Experiment in one of the world's quietest rooms reveals the hairs detect airborne sounds--like predators. Breakthroughs, discoveries, and DIY tips sent six days a week. Have you ever walked into a room full of caterpillars? While the answer for most people is probably no, those of us who have may have noticed the insects reacting to the sound of your voice. That's what happened to Carol Miles, a biologist at Binghamton University in New York.

Message-passing graph neural networks (MPGNNs) dominate modern graph learning. Typical efforts enhance MPGNN's expressive power by enriching the adjacency-based aggregation. In contrast, we introduce an efficient aggregation over walk incidence-based matrices that are constructed to deliberately trade off some expressivity for stronger and more structured inductive bias. Our approach allows for seamless scaling between classical message-passing and simpler methods based on walks. We rigorously characterize the expressive power at each intermediate step using homomorphism counts over a hierarchy of generalized caterpillar graphs. Based on this foundation, we propose Caterpillar GNNs, whose robust graph-level aggregation successfully tackles a benchmark specifically designed to challenge MPGNNs. Moreover, we demonstrate that, on real-world datasets, Caterpillar GNNs achieve comparable predictive performance while significantly reducing the number of nodes in the hidden layers of the computational graph.

The United Nations special rapporteur on the situation of human rights in the occupied Palestinian territory (oPt) has released a new report mapping the corporations aiding Israel in the displacement of Palestinians and its genocidal war on Gaza, in breach of international law. Francesca Albanese's latest report, which is scheduled to be presented at a news conference in Geneva on Thursday, names 48 corporate actors, including United States tech giants Microsoft, Alphabet Inc. – Google's parent company – and Amazon. A database of more than 1000 corporate entities was also put together as part of the investigation. "[Israel's] forever-occupation has become the ideal testing ground for arms manufacturers and Big Tech – providing significant supply and demand, little oversight, and zero accountability – while investors and private and public institutions profit freely," the report said. "Companies are no longer merely implicated in occupation – they may be embedded in an economy of genocide," it said, in a reference to Israel's ongoing assault on the Gaza Strip.

We introduce novel null models for assessing the results obtained from observed binary transactional and sequence datasets, using statistical hypothesis testing. Our null models maintain more properties of the observed dataset than existing ones. Specifically, they preserve the Bipartite Joint Degree Matrix of the bipartite (multi-)graph corresponding to the dataset, which ensures that the number of caterpillars, i.e., paths of length three, is preserved, in addition to other properties considered by other models. We describe Alice, a suite of Markov chain Monte Carlo algorithms for sampling datasets from our null models, based on a carefully defined set of states and efficient operations to move between them. The results of our experimental evaluation show that Alice mixes fast and scales well, and that our null model finds different significant results than ones previously considered in the literature.

A tournament is a method to decide the winner in a competition, and describes the overall sequence in which matches between the players are held. While deciding a worthy winner is the primary goal of a tournament, a close second is to maximize the value generated for the matches played, with value for a match measured either in terms of tickets sold, television viewership, advertising revenue, or other means. Tournament organizers often seed the players -- i.e., decide which matches are played -- to increase this value. We study the value maximization objective in a particular tournament format called Challenge the Champ. This is a simple tournament format where an ordering of the players is decided. The first player in this order is the initial champion. The remaining players in order challenge the current champion; if a challenger wins, she replaces the current champion. We model the outcome of a match between two players using a complete directed graph, called a strength graph, with each player represented as a vertex, and the direction of an edge indicating the winner in a match. The value-maximization objective has been recently explored for knockout tournaments when the strength graph is a directed acyclic graph (DAG). We extend the investigation to Challenge the Champ tournaments and general strength graphs. We study different representations of the value of each match, and completely characterize the computational complexity of the problem.

Significant progress has been made in advancing large multimodal conversational models (LMMs), capitalizing on vast repositories of image-text data available online. Despite this progress, these models often encounter substantial domain gaps, hindering their ability to engage in complex conversations across new domains. Recent efforts have aimed to mitigate this issue, albeit relying on domain-specific image-text data to curate instruction-tuning data. However, many domains, such as agriculture, lack such vision-language data. In this work, we propose an approach to construct instruction-tuning data that harnesses vision-only data for the agriculture domain. We utilize diverse agricultural datasets spanning multiple domains, curate class-specific information, and employ large language models (LLMs) to construct an expert-tuning set, resulting in a 70k expert-tuning dataset called AgroInstruct. Subsequently, we expert-tuned and created AgroGPT, an efficient LMM that can hold complex agriculture-related conversations and provide useful insights. We also develop AgroEvals for evaluation and compare {AgroGPT's} performance with large open and closed-source models. {AgroGPT} excels at identifying fine-grained agricultural concepts, can act as an agriculture expert, and provides helpful information for multimodal agriculture questions. The code, datasets, and models are available at https://github.com/awaisrauf/agroGPT.

With the recent Nobel Prize awarded for radical advances in protein discovery, foundation models (FMs) for exploring large combinatorial spaces promise to revolutionize many scientific fields. Artificial Life (ALife) has not yet integrated FMs, thus presenting a major opportunity for the field to alleviate the historical burden of relying chiefly on manual design and trial-and-error to discover the configurations of lifelike simulations. This paper presents, for the first time, a successful realization of this opportunity using vision-language FMs. The proposed approach, called Automated Search for Artificial Life (ASAL), (1) finds simulations that produce target phenomena, (2) discovers simulations that generate temporally open-ended novelty, and (3) illuminates an entire space of interestingly diverse simulations. Because of the generality of FMs, ASAL works effectively across a diverse range of ALife substrates including Boids, Particle Life, Game of Life, Lenia, and Neural Cellular Automata. A major result highlighting the potential of this technique is the discovery of previously unseen Lenia and Boids lifeforms, as well as cellular automata that are open-ended like Conway's Game of Life. Additionally, the use of FMs allows for the quantification of previously qualitative phenomena in a human-aligned way. This new paradigm promises to accelerate ALife research beyond what is possible through human ingenuity alone.

The pebble motion on trees (PMT) problem consists in finding a feasible sequence of moves that repositions a set of pebbles to assigned target vertices. This problem has been widely studied because, in many cases, the more general Multi-Agent path finding (MAPF) problem on graphs can be reduced to PMT. We propose a simple and easy to implement procedure, which finds solutions of length O(knc + n^2), where n is the number of nodes, $k$ is the number of pebbles, and c the maximum length of corridors in the tree. This complexity result is more detailed than the current best known result O(n^3), which is equal to our result in the worst case, but does not capture the dependency on c and k.

Amazon sells nearly everything under the sun, but the e-commerce giant has strict rules on what items customers can return. The policy's fine print shows that software downloads, video games and gift cards cannot be returned for a refund. While these sound reasonable, Amazon also clarifies that it will not take back live cockroaches, pet food and theme park tickets - so be sure you are committed to these purchases. You bought new photo editing software but never opened the box. Good news: You can return it within 30 days of purchase.

Just a few years ago, the promise seemed limitless: Automate cars and bring an end to traffic accidents, the biggest killer in the United States. Automate construction, with robot dozers, excavators, and other heavy machinery, and US housing and infrastructure shortfalls could be solved. Built Robotics began testing autonomous excavators in 2017 with the goal of training machines to do more on construction sites. At the time, CEO Noah Ready-Campbell predicted that fully autonomous equipment would become commonplace on construction sites before fully autonomous cars hit public roads. But after nearly seven years of digging trenches with autonomous excavators, Built Robotics last month announced plans to shift its focus from general construction projects to installation of solar farms.