A faster way to estimate AI power consumption
The “EnergAIzer” method generates reliable results in seconds, enabling data center operators to efficiently allocate resources and reduce wasted energy.
Archives AI News
LLMPhy: Parameter-Identifiable Physical Reasoning Combining Large Language Models and Physics Engines
arXiv:2411.08027v3 Announce Type: replace Abstract: Most learning-based approaches to complex physical reasoning sidestep the crucial problem of parameter identification (e.g., mass, friction) that governs scene dynamics, despite its importance in real-world applications such as collision avoidance and robotic manipulation. In…
Presenting DiaData for Research on Type 1 Diabetes
arXiv:2508.09160v2 Announce Type: replace Abstract: Type 1 diabetes (T1D) is an autoimmune disorder that leads to the destruction of insulin-producing cells, resulting in insulin deficiency, as to why the affected individuals depend on external insulin injections. However, insulin can decrease…
Sparse Network Inference under Imperfect Detection and its Application to Ecological Networks
arXiv:2604.18820v2 Announce Type: replace-cross Abstract: Recovering latent structure from count data has received considerable attention in network inference, particularly when one seeks both cross-group interactions and within-group similarity patterns in bipartite networks, which is widely used in ecology research. Such…
Adversarial Malware Generation in Linux ELF Binaries via Semantic-Preserving Transformations
arXiv:2604.22639v1 Announce Type: cross Abstract: Malware development and detection have undergone significant changes in recent years as modern concepts, such as machine learning, have been used for both adversarial attacks and defense. Despite intensive research on Windows Portable Executable (PE)…
Online Distributional Regression
arXiv:2407.08750v4 Announce Type: replace-cross Abstract: Large-scale streaming data are common in modern machine learning applications and have led to the development of online learning algorithms. Many fields, such as supply chain management, weather and meteorology, energy markets, and finance, have…
Interpretable Deep Learning for Stock Returns: A Consensus-Bottleneck Asset Pricing Model
arXiv:2512.16251v5 Announce Type: replace-cross Abstract: We introduce the Consensus-Bottleneck Asset Pricing Model (CB-APM), which embeds aggregate analyst consensus as a structural bottleneck, treating professional beliefs as a sufficient statistic for the market’s high-dimensional information set. Unlike post-hoc explainability approaches, CB-APM…
Kernel Contracts: A Specification Language for ML Kernel Correctness Across Heterogeneous Silicon
arXiv:2604.22032v1 Announce Type: new Abstract: Every ML kernel ships with an implicit contract about what it computes. People rarely write the contract down. When two kernels disagree — when a matmul on AMD produces a different gradient than the same…
Regularized Meta-Learning for Improved Generalization
arXiv:2602.12469v2 Announce Type: replace Abstract: Deep ensemble methods often improve predictive performance, yet they suffer from three practical limitations: redundancy among base models that inflates computational cost and degrades conditioning, unstable weighting under multicollinearity, and overfitting in meta-learning pipelines. We…
Universal Transformers Need Memory: Depth-State Trade-offs in Adaptive Recursive Reasoning
arXiv:2604.21999v1 Announce Type: new Abstract: We study learned memory tokens as computational scratchpad for a single-block Universal Transformer (UT) with Adaptive Computation Time (ACT) on Sudoku-Extreme, a combinatorial reasoning benchmark. We find that memory tokens are empirically necessary: across all…