Learning informative representations of phylogenetic tree structures is essential for analyzing evolutionary relationships. Classical distance-based methods have been widely used to project phylogenetic trees into Euclidean space, but they are often sensitive to the choice of distance metric and may lack sufficient resolution. In this paper, we introduce phylogenetic variational autoencoders (PhyloVAEs), an unsupervised learning framework designed for representation learning and generative modeling of tree topologies. Leveraging an efficient encoding mechanism inspired by autoregressive tree topology generation, we develop a deep latent-variable generative model that facilitates fast, parallelized topology generation. Phylo-VAE combines this generative model with a collaborative inference model based on learnable topological features, allowing for high-resolution representations of phylogenetic tree samples. Extensive experiments demonstrate PhyloVAE's robust representation learning capabilities and fast generation of phylogenetic tree topologies. Phylogenetic trees are the foundational structure for describing the evolutionary processes among individuals or groups of biological entities. Reconstructing these trees based on collected biological sequences (e.g., DNA, RNA, protein) from observed species, also known as phylogenetic inference (Felsenstein, 2004), is an essential discipline of computational biology (Fitch, 1971; Felsenstein, 1981; Yang & Rannala, 1997; Ronquist et al., 2012). Large collections of trees obtained from these approaches (e.g., posterior samples from MCMC runs (Ronquist et al., 2012)), however, are often difficult to summarize or visualize due to the discrete and non-Euclidean nature of the tree topology space The classical approach to visualize and analyze distributions of phylogenetic trees is to calculate pairwise distances between the trees and project them into a plane using multidimensional scaling (MDS) (Amenta & Klingner, 2002; Hillis et al., 2005; Jombart et al., 2017). However, these approaches have the shortcoming that one can not map an arbitrary point in the visualization to a tree, and therefore do not form an actual visualization of the relevant tree space.

Quantum computing promises advantages over classical computing. The manufacturing of quantum hardware is in the infancy stage, called the Noisy Intermediate-Scale Quantum (NISQ) era. A major challenge is automated quantum circuit design that map a quantum circuit to gates in a universal gate set. In this paper, we present a generic MDP modeling and employ Q-learning and DQN algorithms for quantum circuit design. By leveraging the power of deep reinforcement learning, we aim to provide an automatic and scalable approach over traditional hand-crafted heuristic methods.

In real-world applications, spectral Graph Neural Networks (GNNs) are powerful tools for processing diverse types of graphs. However, a single GNN often struggles to handle different graph types-such as homogeneous and heterogeneous graphs-simultaneously. This challenge has led to the manual design of GNNs tailored to specific graph types, but these approaches are limited by the high cost of labor and the constraints of expert knowledge, which cannot keep up with the rapid growth of graph data. To overcome these challenges, we propose AutoSGNN, an automated framework for discovering propagation mechanisms in spectral GNNs. AutoSGNN unifies the search space for spectral GNNs by integrating large language models with evolutionary strategies to automatically generate architectures that adapt to various graph types. Extensive experiments on nine widely-used datasets, encompassing both homophilic and heterophilic graphs, demonstrate that AutoSGNN outperforms state-of-the-art spectral GNNs and graph neural architecture search methods in both performance and efficiency.

In this work, we present a comprehensive exploration of finetuning Malaysian language models, specifically Llama2 and Mistral, on embedding tasks involving negative and positive pairs. We release two distinct models tailored for Semantic Similarity and Retrieval-Augmented Generation (RAG). For Semantic Similarity, our 600 million parameter Llama2 model outperforms OpenAI text-embedding-ada-002 across all recall@k metrics for b.cari.com.my, c.cari.com.my, Malay news, and Malaysian Twitter test sets. In the realm of RAG models, our approach proves competitive with OpenAI text-embedding-ada-002 in the Malaysian context. Notably, our 2 billion parameter Llama2 model achieves superior Recall@5, Recall@10 for the "Melayu" keyword research papers dataset and excels in Recall@3, Recall@5, and Recall@10 for the lom.agc.gov.my dataset. These findings underscore the effectiveness of our finetuning strategy and highlight the performance gains in both Semantic Similarity and RAG tasks. All models released at https://huggingface.co/collections/mesolitica/malaysian-embedding-6523612bfe5881ad35f81b99

Language Models (LMs) can perform new tasks by adapting to a few in-context examples. For humans, explanations that connect examples to task principles can improve learning. We therefore investigate whether explanations of few-shot examples can help LMs. We annotate questions from 40 challenging tasks with answer explanations, and various matched control explanations. We evaluate how different types of explanations, instructions, and controls affect zero- and few-shot performance. We analyze these results using statistical multilevel modeling techniques that account for the nested dependencies among conditions, tasks, prompts, and models. We find that explanations can improve performance -- even without tuning. Furthermore, explanations hand-tuned for performance on a small validation set offer substantially larger benefits, and building a prompt by selecting examples and explanations together substantially improves performance over selecting examples alone. Finally, even untuned explanations outperform carefully matched controls, suggesting that the benefits are due to the link between an example and its explanation, rather than lower-level features. However, only large models benefit. In summary, explanations can support the in-context learning of large LMs on challenging tasks.

Swiss Re, the world's leading reinsurance organisation, in collaboration with MachineHack, is set to launch a Machine Learning Hackathon from March 11th to 28th to predict accident risk scores for unique postcodes. The top three winners stand a chance to win prizes worth INR 1.5 lakh. Swiss Re applies fresh perspectives, knowledge and capital to anticipate and manage risk to create smarter solutions. Swiss Re's Global Business Solutions Center (BSC) in Bangalore has more than 1,300 professionals leveraging experience, expertise and out-of-the-box thinking to create new business opportunities. Click here to participate in the hackathon.

Here we have used Conv1d with TimeDistributed Layer, which is then fed to a single layer of LSTM, to predicted different sequences, as illustrated by the figure below. The CNN model is built first, where each layer in the CNN model is wrapped in a TimeDistributed layer, and then added to the LSTM model. However, the other alternative approach could be used to construct the CNN model first, then add it to the LSTM model by wrapping the entire sequence of CNN layers in a TimeDistributed layer. TimeDistributed Layer is primarily used to present several sets of data (say sequences/mages) that are chronologically ordered to detect trends/ movements, actions, directions.

The following letter was addressed to Daniel Bobrow, editor of Artificial Intelligence Many of us felt that the issue raised is a very important one for the AAAI and deserved wide exposure It is printed here, along with Bobrow's reply, for your interest. The intervening three centuries have proven Oldenburg's invention to be a priceless vehicle for the dissemination of knowledge. It is, therefore, ironic indeed that artificial intelligence, a field whose very essence is knowledge, has developed a literature that is extraordinarily difficult and inefficient to use. Effective use of the literature of AI is frustrated by two fundamental deficiencies: (a) there is no central index to the field's published works, and (b) not only are far too many original works not published in journals, but a shockingly high percentage of these are "published" in sources that may be generously described as inaccessible. As an example of a field that does not have these problems, consider medicine.

Collaborative query routing is a new paradigm for web search that treats both established search engines and other publicly available indexes as intelligent peer agents in a search network. The approach makes it transparent for anyone to build his or her own (micro) search engine by integrating established web search services, desktop search, and topical crawling techniques. The challenge in this model is that each of these agents must learn about its environment--the existence, knowledge, diversity, reliability, and trustworthiness of other agents--by analyzing the queries received from and results exchanged with these other agents. We present the 6S peer network, which uses machine-learning techniques to learn about the changing query environment. We show that simple reinforcement learning algorithms are sufficient to detect and exploit semantic locality in the network, resulting in efficient routing and highquality search results.