Tootfinder

ZORRO: Zero-Knowledge Robustness and Privacy for Split Learning (Full Version)
Nojan Sheybani, Alessandro Pegoraro, Jonathan Knauer, Phillip Rieger, Elissa Mollakuqe, Farinaz Koushanfar, Ahmad-Reza Sadeghi
https://arxiv.org/abs/2509.09787

ZORRO: Zero-Knowledge Robustness and Privacy for Split Learning (Full Version)
Split Learning (SL) is a distributed learning approach that enables resource-constrained clients to collaboratively train deep neural networks (DNNs) by offloading most layers to a central server while keeping in- and output layers on the client-side. This setup enables SL to leverage server computation capacities without sharing data, making it highly effective in resource-constrained environments dealing with sensitive data. However, the distributed nature enables malicious clients to manipul…

The large-scale kinematics of young stars in the Milky Way disc: first results from SDSS-V
Eleonora Zari, Jaime Villase\~nor, Marina Kounkel, Hans-Walter Rix, Neige Frankel, Andrew Tkachenko, Sergey Khoperskov, Elena D'Onghia, Alexandre Roman-Lopes, Carlos Rom\'an-Z\'u\~niga, S. Guy Stringfellow, C. Jonathan Tan, Aida Wofford, Dmitry Bizyaev, John Donor, G. Jos\'e Fern\'andez-Trincado, Sean Morrison, Kaike Pan, F. Sebastian Sanchez, Andrew Saydjari

The large-scale kinematics of young stars in the Milky Way disc: first results from SDSS-V
We present a first large-scale kinematic map of $\sim$50,000 young OB stars ($T_{\rm eff} \geq 10,000$ K), based on BOSS spectroscopy from the Milky Way Mapper OB program in the ongoing Sloan Digital Sky Survey V (SDSS-V). Using photogeometric distances, line-of-sight velocities and Gaia DR3 proper motions, we map 3D Galactocentric velocities across the Galactic plane to $\sim$5 kpc from the Sun, with a focus on radial motions ($v_R$). Our results reveal mean radial motion with amplitudes of $\…

Bag of Tricks for Subverting Reasoning-based Safety Guardrails
Shuo Chen, Zhen Han, Haokun Chen, Bailan He, Shengyun Si, Jingpei Wu, Philip Torr, Volker Tresp, Jindong Gu
https://arxiv.org/abs/2510.11570

Bag of Tricks for Subverting Reasoning-based Safety Guardrails
Recent reasoning-based safety guardrails for Large Reasoning Models (LRMs), such as deliberative alignment, have shown strong defense against jailbreak attacks. By leveraging LRMs' reasoning ability, these guardrails help the models to assess the safety of user inputs before generating final responses. The powerful reasoning ability can analyze the intention of the input query and will refuse to assist once it detects the harmful intent hidden by the jailbreak methods. Such guardrails have show…

Officials botch overtime coin toss during Berlin matchup between Colts, Falcons

https://www.cbssports.com/nfl/news/colts-falcons-overtime-coin-toss-berlin-ind…

EDUMATH: Generating Standards-aligned Educational Math Word Problems
Bryan R. Christ, Penelope Molitz, Jonathan Kropko, Thomas Hartvigsen
https://arxiv.org/abs/2510.06965 https:…

EDUMATH: Generating Standards-aligned Educational Math Word Problems
Math word problems (MWPs) are critical K-12 educational tools, and customizing them to students' interests and ability levels can increase learning outcomes. However, teachers struggle to find time to customize MWPs for each student given large class sizes and increasing burnout. We propose that LLMs can support math education by generating MWPs customized to student interests and math education standards. To this end, we use a joint human expert-LLM judge approach to evaluate over 11,000 MWPs …

TIT-Score: Evaluating Long-Prompt Based Text-to-Image Alignment via Text-to-Image-to-Text Consistency
Juntong Wang, Huiyu Duan, Jiarui Wang, Ziheng Jia, Guangtao Zhai, Xiongkuo Min
https://arxiv.org/abs/2510.02987

TIT-Score: Evaluating Long-Prompt Based Text-to-Image Alignment via Text-to-Image-to-Text Consistency
With the rapid advancement of large multimodal models (LMMs), recent text-to-image (T2I) models can generate high-quality images and demonstrate great alignment to short prompts. However, they still struggle to effectively understand and follow long and detailed prompts, displaying inconsistent generation. To address this challenge, we introduce LPG-Bench, a comprehensive benchmark for evaluating long-prompt-based text-to-image generation. LPG-Bench features 200 meticulously crafted prompts wit…

Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards
Yiran Shen, Yu Xia, Jonathan Chang, Prithviraj Ammanabrolu
https://arxiv.org/abs/2510.01167 h…

Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards
Aligning large language models to human preferences is inherently multidimensional, yet most pipelines collapse heterogeneous signals into a single optimizeable objective. We seek to answer what it would take to simultaneously align a model across various domains spanning those with: verifiable rewards (mathematical accuracy), non-verifiable subjective preferences (human values), and complex interactive scenarios (multi-turn AI tutoring dialogues). Such multi-objective reinforcement learning se…

Safety Instincts: LLMs Learn to Trust Their Internal Compass for Self-Defense
Guobin Shen, Dongcheng Zhao, Haibo Tong, Jindong Li, Feifei Zhao, Yi Zeng
https://arxiv.org/abs/2510.01088

Safety Instincts: LLMs Learn to Trust Their Internal Compass for Self-Defense
Ensuring Large Language Model (LLM) safety remains challenging due to the absence of universal standards and reliable content validators, making it difficult to obtain effective training signals. We discover that aligned models already possess robust internal safety beliefs: they consistently produce high-confidence refusals to harmful requests while exhibiting high entropy when generating potentially dangerous content. This entropy gap reveals an untapped signal--models intrinsically "know" wh…

Fairness in Token Delegation: Mitigating Voting Power Concentration in DAOs
Johnnatan Messias, Ayae Ide
https://arxiv.org/abs/2510.05830 https://arxiv.org/…

Fairness in Token Delegation: Mitigating Voting Power Concentration in DAOs
Decentralized Autonomous Organizations (DAOs) aim to enable participatory governance, but in practice face challenges of voter apathy, concentration of voting power, and misaligned delegation. Existing delegation mechanisms often reinforce visibility biases, where a small set of highly ranked delegates accumulate disproportionate influence regardless of their alignment with the broader community. In this paper, we conduct an empirical study of delegation in DAO governance, combining on-chain da…

Safety Instincts: LLMs Learn to Trust Their Internal Compass for Self-Defense
Guobin Shen, Dongcheng Zhao, Haibo Tong, Jindong Li, Feifei Zhao, Yi Zeng
https://arxiv.org/abs/2510.01088

Safety Instincts: LLMs Learn to Trust Their Internal Compass for Self-Defense
Ensuring Large Language Model (LLM) safety remains challenging due to the absence of universal standards and reliable content validators, making it difficult to obtain effective training signals. We discover that aligned models already possess robust internal safety beliefs: they consistently produce high-confidence refusals to harmful requests while exhibiting high entropy when generating potentially dangerous content. This entropy gap reveals an untapped signal--models intrinsically "know" wh…