A new framework called decoupled norm analysis (DNA) advances bilevel optimization by improving convergence rates for approximate implicit differentiation (AID) and iterative differentiation (ITD). AI…
Landmark-based embeddings on inhomogeneous random graphs offer tighter dimension-distortion trade-offs than traditional worst-case bounds, improving distance preservation in graph machine learning. A …
The VERaiPHY initiative provides a structured framework to evaluate machine learning's trustworthiness in physics, as ML systems become more autonomous in making scientific claims. Physicists are shif…
DAG-FM, a new model using Transformers and a Mixture-of-Leaf-Experts mechanism, outperforms traditional algorithms and other foundation models in causal discovery from observational data, achieving hi…
Researchers have developed LLM-PDESR, a framework that integrates large language models with rigorous evaluation to discover partial differential equations from noisy data, outperforming current metho…
A new framework grounded in generalized extrinsic information transfer (GEXIT) functions redefines diffusion model training by defining cross-entropy as an integral of local information-theoretic deri…
PG-EVIKAL, a new method for refining molecular property predictions at test time using neighbor fusion and evidential uncertainty, reduced root-mean-square error (RMSE) by a median of 19.4% across 16 …
A new method using compressed observable operators reveals latent treatment effects in observational data, offering a simpler and more stable alternative to traditional causal inference techniques. Th…
A machine learning framework using the IBM Telco Customer Churn dataset achieved 77.68% accuracy and a ROC AUC of 0.8403 in predicting customer churn, with CatBoost as the top performer among three gr…
Australia will become the first nation to house economic, social, security, and environmental concerns of artificial intelligence under a single national office, Prime Minister Anthony Albanese announ…
Vrbo's new AI-based candidate generation pipeline, using a large language model to generate diverse semantic queries, extends coverage to long-tail vacation rental properties that traditional item-bas…
Vilya, a new deep learning model called Vilya-1, improves geometric accuracy and broad chemical coverage for macrocyclic peptide design, addressing core challenges in drug development. Trained on dive…
AuditWeave, a new Python library, enhances accountability in AI-assisted decisions by creating a tamper-proof, hash-chained ledger that records each step in AI workflows. The library, which operates w…
A new study on quantized language models reveals that 4-bit models offer the best balance between efficiency and reliability, showing enhanced robustness to real-world input perturbations. The researc…
A new study reveals that low-precision training can cause AI model parameters to freeze when gradient updates fall below half the unit in the last place (ULP) of a weight, effectively halting learning…
Ground truth datasets in machine learning are not objective or universal but are constructed through human decisions and technological limitations, argues a new analysis calling for transparency and c…
A new method proposes a predictive divergence mask for reinforcement learning in large language models, offering potentially more stable updates than traditional Proximal Policy Optimization (PPO)-sty…
The Energy-guided Recursive Model (ERM) uses Hopfield energies to achieve a 98.97% completion rate on Sudoku puzzles, 88.04% on the Pencil Puzzle Benchmark, and 99.30% on Maze puzzles, signaling a pot…
Researchers have introduced a bilevel optimization framework for Direct Preference Optimization (DPO) that improves large language model alignment by filtering out noise in preference data. The method…
A Nobel laureate has warned that society has a limited window to prepare for the accelerating pace of technological advancement, citing risks from AI and quantum computing. The laureate urged governme…