Skip to content
TILens What matters today in tech v0.3.2
Theme

Topic - Edition

AI Research

537 items on 16 Nov 2026
AI Research AI Python

After 10 Heads in a Row, Small LLMs Bet Up to 82% on an 11th

Telling eight base and instruction-tuned open models that the coin is fair and the flips are independent trims their streak bias by only a few points. The post After 10 Heads in a Row, Small LLMs Bet Up to 82% on an…

Source: Towards Data Science Utkarsh Mangal
AI Research AI Python

Why Human in the Loop AI Oversight Fails and How to Fix It

Kahneman's System 1 and System 2, plus the ODPS, ODCS, and Ossie standards, show how to wake reviewers up only when a check fails. The post Why Human in the Loop AI Oversight Fails and How to Fix It appeared first on…

Source: Towards Data Science Corné Potgieter
AI Research AI

Do Mixture-of-Experts Routers Benefit from Ensembling?

arXiv:2611.17472v1 Announce Type: new Abstract: Ensembles of neural networks have repeatedly been shown to outperform single networks. Ensemble theory attributes this gain to the accuracy of the individual members and…

Source: arXiv cs.LG Viktor Vesel\'y, Sebastian Jitaru
AI Research AI

Manifold Approximation leads to Robust Kernel Alignment

arXiv:2510.22953v3 Announce Type: replace Abstract: Centered kernel alignment (CKA) is a popular metric for comparing representations, determining equivalence of networks, and conducting neuroscience research. However,…

Source: arXiv cs.LG Mohammad Tariqul Islam, Du Liu, Deblina Sarkar
AI Research AI

Fuse-All MoE Inference Kernel with Load Balancing on TPUs

arXiv:2611.17857v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures activate only a subset of experts for each token, allowing large language models (LLMs) to scale parameter capacity without a…

Source: arXiv cs.LG Rupeng Liu, Bangsheng Tang, Zongwei Zhou, Chengji Yao, Yejin Lee
AI Research AI

Fuse-PINN: Combining Finite Element Methods and Physics-Informed Neural Networks to enable massively parallel simulations of non-linear PDEs

arXiv:2611.18409v1 Announce Type: new Abstract: Research in the domain of Physics-Informed Neural Networks applied to PDE modelling has advanced significantly in recent years, providing a wide ecosystem of novel…

Source: arXiv cs.LG Stanislas Pamela, Nicolas Pailliez, Emmanuel Franck, Victor Michel-Dansac, Laurent Navoret, Vignesh Gopakumar
AI Research AI

Bayesian Transfer Operators in Reproducing Kernel Hilbert Spaces

arXiv:2509.22482v3 Announce Type: replace Abstract: Transfer operators provide a linear description of nonlinear dynamical systems by propagating observables or probability distributions. In reproducing kernel Hilbert…

Source: arXiv cs.LG Septimus Boshoff, Stefan Klus, Sebastian Peitz
AI Research AI

SA-RAG: Structuring Noisy Conversations for Retrieval-Augmented Generation

arXiv:2605.24366v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have been widely adopted in conversational applications. However, their reliance on parametric knowledge limits reliability in…

Source: arXiv cs.LG Kaiqiao Han, LuAn Tang, Renliang Sun, Peng Yuan, Wei Cheng, Haoyu Wang, Wei Wang, Yizhou Sun, Haifeng Chen
AI Research AI

Compiling Specialized GPU-Initiated Networking

arXiv:2611.18145v1 Announce Type: cross Abstract: Machine learning systems specialize computation to the workload and hardware, but communication remains in generic libraries whose device code and transport decisions…

Source: arXiv cs.LG Javid Baydamirli, Ismayil Ismayilov, Kaan Oktay, Didem Unat
AI Research AI

Adversarially Batched Online Learning

arXiv:2611.17500v1 Announce Type: new Abstract: We introduce adversarially batched online learning, where the learner may update its decision rule only at a restricted set of time steps. Equivalently, the time horizon…

Source: arXiv cs.LG Mingda Qiao, Kerui Wu
AI Research AI

Binarization as an Attack Surface in Weightless Neural Networks

arXiv:2611.17646v1 Announce Type: cross Abstract: Weightless Neural Networks (WNNs) are lightweight classifiers that binarize their inputs and learn by storing binary patterns in lookup memories, which makes them…

Source: arXiv cs.LG Lucas Senos Coutinho, Matheus Vargas, Pedro Teixeira, Heudson Tosta Mirandola, Ori Rottenstreich, Priscila Machado Vieira Lima, Leandro Santiago, Daniel Sadoc Menasche

537 items available