Tootfinder

Efficient Multilingual ASR Finetuning via LoRA Language Experts
Jiahong Li, Yiwen Shao, Jianheng Zhuo, Chenda Li, Liliang Tang, Dong Yu, Yanmin Qian
https://arxiv.org/abs/2506.21555

Efficient Multilingual ASR Finetuning via LoRA Language Experts
Recent advancements in deep learning have significantly enhanced multilingual automatic speech recognition (ASR) due to the development of advanced model architectures and available large-scale multilingual datasets. Despite that, multilingual ASR still suffers from the curse of multilinguality in that different languages tend to interfere with each other, making it difficult for the ASR model to identify multiple languages effectively while sharing model capacity across them. This paper propos…

AURA: Agent for Understanding, Reasoning, and Automated Tool Use in Voice-Driven Tasks
Leander Melroy Maben, Gayathri Ganesh Lakshmy, Srijith Radhakrishnan, Siddhant Arora, Shinji Watanabe
https://arxiv.org/abs/2506.23049

AURA: Agent for Understanding, Reasoning, and Automated Tool Use in Voice-Driven Tasks
Despite advances in language and speech technologies, no open-source system enables full speech-to-speech, multi-turn dialogue with integrated tool use and agentic reasoning. We introduce AURA (Agent for Understanding, Reasoning, and Automated Tool Use), the first open-source, speech-native assistant capable of completing complex, goal-driven tasks through dynamic tool invocation and multi-turn conversation. AURA combines open-weight ASR, TTS, and LLMs in a cascaded pipeline and supports tools …

Learning Motion Skills with Adaptive Assistive Curriculum Force in Humanoid Robots
Zhanxiang Cao, Yang Zhang, Buqing Nie, Huangxuan Lin, Haoyang Li, Yue Gao
https://arxiv.org/abs/2506.23125

Learning Motion Skills with Adaptive Assistive Curriculum Force in Humanoid Robots
Learning policies for complex humanoid tasks remains both challenging and compelling. Inspired by how infants and athletes rely on external support--such as parental walkers or coach-applied guidance--to acquire skills like walking, dancing, and performing acrobatic flips, we propose A2CF: Adaptive Assistive Curriculum Force for humanoid motion learning. A2CF trains a dual-agent system, in which a dedicated assistive force agent applies state-dependent forces to guide the robot through difficul…

NoticeLight: Embracing Socio-Technical Asymmetry through Tangible Peripheral Robotic Embodiment in Hybrid Collaboration
Marie Altmann, Kimberly Hegemann, Ali Askari, Vineetha Rallabandi, Max Pascher, Jens Gerken
https://arxiv.org/abs/2506.22125

NoticeLight: Embracing Socio-Technical Asymmetry through Tangible Peripheral Robotic Embodiment in Hybrid Collaboration
Hybrid collaboration has become a fixture in modern workplaces, yet it introduces persistent socio-technical asymmetries-especially disadvantaging remote participants, who struggle with presence disparity, reduced visibility, and limited non-verbal communication. Traditional solutions often seek to erase these asymmetries, but recent research suggests embracing them as productive design constraints. In this context, we introduce NoticeLight: a tangible, peripheral robotic embodiment designed to…

The DevSafeOps Dilemma: A Systematic Literature Review on Rapidity in Safe Autonomous Driving Development and Operation
Ali Nouri, Beatriz Cabrero-Daniel, Fredrik T\"orner, Christian Berger
https://arxiv.org/abs/2506.21693

The DevSafeOps Dilemma: A Systematic Literature Review on Rapidity in Safe Autonomous Driving Development and Operation
Developing autonomous driving (AD) systems is challenging due to the complexity of the systems and the need to assure their safe and reliable operation. The widely adopted approach of DevOps seems promising to support the continuous technological progress in AI and the demand for fast reaction to incidents, which necessitate continuous development, deployment, and monitoring. We present a systematic literature review meant to identify, analyse, and synthesise a broad range of existing literatur…

Report on NSF Workshop on Science of Safe AI
Rajeev Alur, Greg Durrett, Hadas Kress-Gazit, Corina P\u{a}s\u{a}reanu, Ren\'e Vidal
https://arxiv.org/abs/2506.22492

Report on NSF Workshop on Science of Safe AI
Recent advances in machine learning, particularly the emergence of foundation models, are leading to new opportunities to develop technology-based solutions to societal problems. However, the reasoning and inner workings of today's complex AI models are not transparent to the user, and there are no safety guarantees regarding their predictions. Consequently, to fulfill the promise of AI, we must address the following scientific challenge: how to develop AI-based systems that are not only accura…

Evaluating the Robustness of Dense Retrievers in Interdisciplinary Domains
Sarthak Chaturvedi, Anurag Acharya, Rounak Meyur, Koby Hayashi, Sai Munikoti, Sameera Horawalavithana
https://arxiv.org/abs/2506.21581

Evaluating the Robustness of Dense Retrievers in Interdisciplinary Domains
Evaluation benchmark characteristics may distort the true benefits of domain adaptation in retrieval models. This creates misleading assessments that influence deployment decisions in specialized domains. We show that two benchmarks with drastically different features such as topic diversity, boundary overlap, and semantic complexity can influence the perceived benefits of fine-tuning. Using environmental regulatory document retrieval as a case study, we fine-tune ColBERTv2 model on Environment…

Speaker Targeting via Self-Speaker Adaptation for Multi-talker ASR
Weiqing Wang, Taejin Park, Ivan Medennikov, Jinhan Wang, Kunal Dhawan, He Huang, Nithin Rao Koluguri, Jagadeesh Balam, Boris Ginsburg
https://arxiv.org/abs/2506.22646

Speaker Targeting via Self-Speaker Adaptation for Multi-talker ASR
We propose a self-speaker adaptation method for streaming multi-talker automatic speech recognition (ASR) that eliminates the need for explicit speaker queries. Unlike conventional approaches requiring target speaker embeddings or enrollment audio, our technique dynamically adapts individual ASR instances through speaker-wise speech activity prediction. The key innovation involves injecting speaker-specific kernels generated via speaker supervision activations into selected ASR encoder layers. …

Leveraging In-Context Learning for Political Bias Testing of LLMs
Patrick Haller, Jannis Vamvas, Rico Sennrich, Lena A. J\"ager
https://arxiv.org/abs/2506.22232

Leveraging In-Context Learning for Political Bias Testing of LLMs
A growing body of work has been querying LLMs with political questions to evaluate their potential biases. However, this probing method has limited stability, making comparisons between models unreliable. In this paper, we argue that LLMs need more context. We propose a new probing task, Questionnaire Modeling (QM), that uses human survey data as in-context examples. We show that QM improves the stability of question-based bias evaluation, and demonstrate that it may be used to compare instruct…

Validation of the MySurgeryRisk Algorithm for Predicting Complications and Death after Major Surgery: A Retrospective Multicenter Study Using OneFlorida Data Trust
Yuanfang Ren, Esra Adiyeke, Ziyuan Guan, Zhenhong Hu, Mackenzie J Meni, Benjamin Shickel, Parisa Rashidi, Tezcan Ozrazgat-Baslanti, Azra Bihorac
https://arxiv.org/abs…

Validation of the MySurgeryRisk Algorithm for Predicting Complications and Death after Major Surgery: A Retrospective Multicenter Study Using OneFlorida Data Trust
Despite advances in surgical techniques and care, postoperative complications are prevalent and effects up to 15% of the patients who underwent a major surgery. The objective of this study is to develop and validate models for predicting postoperative complications and death after major surgery on a large and multicenter dataset, following the previously validated MySurgeryRisk algorithm. This retrospective, longitudinal and multicenter cohort analysis included 508,097 encounters from 366,875 a…