Wednesday, October 28, 2026 |
| 8:45–9:00 | Opening Remarks |
| 9:00–10:30 | Session 1: Shared Task Overview Papers I |
| 9:00–9:25 | Findings of the WMT26 General Machine Translation Shared Task: Contrastive Dynamic Human Evaluation at Scale
Tom Kocmi, Ekaterina Artemova, Eleftherios Avramidis, Rachel Bawden, Ondřej Bojar, Sergey Dukanov, Anton Dvorkovich, Mark Fishel, Markus Freitag, Samuel Frontull, Thamme Gowda, Roman Grundkiewicz, Barry Haddow, Stan Kharevich, Philipp Koehn, Zheng Li, Jean Maillard, Christof Monz, Alexander Murauski, Kenton Murray, Masaaki Nagata, Stefano Perrella, Martin Popel, Maja Popović, Lorenzo Proietti, Sara Rajaee, Parker Riley, Mariya Shmatova, Steinþór Steingrímsson, Lisa Yankovskaya and Vilem Zouhar |
| 9:25–9:45 | Findings of the WMT26 Shared Task on Automated Translation Quality Evaluation Systems: Compact Open Models are Competitive Quality Evaluators
Alon Lavie, Greg Hanneman, Stefano Perrella, Shuoyang Ding, Eleftherios Avramidis, Lorenzo Proietti, Chi-kiu Lo, Ammon Shurtz, Chrysoula Zerva, Archchana Sindhujan, Vilem Zouhar, Diptesh Kanojia, Frederic Blain, Brian Thompson, Giorgos Filandrianos, Orfeas Menis Mastromichalakis, Tom Kocmi and Pranav Gupta |
| 9:45–10:00 | Findings of the WMT26 Multilingual Instruction Shared Task: Small Models Are Not Yet Polyglots
Patricia Schmidtova, Ekaterina Artemova, Seth Aycock, Niyati Bafna, Shobhit Banga, Manmeet Kaur, Tom Kocmi, Philipp Koehn, Danni Liu, Nam Luu, Sara Papi, Beatrice Savoldi, Mariya Shmatova, Hanuman Sidh, Evfrosiniya Zerminova, Vilem Zouhar, Maike Züfle and Pinzhen Chen |
| 10:00–10:15 | Findings of the WMT26 Terminology Translation Task: The Hard Part is Finding the Terms, Not Using Them
Adrian Charkiewicz, Pinzhen Chen, Thierry Etchegoyhen, Harritxu Gete, Kamil Guttmann, Xu Huang, David Ponce, Artur Nowakowski, Frederic Odermatt, Arturo Oncevay, Dawei Zhu, Vilem Zouhar and Kirill Semenov |
| 10:15–10:30 | Findings of the WMT 2026 Shared Task on Model Compression: No Free Lunch at Extreme Compression
Thamme Gowda, Marco Gaido, Roman Grundkiewicz and Matteo Negri |
| 10:30–11:00 | Coffee Break |
| 11:00–12:00 | Session 2: Invited Talk by Marta Ruiz Costa-jussa: Towards Omnilinguality in AI: MT as a Starting Point for Language Coverage and Capability Parity |
| 12:00–13:00 | Session 3: Shared Task Posters I |
| 12:00–13:00 | General Translation Shared Task |
| 12:00–13:00 | LiLa at WMT 2026 General MT Task: Exploring Beyond NMT and Learning the Limits of LLM Adaptation for Ligurian and Ladin
Mirelle Candida Bueno, Lucas Domingues, Samuel Frontull, Jean Maillard and Sushil Garg |
| 12:00–13:00 | SCIR-TG-MT’s Submission for the WMT 2026 General Machine Translation Task
Xiayu Cao, Baohang Li, Zekun Yuan, Zekai Ye and Xiaocheng Feng |
| 12:00–13:00 | GRIAL-TA participation in the WMT26 General Translation Shared Task: SalamandraTA7bFFT
marta cozzini, Antoni Oliver, Gonzalo López-Sánchez, Mercè Vàzquez, Patricia Morales-Hurtado and Sergi Alvarez-Vidal |
| 12:00–13:00 | Dubformer at WMT26 General MT: Translating the Video, Not the Transcript
Sergey Dukanov, Maria Tsyurupa and Anton Dvorkovich |
| 12:00–13:00 | Relay-MT: Multi-agent LLM Ensembling for Machine Translation – Samsung R&D Poland Submission for WMT2026
Adam Dobrowolski, Paweł Przybysz, Marcin Szymański, Paweł Przewłocki and Artur Janicki |
| 12:00–13:00 | Grammatist at WMT 2026 General MT Task: An Agentic LLM Framework for Machine Translation with Explicit Linguistic Knowledge
Samuel Frontull, Jean Maillard, Christopher R. Haberland, Ruth Videsott and Stefano Lusito |
| 12:00–13:00 | HW-TSC’s Submission to the WMT 2026 General Machine Translation Track
Yu He, Xiaoqing Lan, Daimeng Wei, Jiaxin GUO, Yuanchang Luo, Hengchao Shang, Zongyao Li, Jinlong Yang, Zhanglin Wu and Boqi Huang |
| 12:00–13:00 | CUNI-MH and CUNI-EdUKate at the WMT26 General MT Shared Task
Miroslav Hrabal, Josef Jon and Ondřej Bojar |
| 12:00–13:00 | CUNI-AR Team at WMT26 General Translation Task for Egyptian Arabic
Josef Jon, Rawan Bondok, Miroslav Hrabal and Ondřej Bojar |
| 12:00–13:00 | In the Blind: Building Pseudo-References for MT Evaluation
Diptesh Kanojia, Chi-kiu Lo, Archchana Sindhujan, Samuel Larkin, Greg Hanneman and Alon Lavie |
| 12:00–13:00 | North Small Translate: Advanced Cost-Effective Translation (Cohere CAT+)
Tom Kocmi, Alexandre Berard, Phil Blunsom, Samuel Cahyawijaya, Shaun Rafael Cassini, Ona de Gibert, Aidan Gomez, Nithya Govindarajan, Shun Kiyono, Olivia Lasche, Lawrence Rogers, Kelly Marchisio, Nikita Moghe, Yash More, Camila Moran-Hidalgo, Yiyang Nan, Michael Sachs, Trisha Starostina, Daan van Stigt, Spencer Taylor Rarrick, Sebastian Vincent, Ivan Zhang and Nicholas Frosst |
| 12:00–13:00 | AdaptiveMT at WMT26: A Controller–Executor–Reducer Agent Harness for Document-Level Translation
Soyoung Lee |
| 12:00–13:00 | BSC Submission for WMT26 General Machine Translation Shared Task
Audrey Mash, Jonathan Orama Ayebakuro, Ella Paulina Bohman, Xixian Liao, Francesca De Luca Fornaciari and Maite Melero |
| 12:00–13:00 | RFMT at WMT 2026 General Translation Task
Ryosuke Matsuda, Keito Kudo, Ryo Fujii, Takumi Ito, Makoto Morishita and Jun Suzuki |
| 12:00–13:00 | MakotoAI at WMT26: Per-Pair Model Selection with Deterministic Output Normalization for the General Machine Translation Task
Chris Nishihama |
| 12:00–13:00 | ReMova: Fine-tuning LLMs for English to Belarusian translation
Mikita Pilinka, Aliaksandr Kliuyeu, David Samuel and Yves Scherrer |
| 12:00–13:00 | Apertium-sme-eng for WMT2026 shared task—creating new pair by crossing dictionaries and translating rules
Flammie A. Pirinen |
| 12:00–13:00 | Yandex at WMT26: Translation Adaptation at 235B and Hard-Label Distillation to 8B
Dmitrii Popov, Elizaveta Kozlova, Ekaterina Taracheva, Elizaveta Makhotina, Artem Mekhraliev, Miron Baratelia, Ekaterina Enikeeva and Nikolay Karpachev |
| 12:00–13:00 | Wayfinder: An Agentic Ensemble-and-Postcheck System for WMT26 GenMT
Liangying Shao, Xinwei Wu, Yichong Huang, Jifang Wang, Ruoxi Xu, Ling Shi, Baosong Yang and Linlong Xu |
| 12:00–13:00 | What a DRAG (it is being small): The AMI Submission to the WMT 2026 General Translation Shared Task
Steinþór Steingrímsson, Sveinbjörn Þórðarson and Jón Friðrik Daðason |
| 12:00–13:00 | Krosny at WMT26 General Translation Task: Dictionary Augmentation and Iterative Refinement for English–Belarusian Translation
Oksana Volchek and Vladislav Poritski |
| 12:00–13:00 | Lumen at WMT2026: Instruction-Specialized Translation via Quality-Aware Training and On-Policy Distillation
Hao Wang, Yangyang Liu, Xiaohu Zhao, Heng Liu, Zifu Shang, Tianhao Li, Ruize Gao, Jialong Tang, Shiao Shao, Haoran Wei, Baosong Yang, Linlong Xu, Longyue Wang and Weihua Luo |
| 12:00–13:00 | UvA-MT’s Participation in the WMT26 General Translation Shared Task
Di Wu, Sergey Troshin, Wafaa Mohammed, Seth Aycock, Evgeniia Tokarchuk, Vlad Niculae and Christof Monz |
| 12:00–13:00 | QINGQIU-MT-9B: An Instruction-Following Multilingual Translation Model
Tian Xia, Chao Chen, Mengpeng Yang, Jingxu Yang, Yabo Sun and Qiang Liu |
| 12:00–13:00 | TRIVE: A Tri-Fusion Verified Translation Agent
Mengpeng Yang, Tian Xia, Jingxu Yang, Chao Chen, Yabo Sun and Qiang Liu |
| 12:00–13:00 | TransCore: The NewTranx Submission to the Constrained Track of the WMT26 General Machine Translation Shared Task
Hao Yu, Ziyan Chen, Hongyu Zhao, Yulong Zhang, Xiaogang Wang, Kaiyu Huang and Degen Huang |
| 12:00–13:00 | Test Suites |
| 12:00–13:00 | KUEST: Korean game Usage Evaluation Suite for LLM Translation
Minjoo Choi, Jaejun Jung, Gunwoo Han, Junhyeop Kim, Yiji Yoon, Hyemi Kim, Yeonseo Cho and Jinwoo Jang |
| 12:00–13:00 | Terminology Resources as (MT) Benchmarks: Evaluation of Legal Terminology Challenges in German Language Varieties by EURAC
Paolo Di Natale, Elena Chiocchetti, Natascia Ralli, Marlies Alber and Egon W. Stemle |
| 12:00–13:00 | Mind the Gap: Exposing LLM Translation Blind Spots Using the AlphaMWE Multilingual Parallel Corpus
Lifeng Han, Jiahui Liang, Anna Latusek, Karim El Haff, Amal Haddad Haddad, Josua Höfgen, Kilian Evang, Min Ma and Maryia Zhyrko |
| 12:00–13:00 | Lost in Morphology at WMT26: A Korean-English Test Suite for LLM Translation Blind Spots
Deun Sol Lee, Dae Woong Kim and Yun Ha Seo |
| 12:00–13:00 | Evaluating Occupational Gender Bias and Male Default in Turkish-to-English Machine Translation
Yusuf Öztop |
| 12:00–13:00 | Translating Syntactic Structures: An English-Icelandic Test Suite for Syntactic Divergence
Einar Freyr Sigurðsson, Steinþór Steingrímsson, Bjarki Ármannsson, Atli Jasonarson, Helga Svala Sigurdardottir and Jón Símon Markússon |
| 12:00–13:00 | "I’m Sorry, I Can’t Translate That": A Challenge Set for Refusal to Translate, Overgeneration and Hallucination in LLM Translation Systems
Lisa Vasileva |
| 12:00–13:00 | Finding the Gaps in LLM Translation with CoST
Saumitra Yadav, Ananya Mukherjee and Manish Shrivastava |
| 12:00–13:00 | Metrics Shared Task |
| 12:00–13:00 | Phrase at WMT26 Automated MT Evaluation Task
Alan Eckhardt, Ondrej Glembek and Craig Stewart |
| 12:00–13:00 | FECE: A Challenge Set for Evaluating Fine-Grained Translation Error Correction
Jie Ding and Xiangyu Duan |
| 12:00–13:00 | Pterodactyl: Pushing the Limits of Efficient Automated Translation Evaluation
Evelyn Y. Garland and Carola F. Berger |
| 12:00–13:00 | AGGREE: An Aggregation-Grounded Challenge Set for Segment-Level MT Metric Evaluation
Lena Griesbeck and Michaela Geierhos |
| 12:00–13:00 | CUNI at the WMT26 Automated MT Evaluation Shared Task
Miroslav Hrabal and Ondřej Bojar |
| 12:00–13:00 | HUFS-DILAB at WMT 2026 Automated Translation Quality Evaluation Task 1: Language-Pair Prompt Routing for Error Span Annotation
Jisoo Jang, Haewon Cho and Seungtaek Choi |
| 12:00–13:00 | FACET at WMT 2026 Automated Translation Quality Evaluation Task
Ahrii Kim, Chanjun Park and Seong-heum Kim |
| 12:00–13:00 | PragmaSpan at WMT26: Taxonomy-Guided Few-Shot Error Span Detection and an Empirical Analysis of MPP
Soyoung Lee |
| 12:00–13:00 | Benchmarking Gender Bias in Machine Translation Evaluation Metrics across Occupations
Orfeas Menis Mastromichalakis, Giorgos Filandrianos, Wafaa Mohammed, Giuseppe Attanasio and Chrysoula Zerva |
| 12:00–13:00 | Translation Metrics Cannot Judge What Their Tokeniser Deletes: LIGATUR and AEGIS Submissions to the WMT26 Shared Task on Automated Translation Quality Evaluation
Animesh Mishra, Krishang Sharma and Sonia Khetarpaul |
| 12:00–13:00 | Algebras FluencyScore at WMT26 Automated Translation Quality Evaluation
Airana Mongush and Dmitrii Pukhov |
| 12:00–13:00 | Vertical: Quality Estimation of Machine Translation from Université Grenoble Alpes
Mariam Nakhlé, Raheel Qader, Marco Dinarelli and Hervé Blanchon |
| 12:00–13:00 | Post-hoc Correction of Machine Translation Error Span Predictions
Benjamin Pong |
| 12:00–13:00 | Leveraging Verbalized Confidence in LLM-as-a-Judge for Automated Translation Quality Evaluation
Richard Servajean, Mohammad Golam Sohrab, Lucie Kunitomo-Jacquin and Matiss Rikters |
| 12:00–13:00 | Reference-Free Consensus Evaluation of Machine Translation: Ensembling LLM Error-Span Judgments with Neutral Cross-Verification and STAPLE Reliability Fusion
Assaf Siani |
| 12:00–13:00 | QEbreak at WMT26: A Pre-Registered Audit of Omission and Addition Asymmetry in Machine Translation Quality Metrics
Maksim Silchenko |
| 12:00–13:00 | SpinPop: A Fast Spin Metric for the WMT26 Metrics Shared Task
Jia Xu |
| 12:00–13:00 | Beyond Rankings: Insights from ALTAE’s PTT-MULTITAN Submission to the WMT 2026 Shared Task on Automated Translation Quality Evaluation Systems
Lichao Zhu, Maria Zimina-Poirot and Nicolas Froeliger |
| 12:00–13:00 | Terminology Translation Shared Task |
| 12:00–13:00 | RWS at WMT26 Terminology Translation Task
Jon Cambra Guinea and Andrea Alfieri |
| 12:00–13:00 | UniOR-MT: An Agentic Pipeline for Terminology Translation
Antonio Castaldo, Giulia Speranza, Maria Carmen Staiano, Petra Giommarelli, Johanna Monti and Maria Pia Di Buono |
| 12:00–13:00 | Agenteak: A Multi-Agent Pipeline for Terminology-Constrained Spanish-Basque Translation
Jurgi Giraud and Andrew Gargett |
| 12:00–13:00 | HW-TSC’s Submission to the WMT26 Terminology Translation Shared Task
Boqi Huang, Daimeng Wei, Jiaxin GUO, Yuanchang Luo, Hengchao Shang, Zongyao Li, Jinlong Yang, Zhanglin Wu, Yu He and Xiaoqing Lan |
| 12:00–13:00 | SalamandraTA at WMT 2026 Terminology Shared Task: Hard Examples Are Better Teachers
Xixian Liao and Maite Melero |
| 12:00–13:00 | GRIAL-TA participation in the WMT26 Terminology Shared Task
Gonzalo López-Sánchez, Antoni Oliver, marta cozzini, Mercè Vàzquez, Patricia Morales-Hurtado and Sergi Alvarez-Vidal |
| 12:00–13:00 | STaR-MT: Select, Translate, and Revise Pipeline for Terminology Aware Machine Translation
Guilherme Aren Marchetti, Gil Rocha, Henrique Lopes Cardoso and Rui Sousa-Silva |
| 12:00–13:00 | TARL: A Terminology-Aware Agentic Repair Loop for Language-Agnostic Translation
Shivam Ratnakant Mhaskar, Vrunda Nileshkumar Sukhadia, Anurag Deshmukh, Manan Sharma and Pawan Kumar Rajpoot |
| 12:00–13:00 | CUNI-ÚFAL at the WMT26 Terminology Translation Task
Aleš Manuel Manuel Papáček and Tomáš Sourada |
| 12:00–13:00 | Tilde’s Submission for the WMT2026 Shared Task on Terminology Translation
Marcis Pinnis, Martins Kronis, Emils Grims, Ervins Jakovelis, Roberts Rozis and Toms Bergmanis |
| 12:00–13:00 | UniVie-HAITrans at WMT26 Terminology Translation Task: Terminology-Guided Data Filtering and Few-Shot Fine-Tuning for Lightweight LLMs
Miguel Angel Rios Gaona |
| 12:00–13:00 | STRA-MT: Deterministic Terminology Control for Document-Level Machine Translation
Vania Velda, Yigyu Hwang and Yongho Kim |
| 12:00–13:00 | TaT at WMT26 Terminology Translation Shared Task
Fan Zhang, Tu Mei, Zhang Mengchao, Jinting Wu and Bowbjut.edu.cnen Zhang |
| 12:00–13:00 | Multilingual Instruction Shared Task |
| 12:00–13:00 | A Monolingual LoRA-Tuned Qwen2.5-3B System for Arabic Context-Based Question Answering
Hasan Alkhder, Maria Hanini, Imane Hocine, Maher Pasa and Amro Najjar |
| 12:00–13:00 | Laniqo at WMT26 Multilingual Instruction Shared Task (MIST): Full-Parameter Knowledge Distillation with Task-Conditional Pivot Decoding Under a 10B-Parameter Constraint
Adrian Charkiewicz and Artur Nowakowski |
| 12:00–13:00 | SentinelQA: Task-Level Routing and Output Verification for Multilingual Instruction Following
Asher Uyiosa Egerton-Idehen |
| 12:00–13:00 | TUM-Heilbronn: WMT26 Multilingual Instruction Shared Task
Jen-Chien Hou, Tsedeniya Kinfe Temesgen and Alexander Fraser |
| 12:00–13:00 | Probe Before you Answer! Answerability Probing for Abstention in Cross-Lingual Context-Based Question Answering
Lea Krause, Stefan F. Schouten, Michiel van der Meer and Piek T.J.M. Vossen |
| 12:00–13:00 | CUNI-UFAL at WMT26 Multilingual Instruction Shared Task
Aleš Manuel Manuel Papáček and Patricia Schmidtova |
| 12:00–13:00 | PSK at WMT 2026 MIST: Task-Specialized QLoRA Adapters for Multilingual Summarization and Question Answering
Srikar Kashyap Pulipaka |
| 12:00–13:00 | Task-Preserving Multilingual Instruction Tuning for Open-Ended QA at WMT 2026 MIST
Aleix Sant, Jordi Luque Serrano and Carlos Escolano Peinado |
| 12:00–13:00 | Model Compression Shared Task |
| 12:00–13:00 | COMET Sensitivity-Guided Mixed Precision Quantization for the WMT26 Model Compression Task
Angad Ripudaman Singh Bajwa |
| 12:00–13:00 | Importance-Guided Structural Pruning of Aya Expanse 8B and Gemma-3-12B for English–Chinese Machine Translation
Havish Balaga, Anish Racherla, Kolupoti Navadeep Kiran, Saumitra Yadav and Manish Shrivastava |
| 12:00–13:00 | Pare4Bit: Quantization, Depth Pruning, and Model Selection for the WMT26 Model Compression Task
Nail Fakhrutdinov |
| 12:00–13:00 | Quantize, Qualify, Rerank: A Recipe for Compressing LLMs Without Losing Quality
Thamme Gowda |
| 12:00–13:00 | WMT26 Model Compression Task: Quantising and Distilling TildeOpen
Martins Kronis, Toms Bergmanis, Ingus Jānis Pretkalniņš and Marcis Pinnis |
| 12:00–13:00 | ESTS at WMT26: Routing-Informed Expert Pruning for Model Compression
Liu O. Martin, Lucas Bandarkar and Nanyun Peng |
| 12:00–13:00 | TMU-onono at WMT26: DiBA-Based Model Compression for Czech-to-German Machine Translation
Nobutaka Ono |
| 12:00–13:00 | Layer-Aware Native Quantization for Compact Machine Translation: A WMT26 English-to-Chinese Submission
Alonso Palomino |
| 12:00–13:00 | Tiny Titans at WMT26: Task-Calibrated Quantization and Activation-Aware Low-Rank Compression of Gemma 3 12B
Vania Raya-Rios, Aleksandr Klimchuk, Nicolas M. Cuadrado Avila, Ivo Gollini Navarrete, Samuel Horvath and Martin Takác |
| 12:00–13:00 | Vicomtech@WMT 2026: Mask-based Pruning for Model Compression
David Ponce and Thierry Etchegoyhen |
| 12:00–13:00 | The ILSP/ARC submission to the WMT26 Model Compression Task
Sokratis Sofianopoulos and Prokopis Prokopidis |
| 12:00–13:00 | FBK’s Submission to WMT26 Model Compression Task: Improving Inference Speed for Quantized Models
Dhairya Suman and Luisa Bentivogli |
| 13:00–14:00 | Lunch Break |
| 14:00-15:30 | Session 4: Research Papers Boaster Talks |
| 14:00-15:30 | Efficient Multilingual Neural Machine Translation via Corpus-Driven Vocabulary Pruning: An English-Arabic Case Study.
Ahmed Amine Aliane, Nasredine Semmar and Hassina Aliane |
| 14:00-15:30 | TACTICS: Taxonomy-Aware Intelligent Corpus Sampling for Machine Translation
Prasanth Bathala, Anubhav Shrimal, Sukhdeep Singh Kharbhanda, Pradyumna Lanka and Rohit Dhaipule |
| 14:00-15:30 | Synthetic Slang Generation for Benchmarking Machine Translation
Eric R. Bennett |
| 14:00-15:30 | The Constitution Speaks Nheengatu: An Open MT System and Reproducible Corpus Pipeline for the Amazonian Língua Geral
Fabrício Carraro, Rodolfo Joel Zevallos, Rodrigo Gonçalves de Souza, Caio Henrique Faustino da Silva and John E. Ortega |
| 14:00-15:30 | ChakmaNMT: Machine Translation for a Low-Resource and Endangered Language via Transliteration
Aunabil Chakma, Aditya Chakma, Masum Hasan, Soham Khisa, Chumui Tripura and Rifat Shahriyar |
| 14:00-15:30 | TermJudge: A Document-Level Metric Judging, Not Counting, Terminology in Machine Translation Evaluation
Nicolas Dahan, François Yvon and Rachel Bawden |
| 14:00–15:30 | BaatCheet: A Multilingual Corpus for Dialogue Translation in Indian Languages
Priyanka Dasari, Yuvrajsinh D. Bodana, Vandan Vasantlal Mujadia, Arafat Ahsan, Dipti Misra Sharma and Parameswari Krishnamurthy |
| 14:00–15:30 | StalePO: Anchored Token-Level Preference Optimization using Legacy Post-Edits in Machine Translation
Rohit Dhaipule, Sukhdeep Singh Kharbanda, Prasanth Bathala, Pradyumna Lanka and Anubhav Shrimal |
| 14:00–15:30 | Balancing Global Quality and Pronoun-Specific Feedback for Context-Aware Machine Translation
Harshit Dhankhar, Baban Gain, Asif Ekbal and Yogesh Mani Tripathi |
| 14:00–15:30 | Compact Models for Machine Translation in the Bioinformatics Domain: Synthetic Data, Domain Adaptation, and Expert Evaluation
Jurgi Giraud and Andrew Gargett |
| 14:00–15:30 | ChainAlign: Cross-Lingual Sentence Alignment via Sparse Co-linear Chaining
Owen Nicholas Goldner and Connor Casey Gramazio |
| 14:00–15:30 | LocQE: Principled Domain Adaptation for Localisation Quality Estimation by Leveraging Post-Edits
Kathy Haemmerl, Gabriel Bretschner and Joern Wuebker |
| 14:00–15:30 | Low-resource machine translation using a general-purpose LLM informed by a dedicated NMT model and lexical resources: A case study on Ainu–Japanese translation
Nagito Hara, Karol Nowakowski, Michal Ptaszynski, Lloyd Nicholas Overacker and Masahiro Toyoura |
| 14:00–15:30 | SNAPP: Segment-Level Neural Alignment Post-Processing for Low-Resource Parallel Sentence Mining
Niklas Hettich, Shu Okabe and Alexander Fraser |
| 14:00–15:30 | Dynamic Lagging using Stable-Prefix Training for Simultaneous Translation
Hieu Hoang, Amittai Axelrod and Matt Post |
| 14:00–15:30 | Evaluating Pragmatic Appropriateness in English–Vietnamese Machine Translation with Dyadic Profiles
Zheng-Yu Huang and Richard Tzong-Han Tsai |
| 14:00–15:30 | Which Metric for Which Script? A Quantified Meta-Evaluation of Automatic Metrics and LLM Judges for Low-Resource Indic Machine Translation
Rudali Huidrom, Vikas Kumar, Hoomexsun Pangsatabam, Pinaki Das, Kshetrimayum Boynao Singh and Anand Konjengbam |
| 14:00–15:30 | Align, Integrate, and Fire: Efficient Token-Level Alignment for Zero-Shot SpeechLLMs
Abderrahmane Issam, Yusuf Can Semerci, Jan Scholtes and Gerasimos Spanakis |
| 14:00–15:30 | IndicQE-APE: A Consolidated Benchmark for Quality Estimation and Automatic Post-Editing over Indic Languages
Diptesh Kanojia, Archchana Sindhujan, Sourabh Dattatray Deoghare, Daria Sokova, Shenbin Qian, Girish Koushik, Tharindu Ranasinghe, Constantin Orasan, Chrysoula Zerva, Ricardo Rei, Frederic Blain, André Martins, Marco Turchi, Matteo Negri, Anoop Kunchukuttan, Mitesh M. Khapra and Pushpak Bhattacharyya |
| 14:00–15:30 | Text-Only vs. Image-Aware VLM Judges for Manga Translation Evaluation
Subaru Kimura and Jun Suzuki |
| 14:00–15:30 | From Error Detection to Credit Assignment: Do xCOMET Error Spans Provide Useful Policy Credit for Chinese–Malay Translation?
Zi Chen Koo |
| 14:00–15:30 | Translationese as a Rational Response to Translation Task Difficulty
Maria Kunilovskaya |
| 14:00–15:30 | RT-SFT: Text Style Transfer from Non-Parallel Corpora by Roundtrip Translation
Ruoxi Liu and Philipp Koehn |
| 14:00–15:30 | Multilingual Reasoning Cascades Need More Context
Arnav Mazumder, Dengjia Zhang, Shuyue Stella Li, Yulia Tsvetkov and Niyati Bafna |
| 14:00–15:30 | Lost in Mimicry: Verified Training-Free Post-Editing for LLM Translationese
Dongwon Noh, Donghyeok Koh, Yeon-Soo Lim, Seohyeong Jeong, Yunsu Kim, Gyuwan Kim, SooJong Do, JinYeong Bak, Sugyeong Eo and Cheoneum Park |
| 14:00–15:30 | MITRA-MT: Continued Pretraining, Parallel Corpus Mining, and Multi-Directional Machine Translation for Sanskrit, Tibetan, and Buddhist Chinese
Sebastian Nehrdich and Kurt Keutzer |
| 14:00–15:30 | Mitrasamgraha: A Comprehensive Classical Sanskrit Machine Translation Dataset
Sebastian Nehrdich, David Allport, Jivnesh Sandhan, Manoj Balaji Jagadeeshan, Sujeet Kumar, Sven Sellmer, Pawan Goyal and Kurt Keutzer |
| 14:00–15:30 | LAND: Learning an Adaptive Number of Draws for Bayesian Best-of-N Selection
Koen Oostermeijer and Teryn Jones |
| 14:00–15:30 | How many raters do we need to recognize a bad translation via perplexity?
Antonín Otmar and Ondřej Bojar |
| 14:00–15:30 | Comparing Machine and Human Simultaneous Interpreting
Dongpeng PAN and Kilian G. Seeber |
| 14:00–15:30 | An Analysis of Source-Side Diversity in Machine Translation Evaluation
Esther Ploeger, Johannes Bjerva, Dong Nguyen and Robert Östling |
| 14:00–15:30 | TransClean: A Benchmark for Detecting and Extracting Clean Translations from Large Language Model Outputs
Shenbin Qian and Yves Scherrer |
| 14:00–15:30 | Unlocking Reasoning Capability on Machine Translation in Large Language Models
Sara Rajaee, Sebastian Vincent, Alexandre Berard, Marzieh Fadaee, Kelly Marchisio and Tom Kocmi |
| 14:00–15:30 | DoDS-IITPKD: LoRA Fine-Tuning and LLM Post-Editing for Low-Resource Indic Machine Translation
G.L. John Salvin, Amisha Ramesan, Abigairl Nyasha Chigwededza, Shrikant Tryambak Budde and Swapnil Hingmire |
| 14:00–15:30 | Making COMET Comparable Across Scripts: Diagnosis and Correction of Tokeniser-Induced Script Bias in Indic MT Evaluation
G.L. John Salvin and Swapnil Hingmire |
| 14:00–15:30 | Fine-Tuning LLMs for Translation: General Forgetting Mitigation Does Not Preserve MT-Specific Instruction Following
Niklas Scholz, David Thulke, Abdallah Nasir, Will Allred, Evgeny Matusov and Hermann Ney |
| 14:00–15:30 | AQI: a composite human-calibrated metric for machine translation quality assessment
Anastasiya Serdioukova and Denis Zhilko |
| 14:00–15:30 | Mind Which Bird You Favour: Parameterizing Adequacy-Fluency Balance in Meta-Evaluation of Machine Translation
Behzad Shayegh and Niloofar Kazemi |
| 14:00–15:30 | In-Context Learning for Upper Sorbian to German Translation: Comparing Lexical and Morpho-Syntactic Information
Qimin Sheng, Marion Di Marco and Alexander Fraser |
| 14:00–15:30 | Retrieval-Augmented Terminology Translation for English-Russian: A Multi-Domain Study
Maria Sukhareva and Ekaterina Enikeeva |
| 14:00–15:30 | Obligatory Slots: Under Reference-Free Evaluation, Dropping a Distinction the Source Never Made Is Free
Luxshan Thavarasa, Jubeerathan Thevakumar and Sivasuthan Sukumar |
| 14:00–15:30 | AmanaMT: Translation Direction Predicts Automatic Metric Reliability
Isaac Thompson |
| 14:00–15:30 | ImgMT: Wikipedia-based Dataset For Evaluating Text-in-Image Translation
Šárka Uramová, Petar Kirilov Petrov, Josef Jon, Ondřej Bojar and Michal Novák |
| 14:00–15:30 | Doc2FRC: Length-Consistent Document-Level Machine Translation via Fixed-Range Chunking
Xiaotian Wang, Youyuan Lin, Zhan Shen and Hitomi Yanaka |
| 14:00–15:30 | Learning from Many Voices: Literary MT Using Multi-Reference Human and Synthetic Data
Si Wu, John Wieting and David A. Smith |
| 14:00–15:30 | Studying quantization trade-offs for efficient inference deployment in machine translation
Jim Zhao, Sohir Maskey, Koen Oostermeijer, Douglas Orr and Teryn Jones |
| 14:00–15:30 | Contrastive ESA: Human Evaluation of Multiple Translations at Once
Vilem Zouhar, Roman Grundkiewicz, Sara Rajaee, Parker Riley, Rachel Bawden, Philipp Koehn, Marine Carpuat and Tom Kocmi |
| 16:00-17:30 | Session 5: Research Papers Posters |
Thursday, October 29, 2026 |
| 8:45–10:30 | Session 6: Shared Task Overview Papers II |
| 8:45–9:00 | Findings of WMT 2026 shared task on Low-resource Indic Languages Translation
Partha Pakray, Santanu Pal, Advaitha Vetagiri, Kshetrimayum Boynao Singh, Sandeep Kumar Dash, Arnab Kumar Maji, Saralin A. Lyngdoh, Lenin Laitonjam, Anupam Jamatia, Ajit Das, Sunita Warjri, Uzzal Sharma, Koj Sambyo and Riyanka Manna |
| 9:00–9:15 | Findings of the WMT 2026 Shared Task on Low-Resource Arabic-Asian Language Translation
Sahinur Rahman Laskar, Firoj Alam, Bishwaraj Paul, Irfan Ahmad, Maya Silvi Lydia and Pankaj Dadure |
| 9:15–9:30 | Findings of the WMT26 Chinese–Southeast Asian Multilingual MT Shared Task
Tianyu Dong, Ziyan Chen, Jingsong Liu and Shaolin Zhu |
| 9:30–9:45 | Findings of the Second Shared Task for Creole Language Machine Translation, at WMT 2026
Nathaniel R. Robinson, Ruth-Ann Hazel Armstrong, Claire Bizon Monroc, Rasul Dent, Pranav Gupta, Raj Dabre, Andre Coy and Kenton Murray |
| 9:45–10:00 | Findings of the WMT 2026 Shared Task of the Open Language Data Initiative
Laurie Burchell, David Dale, Jean Maillard, Idris Abdulmumin, Antonios Anastasopoulos, Isaac Caswell and Philipp Koehn |
| 10:00–10:15 | Findings of the WMT26 Video Subtitle Translation Shared Task: Context and Candidate Selection Matter
Zheng Li and Mao Zheng |
| 10:15–10:30 | Findings of the WMT 2026 Shared Task: Multitask LLMs with Limited Resources
Shu Okabe, Marion Di Marco, Kathy Haemmerl, Daryna Dementieva, Lukas Edman, Marko Měškank, Anita Hendrichowa and Alexander Fraser |
| 10:30–11:00 | Coffee Break |
| 11:00–12:00 | Session 7: Shared Task Posters I |
| 11:00–12:00 | Indic Translation Shared Task |
| 11:00–12:00 | LTRC_Plural: Better Data and Better Rewards for Low-Resource Indic MT
VISHNURAJ K. A, Yuvrajsinh D. Bodana, Heli Hitesh bhai Hingrajiya, Priyanka Dasari and Parameswari Krishnamurthy |
| 11:00–12:00 | ADI-IITP: Reward-Guided Preference Optimization for Low-Resource English-Assamese Machine Translation
Aditya Aditya and Asif Ekbal |
| 11:00–12:00 | BVSLP: Enhancing Machine Translation through NMT Fine-Tuning, Back-Translation, and LLM-Assisted Synthetic Data Generation
Palak Arora, Adhikarimayum Meerajita Sharma, Mrityunjaya Indoria, Keneiwenuo Lhoungu, Lalthafamkimi Lalthafamkimi, Bharti Nathani and Nisheeth Joshi |
| 11:00–12:00 | EROL: Transformer-Based Multilingual Translation for Northeastern Indian Language Pairs
Laishram Thoibisana Devi and Grace Lee |
| 11:00–12:00 | NLP-MT_Amrita: A RL-Inspired GRPO based Agentic RAG Framework for Manipuri and Bodo
Kuruva Divya Sree and Deepa Gupta |
| 11:00–12:00 | gators: BM25-Augmented Many-Shot Translation for Low-Resource North-Eastern Indian Languages
Aashish Dhawan, Christopher William Driggers-Ellis, Dzmitry Kasinets, Christan Grant and Zhe Wang |
| 11:00–12:00 | AkibaNLP-TUT: Improving Low-Resource Machine Translation via Language-Specific and Length-Adaptive Noise Injection
Takumi Kachi, Tomoyosi Akiba and Hajime Tsukada |
| 11:00–12:00 | TIP-RBG-AI: Overcoming Orthographic Discrepancies via Algorithmic Translinear Pipelines and Phylogenetic Script Mapping
Barathi Ganesh HB, Michal Ptaszynski, Meenakshi Sharma and Jairam R |
| 11:00–12:00 | MTG-LIRA: Scaling Neural Machine Translation for Low-Resource Indian Languages through Multilingual Learning and Synthetic Data
Vedarth Hede, Neha Gupta, Harish Bapat and Harsh Ekbote |
| 11:00–12:00 | PANINI: Improving Low-Resource English-Manipuri Translation in Two Scripts via rsLoRA and Three-Stream Self-Augmentation
Rudali Huidrom, Vikas Kumar, Hoomexsun Pangsatabam, Pinaki Das, K. Kabi Khanganba, Nongmaithem Zeno, NICHOLAS KHUMUKCHAM, Mangalton Okram, Justice Konjengbam, Sai Varun Jamalpoor, Alex D. Nelson Khangembam, Anand Konjengbam and Vikram Goyal |
| 11:00–12:00 | ANVITA : Machine Translation System for Low-resource Indian Languages - Khasi, Nagamese and Tagin
Siva Bhavani J, Daneshwari Kankanwadi, Abhinav Gugulothu and Biswajit Paul |
| 11:00–12:00 | SCE-KIIT: Fine-Tuning NLLB-200 for English-Nagamese Translation
Agniva Maiti, Aarsh Muley and Sovan Kumar Sahoo |
| 11:00–12:00 | SCE-KIIT: KokLLaMA: Cross-Task Adaptation for Low-Resource English–Kokborok Translation
Agniva Maiti, Aarsh Muley and Sovan Kumar Sahoo |
| 11:00–12:00 | KrenTransV0.1: Multi-Model Routing and Reranking for Low-Resource Northeast Indian Translation
Badal Nyalang, Riya Tekcham and Biman Debbarma |
| 11:00–12:00 | DELAB-IIITM WMT26: Full Fine-Tuning and LoRA-Based Adaptation for English-to-Low-Resource Indic Translation
Dingku Singh Oinam and Navanath Saharia |
| 11:00–12:00 | Decepticons-IIITH : Morphology-Aware Lexicon Filtering of Back-Translated Data for Low-Resource English-to-Indic Translation
Soujanya Rao, Sakhil Taneja, Krishna Chaitanya and Radhika Mamidi |
| 11:00–12:00 | Winterpeg: Do Neural Cellular Automata Help Where Pretraining Ends?
Sujay Uday Rittikar and Sheela Ramanna |
| 11:00–12:00 | An LLM-Driven Pipeline for Extremely Low-Resource English-to-Indic Translation — From Vocabulary Injection to Post-Training and Decoding
Lu Ruan, shaoying jia, fan ning, wei wang, zhengzhen cai, fei hu, heng hu and chenzi wang |
| 11:00–12:00 | JH_NLP_APAShreya2: LoRA Fine-Tuning of NLLB-200 for English–Manipuri Machine Translation at WMT 2026
Aparajita Sinha, Monika Agarwal, Shreya Narayana Bhat, Shreya Bonal and Aryan Agrahari |
| 11:00–12:00 | BRS-NK: Bidirectional Finetuning of NLLB-200 for Low-Resource Indic Languages: Assamese-English and Bodo-English Machine Translation
Bipesh Subedi and Nischal Karki |
| 11:00–12:00 | RozarNLP-cr7 at WMT 2026: LoRA-Fine-Tuned NLLB for Low-Resource Machine Translation in Northeastern Indian Languages
Suyash Yadav, Utkarsh Chaudhary and Alapan Kuila |
| 11:00–12:00 | Arabic-Asian Translation Shared Task |
| 11:00–12:00 | FARABI at WMT 2026: Post-Hoc Channel Controllers for Low-Resource Arabic–Asian Machine Translation
Farizeh Aldabbas, Zyad Altahan, Hossam Elsafty and Rafet Sifa |
| 11:00–12:00 | OpenBracket at WMT 2026: COMET-MBR System Combination over Arabic-Native and Multilingual Models for Low-Resource Arabic-English Translation
Abrar M. Alotaibi |
| 11:00–12:00 | BVSLP at WMT 2026: An Empirical Study of Multilingual Transfer for Low-Resource Arabic-Centric Translation
Palak Arora, Syed Afroz Ahmed, Mansi Jangid, Bharti Nathani and Nisheeth Joshi |
| 11:00–12:00 | MAGADIR at WMT 2026: Cross-System QE Re-ranking and Entity-Aware Selection for Low-Resource Arabic-English Translation
Hossam Boudraa |
| 11:00–12:00 | NCI-MT at WMT 2026: A Quality-Gated Cascade for Low-Resource Arabic-Asian Machine Translation
Satarupa Deb and Prashanth Nayak |
| 11:00–12:00 | MTG-LIRA at WMT 2026: Data-Centric Arabic-Hindi Machine Translation through Corpus Augmentation, Synthetic Parallel Data Generation and Transformer Models.
Vedarth Hede, Neha Gupta, Harish Bapat and Harsh Ekbote |
| 11:00–12:00 | IndicMT at WMT 2026: Full Fine-Tuning of NLLB-200-600M with Round-Trip Filtering and Forward Self-Training for Arabic-Asian Translation
Pramit Jana, Arindam Adhikari, Priyobroto Acharya and Dipankar Das |
| 11:00–12:00 | NERDS-NITS at WMT2026: Pivot-Based and Direct Neural Machine Translation for Arabic–Asian Low-Resource Language Pairs
Misbahul Karim, Faruk Ahmed, Mishbahul Al Islam, Sahinur Rahman Laskar and Rabul Hussain Laskar |
| 11:00–12:00 | NITM AI Lab at WMT 2026 Shared Task: Low-Resource Arabic-Asian Language Translation
Nabin Koirala, Rhythm Bhetwal and Nurul Amin Choudhury |
| 11:00–12:00 | NLP-IIT Patna at WMT 2026: Corpus-Driven Adaptation of Multilingual MT Models for Low-Resource Arabic–Asian Machine Translation
Pushkar Sharma, Mo Ahtasam, Kshetrimayum Boynao Singh, Deepak Kumar and Asif Ekbal |
| 11:00–12:00 | UPES_NLP at WMT 2026 Low-Resource Arabic–Asian Machine Translation Shared Task: Arabic-Centric Machine Translation with NLLB-200-MOE and Prompt-Constrained Entity-Preserving Translation with GPT-5-mini
Sumit Singh, Anish Kumar Vishwakarma, Brijmohan Lal Sahu and Ashwani Kumar |
| 11:00–12:00 | Code & Corpus at WMT 2026: Checkpoint-Pool Minimum Bayes Risk Decoding for Arabic-Hindi and Arabic-Bangla Translation
Raman Kumar Yadav and Alapan Kuila |
| 11:00–12:00 | SLPG_FJWU at WMT 2026: Domain Adapted Augmentation for Low-Resource Arabic-Asian Language Translation
Shomaiza Zafar, Sadaf Abdul Rauf, Sheema Firdous, Muhammad Saad Munir and Nadeem Fakhar |
| 11:00–12:00 | Chinese-Southeast Asian Translation Shared Task |
| 11:00–12:00 | ASEAN-8B: A Prompted Qwen3.5-9B System for Chinese–Southeast Asian Web Translation
WEN HAOBIN |
| 11:00–12:00 | Jiutian-MT-8B at WMT26: Faithfulness-First Training for Chinese-Southeast Asian Translation
Meng Su, Jian Liu and Youxuan Fang |
| 11:00–12:00 | Xiaoyu-MT: Kunming University of Science and Technology at WMT 2026 Chinese-Southeast Asian Multilingual MT Task
Zhenhan Wang, Fengzhao Fan, Yuxin Huang, Kaiwen Tan, Zhengtao Yu, Shengxiang Gao, Cunli Mao, Siqi Zhang and Shuting Jiang |
| 11:00–12:00 | A Direction-Specialized System for WMT26 Chinese-Southeast Asian Multilingual Machine Translation
Xiaojing Yan and Rile HU |
| 11:00–12:00 | Hy-MT2-1.8B for WMT26: Staged Multilingual Adaptation for Chinese–Southeast Asian Translation
Ma Ziwei |
| 11:00–12:00 | Creole Language Translation Shared Task |
| 11:00–12:00 | HT WMT 2026 CreoleMT System Description: Learning Hierarchies for Low-Resource Creole Language Identification
Ananya Ayasi |
| 11:00–12:00 | Enhancing Cultural Awareness for Haitian Creole Machine Translation
Tabitha Megane Bellune, Ngoc Tan Le and Fatiha Sadat |
| 11:00–12:00 | ChapsVision (CHV) at WMT 2026 CreoleMT: Shifting Creole MT from Train-Time to Test-Time Compute for Haitian Creole
Louis Jourdain, Aurélie Pradelles and Nasredine Semmar |
| 11:00–12:00 | GMU WMT 2026 CreoleMT System Description
Chutong Meng and Antonios Anastasopoulos |
| 11:00–12:00 | The University of Melbourne WMT 2026 CreoleMT Submission: A Domain-Balanced Approach to Low-Resource Pacific Creole Machine Translation
Raphael Merx, Nick Thieberger and Ekaterina Vylomova |
| 11:00–12:00 | KYX WMT 2026 CreoleMT System Description: A Contamination- and Orthography-Aware Evaluation for Réunion Creole to English
Yusuf Öztop |
| 11:00–12:00 | Gwo-K Kreyol Classifier: Rock Pidgins (RP) Submission to the WMT 2026 CreoleMT Language Identification Shared Task
Emmett Strickland |
| 11:00–12:00 | Open Data Shared Task |
| 11:00–12:00 | A Human-Translated FLORES+ Dataset for Chakma Language
Firoz Ahmed and Dinalo Chakma |
| 11:00–12:00 | Measuring the Cost of Variety Conflation in Multilingual MT Evaluation: Adding Mozambican Xichangana, Nyanja and Sena to FLORES+
Felermino Dario Mario Ali, Delfina Lázaro Mateus and Manuel Valente Mangue |
| 11:00–12:00 | Adding ciofs and ciüfs to BOUQuET: Benchmark Extension to Ladin
Samuel Frontull, Lara Castlunger, Maximilian Oberhollenzer, Karin Comploj, Ruth Videsott, Robert Sama, Gabriel Perathoner, Carlo Zoli and Paul Videsott |
| 11:00–12:00 | Expanding Chechen Machine Translation Resources: SMOL, BOUQuET, and WMT24++ Extensions
Vladislav Grigorian and Abu-Viskhan Umishov |
| 11:00–12:00 | Closing the Resource Gap for Tigre: A Diaspora-Sourced English–Tigre Parallel Dataset for SMOL
Beshir Ibrahim |
| 11:00–12:00 | A French Version of the SmolSent Corpus
Malik Marmonier, Rachel Bawden and Benoît Sagot |
| 11:00–12:00 | A Savoyard Version of the FLORES+ Corpus
Malik Marmonier, Alain Favre, Benoît Sagot and Rachel Bawden |
| 11:00–12:00 | FIÙR: A Benchmark Dataset for Eastern Lombard Machine Translation
Edoardo Signoroni and Pavel Rychly |
| 11:00–12:00 | Script Matters: Benchmarking Open-Source Machine Translation for Manipuri in Meetei-Mayek and Bengali Script
Kshetrimayum Boynao Singh, Asif Ekbal and Partha Pakray |
| 11:00–12:00 | The Croatian Dataset Seed Submission to the WMT26 Open Language Data Initiative Shared Task
Dragana Zundanović, Hrvoje Leventić, Dragana Božić Lenard and Krešimir Romić |
| 11:00–12:00 | Subtitle Translation Shared Task |
| 11:00–12:00 | QwenSub-MT Framework for WMT 2026 Video Subtitle Translation
Palak Arora, Mansi Jangid, Bharti Nathani and Nisheeth Joshi |
| 11:00–12:00 | SubVision@WMT26: QLoRA Fine-Tuning of Hy-MT2-1.8B for Chinese to English Video Subtitle Translation
Prajwal Ghimire and Aashish Mahato |
| 11:00–12:00 | Laniqo at WMT26 Video Subtitle Translation Shared Task: Multi-Objective Fusion of Pareto-Optimal Candidates
Kamil Guttmann and Artur Nowakowski |
| 11:00–12:00 | paramanandaAI@WMT26 Video Subtitle Translation: QLoRA Fine-Tuning with Test-Time Metadata Prompting
Shiv Ram Saud, Sundeep Dawadi and Sunil Regmi |
| 11:00–12:00 | rupiah at WMT26: Training-Free Context-Aware Subtitle Translation with QE Selection
Pieter Christy Yan Yudhistira, Sayyidah Fatimah Azzahra, Dzaki Rafif Malik and Tirana Noor Fatyanosa |
| 11:00–12:00 | Full-Video Context and Anonymous Candidate Selection for WMT26 Video Subtitle Translation
jianfeng Wu |
| 11:00–12:00 | A Translator–Critic System for Chinese-to-English Subtitle Translation
Aaryan Yekkisetty |
| 11:00–12:00 | Limited Resource Slavic LLM Shared Task |
| 11:00–12:00 | One Model, Five Tasks, Two RTX 3090 GPUs: The HSE System for the Sorbian Track of WMT26 Multitask LLMs with Limited Resources
Michael Diskin |
| 11:00–12:00 | HeyBusan at WMT26: A System for the Sorbian Track
Mikhail Khasykov |
| 11:00–12:00 | Getting More from Small LLMs and Limited Data: Fuzzy-Match Retrieval and Candidate Scoring for Multitask Sorbian NLP
Thomas Moerman and Arda Tezcan |
| 11:00–12:00 | TUMHN@WMT2026: LLMs with Limited Resources for Slavic Languages
Tsedeniya Kinfe Temesgen, Sinan Kurtyigit and Alexander Fraser |
| 11:00–12:00 | Zolint at WMT 2026: A Multitask LLM Submission for the Low-Resource Ukrainian Track
Lingchu Yang, Zitong Fu, Hämmerl Kathy and Masaki Ito |
| 11:00–12:00 | HITSZ at WMT 2026: Mixed Continued Pre-training and Supervised Fine-tuning for Low-Resource Sorbian
cong zhang, Yutong Wang, Xuebo Liu and Min Zhang |
| 12:00–14:00 | Lunch Break |
| 14:00-15:30 | Session 8: Selected Research Papers Talks |
| 14:00–14:15 | Unlocking Reasoning Capability on Machine Translation in Large Language Models
Sara Rajaee, Sebastian Vincent, Alexandre Berard, Marzieh Fadaee, Kelly Marchisio and Tom Kocmi |
| 14:15–14:30 | Fine-Tuning LLMs for Translation: General Forgetting Mitigation Does Not Preserve MT-Specific Instruction Following
Niklas Scholz, David Thulke, Abdallah Nasir, Will Allred, Evgeny Matusov and Hermann Ney |
| 14:30–14:45 | SNAPP: Segment-Level Neural Alignment Post-Processing for Low-Resource Parallel Sentence Mining
Niklas Hettich, Shu Okabe and Alexander Fraser |
| 14:45-15:00 | Synthetic Slang Generation for Benchmarking Machine Translation
Eric R. Bennett |
| 15:00–15:15 | Comparing Machine and Human Simultaneous Interpreting
Dongpeng PAN and Kilian G. Seeber |
| 15:15–15:30 | Align, Integrate, and Fire: Efficient Token-Level Alignment for Zero-Shot SpeechLLMs
Abderrahmane Issam, Yusuf Can Semerci, Jan Scholtes and Gerasimos Spanakis |