Tootfinder

Use multi level models with {parsnip}: http://multilevelmod.tidymodels.org/ #rstats #ML

via https://www.theguardian.com/technology/2025/may/26/large-language-models-that-power-ai-should-be-publicly-owned:
Matteo Valleriani: "It is time to build public, open-access LLMs for the humanities…

Source: Meta has hired highly influential OpenAI researcher Trapit Bansal to work on its AI reasoning models under the company's new AI superintelligence unit (Maxwell Zeff/TechCrunch)
https://techcrunch.com/2025/06/26/meta-hi…

Meta hires key OpenAI researcher to work on AI reasoning models | TechCrunch
Meta has hired a key OpenAI researcher to work on AI reasoning models under its new AI superintelligence unit.

Hybrid Models for Financial Forecasting: Combining Econometric, Machine Learning, and Deep Learning Models
Dominik Stempie\'n, Robert \'Slepaczuk
https://arxiv.org/abs/2505.19617

Hybrid Models for Financial Forecasting: Combining Econometric, Machine Learning, and Deep Learning Models
This research systematically develops and evaluates various hybrid modeling approaches by combining traditional econometric models (ARIMA and ARFIMA models) with machine learning and deep learning techniques (SVM, XGBoost, and LSTM models) to forecast financial time series. The empirical analysis is based on two distinct financial assets: the S&P 500 index and Bitcoin. By incorporating over two decades of daily data for the S&P 500 and almost ten years of Bitcoin data, the study provides a comp…

Last week, we continued our #ISE2025 lecture on distributional semantics with the introduction of neural language models (NLMs) and compared them to traditional statistical n-gram models.
Benefits of NLMs:
- Capturing Long-Range Dependencies
- Computational and Statistical Tractability
- Improved Generalisation
- Higher Accuracy
@…

CodeGuard: A Generalized and Stealthy Backdoor Watermarking for Generative Code Models
Haoxuan Li, Jiale Zhang, Xiaobing Sun, Xiapu Luo
https://arxiv.org/abs/2506.20926

CodeGuard: A Generalized and Stealthy Backdoor Watermarking for Generative Code Models
Generative code models (GCMs) significantly enhance development efficiency through automated code generation and code summarization. However, building and training these models require computational resources and time, necessitating effective digital copyright protection to prevent unauthorized leaks and misuse. Backdoor watermarking, by embedding hidden identifiers, simplifies copyright verification by breaking the model's black-box nature. Current backdoor watermarking techniques face two mai…

$T^3$: Multi-level Tree-based Automatic Program Repair with Large Language Models
Quanming Liu, Xupeng Bu, Zhichao Yan, Ru Li
https://arxiv.org/abs/2506.21211

$T^3$: Multi-level Tree-based Automatic Program Repair with Large Language Models
Automatic Program Repair (APR) is a core technology in software development and maintenance, with aims to enable automated defect repair with minimal human intervention. In recent years, the substantial advancements in Large Language Models (LLMs) and the Chain-of-Thought (CoT) techniques have significantly enhanced the reasoning capabilities of these models. However, due to the complex logic and multi-step reasoning ability needed, the application of CoT techniques in the APR domain remains in…

Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trends
Tian-Yu Xiang, Ao-Qun Jin, Xiao-Hu Zhou, Mei-Jiang Gui, Xiao-Liang Xie, Shi-Qi Liu, Shuang-Yi Wang, Sheng-Bin Duan, Fu-Chao Xie, Wen-Kai Wang, Si-Cheng Wang, Ling-Yun Li, Tian Tu, Zeng-Guang Hou
https://arxiv.org/abs/2506.20966…

Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trends
Vision-language-action (VLA) models extend vision-language models (VLM) by integrating action generation modules for robotic manipulation. Leveraging strengths of VLM in vision perception and instruction understanding, VLA models exhibit promising generalization across diverse manipulation tasks. However, applications demanding high precision and accuracy reveal performance gaps without further adaptation. Evidence from multiple domains highlights the critical role of post-training to align fou…

After training, we finetune on real-world data. We observe that the models that have been pre-trained with noise converge very quickly compared to a baseline which is trained from scratch.
Moreover, on the other datasets, the UP models retain their zero-shot performance during finetuning. This suggests that there may be a generalization benefit to using a UP model.
All this is at the expense of much longer training, but that cost can be amortized over many tasks.

Crystallization of metallic glass as a grain-boundary nucleated process: experimental and theoretical evidence for the grain structure of metallic glasses
Nikolay V. Alekseechkin
https://arxiv.org/abs/2506.21261

Crystallization of metallic glass as a grain-boundary nucleated process: experimental and theoretical evidence for the grain structure of metallic glasses
Experimental DSC and Avrami curves for the crystallization of metallic glasses demonstrate nucleation at grain boundaries and thus indicate their grain structure, which refutes the generally accepted idea of glass as a homogeneous frozen liquid obtained as a result of avoiding crystallization. Under certain conditions, this nucleation mechanism results in the appearance of two-peak DSC curves and three-step Avrami plots which are observed experimentally. To clarify these conditions, isothermal …