Related papers: Interpretable structural-semantic decoding reveals…
Universally modeling all typical information extraction tasks (UIE) with one generative language model (GLM) has revealed great potential by the latest study, where various IE predictions are unified into a linearized hierarchical…
Sparse Autoencoder (SAE) has emerged as a powerful tool for mechanistic interpretability of large language models. Recent works apply SAE to protein language models (PLMs), aiming to extract and analyze biologically meaningful features from…
The nondeterminism of Deep Learning (DL) training algorithms and its influence on the explainability of neural network (NN) models are investigated in this work with the help of image classification examples. To discuss the issue, two…
We investigate molecular mechanisms of resistant or sensitive response of cancer drug combination therapies in an inductive and interpretable manner. Though deep learning algorithms are widely used in the drug synergy prediction problem, it…
In the rewriting logic framework, equational-based specifications are used to define deterministic functional behavior, abstract data types, and canonical representations of data. These specifications include a (possibly order-sorted)…
Modern Artificial Intelligence (AI) systems excel at diverse tasks, from image classification to strategy games, even outperforming humans in many of these domains. After making astounding progress in language learning in the recent decade,…
The current structure-centric paradigm in artificial intelligence (AI)-driven materials discovery, despite delivering thousands of candidate structures, is stalling at a critical barrier: the synthesizability gap. We argue that closing this…
AI policy guidance is predominantly written as prose, which practitioners must first convert into executable rules before frameworks can evaluate or enforce them. This manual step is slow, error-prone, difficult to scale, and often delays…
The future development of an AI scientist, a tool that is capable of integrating a variety of experimental data and generating testable hypotheses, holds immense potential. So far, bespoke machine learning models have been created to…
While AI innovation accelerates rapidly, the intellectual process behind breakthroughs -- how researchers identify gaps, synthesize prior work, and generate insights -- remains poorly understood. The lack of structured data on scientific…
Structural probes learn a linear transformation to find how dependency trees are embedded in the hidden states of language models. This simple design may not allow for full exploitation of the structure of the encoded information. Hence, to…
Natural language understanding (NLU) of text is a fundamental challenge in AI, and it has received significant attention throughout the history of NLP research. This primary goal has been studied under different tasks, such as Question…
Compositional generalization remains a foundational weakness of modern neural networks, limiting their robustness and applicability in domains requiring out-of-distribution reasoning. A central, yet unverified, assumption in neuro-symbolic…
Inverse Protein Folding (IPF) is a critical subtask in the field of protein design, aiming to engineer amino acid sequences capable of folding correctly into a specified three-dimensional (3D) conformation. Although substantial progress has…
Modeling genomic sequences faces two unsolved challenges: the information density varies widely across different regions, while there is no clearly defined minimum vocabulary unit. Relying on either four primitive bases or independently…
Institutional decisions -- regulatory compliance, clinical triage, prior authorization appeal -- require a different AI architecture than general-purpose agents provide. Agent frameworks infer authority conversationally, reconstruct…
Generative AI is entering research, education, and professional work faster than current governance frameworks can specify how AI-assisted outputs should be judged in learning-intensive settings. The central problem is proxy failure: a…
Despite recent advances in modern machine learning algorithms, the opaqueness of their underlying mechanisms continues to be an obstacle in adoption. To instill confidence and trust in artificial intelligence systems, Explainable Artificial…
Despite the practical success of Artificial Intelligence (AI), current neural AI algorithms face two significant issues. First, the decisions made by neural architectures are often prone to bias and brittleness. Second, when a chain of…
Understanding how the human brain progresses from processing simple linguistic inputs to performing high-level reasoning is a fundamental challenge in neuroscience. While modern large language models (LLMs) are increasingly used to model…