activity
20242026
collaborators

5 papers

cond-mat.mtrl-sci2026

Realizing record-high transverse thermoelectric figure of merit at room temperature in artificially tilted multilayers based on high power factor NiFe alloy

Yebin Lee, Fuyuki Ando, Takamasa Hirai +3

Transverse thermoelectric conversion using artificially tilted multilayers (ATMLs) offers a versatile device architecture that circumvents the structural limitations of conventiona…

cs.CL2026

Unified Audio Intelligence Without Regressing on Text Intelligence

Zhifeng Kong, Sang-gil Lee, Jaehyeon Kim +17

Audio intelligence involves understanding, reasoning about, and generating both audio and speech. In this work, we introduce Nemotron-Labs-Audex-30B-A3B (Audex), a unified audio-te…

cs.CL2026

PersonaPlex: Voice and Role Control for Full Duplex Conversational Speech Models

Rajarshi Roy, Jonathan Raiman, Sang-gil Lee +5

Recent advances in duplex speech models have enabled natural, low-latency speech-to-speech interactions. However, existing models are restricted to a fixed role and voice, limiting…

cs.CL2025

NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models

Chankyu Lee, Rajarshi Roy, Mengyao Xu +4

Decoder-only LLM-based embedding models are beginning to outperform BERT or T5-based embedding models in general-purpose text embedding tasks, including dense vector-based retrieva…

cs.CL2024

ChatQA: Surpassing GPT-4 on Conversational QA and RAG

Zihan Liu, Wei Ping, Rajarshi Roy +4

In this work, we introduce ChatQA, a suite of models that outperform GPT-4 on retrieval-augmented generation (RAG) and conversational question answering (QA). To enhance generation…