International Conference on Learning Representations (ICLR) 2026
Apple is presenting new research at the annual International Conference on Learning Representations (ICLR), which takes place in person in Rio de Janeiro, Brazil, from April 23 to 27. We are proud to again sponsor the conference, which brings together the scientific and industrial research communiti...
AI safety shifts from the model to the system level. As AI becomes agentic and tool-driven, risk emerges from complex interactions, widening the gap between evaluation and real-world behavior.
Spectral Entropy Collapse as an Empirical Signature of Delayed Generalisation in Grokking
arXiv:2604.13123v1 Announce Type: new
Abstract: Grokking -- delayed generalisation long after memorisation -- lacks a predictive mechanistic explanation. We identify the normalised spectral entropy $\tilde{H}(t)$ of the representation covariance as a scalar order parameter for this transition, vali...
arXiv:2604.11838v1 Announce Type: new
Abstract: While critical for alignment, Supervised Fine-Tuning (SFT) incurs the risk of catastrophic forgetting, yet the layer-wise emergence of instruction-following capabilities remains elusive. We investigate this mechanism via a comprehensive analysis utili...
The Non-Optimality of Scientific Knowledge: Path Dependence, Lock-In, and The Local Minimum Trap
arXiv:2604.11828v1 Announce Type: new
Abstract: Science is widely regarded as humanity's most reliable method for uncovering truths about the natural world. Yet the \emph{trajectory} of scientific discovery is rarely examined as an optimization problem in its own right. This paper argues that the b...
The Long-Horizon Task Mirage? Diagnosing Where and Why Agentic Systems Break
arXiv:2604.11978v1 Announce Type: new
Abstract: Large language model (LLM) agents perform strongly on short- and mid-horizon tasks, but often break down on long-horizon tasks that require extended, interdependent action sequences. Despite rapid progress in agentic systems, these long-horizon failur...
Linear Programming for Multi-Criteria Assessment with Cardinal and Ordinal Data: A Pessimistic Virtual Gap Analysis
arXiv:2604.09555v1 Announce Type: new
Abstract: Multi-criteria Analysis (MCA) is used to rank alternatives based on various criteria. Key MCA methods, such as Multiple Criteria Decision Making (MCDM) methods, estimate parameters for criteria to compute the performance of each alternative. Nonethele...
Memory-Guided Trust-Region Bayesian Optimization (MG-TuRBO) for High Dimensions
arXiv:2604.08569v1 Announce Type: new
Abstract: Traffic simulation and digital-twin calibration is a challenging optimization problem with a limited simulation budget. Each trial requires an expensive simulation run, and the relationship between calibration inputs and model error is often nonconvex...
Sustained Impact of Agentic Personalisation in Marketing: A Longitudinal Case Study
arXiv:2604.08621v1 Announce Type: new
Abstract: In consumer applications, Customer Relationship Management (CRM) has traditionally relied on the manual optimisation of static, rule-based messaging strategies. While adaptive and autonomous learning systems offer the promise of scalable personalisati...
Inside the AI Index: 12 Takeaways from the 2026 Report
The annual report reveals a field hitting breakthrough capabilities while raising urgent questions about environmental costs, transparency, and who benefits from the technology.
AI is splitting in two directions. One path is controlled, restricted, and security-first. The other is open, autonomous, and scaling fast. The real question isn’t which is better, it’s what this means for trust.
We call it machine learning. But do machines actually learn?
Today's AI systems train, optimize, and scale, but real learning is something else entirely. The distinction matters more than the industry wants to admit.
Flow Learners for PDEs: Toward a Physics-to-Physics Paradigm for Scientific Computing
arXiv:2604.07366v1 Announce Type: new
Abstract: Partial differential equations (PDEs) govern nearly every physical process in science and engineering, yet solving them at scale remains prohibitively expensive. Generative AI has transformed language, vision, and protein science, but learned PDE solv...
Apple is presenting new research at the annual ACM (Association of Computing Machinery) CHI Conference on Human Factors in Computing Systems, which takes place in person in Barcelona, Spain, from April 13 to 17. We are proud to again sponsor the conference, which brings together the scientific and i...
High-Precision Estimation of the State-Space Complexity of Shogi via the Monte Carlo Method
arXiv:2604.06189v1 Announce Type: new
Abstract: Determining the state-space complexity of the game of Shogi (Japanese Chess) has been a challenging problem, with previous combinatorial estimates leaving a gap of five orders of magnitude ($10^{64}$ to $10^{69}$). This large gap arises from the diffi...
SymptomWise: A Deterministic Reasoning Layer for Reliable and Efficient AI Systems
arXiv:2604.06375v1 Announce Type: new
Abstract: AI-driven symptom analysis systems face persistent challenges in reliability, interpretability, and hallucination. End-to-end generative approaches often lack traceability and may produce unsupported or inconsistent diagnostic outputs in safety-critic...
Proximity Measure of Information Object Features for Solving the Problem of Their Identification in Information Systems
arXiv:2604.04939v1 Announce Type: new
Abstract: The paper considers a new quantitative-qualitative proximity measure for the features of information objects, where data enters a common information resource from several sources independently. The goal is to determine the possibility of their relatio...
ReVEL: Multi-Turn Reflective LLM-Guided Heuristic Evolution via Structured Performance Feedback
arXiv:2604.04940v1 Announce Type: new
Abstract: Designing effective heuristics for NP-hard combinatorial optimization problems remains a challenging and expertise-intensive task. Existing applications of large language models (LLMs) primarily rely on one-shot code synthesis, yielding brittle heuris...
Structural Segmentation of the Minimum Set Cover Problem: Exploiting Universe Decomposability for Metaheuristic Optimization
arXiv:2604.03234v1 Announce Type: new
Abstract: The Minimum Set Cover Problem (MSCP) is a classical NP-hard combinatorial optimization problem with numerous applications in science and engineering. Although a wide range of exact, approximate, and metaheuristic approaches have been proposed, most me...
General Explicit Network (GEN): A novel deep learning architecture for solving partial differential equations
arXiv:2604.03321v1 Announce Type: new
Abstract: Machine learning, especially physics-informed neural networks (PINNs) and their neural network variants, has been widely used to solve problems involving partial differential equations (PDEs). The successful deployment of such methods beyond academic ...
arXiv:2604.02434v1 Announce Type: new
Abstract: We study structured abstraction-based reasoning for the Abstraction and Reasoning Corpus (ARC) and compare its generalization to test-time approaches. Purely neural architectures lack reliable combinatorial generalization, while strictly symbolic syst...
AI breakthrough cuts energy use by 100x while boosting accuracy
AI is consuming staggering amounts of energy—already over 10% of U.S. electricity—and the demand is only accelerating. Now, researchers have unveiled a radically more efficient approach that could slash AI energy use by up to 100× while actually improving accuracy. By combining neural networks with ...
DySCo: Dynamic Semantic Compression for Effective Long-term Time Series Forecasting
arXiv:2604.01261v1 Announce Type: new
Abstract: Time series forecasting (TSF) is critical across domains such as finance, meteorology, and energy. While extending the lookback window theoretically provides richer historical context, in practice, it often introduces irrelevant noise and computationa...