Chao-Hong Liu

@eaclmeeting @RicoSennrich @Jiang_Zifan @amitmoryossef @bricksdont @ebling_sarah @protonish_ @SFU @AnoopSarkar @LTIatCMU @SCSatCMU @CarnegieMellon @_janius_ @saratoga_high @StanfordData @Stanford @alexandraxron @CisLmu @LMU_Muenchen @StDario1 @bryanlics @upennnlp @SonalSannigrahi @Saar_Uni @DFKI @cnerg @pawang_iitk @heigvd @EPFL_en @apopescubelis @WeiRuiChen1 @UBCLinguistics @UBCiSchool @UBCLangScis @mageed @UnivOfTehran @NYUAbuDhabi @nyhabash @Uni_Stuttgart @edo_signoroni @MasarykUni @FI_MUNI @Orange_SV LoResMT (workshop on low-resource MT) concluded. Thanks for all who contributed and participated. See you next time. Here is the thread of presentations and two keynotes. twitter.com/chstoneliu/sta…

🚨BREAKING - Galway It’s going to kick off on Galway tonight! Huge numbers of masked, heavily-armed Gardai have arrived in Galway to beat peaceful fuel protesters off the harbour. Things will explode tonight 🤯 Follow us and share

NEW paper from Meta. (bookmark this one) What if the model wasn't just using the computer, but became the computer? New research from Meta AI and KAUST makes a serious case for Neural Computers (NCs). The paper proposes NCs as learned runtimes where computation, memory, and I/O live inside a single latent state. Their first prototypes use video models to roll out terminal and GUI interfaces from prompts, pixels, and user actions. Why does it matter? Today's agents still depend on external computers to store state, execute actions, and enforce system contracts. Neural Computers point to a different machine form: one where interface dynamics, working memory, and execution are learned together. The early results are promising but grounded. CLI rendering improves, GUI cursor control reaches 98.7% with explicit visual supervision, and reprompting boosts arithmetic-probe accuracy from 4% to 83%. But symbolic reliability, stable reuse, and runtime governance remain open. This is less "agents got better" and more "what comes after agents as a computing substrate?" Paper: arxiv.org/abs/2604.06425 Learn to build effective AI agents in our academy: academy.dair.ai

@shashwatup9k @eaclmeeting @aclmeeting @insight_centre @ivrik @tuetschek @CharlesUniPRG @ufal_cuni @madrugad0 @DLSUManila @uni_lu @lahore_uet @NICT_Publicity Dr Julia Kreutzer (Cohere for Labs @Cohere_Labs) to give invited talk at LoResMT 2026. Title: Building Tiny Aya: Optimizing for Multilinguality in Small LLMs juliakreutzer.github.io Chair: Atul Kr. Ojha (University of Galway @uniofgalway)

@shashwatup9k @eaclmeeting @aclmeeting @insight_centre @ivrik @tuetschek @CharlesUniPRG @ufal_cuni @madrugad0 @DLSUManila @uni_lu @lahore_uet @NICT_Publicity @Cohere_Labs @uniofgalway @unimelb @jaredraycoleman @LoyolaMarymount Context Volume Drives Performance: Tackling Domain Shift in Extremely Low-Resource Translation via RAG Authors: David Samuel Setiawan, Raphaël Merx, Jey Han Lau aclanthology.org/2026.loresmt-1…

@shashwatup9k @eaclmeeting @aclmeeting @insight_centre @ivrik @tuetschek @CharlesUniPRG @ufal_cuni @madrugad0 @DLSUManila @uni_lu @lahore_uet @NICT_Publicity @Cohere_Labs @uniofgalway Kickoff of LoResMT 2026 Session 4: Scientific Research Papers Chair: Ekaterina Vylomova @ivrik (University of Melbourne, Australia @UniMelb)

@shashwatup9k @eaclmeeting @aclmeeting @insight_centre @ivrik @tuetschek @CharlesUniPRG @ufal_cuni Kartáč et al., 2025 arxiv.org/abs/2603.20133 Onderková et al., 2025 aclanthology.org/2025.inlg-main…

@shashwatup9k @eaclmeeting @aclmeeting @insight_centre @ivrik @tuetschek @CharlesUniPRG @ufal_cuni aclanthology.org/2026.mme-main.… LLMs as Span Annotators: A Comparative Study of LLMs and Humans Kasner et al., 2026

@shashwatup9k @eaclmeeting @aclmeeting @insight_centre @ivrik @tuetschek @CharlesUniPRG @ufal_cuni Real-World Summarization: When Evaluation Reaches Its Limits Schmidtová et al., 2025 aclanthology.org/2025.findings-…

@shashwatup9k @eaclmeeting @aclmeeting @insight_centre @ivrik @tuetschek @CharlesUniPRG @ufal_cuni How (un)faithful are explainable LLM-based NLG metrics? Terentowicz et al., 2025 aclanthology.org/2025.inlg-main…

@shashwatup9k @eaclmeeting @aclmeeting @insight_centre @ivrik @tuetschek @CharlesUniPRG @ufal_cuni When LLMs Can’t Help: Real-World Evaluation of LLMs in Nutrition Li et al., 2025 aclanthology.org/2025.inlg-main…

@shashwatup9k @eaclmeeting @aclmeeting @insight_centre @ivrik @tuetschek @CharlesUniPRG @ufal_cuni @madrugad0 Turkic Languages Overview.

@shashwatup9k @eaclmeeting @aclmeeting @insight_centre @ivrik @tuetschek @CharlesUniPRG @ufal_cuni @madrugad0 @DLSUManila @uni_lu @lahore_uet @NICT_Publicity @Cohere_Labs @uniofgalway @unimelb @jaredraycoleman @LoyolaMarymount @fc_univ A Fine-Grained Linguistic Evaluation of Low-Resource Luxembourgish–English MT by Nils Rehlinger (University of Luxembourg @uni_lu) aclanthology.org/2026.loresmt-1…

@shashwatup9k @eaclmeeting @aclmeeting @insight_centre @ivrik @tuetschek @CharlesUniPRG @ufal_cuni @madrugad0 @DLSUManila @uni_lu @lahore_uet @NICT_Publicity @Cohere_Labs @uniofgalway @unimelb @jaredraycoleman @LoyolaMarymount Maximiliano Duran from University of Franche-Comté @fc_univ presenting Semi-Automatic construction of a Quechua-Spanish dictionary Authors: Maximiliano Duran, Max Silberztein aclanthology.org/2026.loresmt-1…

@shashwatup9k @eaclmeeting @aclmeeting @insight_centre @ivrik @tuetschek @CharlesUniPRG @ufal_cuni @madrugad0 @DLSUManila @uni_lu @lahore_uet @NICT_Publicity @Cohere_Labs @uniofgalway SimMerge: Learning to Select Merge Operators from Similarity Signals Bolton et al., 2026 arxiv.org/abs/2601.09473

@shashwatup9k @eaclmeeting @aclmeeting @insight_centre @ivrik @tuetschek @CharlesUniPRG @ufal_cuni @madrugad0 @DLSUManila @uni_lu @lahore_uet @NICT_Publicity @Cohere_Labs @uniofgalway Command-A-Translate: Raising the Bar of Machine Translation with Difficulty Filtering Kocmi et al., 2025 aclanthology.org/2025.wmt-1.55/

@shashwatup9k @eaclmeeting @aclmeeting @insight_centre @ivrik @tuetschek @CharlesUniPRG @ufal_cuni @madrugad0 @DLSUManila @uni_lu @lahore_uet @NICT_Publicity @Cohere_Labs @uniofgalway Making, not Taking, the Best of N Khairi et al., 2025 arxiv.org/abs/2510.00931

@shashwatup9k @eaclmeeting @aclmeeting @insight_centre @ivrik @tuetschek @CharlesUniPRG @ufal_cuni @madrugad0 @DLSUManila @uni_lu @lahore_uet @NICT_Publicity @Cohere_Labs @uniofgalway The Art of Asking: Multilingual Prompt Optimization for Synthetic Data Mora et al., 2025 arxiv.org/abs/2510.19806

@shashwatup9k @eaclmeeting @aclmeeting @insight_centre @ivrik @tuetschek @CharlesUniPRG @ufal_cuni @madrugad0 @DLSUManila @uni_lu @lahore_uet @NICT_Publicity @Cohere_Labs @uniofgalway Post-training: Overcoming Data Scarcity with Multi-stage Synthetic Data Pipeline

@shashwatup9k @eaclmeeting @aclmeeting @insight_centre @ivrik @tuetschek @CharlesUniPRG @ufal_cuni @madrugad0 @DLSUManila @uni_lu @lahore_uet @NICT_Publicity @Cohere_Labs @uniofgalway Tiny Aya: Making Multilingual AI cohere.com/blog/cohere-la… Tiny Aya: Bridging Scale and Multilingual Depth Salamanca et al., 2026 arxiv.org/abs/2603.11510

@shashwatup9k @eaclmeeting @aclmeeting @insight_centre @ivrik @tuetschek @CharlesUniPRG @ufal_cuni @madrugad0 @DLSUManila @uni_lu @lahore_uet @NICT_Publicity @Cohere_Labs @uniofgalway @unimelb @jaredraycoleman @LoyolaMarymount @fc_univ CTC Regularization for Low-Resource Speech-to-Text Translation Authors: Zachary William Hopton, Rico Sennrich @RicoSennrich aclanthology.org/2026.loresmt-1… Zurich Computational Linguistics Group @cl_uzh University of Zurich @UZH_en