Skip to content

Author

N. Dehak

We have 6 of 282 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

MyoCodec: A Streaming Neural Codec for Electromyography

The discrete token representation provided by MyoCodec has the potential to support integration into language-model based approaches, creating a path toward LLM-based interactive systems, where tokenized EMG representations are directly processed into such language or speech models.

Jih-Wan Lee, Kleanthis Avramidis, Junhyeok Lee et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Nutri-ATLAS: Embodied Agent for Tabulated Lookup and Assistance for Smarter nutrition

This work proposes Nutri-ATLAS, an Embodied Agent for Tabulated Lookup and Assistance for smarter nutrition in the real world that integrates graph-grounded nutrition reasoning, hardware-aware LLM selection, and robot-based evidence acquisition.

Utteja Kallakuri, Bo-Xun Hu, A. Butala et al. · 0 citations
#natural language process... Preprint Sep 2026

Who Are They to Each Other? Multi-Agent Reasoning for Speaker Relationship Inference

This work proposes Multi-Role Multi-Agent Debate as a task-specific adaptation of standard multi-agent debate for speaker relationship inference, assigning agents complementary roles or social-theory-grounded perspectives rather than a single undifferentiated viewpoint, and introduces Multi-Agent Compete, a competition...

Yao-Han Guan, Yen-Ju Lu, Yu-Zhe Wang et al. · 0 citations
Preprint Aug 2026

When Text Misleads: Inconsistent-Aware Reasoning for Audio-Grounded Dialogue

A scalable framework that identifies text-biased surface interpretations and converts disagreement regions into conflict QA examples and develops an agentic-style reasoning framework that converts speech into an Audio Twin, a text-readable representation of localized acoustic cues that exposes acoustic evidence to the...

Yen-Ju Lu, Yu-Zhe Wang, Yao-Han Guan et al. · 1 citation

Reconstruct! Don't Encode: Self-Supervised Representation Reconstruction Loss for High-Intelligibility and Low-Latency Streaming Neural Audio Codec

It is demonstrated that self-supervised representation reconstruction (SSRR) loss fundamentally improves codec training and performance, and enhances intelligibility by reconstructing distilled self-supervised representations from codec outputs.

Junhyeok Lee, Xiluo He, Jihwan Lee et al. · 2 citations
Preprint Jul 2026

Leveraging Gradient Reversal Loss and Multitask Learning for Datasets-Aware Audio Deepfake Detection

This work proposes a practical dataset-aware framework for deepfake detection that relies only on dataset identity as a naturally available supervisory signal for multitask (MT) and gradient reversal layer (GRL) training, allowing the model to investigate both dataset-aware multitask supervision and adversarial suppres...

Mingrui Liang, Thomas Thebaud, Lukasz Wójciak et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.