Research & patent
- Earnings25: A Comprehensive 500-Hour Speech Benchmark for Finance — Interspeech 2026, with dataset
- LLM-Augmented Digital Twin for Policy Evaluation in Short-Video Platforms — Preprint 2026
- Adapting whisper for streaming speech recognition via two-pass decoding — Interspeech 2025
- Method and system for evaluating and improving live translation captioning systems — US Patent 11,715,475, granted 2023
- Metallic chemical potentials in an insulating topological state — Preprint 2022, cited in Nature and Science
- MeetDot: Videoconferencing with live translation captions — EMNLP 2021
- Adaptive transfer learning of multi-view time series classification — Preprint 2019
- Fis-gan: Gan with flow-based importance sampling — Preprint 2019
- Small-scale demographic sequences projection based on time series clustering and lstm-rnn — IEEE ICDMW 2018