Tootfinder

RewardBench 2: Advancing Reward Model Evaluation
Saumya Malik, Valentina Pyatkin, Sander Land, Jacob Morrison, Noah A. Smith, Hannaneh Hajishirzi, Nathan Lambert
https://arxiv.org/abs/2506.01937

RewardBench 2: Advancing Reward Model Evaluation
Reward models are used throughout the post-training of language models to capture nuanced signals from preference data and provide a training target for optimization across instruction following, reasoning, safety, and more domains. The community has begun establishing best practices for evaluating reward models, from the development of benchmarks that test capabilities in specific skill areas to others that test agreement with human preferences. At the same time, progress in evaluation has not…

CyberGym: Evaluating AI Agents' Cybersecurity Capabilities with Real-World Vulnerabilities at Scale
Zhun Wang, Tianneng Shi, Jingxuan He, Matthew Cai, Jialin Zhang, Dawn Song
https://arxiv.org/abs/2506.02548

CyberGym: Evaluating AI Agents' Cybersecurity Capabilities with Real-World Vulnerabilities at Scale
Large language model (LLM) agents are becoming increasingly skilled at handling cybersecurity tasks autonomously. Thoroughly assessing their cybersecurity capabilities is critical and urgent, given the high stakes in this domain. However, existing benchmarks fall short, often failing to capture real-world scenarios or being limited in scope. To address this gap, we introduce CyberGym, a large-scale and high-quality cybersecurity evaluation framework featuring 1,507 real-world vulnerabilities fo…

A High-Performance Evolutionary Multiobjective Community Detection Algorithm
Guilherme O. Santos, Lucas S. Vieira, Giulio Rossetti, Carlos H. G. Ferreira, Gladston Moreira
https://arxiv.org/abs/2506.01752

A High-Performance Evolutionary Multiobjective Community Detection Algorithm
Community structure is a key feature of complex networks, underpinning a diverse range of phenomena across social, biological, and technological systems. While traditional methods, such as Louvain and Leiden, offer efficient solutions, they rely on single-objective optimization, often failing to capture the multifaceted nature of real-world networks. Multi-objective approaches address this limitation by considering multiple structural criteria simultaneously, but their high computational cost r…

HASD: Hierarchical Adaption for pathology Slide-level Domain-shift
Jingsong Liu, Han Li, Chen Yang, Michael Deutges, Ario Sadafi, Xin You, Katharina Breininger, Nassir Navab, Peter J. Sch\"uffler
https://arxiv.org/abs/2506.23673

HASD: Hierarchical Adaption for pathology Slide-level Domain-shift
Domain shift is a critical problem for pathology AI as pathology data is heavily influenced by center-specific conditions. Current pathology domain adaptation methods focus on image patches rather than WSI, thus failing to capture global WSI features required in typical clinical scenarios. In this work, we address the challenges of slide-level domain shift by proposing a Hierarchical Adaptation framework for Slide-level Domain-shift (HASD). HASD achieves multi-scale feature consistency and comp…

This https://arxiv.org/abs/2505.13476 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Unified Structural Embedding of Orbifold Sigma Models
This paper introduces a unified structural embedding framework for orbifold sigma models that systematically incorporates twisted sectors, singularities, and smooth regions into a single algebraic object. Traditional approaches to orbifold theories often treat sectors separately, requiring ad hoc regularizations near singularities and failing to capture inter-sector interactions under renormalization group flow. The framework presented herein resolves these limitations through the construction …

Characterizing Small Circuit Classes from FAC^0 to FAC^1 via Discrete Ordinary Differential Equations
Melissa Antonelli, Arnaud Durand, Juha Kontinen
https://arxiv.org/abs/2506.23404

Characterizing Small Circuit Classes from FAC^0 to FAC^1 via Discrete Ordinary Differential Equations
In this paper, we provide a uniform framework for investigating small circuit classes and bounds through the lens of ordinary differential equations (ODEs). Following an approach recently introduced to capture the class of polynomial-time computable functions via ODE-based recursion schemas and later applied to the context of functions computed by unbounded fan-in circuits of constant depth (FAC^0), we study multiple relevant small circuit classes. In particular, we show that natural restrictio…

Any #flameshot #sway users who might have a problem with fullscreen captures, you want this:
# fix flameshot
for_window [app_id="flameshot"] border pixel 0, floating enable, fullscreen disable, move absolute position 0 0, focus

me and who

CBF-AFA: Chunk-Based Multi-SSL Fusion for Automatic Fluency Assessment
Papa S\'ega Wade, Mihai Andries, Ioannis Kanellos, Thierry Moudenc
https://arxiv.org/abs/2506.20243

CBF-AFA: Chunk-Based Multi-SSL Fusion for Automatic Fluency Assessment
Automatic fluency assessment (AFA) remains challenging, particularly in capturing speech rhythm, pauses, and disfluencies in non-native speakers. We introduce a chunk-based approach integrating self-supervised learning (SSL) models (Wav2Vec2, HuBERT, and WavLM) selected for their complementary strengths in phonetic, prosodic, and noisy speech modeling, with a hierarchical CNN-BiLSTM framework. Speech is segmented into breath-group chunks using Silero voice activity detection (Silero-VAD), enabl…

Dynamics of thin film flows on a vertical fibre with vapor absorption
Souradip Chattopadhyay, Zihao Yu, Y. Sungtaek Ju, Hangjie Ji
https://arxiv.org/abs/2505.22379

Dynamics of thin film flows on a vertical fibre with vapor absorption
Water vapor capture through free surface flows plays a crucial role in various industrial applications, such as liquid desiccant air conditioning systems, water harvesting, and dewatering. This paper studies the dynamics of a silicone liquid sorbent (also known as water-absorbing silicone oil) flowing down a vertical cylindrical fibre while absorbing water vapor. We propose a one-sided thin-film-type model for these dynamics, where the governing equations form a coupled system of nonlinear four…