TOSCA-MP

Oct 1, 2011 | Projects

1 October 2011 to 31 March 2014 - PROJECT CLOSED

The TOSCA-MP project aimed to develop user-centric content annotation and search tools for professionals in networked media production and archiving (television, radio, online), addressing their specific use cases and workflow requirements. The project brought together 10 partners from 6 European countries including industry partners providing solutions for the media industry, public service broadcasters as well as their European association, a university and research centres. TOSCA-MP investigated scalable and distributed content processing methods performing advanced multimodal information extraction and semantic enrichment. Other key technology areas included search methods across heterogeneous networked content repositories and novel user interfaces. An open standards based service oriented framework integrated the components of the system.

MT Group at FBK Follow

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

Avatar MT Group at FBK @fbk_mt ·

3 Sep

Our pick of the week by
@dhairya_su47605
: "Task-Circuit Quantization: Leveraging Knowledge Localization and Interpretability for Compression" by @hanqi_xiao, @yilin_sung, @EliasEskin and @mohitban47
#Quantization #Interpretibility

Dhairya Suman @dhairya_su47605

#PickoftheWeek @fbk_mt
Super cool paper on leavaraging Interpretability for Compression!

https://arxiv.org/pdf/2504.07389

Reply on Twitter 2095460605318648068 Retweet on Twitter 2095460605318648068 1 Like on Twitter 2095460605318648068 6 Twitter 2095460605318648068

Avatar MT Group at FBK @fbk_mt ·

12 Aug

Our pick of the week:

"Large Language Diffusion Model" by Shen Nie, Fengqi Zhu, @ZebinYou, Xiaolu Zhang, Jingyang Ou, Jun Hu, Jun Zhou, Yankai Lin, Ji-Rong Wen, @LiChongxuan

It is very cool to see how the researcher combine diffusion model and transformer blocks to train

Reply on Twitter 2087492676358730231 Retweet on Twitter 2087492676358730231 Like on Twitter 2087492676358730231 4 Twitter 2087492676358730231

Avatar MT Group at FBK @fbk_mt ·

24 Jul

Our pick of the week by
@mgaido91

: "FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model" by Jiaqi Li, Chaoren Wang, Xiaohai Tian, Mingjie Chen, Xinyu Liang, Xu Li, Yufan Lin, Junwen Qiu, Jun Zhang, Lu Lu, Haizhou Li and @drwuz
#SLM #EfficientInference

Marco Gaido @mgaido91

Cool to see a work that adaptively chooses at inference how much to compress the input speech sequence, to control inference costs and quality based on the input, without enforcing a global trade-off to each segment: https://arxiv.org/pdf/2606.31247

@fbk_mt

Reply on Twitter 2080585458933719345 Retweet on Twitter 2080585458933719345 Like on Twitter 2080585458933719345 3 Twitter 2080585458933719345

Avatar MT Group at FBK @fbk_mt ·

8 Jul

Our pick of the week by
@FBKZhihangXie : "Speech-XL: Towards Long-Form Speech Understanding in Large Speech Language Models" by Haoqin Sun, @Chenyang_Lyu, Shiwan Zhao, Xuanfan Ni, Xiangyu Kong, @wangly0229, Weihua Luo and Yong Qin
#SpeechLLM #LongFormSpeech #SLU

Zhihang Xie @FBKZhihangXie

🚀 New paper: Speech-XL for long-form SpeechLLMs
📄 https://arxiv.org/abs/2602.05373
🧩 Uses Speech Summarization Tokens to compress local speech intervals into compact KV states efficiently.
✨ Improves long-form speech understanding while reducing memory and FLOPs on 10-minute audio.

Reply on Twitter 2074844624506503630 Retweet on Twitter 2074844624506503630 Like on Twitter 2074844624506503630 3 Twitter 2074844624506503630