April 2026

arXiv:2604.16878v1 Announce Type: new Abstract: Early prediction of severe clinical deterioration and remaining length of stay can enable timely intervention and better resource allocation in high-acuity settings such as the ICU. This has driven the development of machine learning models that leverage continuous streams of vital signs and other physiological signals for real-time risk prediction. Despite their promise, existing methods have important limitations. Contrastive pretraining treats all patients as equally strong negatives, failing to capture clinically meaningful similarity […]

Ver mais

arXiv:2604.16875v1 Announce Type: new Abstract: A central question in computational neuroscience is whether the learning rule used to train a neural network determines how well its internal representations align with those of the human visual cortex. We present a systematic comparison of four learning rules — backpropagation (BP), feedback alignment (FA), predictive coding (PC), and spike-timing-dependent plasticity (STDP) — applied to identical convolutional architectures and evaluated against human fMRI data from the THINGS-fMRI dataset (720 stimuli, 3 subjects) […]

Ver mais

arXiv:2604.16872v1 Announce Type: new Abstract: Large Language Models (LLMs) can be helpful for literature search and summarisation, but retracted articles can confuse them. This article asks three open weights (offline) LLMs whether 161 high profile retracted articles had been retracted, performing a similar check for a benchmark multidisciplinary set of 34,070 non-retracted articles. Based on titles and abstracts, in over 80% of cases the LLMs claimed that a retracted article had not been retracted (GPT OSS 120B: 82%; […]

Ver mais

arXiv:2604.16871v1 Announce Type: new Abstract: Neuro-symbolic Reinforcement Learning (NeSy-RL) combines symbolic reasoning with gradient-based optimization to achieve interpretable and generalizable policies. Relational concepts, such as “left of” or “close by”, serve as foundational building blocks that structure how agents perceive and act. However, conventional approaches require human experts to manually define these concepts, limiting adaptability since concept semantics vary across environments. We propose GRAIL (Grounding Relational Agents through Interactive Learning), a framework that autonomously grounds relational concepts through […]

Ver mais

Faster execution, weaker understanding Most companies think AI agents create a tooling problem. They don’t. They create an interpretation problem. Agents write code. n Answer customers. n Generate dashboards. n Trigger workflows. n Approve actions. That looks like execution. But underneath, something else is happening. Every agent is also interpreting reality. And once enough agents are operating inside the same company, the real risk is no longer automation. It is unaligned interpretation at scale. Every Agent Carries Its […]

Ver mais

In gradient-based learning, a step size chosen in parameter units does not produce a predictable per-step change in function output. This often leads to instability in the streaming setting (i.e., batch size=1), where stochasticity is not averaged out and update magnitudes can momentarily become arbitrarily big or small. Instead, we propose intentional updates: first specify the intended outcome of an update and then solve for the step size that approximately achieves it. This strategy has precedent in online […]

Ver mais

One of the most challenging problems in graph machine learning is generalizing across graphs with diverse properties. Graph neural networks (GNNs) face a fundamental limitation: they require separate training for each new graph, preventing universal generalization across diverse graph datasets. A critical challenge facing GNNs lies in their reliance on labeled training data for each individual graph, a requirement that hinders the capacity for universal node classification due to the heterogeneity inherent in graphs — differences in homophily […]

Ver mais

Safe Reinforcement Learning from Human Feedback (Safe RLHF) has recently achieved empirical success in developing helpful and harmless large language models by decoupling human preferences regarding helpfulness and harmlessness. Existing approaches typically rely on fitting fixed horizon reward models from human feedback and have only been validated empirically. In this paper, we formulate safe RLHF as an infinite horizon discounted Con- strained Markov Decision Process (CMDP), since humans may interact with the model over a continuing sequence of […]

Ver mais

Diffusion distillation, exemplified by Distribution Matching Distillation (DMD), has shown great promise in few-step generation but often sacrifices quality for sampling speed. While integrating Reinforcement Learning (RL) into distillation offers potential, a naive fusion of these two objectives relies on suboptimal raw sample evaluation. This sample-based scoring creates inherent conflicts with the distillation trajectory and produces unreliable rewards due to the noisy nature of early-stage generation. To overcome these limitations, we propose GDMD, a novel framework that redefines […]

Ver mais

Here are two beliefs that are sort of haunting me right now: Folk who try to push people to uphold principles (whether established ones or novel ones), are kinda an important bedrock of civilization. Also, those people are really annoying and often, like, a little bit crazy And these both feel fairly important. I’ve learned a lot from people who have some kind of hobbyhorse about how society is treating something as okay/fine, when it’s not okay/fine. When […]

Ver mais