MT Group at FBK

#MachineTranslation Research Unit @FBK_research.
#nlproc #deeplearning #ai

[MT Group at FBK @fbk_mt]

Our pick of the week by @dhairya_su47605

: "Scaling Laws for Precision" by @tanishqkumar07, Zachary Ankner, @bfspectorShiekh, @blake__bordelon, @Muennighoff, @mansiege, @CPehlevan, Christopher R´e, @AdtRaghunathan

📰https://t.co/PZCB3fyOCw

#Quantization #LLM #ScalingLaw

[Dhairya Suman @dhairya_su47605]

Pick of the week @fbk_mt
Super interesting paper on the limitations of quantization, demonstrating how post-training quantization scales poorly in data.

https://t.co/tBuGTL0Myi

[MT Group at FBK @fbk_mt]

✨ A useful read for anyone working on speech models, multimodal AI, and benchmarking.
#PickOfTheWeek #MTUnit #FBK #Speech

[MT Group at FBK @fbk_mt]

⭐ For our #PickOfTheWeek, this paper explores an important question for modern speech AI:

🎙️ Which Evaluation for Which Speech Model?
👥 Authors: @Maureendss , @EeshanDhekane

Speech foundation models are evolving rapidly, but evaluation practices are still fragmented.

[MT Group at FBK @fbk_mt]

👉🏻 What is being evaluated
👉🏻 Which capabilities are required
👉🏻 What task/protocol constraints define the setup
One key takeaway is that benchmark choice can strongly shape conclusions about model performance and generalization.

[MT Group at FBK @fbk_mt]

🏝️ Also at #LREC2026, Palma de Mallorca!
@luisabentivogli presented our second paper.
"Phonetic-based Ranking for Improved Pseudo-Labeling in Low-Resource ASR"
📄 Paper: https://t.co/X7x431OkNB

Bravi!! 🎉

[MT Group at FBK @fbk_mt]

🏝️ Yesterday at #LREC2026, Palma de Mallorca!
@lina_conti presented "Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation" at the poster session.
📄Paper: https://t.co/DOKHeEdSw4
💻Code: https://t.co/agdakUJiXP
#SpeechTranslation #NLProc

[MT Group at FBK @fbk_mt]

@vishaal_urao @FartashFg #PickOfTheWeek #SpeechLLM #LLM #MachineLearning #AI

[MT Group at FBK @fbk_mt]

How does the granularity of speech-text pairs impact SpeechLLM performance, and what is the optimal way to interleave tokens? Furthermore, what are the best practices for generating synthetic data to boost training?🧐

[MT Group at FBK @fbk_mt]

The paper "Data-Centric Lessons To Improve Speech-Language Pretraining" by @vishaal_urao, Zhiyun Lu, Xuankai Chang, Yongqiang Wang, Violet Z. Yao, Albin Madapally Jose, @FartashFg , Josh Gardner & Chung-Cheng Chiu provides the answers!

📰 Read more: https://t.co/X38qYJAcMi

[Meetween @MeetweenEU]

🎙️ Our paper on connecting Speech Foundation Models with LLMs is featured in the SpeechLMM Training Journal on Weights & Biases.

Read it 👉 https://t.co/996YPS97Q0

SpeechLMM 2.0 coming this summer. 👀

#Meetween #SpeechLMM #AI #NLP

[Meetween @MeetweenEU]

Meetween is part of the organising committee of #IWSLT2026 — the premier conference on spoken language translation. The Shared Task Evaluation Period is open. Working on #speechtranslation, instruction following, or #modelcompression?
Get involved now! 🔗 https://t.co/GbfzpadZyq

[Meetween @MeetweenEU]

4 papers accepted at #LREC -COLING 2026 in Palma de Mallorca 🎉

Sarcasm detection, reference prediction, gender bias in speech translation, and low-resource ASR.
Meet the team, 11–16 May 2026 👉 https://t.co/v9B5twV3Lu

Follow us for paper deep-dives in the coming weeks.
#NLP

[Meetween @MeetweenEU]

𝐂𝐨𝐦𝐞 𝐚𝐧𝐝 𝐦𝐞𝐞𝐭 #𝐌𝐞𝐞𝐭𝐰𝐞𝐞𝐧 𝐚𝐭 𝐋𝐑𝐄�� 𝟐𝟎𝟐𝟔! Two @FBK_research papers accepted. Palma de Mallorca, 11–16 May.
#LREC2026

[Meetween @MeetweenEU]

Many languages are left behind by AI translation. Not for lack of need, but lack of data. Meetween is closing that gap. See us at #TAUS2026 in Rome, 3–5 June. #Meetween #MultilingualAI

[MT Group at FBK @fbk_mt]

🏝️ At #LREC2026? @luisabentivogli is there too, come say hi and chat about the positions in person!

#PhDPosition #MachineTranslation #NLProc #LREC2026 #FBK

[MT Group at FBK @fbk_mt]

⏰ 4 days left to apply!
🎓 2 PhD positions still open:
🎯 Human-Centred Evaluation Frameworks for Multilingual Technologies
✨ Multimedia Personalization with Multimodal Large Language Models
📅 Deadline: 15 May 2026
🔗 Full details: https://t.co/ZagIUM3UCo

[MT Group at FBK @fbk_mt]

📄 "Phonetic-based Ranking for Improved Pseudo-Labelling in Low-Resource ASR"
Paper link: https://t.co/X7x431NMY3
See you there! 🌴

[MT Group at FBK @fbk_mt]

🌍 @lina_conti and @luisabentivogli are heading to #LREC2026 in Palma! They'll present two papers:
📄 "Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation"
Paper link: https://t.co/DOKHeEdkGw