all minimal-perimeter animals of a certain size yields (without repetitions) all minimal-perimeter animals of a new, larger size. We demonstrate this result on the two-dimensional square and hexagonal lattices. In addition, we characterize the sizes of minimal-perimeter animals on these lattices that are not created by inflating members of another set of minimal-perimeter animals.

In-situ visual observations of marine organisms is crucial to developing behavioural understandings and their relations to their surrounding ecosystem. Typically, these observations are collected via divers, tags, and remotely-operated or human-piloted vehicles. Recently, however, autonomous underwater vehicles equipped with cameras and embedded computers with GPU capabilities are being developed for a variety of applications, and in particular, can be used to supplement these existing data collection mechanisms where human operation or tags are more difficult. Existing approaches have focused on using fully-supervised tracking methods, but labelled data for many underwater species are severely lacking. Semi-supervised trackers may offer alternative tracking solutions because they require less data than fully-supervised counterparts. However, because there are not existing realistic underwater tracking datasets, the performance of semi-supervised tracking algorithms in the marine domain is not well understood. To better evaluate their performance and utility, in this paper we provide (1) a novel dataset specific to marine animals located at http://warp.whoi.edu/vmat/, (2) an evalua

There has been significant work on learning realistic, articulated, 3D models of the human body. In contrast, there are few such models of animals, despite many applications. The main challenge is that animals are much less cooperative than humans. The best human body models are learned from thousands of 3D scans of people in specific poses, which is infeasible with live animals. Consequently, we learn our model from a small set of 3D scans of toy figurines in arbitrary poses. We employ a novel part-based shape model to compute an initial registration to the scans. We then normalize their pose, learn a statistical shape model, and refine the registrations and the model together. In this way, we accurately align animal scans from different quadruped families with very different shapes and poses. With the registration to a common template we learn a shape space representing animals including lions, cats, dogs, horses, cows and hippos. Animal shapes can be sampled from the model, posed, animated, and fit to data. We demonstrate generalization by fitting it to images of real animals including species not seen in training.

In this paper, we revisit the enumeration of directed animals using gas models. We show that there exists a natural construction of random directed animals on any directed graph together with a particle system that explains at the level of objects the formal link known between the density of the gas model and the generating function of directed animals counted according to the area. This provides some new methods to compute the generating function of directed animals counted according to area, and leads in the particular case of the square lattice to new combinatorial results and questions. A model of gas related to directed animals counted according to area and perimeter on any directed graph is also exhibited.