Tootfinder

Probabilistic Aggregation and Targeted Embedding Optimization for Collective Moral Reasoning in Large Language Models
Chenchen Yuan, Zheyu Zhang, Shuo Yang, Bardh Prenkaj, Gjergji Kasneci
https://arxiv.org/abs/2506.14625

Probabilistic Aggregation and Targeted Embedding Optimization for Collective Moral Reasoning in Large Language Models
Large Language Models (LLMs) have shown impressive moral reasoning abilities. Yet they often diverge when confronted with complex, multi-factor moral dilemmas. To address these discrepancies, we propose a framework that synthesizes multiple LLMs' moral judgments into a collectively formulated moral judgment, realigning models that deviate significantly from this consensus. Our aggregation mechanism fuses continuous moral acceptability scores (beyond binary labels) into a collective probability,…

Enhancing Urban GNSS Positioning Reliability via Conservative Satellite Selection Using Unanimous Voting Across Multiple Machine Learning Classifiers
Sanghyun Kim, Jiwon Seo
https://arxiv.org/abs/2507.12706

Enhancing Urban GNSS Positioning Reliability via Conservative Satellite Selection Using Unanimous Voting Across Multiple Machine Learning Classifiers
In urban environments, global navigation satellite system (GNSS) positioning is often compromised by signal blockages and multipath effects caused by buildings, leading to significant positioning errors. To address this issue, this study proposes a robust enhancement of zonotope shadow matching (ZSM)-based positioning by employing a conservative satellite selection strategy using unanimous voting across multiple machine learning classifiers. Three distinct models - random forest (RF), gradient …

Enhancing Forecasting Accuracy in Dynamic Environments via PELT-Driven Drift Detection and Model Adaptation
Nikhil Pawar, Guilherme Vieira Hollweg, Akhtar Hussain, Wencong Su, Van-Hai Bui
https://arxiv.org/abs/2506.14133

Enhancing Forecasting Accuracy in Dynamic Environments via PELT-Driven Drift Detection and Model Adaptation
Accurate time series forecasting models are often compromised by data drift, where underlying data distributions change over time, leading to significant declines in prediction performance. To address this challenge, this study proposes an adaptive forecasting framework that integrates drift detection with targeted model retraining to compensate for drift effects. The framework utilizes the Pruned Exact Linear Time (PELT) algorithm to identify drift points within the feature space of time serie…

GraspGen: A Diffusion-based Framework for 6-DOF Grasping with On-Generator Training
Adithyavairavan Murali, Balakumar Sundaralingam, Yu-Wei Chao, Wentao Yuan, Jun Yamada, Mark Carlson, Fabio Ramos, Stan Birchfield, Dieter Fox, Clemens Eppner
https://arxiv.org/abs/2507.13097

GraspGen: A Diffusion-based Framework for 6-DOF Grasping with On-Generator Training
Grasping is a fundamental robot skill, yet despite significant research advancements, learning-based 6-DOF grasping approaches are still not turnkey and struggle to generalize across different embodiments and in-the-wild settings. We build upon the recent success on modeling the object-centric grasp generation process as an iterative diffusion process. Our proposed framework, GraspGen, consists of a DiffusionTransformer architecture that enhances grasp generation, paired with an efficient discr…

MAD-Spear: A Conformity-Driven Prompt Injection Attack on Multi-Agent Debate Systems
Yu Cui, Hongyang Du
https://arxiv.org/abs/2507.13038 https://

MAD-Spear: A Conformity-Driven Prompt Injection Attack on Multi-Agent Debate Systems
Multi-agent debate (MAD) systems leverage collaborative interactions among large language models (LLMs) agents to improve reasoning capabilities. While recent studies have focused on increasing the accuracy and scalability of MAD systems, their security vulnerabilities have received limited attention. In this work, we introduce MAD-Spear, a targeted prompt injection attack that compromises a small subset of agents but significantly disrupts the overall MAD process. Manipulated agents produce mu…

Tegna adds 100 hours of new daily programming across 50 markets with dedicated 7am-9am streaming of local newscasts to meet increased demand on CTV platforms (Mark K. Miller/TVNewsCheck)
https://tvnewscheck.com/journalism/article/tegna-anno…

Tegna Announces Major Local News Expansion
Tegna Inc. today announced that its stations will be “significantly expanding” their local news programming by launching live and on-demand, local newscasts from 7 to 9 a.m. daily in 50-plus markets through streaming, connected TV apps and station websites.  Tegna said: “This unprecedented expansion of local news programming is designed to meet audiences’ growing demand for coverage of their communities wherever they want to watch and will deliver over 100 hours of daily breaking news,…

D\'ej\`a Vu: Efficient Video-Language Query Engine with Learning-based Inter-Frame Computation Reuse
Jinwoo Hwang, Daeun Kim, Sangyeop Lee, Yoonsung Kim, Guseul Heo, Hojoon Kim, Yunseok Jeong, Tadiwos Meaza, Eunhyeok Park, Jeongseob Ahn, Jongse Park
https://arxiv.org/abs/2506.14107

Déjà Vu: Efficient Video-Language Query Engine with Learning-based Inter-Frame Computation Reuse
Recently, Video-Language Models (VideoLMs) have demonstrated remarkable capabilities, offering significant potential for flexible and powerful video query systems. These models typically rely on Vision Transformers (ViTs), which process video frames individually to extract visual embeddings. However, generating embeddings for large-scale videos requires ViT inferencing across numerous frames, posing a major hurdle to real-world deployment and necessitating solutions for integration into scalabl…

Subjective Evaluation Profile Analysis of Science Fiction Short Stories and its Critical-Theoretical Significance
Kazuyoshi Otsuka
https://arxiv.org/abs/2507.11582

Subjective Evaluation Profile Analysis of Science Fiction Short Stories and its Critical-Theoretical Significance
This study positions large language models (LLMs) as "subjective literary critics" to explore aesthetic preferences and evaluation patterns in literary assessment. Ten Japanese science fiction short stories were translated into English and evaluated by six state-of-the-art LLMs across seven independent sessions. Principal component analysis and clustering techniques revealed significant variations in evaluation consistency (α ranging from 1.00 to 0.35) and five distinct evaluation patterns. Ad…

Tady: A Neural Disassembler without Structural Constraint Violations
Siliang Qin, Fengrui Yang, Hao Wang, Bolun Zhang, Zeyu Gao, Chao Zhang, Kai Chen
https://arxiv.org/abs/2506.13323

Tady: A Neural Disassembler without Structural Constraint Violations
Disassembly is a crucial yet challenging step in binary analysis. While emerging neural disassemblers show promise for efficiency and accuracy, they frequently generate outputs violating fundamental structural constraints, which significantly compromise their practical usability. To address this critical problem, we regularize the disassembly solution space by formalizing and applying key structural constraints based on post-dominance relations. This approach systematically detects widespread e…

WikiMixQA: A Multimodal Benchmark for Question Answering over Tables and Charts
Negar Foroutan, Angelika Romanou, Matin Ansaripour, Julian Martin Eisenschlos, Karl Aberer, R\'emi Lebret
https://arxiv.org/abs/2506.15594

WikiMixQA: A Multimodal Benchmark for Question Answering over Tables and Charts
Documents are fundamental to preserving and disseminating information, often incorporating complex layouts, tables, and charts that pose significant challenges for automatic document understanding (DU). While vision-language large models (VLLMs) have demonstrated improvements across various tasks, their effectiveness in processing long-context vision inputs remains unclear. This paper introduces WikiMixQA, a benchmark comprising 1,000 multiple-choice questions (MCQs) designed to evaluate cross-…