Tootfinder

Risk In Context: Benchmarking Privacy Leakage of Foundation Models in Synthetic Tabular Data Generation
Jessup Byun, Xiaofeng Lin, Joshua Ward, Guang Cheng
https://arxiv.org/abs/2507.17066

Risk In Context: Benchmarking Privacy Leakage of Foundation Models in Synthetic Tabular Data Generation
Synthetic tabular data is essential for machine learning workflows, especially for expanding small or imbalanced datasets and enabling privacy-preserving data sharing. However, state-of-the-art generative models (GANs, VAEs, diffusion models) rely on large datasets with thousands of examples. In low-data settings, often the primary motivation for synthetic data, these models can overfit, leak sensitive records, and require frequent retraining. Recent work uses large pre-trained transformers to …

EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning
Xuan Ju, Tianyu Wang, Yuqian Zhou, He Zhang, Qing Liu, Nanxuan Zhao, Zhifei Zhang, Yijun Li, Yuanhao Cai, Shaoteng Liu, Daniil Pakhomov, Zhe Lin, Soo Ye Kim, Qiang Xu
https://arxiv.org/abs/2509.20360

EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning
Recent advances in foundation models highlight a clear trend toward unification and scaling, showing emergent capabilities across diverse domains. While image generation and editing have rapidly transitioned from task-specific to unified frameworks, video generation and editing remain fragmented due to architectural limitations and data scarcity. In this work, we introduce EditVerse, a unified framework for image and video generation and editing within a single model. By representing all modali…

Analysis of approximate linear programming solution to Markov decision problem with log barrier function
Donghwan Lee, Hyukjun Yang, Bum Geun Park
https://arxiv.org/abs/2509.19800

Analysis of approximate linear programming solution to Markov decision problem with log barrier function
There are two primary approaches to solving Markov decision problems (MDPs): dynamic programming based on the Bellman equation and linear programming (LP). Dynamic programming methods are the most widely used and form the foundation of both classical and modern reinforcement learning (RL). By contrast, LP-based methods have been less commonly employed, although they have recently gained attention in contexts such as offline RL. The relative underuse of the LP-based methods stems from the fact t…

#running slow is hard but my fitness is such that it requires a rebuild of the foundation. Trying to stay in HR2 means a decent amount of walking interspersed. I don’t love it, but it’s necessary.
I have a much more open schedule now, so I should be able to get out and run regularly. The trick will be staying patient and trusting the process.

Compressed Permutation Oracles
Joseph Carolan
https://arxiv.org/abs/2509.18586 https://arxiv.org/pdf/2509.18586

How Well Do LLMs Predict Prerequisite Skills? Zero-Shot Comparison to Expert-Defined Concepts
Ngoc Luyen Le, Marie-H\'el\`ene Abel
https://arxiv.org/abs/2507.18479 https://

How Well Do LLMs Predict Prerequisite Skills? Zero-Shot Comparison to Expert-Defined Concepts
Prerequisite skills - foundational competencies required before mastering more advanced concepts - are important for supporting effective learning, assessment, and skill-gap analysis. Traditionally curated by domain experts, these relationships are costly to maintain and difficult to scale. This paper investigates whether large language models (LLMs) can predict prerequisite skills in a zero-shot setting, using only natural language descriptions and without task-specific fine-tuning. We introdu…

A Nodal Discontinuous Galerkin Method with Low-Rank Velocity Space Representation for the Multi-Scale BGK Model
Andres Galindo-Olarte, Joseph Nakao, Mirjeta Pasha, Jing-Mei Qiu, William Taitano
https://arxiv.org/abs/2508.16564

A Nodal Discontinuous Galerkin Method with Low-Rank Velocity Space Representation for the Multi-Scale BGK Model
A novel hybrid algorithm is presented for the Boltzmann-BGK equation, in which a low-rank decomposition is applied solely in the velocity subspace, while a full-rank representation is maintained in the physical (position) space. This approach establishes a foundation for extending modern low-rank techniques to solve the Boltzmann equation in realistic settings, particularly where structured representations -- such as conformal geometries -- may not be feasible in practical engineering applicati…

Pixels Under Pressure: Exploring Fine-Tuning Paradigms for Foundation Models in High-Resolution Medical Imaging
Zahra TehraniNasab, Amar Kumar, Tal Arbel
https://arxiv.org/abs/2508.14931

Pixels Under Pressure: Exploring Fine-Tuning Paradigms for Foundation Models in High-Resolution Medical Imaging
Advancements in diffusion-based foundation models have improved text-to-image generation, yet most efforts have been limited to low-resolution settings. As high-resolution image synthesis becomes increasingly essential for various applications, particularly in medical imaging domains, fine-tuning emerges as a crucial mechanism for adapting these powerful pre-trained models to task-specific requirements and data distributions. In this work, we present a systematic study, examining the impact of …

Failure Modes of Maximum Entropy RLHF
\"Omer Veysel \c{C}a\u{g}atan, Bar{\i}\c{s} Akg\"un
https://arxiv.org/abs/2509.20265 https://arxiv.org/pdf/…

Failure Modes of Maximum Entropy RLHF
In this paper, we show that Simple Preference Optimization (SimPO) can be derived as Maximum Entropy Reinforcement Learning with length-normalized temperature, providing a theoretical foundation for this reference-free method. Motivated by SimPO's strong performance in offline preference optimization, we investigate whether Maximum Entropy RL can achieve similar results in online RLHF settings. Our experiments find that Maximum Entropy RL consistently exhibits overoptimization and unstable KL d…

SingLEM: Single-Channel Large EEG Model
Jamiyan Sukhbaatar, Satoshi Imamura, Ibuki Inoue, Shoya Murakami, Kazi Mahmudul Hassan, Seungwoo Han, Ingon Chanpornpakdi, Toshihisa Tanaka
https://arxiv.org/abs/2509.17920

SingLEM: Single-Channel Large EEG Model
Current deep learning models for electroencephalography (EEG) are often task-specific and depend on large labeled datasets, limiting their adaptability. Although emerging foundation models aim for broader applicability, their rigid dependence on fixed, high-density multi-channel montages restricts their use across heterogeneous datasets and in missing-channel or practical low-channel settings. To address these limitations, we introduce SingLEM, a self-supervised foundation model that learns rob…