Tootfinder

Table-r1: Self-supervised and Reinforcement Learning for Program-based Table Reasoning in Small Language Models
Rihui Jin, Zheyu Xin, Xing Xie, Zuoyi Li, Guilin Qi, Yongrui Chen, Xinbang Dai, Tongtong Wu, Gholamreza Haffari
https://arxiv.org/abs/2506.06137

Table-r1: Self-supervised and Reinforcement Learning for Program-based Table Reasoning in Small Language Models
Table reasoning (TR) requires structured reasoning over semi-structured tabular data and remains challenging, particularly for small language models (SLMs, e.g., LLaMA-8B) due to their limited capacity compared to large LMs (LLMs, e.g., GPT-4o). To narrow this gap, we explore program-based TR (P-TR), which circumvents key limitations of text-based TR (T-TR), notably in numerical reasoning, by generating executable programs. However, applying P-TR to SLMs introduces two challenges: (i) vulnerabi…

STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis
Jiatao Gu, Tianrong Chen, David Berthelot, Huangjie Zheng, Yuyang Wang, Ruixiang Zhang, Laurent Dinh, Miguel Angel Bautista, Josh Susskind, Shuangfei Zhai
https://arxiv.org/abs/2506.06276

STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis
We present STARFlow, a scalable generative model based on normalizing flows that achieves strong performance in high-resolution image synthesis. The core of STARFlow is Transformer Autoregressive Flow (TARFlow), which combines the expressive power of normalizing flows with the structured modeling capabilities of Autoregressive Transformers. We first establish the theoretical universality of TARFlow for modeling continuous distributions. Building on this foundation, we introduce several key arch…

Resilient Auto-Scaling of Microservice Architectures with Efficient Resource Management
Hussain Ahmad, Christoph Treude, Markus Wagner, Claudia Szabo
https://arxiv.org/abs/2506.05693

Resilient Auto-Scaling of Microservice Architectures with Efficient Resource Management
Horizontal Pod Auto-scalers (HPAs) are crucial for managing resource allocation in microservice architectures to handle fluctuating workloads. However, traditional HPAs fail to address resource disruptions caused by faults, cyberattacks, maintenance, and other operational challenges. These disruptions result in resource wastage, service unavailability, and HPA performance degradation. To address these challenges, we extend our prior work on Smart HPA and propose SecureSmart HPA, which offers re…

ScaleRTL: Scaling LLMs with Reasoning Data and Test-Time Compute for Accurate RTL Code Generation
Chenhui Deng, Yun-Da Tsai, Guan-Ting Liu, Zhongzhi Yu, Haoxing Ren
https://arxiv.org/abs/2506.05566

ScaleRTL: Scaling LLMs with Reasoning Data and Test-Time Compute for Accurate RTL Code Generation
Recent advances in large language models (LLMs) have enabled near-human performance on software coding benchmarks, but their effectiveness in RTL code generation remains limited due to the scarcity of high-quality training data. While prior efforts have fine-tuned LLMs for RTL tasks, they do not fundamentally overcome the data bottleneck and lack support for test-time scaling due to their non-reasoning nature. In this work, we introduce ScaleRTL, the first reasoning LLM for RTL coding that scal…

The scaling regimes for unsteady diffusion across particle-stabilized fluid interfaces
T. J. J. M. van Overveld, V. Garbin
https://arxiv.org/abs/2506.05366

The scaling regimes for unsteady diffusion across particle-stabilized fluid interfaces
Colloidal particles at fluid interfaces can enhance the stability of drops and bubbles. Yet, their effect on mass transfer in these multiphase systems remains ambiguous, with some experiments reporting strongly hindered diffusion, while others show nearly no effect, even at near-complete surface coverage. To resolve this ambiguity, we solve the Fick-Jacobs equation for unsteady diffusion, allowing us to treat the particle-laden interface as a locally reduced cross-sectional area for mass transf…

Compression, simulation, and synthesis of turbulent flows with tensor trains
Stefano Pisoni, Raghavendra Dheeraj Peddinti, Egor Tiunov, Siddhartha E. Guzman, Leandro Aolita
https://arxiv.org/abs/2506.05477

Compression, simulation, and synthesis of turbulent flows with tensor trains
Numerical simulations of turbulent fluids are paramount to real-life applications, from predicting and modeling flows to diagnostic purposes in engineering. However, they are also computationally challenging due to their intrinsically non-linear dynamics, which requires a very high spatial resolution to accurately describe them. A promising idea is to represent flows on a discrete mesh using tensor trains (TTs), featuring a convenient scaling of the number of parameters with the mesh size. Howe…

Unisoma: A Unified Transformer-based Solver for Multi-Solid Systems
Shilong Tao, Zhe Feng, Haonan Sun, Zhanxing Zhu, Yunhuai Liu
https://arxiv.org/abs/2506.06021

Unisoma: A Unified Transformer-based Solver for Multi-Solid Systems
Multi-solid systems are foundational to a wide range of real-world applications, yet modeling their complex interactions remains challenging. Existing deep learning methods predominantly rely on implicit modeling, where the factors influencing solid deformation are not explicitly represented but are instead indirectly learned. However, as the number of solids increases, these methods struggle to accurately capture intricate physical interactions. In this paper, we introduce a novel explicit mod…

LaDEEP: A Deep Learning-based Surrogate Model for Large Deformation of Elastic-Plastic Solids
Shilong Tao, Zhe Feng, Haonan Sun, Zhanxing Zhu, Yunhuai Liu
https://arxiv.org/abs/2506.06001

LaDEEP: A Deep Learning-based Surrogate Model for Large Deformation of Elastic-Plastic Solids
Scientific computing for large deformation of elastic-plastic solids is critical for numerous real-world applications. Classical numerical solvers rely primarily on local discrete linear approximation and are constrained by an inherent trade-off between accuracy and efficiency. Recently, deep learning models have achieved impressive progress in solving the continuum mechanism. While previous models have explored various architectures and constructed coefficient-solution mappings, they are desig…

Mitigating Catastrophic Forgetting with Adaptive Transformer Block Expansion in Federated Fine-Tuning
Yujia Huo, Jianchun Liu, Hongli Xu, Zhenguo Ma, Shilong Wang, Liusheng Huang
https://arxiv.org/abs/2506.05977

Mitigating Catastrophic Forgetting with Adaptive Transformer Block Expansion in Federated Fine-Tuning
Federated fine-tuning (FedFT) of large language models (LLMs) has emerged as a promising solution for adapting models to distributed data environments while ensuring data privacy. Existing FedFT methods predominantly utilize parameter-efficient fine-tuning (PEFT) techniques to reduce communication and computation overhead. However, they often fail to adequately address the catastrophic forgetting, a critical challenge arising from continual adaptation in distributed environments. The tradit…

Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library
Weixun Wang, Shaopan Xiong, Gengru Chen, Wei Gao, Sheng Guo, Yancheng He, Ju Huang, Jiaheng Liu, Zhendong Li, Xiaoyang Li, Zichen Liu, Haizhou Zhao, Dakai An, Lunxi Cao, Qiyang Cao, Wanxi Deng, Feilei Du, Yiliang Gu, Jiahe Li, Xiang Li, Mingjie Liu, Yijia Luo, Zihe Liu, Yadao Wang, Pei Wang, Tianyuan Wu, Yanan Wu, Yuheng Zhao, Shuaibing Zhao, Jin Yang, Siran Yang, Yingshui Tan, …

Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library
We introduce ROLL, an efficient, scalable, and user-friendly library designed for Reinforcement Learning Optimization for Large-scale Learning. ROLL caters to three primary user groups: tech pioneers aiming for cost-effective, fault-tolerant large-scale training, developers requiring flexible control over training workflows, and researchers seeking agile experimentation. ROLL is built upon several key modules to serve these user groups effectively. First, a single-controller architecture combin…