DVPS

non-profit

https://dvps.translated.com/

dvps-ai

Activity Feed

AI & ML interests

Multimodal foundation models. The science, technology and applications. Domains: language, medicine, environment.

Recent Activity

spapi submitted a paper 1 day ago

Simulstream: Open-Source Toolkit for Evaluation and Demonstration of Streaming Speech-to-Text Translation Systems

spapi authored a paper 3 days ago

Simulstream: Open-Source Toolkit for Evaluation and Demonstration of Streaming Speech-to-Text Translation Systems

spapi authored a paper 6 days ago

Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs

View all activity

spapi

submitted a paper to Daily Papers 1 day ago

Simulstream: Open-Source Toolkit for Evaluation and Demonstration of Streaming Speech-to-Text Translation Systems

Paper • 2512.17648 • Published 6 days ago • 3

spapi

authored a paper 3 days ago

Simulstream: Open-Source Toolkit for Evaluation and Demonstration of Streaming Speech-to-Text Translation Systems

Paper • 2512.17648 • Published 6 days ago • 3

spapi

authored a paper 6 days ago

Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs

Paper • 2512.16378 • Published 7 days ago • 7

skoneru

updated a collection 14 days ago

DVPS Research Papers

Collection

1 item • Updated 14 days ago • 1

skoneru

authored a paper 21 days ago

BOOM: Beyond Only One Modality KIT's Multimodal Multilingual Lecture Companion

Paper • 2512.02817 • Published 23 days ago • 1

skoneru

authored a paper 23 days ago

Blending LLMs into Cascaded Speech Translation: KIT's Offline Speech Translation System for IWSLT 2024

Paper • 2406.16777 • Published Jun 24, 2024

skoneru

authored a paper 24 days ago

OmniFusion: Simultaneous Multilingual Multimodal Translations via Modular Fusion

Paper • 2512.00234 • Published 27 days ago

spapi

authored a paper about 2 months ago

How to Evaluate Speech Translation with Source-Aware Neural MT Metrics

Paper • 2511.03295 • Published Nov 5 • 3

spapi

authored 2 papers 3 months ago

FAMA: The First Large-Scale Open-Science Speech Foundation Model for English and Italian

Paper • 2505.22759 • Published May 28 • 19

Better Late Than Never: Evaluation of Latency Metrics for Simultaneous Speech-to-Text Translation

Paper • 2509.17349 • Published Sep 22 • 2

mgaido91

authored a paper 3 months ago

Cross-Attention is Half Explanation in Speech-to-Text Models

Paper • 2509.18010 • Published Sep 22 • 6

spapi

authored 2 papers 3 months ago

Cross-Attention is Half Explanation in Speech-to-Text Models

Paper • 2509.18010 • Published Sep 22 • 6

MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks

Paper • 2507.19634 • Published Jul 25 • 9

skoneru

authored a paper 6 months ago

KIT's Offline Speech Translation and Instruction Following Submission for IWSLT 2025

Paper • 2505.13036 • Published May 19

spapi

authored 2 papers 7 months ago

NUTSHELL: A Dataset for Abstract Generation from Scientific Talks

Paper • 2502.16942 • Published Feb 24 • 1

Granary: Speech Recognition and Translation Dataset in 25 European Languages

Paper • 2505.13404 • Published May 19 • 2

skoneru

authored a paper 9 months ago

Quality-Aware Decoding: Unifying Quality Estimation and Decoding

Paper • 2502.08561 • Published Feb 12

mgaido91

authored 3 papers 10 months ago

When Good and Reproducible Results are a Giant with Feet of Clay: The Importance of Software Quality in NLP

Paper • 2303.16166 • Published Mar 28, 2023

Direct Models for Simultaneous Translation and Automatic Subtitling: FBK@IWSLT2023

Paper • 2309.15554 • Published Sep 27, 2023

Integrating Language Models into Direct Speech Translation: An Inference-Time Solution to Control Gender Inflection

Paper • 2310.15752 • Published Oct 24, 2023

AI & ML interests

Recent Activity

Team members 15

dvps's activity