New method could increase LLM training efficiency
By leveraging idle computing time, researchers can double the speed of model training while preserving accuracy.
Archives AI News
Tackling industry’s burdensome bubble problem
MIT researchers uncovered the physics behind bubble-removing membranes that could improve bioreactors, chemical production, and more.
Spurious Rewards: Rethinking Training Signals in RLVR
arXiv:2506.10947v2 Announce Type: replace-cross Abstract: We show that reinforcement learning with verifiable rewards (RLVR) can elicit strong mathematical reasoning in certain language models even with spurious rewards that have little, no, or even negative correlation with the correct answer. For…
Optimizer choice matters for the emergence of Neural Collapse
arXiv:2602.16642v3 Announce Type: replace Abstract: Neural Collapse (NC) refers to the emergence of highly symmetric geometric structures in the representations of deep neural networks during the terminal phase of training. Despite its prevalence, the theoretical understanding of NC remains limited.…
Overparameterized Multiple Linear Regression as Hyper-Curve Fitting
arXiv:2404.07849v2 Announce Type: replace-cross Abstract: This work demonstrates that applying a fixed-effect multiple linear regression (MLR) model to an overparameterized dataset is mathematically equivalent to fitting a hyper-curve parameterized by a single scalar. This reformulation shifts the focus from global…
Quantum enhanced ensemble GANs for anomaly detection in continuous biomanufacturing
arXiv:2508.21438v2 Announce Type: replace Abstract: The development of continuous biomanufacturing processes requires robust and early anomaly detection, since even minor deviations can compromise yield and stability, leading to disruptions in scheduling, reduced weekly production, and diminished economic performance. These processes…
NTK-Guided Implicit Neural Teaching
arXiv:2511.15487v2 Announce Type: replace Abstract: Implicit Neural Representations (INRs) parameterize continuous signals via multilayer perceptrons (MLPs), enabling compact, resolution-independent modeling for tasks like image, audio, and 3D reconstruction. However, fitting high-resolution signals demands optimizing over millions of coordinates, incurring prohibitive…
Coarsening Bias from Variable Discretization in Causal Functionals
arXiv:2602.22083v1 Announce Type: cross Abstract: A class of causal effect functionals requires integration over conditional densities of continuous variables, as in mediation effects and nonparametric identification in causal graphical models. Estimating such densities and evaluating the resulting integrals can be…
Active operator learning with predictive uncertainty quantification for partial differential equations
arXiv:2503.03178v4 Announce Type: replace Abstract: With the increased prevalence of neural operators being used to provide rapid solutions to partial differential equations (PDEs), understanding the accuracy of model predictions and the associated error levels is necessary for deploying reliable surrogate…
SymTorch: A Framework for Symbolic Distillation of Deep Neural Networks
arXiv:2602.21307v1 Announce Type: new Abstract: Symbolic distillation replaces neural networks, or components thereof, with interpretable, closed-form mathematical expressions. This approach has shown promise in discovering physical laws and mathematical relationships directly from trained deep learning models, yet adoption remains limited…