Tootfinder

Efficient Scaling for LLM-based ASR
Bingshen Mu, Yiwen Shao, Kun Wei, Dong Yu, Lei Xie
https://arxiv.org/abs/2508.04096 https://arxiv.org/pdf/2508.04096

Efficient Scaling for LLM-based ASR
Large language model (LLM)-based automatic speech recognition (ASR) achieves strong performance but often incurs high computational costs. This work investigates how to obtain the best LLM-ASR performance efficiently. Through comprehensive and controlled experiments, we find that pretraining the speech encoder before integrating it with the LLM leads to significantly better scaling efficiency than the standard practice of joint post-training of LLM-ASR. Based on this insight, we propose a new m…

Lightweight Prompt Biasing for Contextualized End-to-End ASR Systems
Bo Ren, Yu Shi, Jinyu Li
https://arxiv.org/abs/2506.06252 https://

Lightweight Prompt Biasing for Contextualized End-to-End ASR Systems
End-to-End Automatic Speech Recognition (ASR) has advanced significantly yet still struggles with rare and domain-specific entities. This paper introduces a simple yet efficient prompt-based biasing technique for contextualized ASR, enhancing recognition accuracy by leverage a unified multitask learning framework. The approach comprises two key components: a prompt biasing model which is trained to determine when to focus on entities in prompt, and a entity filtering mechanism which efficiently…

Satellite-based Rabi rice paddy field mapping in India: a case study on Telangana state
Prashanth Reddy Putta (University of Pavia), Fabio Dell'Acqua (University of Pavia)
https://arxiv.org/abs/2507.05189

Satellite-based Rabi rice paddy field mapping in India: a case study on Telangana state
Accurate rice area monitoring is critical for food security and agricultural policy in smallholder farming regions, yet conventional remote sensing approaches struggle with the spatiotemporal heterogeneity characteristic of fragmented agricultural landscapes. This study developed a phenology-driven classification framework that systematically adapts to local agro-ecological variations across 32 districts in Telangana, India during the 2018-19 Rabi rice season. The research reveals significant s…

Deepfakes in Criminal Investigations: Interdisciplinary Research Directions for CMC Research
Lorenz Meinen, Astrid Schom\"acker, Stefanie Wiedemann, Markus Hartmann, Timo Speith, Lena K\"astner, Niklas K\"uhl, Christian R\"uckert
https://arxiv.org/abs/2507.03457

Deepfakes in Criminal Investigations: Interdisciplinary Research Directions for CMC Research
The emergence of deepfake technologies offers both opportunities and significant challenges. While commonly associated with deception, misinformation, and fraud, deepfakes may also enable novel applications in high-stakes contexts such as criminal investigations. However, these applications raise complex technological, ethical, and legal questions. We adopt an interdisciplinary approach, drawing on computer science, philosophy, and law, to examine what it takes to responsibly use deepfakes in c…

A Deep Unfolding Framework for Diffractive Snapshot Spectral Imaging
Zhengyue Zhuge, Jiahui Xu, Shiqi Chen, Hao Xu, Yueting Chen, Zhihai Xu, Huajun Feng
https://arxiv.org/abs/2507.04622

A Deep Unfolding Framework for Diffractive Snapshot Spectral Imaging
Snapshot hyperspectral imaging systems acquire spectral data cubes through compressed sensing. Recently, diffractive snapshot spectral imaging (DSSI) methods have attracted significant attention. While various optical designs and improvements continue to emerge, research on reconstruction algorithms remains limited. Although numerous networks and deep unfolding methods have been applied on similar tasks, they are not fully compatible with DSSI systems because of their distinct optical encoding …

LUST: A Multi-Modal Framework with Hierarchical LLM-based Scoring for Learned Thematic Significance Tracking in Multimedia Content
Anderson de Lima Luiz
https://arxiv.org/abs/2508.04353

LUST: A Multi-Modal Framework with Hierarchical LLM-based Scoring for Learned Thematic Significance Tracking in Multimedia Content
This paper introduces the Learned User Significance Tracker (LUST), a framework designed to analyze video content and quantify the thematic relevance of its segments in relation to a user-provided textual description of significance. LUST leverages a multi-modal analytical pipeline, integrating visual cues from video frames with textual information extracted via Automatic Speech Recognition (ASR) from the audio track. The core innovation lies in a hierarchical, two-stage relevance scoring mecha…

Mind the Gap: From Resolving Theoretical Foundations of Chiral(ity)-Induced Spin Selectivity to Pioneering Implementations in Quantum Sensing
Yan Xi Foo, Aisha Kermiche, Farhan T. Chowdhury, Clarice D. Aiello, Luke D. Smith
https://arxiv.org/abs/2508.05611

Mind the Gap: From Resolving Theoretical Foundations of Chiral(ity)-Induced Spin Selectivity to Pioneering Implementations in Quantum Sensing
The chiral(ity)-induced spin selectivity (CISS) effect, where electrons passing through a chiral medium acquire significant spin-polarization at ambient temperatures, has been widely observed experimentally, yet its theoretical foundations remain actively debated. Open questions persist regarding whether CISS originates from helical geometry or more general chirality, and whether a unified mechanism can account for phenomena across solid-state and soft-matter systems, mesoscopic films, and sing…

SAGE-HLS: Syntax-Aware AST-Guided LLM for High-Level Synthesis Code Generation
M Zafir Sadik Khan, Nowfel Mashnoor, Mohammad Akyash, Kimia Azar, Hadi Kamali
https://arxiv.org/abs/2508.03558

SAGE-HLS: Syntax-Aware AST-Guided LLM for High-Level Synthesis Code Generation
In today's rapidly evolving field of electronic design automation (EDA), the complexity of hardware designs is increasing, necessitating more sophisticated automation solutions. High-level synthesis (HLS), as a pivotal solution, automates hardware designs from high-level abstractions (e.g., C/C++). However, it faces significant challenges, particularly in design space exploration and optimization. While large language models (LLMs) have shown notable capabilities in code generation, their appli…

JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering
Renmiao Chen, Shiyao Cui, Xuancheng Huang, Chengwei Pan, Victor Shea-Jay Huang, QingLin Zhang, Xuan Ouyang, Zhexin Zhang, Hongning Wang, Minlie Huang
https://arxiv.org/abs/2508.05087

JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering
Jailbreak attacks against multimodal large language Models (MLLMs) are a significant research focus. Current research predominantly focuses on maximizing attack success rate (ASR), often overlooking whether the generated responses actually fulfill the attacker's malicious intent. This oversight frequently leads to low-quality outputs that bypass safety filters but lack substantial harmful content. To address this gap, we propose JPS, \underline{J}ailbreak MLLMs with collaborative visual \underl…

Diarization-Aware Multi-Speaker Automatic Speech Recognition via Large Language Models
Yuke Lin, Ming Cheng, Ze Li, Beilong Tang, Ming Li
https://arxiv.org/abs/2506.05796

Diarization-Aware Multi-Speaker Automatic Speech Recognition via Large Language Models
Multi-speaker automatic speech recognition (MS-ASR) faces significant challenges in transcribing overlapped speech, a task critical for applications like meeting transcription and conversational analysis. While serialized output training (SOT)-style methods serve as common solutions, they often discard absolute timing information, limiting their utility in time-sensitive scenarios. Leveraging recent advances in large language models (LLMs) for conversational audio processing, we propose a novel…