Tootfinder

Take That for Me: Multimodal Exophora Resolution with Interactive Questioning for Ambiguous Out-of-View Instructions
Akira Oyama, Shoichi Hasegawa, Akira Taniguchi, Yoshinobu Hagiwara, Tadahiro Taniguchi
https://arxiv.org/abs/2508.16143

Take That for Me: Multimodal Exophora Resolution with Interactive Questioning for Ambiguous Out-of-View Instructions
Daily life support robots must interpret ambiguous verbal instructions involving demonstratives such as ``Bring me that cup,'' even when objects or users are out of the robot's view. Existing approaches to exophora resolution primarily rely on visual data and thus fail in real-world scenarios where the object or user is not visible. We propose Multimodal Interactive Exophora resolution with user Localization (MIEL), which is a multimodal exophora resolution framework leveraging sound source loc…

UserRL: Training Interactive User-Centric Agent via Reinforcement Learning
Cheng Qian, Zuxin Liu, Akshara Prabhakar, Jielin Qiu, Zhiwei Liu, Haolin Chen, Shirley Kokane, Heng Ji, Weiran Yao, Shelby Heinecke, Silvio Savarese, Caiming Xiong, Huan Wang
https://arxiv.org/abs/2509.19736

UserRL: Training Interactive User-Centric Agent via Reinforcement Learning
Reinforcement learning (RL) has shown promise in training agentic models that move beyond static benchmarks to engage in dynamic, multi-turn interactions. Yet, the ultimate value of such agents lies in their ability to assist users, a setting where diversity and dynamics of user interaction pose challenges. In this work, we propose UserRL, a unified framework for training and evaluating user-centric abilities through standardized gym environments paired with simulated users. We systematically v…

SwissGPC v1.0 -- The Swiss German Podcasts Corpus
Samuel Stucki, Mark Cieliebak, Jan Deriu
https://arxiv.org/abs/2509.19866 https://arxiv.org/pdf/2509.1986…

SwissGPC v1.0 -- The Swiss German Podcasts Corpus
We present SwissGPC v1.0, the first mid-to-large-scale corpus of spontaneous Swiss German speech, developed to support research in ASR, TTS, dialect identification, and related fields. The dataset consists of links to talk shows and podcasts hosted on Schweizer Radio und Fernsehen and YouTube, which contain approximately 5400 hours of raw audio. After segmentation and weak annotation, nearly 5000 hours of speech were retained, covering the seven major Swiss German dialect regions alongside Stan…

@raph_v@mstdn.social
I had a look at your posts, and I'm not sure where it is you're wanting replies. Nothing there I can add to (Maths/Computer Science). I agree with your comments about AI (have written about it a few times). I can see you've been boosted several times, so there are definitely people reading them. You might also like to check out Lemmy...

This is the most blatant, naked gangster corruption I've ever seen in a country.
And I grew up in Mexico in the 80s. https://flipboard.social/@NewsDesk/114908211854266893

Sorry for posting so many YouTube videos but this is great and geeky: a video essay about "Akira elevators", those platforms that travel horizontally and vertically at the same time. I remember the Half-Life example and the original from Akira. They are an awesome design but a bit like mechas they are futuristic tools that feel incredibly dangerous to build as a means to transport humans.

i-LAVA: Insights on Low Latency Voice-2-Voice Architecture for Agents
Anupam Purwar, Aditya Choudhary
https://arxiv.org/abs/2509.20971 https://arxiv.org/pd…

i-LAVA: Insights on Low Latency Voice-2-Voice Architecture for Agents
We experiment with a low-latency, end-to-end voice-to-voice communication model to optimize it for real-time conversational applications. By analyzing components essential to voice to voice (V-2-V) system viz. automatic speech recognition (ASR), text-to-speech (TTS), and dialog management, our work analyzes how to reduce processing time while maintaining high-quality interactions to identify the levers for optimizing V-2-V system. Our work identifies that TTS component which generates life-like…

"Dokumente vergleichen in #Word – lokal und via SharePoint" https://www.deroutlooker365.de/das-loesungsvideo-817-dokumente-verglei…

Lightweight Target-Speaker-Based Overlap Transcription for Practical Streaming ASR
Ale\v{s} Pra\v{z}\'ak, Marie Kune\v{s}ov\'a, Josef Psutka
https://arxiv.org/abs/2506.20288

Lightweight Target-Speaker-Based Overlap Transcription for Practical Streaming ASR
Overlapping speech remains a major challenge for automatic speech recognition (ASR) in real-world applications, particularly in broadcast media with dynamic, multi-speaker interactions. We propose a light-weight, target-speaker-based extension to an existing streaming ASR system to enable practical transcription of overlapping speech with minimal computational overhead. Our approach combines a speaker-independent (SI) model for standard operation with a speaker-conditioned (SC) model selectivel…

UserRL: Training Interactive User-Centric Agent via Reinforcement Learning
Cheng Qian, Zuxin Liu, Akshara Prabhakar, Jielin Qiu, Zhiwei Liu, Haolin Chen, Shirley Kokane, Heng Ji, Weiran Yao, Shelby Heinecke, Silvio Savarese, Caiming Xiong, Huan Wang
https://arxiv.org/abs/2509.19736

UserRL: Training Interactive User-Centric Agent via Reinforcement Learning
Reinforcement learning (RL) has shown promise in training agentic models that move beyond static benchmarks to engage in dynamic, multi-turn interactions. Yet, the ultimate value of such agents lies in their ability to assist users, a setting where diversity and dynamics of user interaction pose challenges. In this work, we propose UserRL, a unified framework for training and evaluating user-centric abilities through standardized gym environments paired with simulated users. We systematically v…