NAVER LABS re-implements pipeline for IWSLT 2026 instruction-following
Paper describes re-implementation of NAVER LABS' IWSLT 2025 pipeline for the 2026 constrained short audio track, using SeamlessM4T-v2-large as speech encoder. A separate NAVER LABS Europe submission jointly performs ASR, ST, and SQA.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Perplexity adds granular effort selector to Computer
- Mystery AI model Ox Alpha draws developers with free access
- GMKtec to launch Ryzen AI Max+ PRO 495 hardware at IFA Berlin 2026
- Drew Breunig: Fable's high cost ends the free lunch for coding models
- Grok voice mode adds two new voices: Aurora and Liora