January 2026

Hi everyone, I’ve made an open-source tool in Python (called Omni-NLI) for natural language inference. It can use different models to check if a piece of text (called a premise) supports another piece of text (a hypothesis). Currently, Omni-NLI has the following features: Can be installed as a Python package with `pip install omni-nli[huggingface]`. Can be used on your own computer, so your data stays local and private. Has an MCP interface and a REST API Supports using […]

Ver mais

Understanding what graph neural networks can learn, especially their ability to learn to execute algorithms, remains a central theoretical challenge. In this work, we prove exact learnability results for graph algorithms under bounded-degree and finite-precision constraints. Our approach follows a two-step process. First, we train an ensemble of multi-layer perceptrons (MLPs) to execute the local instructions of a single node. Second, during inference, we use the trained MLP ensemble as the update function within a graph neural network […]

Ver mais

Cryptocurrency and privacy don’t fit together as easily as you might expect. Blockchains give you the illusion of privacy via pseudonymization: you don’t put your name on a blockchain, but you do put information on a blockchain that can be used to determine your name. Blockchain analysis can often reveal information that no one intended to share. This is true even for privacy coins like Monero and Zcash. These coins put less information directly on chain in the […]

Ver mais

We present MeshGraphNet-Transformer (MGN-T), a novel architecture that combines the global modeling capabilities of Transformers with the geometric inductive bias of MeshGraphNets, while preserving a mesh-based graph representation. MGN-T overcomes a key limitation of standard MGN, the inefficient long-range information propagation caused by iterative message passing on large, high-resolution meshes. A physics-attention Transformer serves as a global processor, updating all nodal states simultaneously while explicitly retaining node and edge attributes. By directly capturing long-range physical interactions, MGN-T eliminates […]

Ver mais

Current neural architectures lack a principled way to handle interchangeable tokens, i.e., symbols that are semantically equivalent yet distinguishable, such as bound variables. As a result, models trained on fixed vocabularies often struggle to generalize to unseen symbols, even when the underlying semantics remain unchanged. We propose a novel Transformer-based mechanism that is provably invariant to the renaming of interchangeable tokens. Our approach employs parallel embedding streams to isolate the contribution of each interchangeable token in the input, […]

Ver mais

Pain management in intensive care usually involves complex trade-offs between therapeutic goals and patient safety, since both inadequate and excessive treatment may induce serious sequelae. Reinforcement learning can help address this challenge by learning medication dosing policies from retrospective data. However, prior work on sedation and analgesia has optimized for objectives that do not value patient survival while relying on algorithms unsuitable for imperfect information settings. We investigated the risks of these design choices by implementing a deep […]

Ver mais

In the post-Dennard era, optimizing embedded systems requires navigating complex trade-offs between energy efficiency and latency. Traditional heuristic tuning is often inefficient in such high-dimensional, non-smooth landscapes. In this work, we propose a Bayesian Optimization framework using Gaussian Processes to automate the search for optimal scheduling configurations on heterogeneous multi-core architectures. We explicitly address the multi-objective nature of the problem by approximating the Pareto Frontier between energy and time. Furthermore, by incorporating Sensitivity Analysis (fANOVA) and comparing different […]

Ver mais

How are you, hacker? 🪐 What’s happening in tech today, January 30, 2026? The HackerNoon Newsletter brings the HackerNoon homepage straight to your inbox. On this day, Charles I, King of England, was executed in 1649, Adolf Hitler was appointed Chancellor of Germany in 1933, Mahatma Gandhi was assassinated by a Hindu nationalist. Gandhi in 1948, and we present you with these top quality stories. From The MoSCoW Method: Key to Agile Product Management to Will Media Over […]

Ver mais