๐ง๐ท Heading to ๐๐๐๐ฅ 2026 to present our paper ๐ ๐๐๐ ๐ The first human-annotated crosslingual multimodal instruction-following benchmark.
๐ฃ๏ธ Drop by the poster if you are interested in Speech AI!
Check it out:
https://t.co/VraL2xPNUw
๐ New Shared Task: Model Compression for Machine Translation at #WMT2026 (co-located with #EMNLP2026)!
๐ Test data out on June 18th, submissions by July 2nd!
Can you shrink an LLM and keep translation quality high? ๐ง ๐ง
๐ https://t.co/8fTecFpZYa #NLP#ML#LLM#ModelCompression
@sarapapi introduces MCIF, a new benchmark evaluating 23 SOTA models, revealing gaps in speechโvideo integration & long-form processing.
๐ฅ Watch the recording: https://t.co/TDdfBu6C6I
#Meetween#MultimodalAI#LLMs#AIResearch
Very interesting new paper about combining Simultaneous Speech Translation and RAG to improve translation quality! Check it out: https://t.co/xptPCHHE0Y
#Speech#SpeechTech#Translation#RAG
Hi all! I am looking for 2 emergency reviewers for #ACL rolling review on speech models. If you can help please get in touch with me and/or spread the word! Thanks!
Thrilled to share our paper โMCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talksโ is accepted at @iclr_conf 2026 ๐
๐๏ธ MCIF is a fully human-annotated, multimodal & cross-lingual IF benchmark.
๐ Preprint: https://t.co/5sw3Q8M60R
#ICLR2026#AI
Our Multimodal group is looking forward to hosting @sarapapi tomorrow, Friday, January 23rd for a presentation on "Towards Crosslingual Evaluation of General-Purpose Instruction-Following Models Across Text, Speech, and Vision."
Learn more: https://t.co/D9p1AzRkgC
13. Simulstream: Open-Source Toolkit for Evaluation and Demonstration of Streaming Speech-to-Text Translation Systems
๐ Keywords: AI-generated summary, Streaming Speech-to-Text Translation, incremental decoding, re-translation methods, web interface
๐ก Category: AI Systems and Tools
๐ Research Objective:
- Introduce simulstream, an open-source framework for evaluating and demonstrating streaming speech-to-text translation systems, with a focus on long-form audio processing.
๐ ๏ธ Research Methods:
- Supports incremental decoding and re-translation methods, providing a unified framework for comparing quality and latency. Incorporates an interactive web interface for system demonstrations.
๐ฌ Research Conclusions:
- Simulstream is highlighted as a solution to the limitations of SimulEval, offering features for long-form audio processing and an easy demonstration platform.
๐ Paper link: https://t.co/sgUshS8Zuk
Simulstream: Open-Source Toolkit for Evaluation and Demonstration of Streaming Speech-to-Text Translation Systems
https://t.co/igy8foyZre
by @mgaido91@sarapapi
Sara Papi, Javier Garcia Gilabert, et al., "Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs,", https://t.co/uIG13VsOUV
๐ฃ๏ธ Calling all researchers & practitioners in #Speech#Translation!
Help shape the future of the #Simultaneous track at @iwslt 2026. Your input matters!
Please spare 3-5 min to fill out this quick survey๐:
โก๏ธ https://t.co/tMw4NfVqZZ
Leonardo Fornaroli is your 2025 FIA Formula 2 Champion !! ๐
After winning the FIA F3 championship last year, he seals the FIA F2 championship in Qatar ๐ถ๐ฆ
#FIA#F2#QatarGP
Our next presentation is by @sarapapi: "How real is your real-time simultaneous speech-to-text translation system?"
Look for the answer in her TACL paper: https://t.co/psaL5wwbTO
#lt2025fbk
๐ Join us for the LT@FBK day 2025! Discover cutting-edge research and highlights in speech and language technologies from @FBK_research
๐ October 28, 2025
๐FBK, Trento
โน๏ธ https://t.co/38IG1HDAj0