Andre Martins

TOWER+: Bridging Generality and Translation Specialization in Multilingual LLMs ACL 2026 Did Translation Models Get More Robust Without Anyone Even Noticing? ACL 2025 From Tower to Spire: Adding the Speech Modality to a Translation-Specialist LLM EMNLP 2025 Translate Smart, not Hard: Cascaded Translation Systems with Quality-Aware Deferral EMNLP 2025 Formalizing Test-Time Compute for Function-Level Code Generation AACL 2025 A Recipe of Parallel Corpora Exploitation for Multilingual Large Language Models NAACL 2025 XAMPLER: Learning to Retrieve Cross-Lingual In-Context Examples NAACL 2025 AdaSplash: Adaptive Sparse Flash Attention ICML 2025 $∞$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation ICML 2025 Formalizing Test-Time Compute for Function-Level Code Generation IJCNLP 2025 Sparse Activations as Conformal Predictors AISTATS 2025 Different Speech Translation Models Encode and Translate Speaker Gender Differently ACL 2025 LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks ACL 2025 Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation ACL 2025 Watching the Watchers: Exposing Gender Disparities in Machine Translation Quality Estimation ACL 2025 Non-Exchangeable Conformal Risk Control ICLR 2024 Sparse and Structured Hopfield Networks ICML 2024 mPLM-Sim: Better Cross-Lingual Similarity and Transfer in Multilingual Pretrained Language Models EACL 2024 Non-Exchangeable Conformal Language Generation with Nearest Neighbors EACL 2024 Can Automatic Metrics Assess High-Quality Translations? EMNLP 2024 Modeling User Preferences with Automatic Metrics: Creating a High-Quality Preference Dataset for Machine Translation EMNLP 2024 Analyzing Context Contributions in LLM-based Machine Translation EMNLP 2024 xTower: A Multilingual LLM for Explaining and Correcting Translation Errors EMNLP 2024 Findings of the Quality Estimation Shared Task at WMT 2024: Are LLMs Closing the Gap in QE? EMNLP 2024 Tower v2: Unbabel-IST 2024 Submission for the General MT Shared Task EMNLP 2024 Improving Context Usage for Translating Bilingual Customer Support Chat with Large Language Models EMNLP 2024 How Effective Are State Space Models for Machine Translation? EMNLP 2024 When Does Translation Require Context? A Data-driven, Multilingual Exploration ACL 2023 CREST: A Joint Framework for Rationalization and Counterfactual Text Generation ACL 2023 The Inside Story: Towards Better Understanding of Machine Translation Neural Evaluation Metrics ACL 2023 Python Code Generation by Asking Clarification Questions ACL 2023 Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation EACL 2023 Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages ACL 2023 Optimal Transport for Unsupervised Hallucination Detection in Neural Machine Translation ACL 2023 Findings of the WMT 2023 Shared Task on Quality Estimation EMNLP 2023 The Devil Is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation EMNLP 2023 Differentiable Causal Discovery Under Latent Interventions CLEAR 2022 Sparse Communication via Mixed Distributions ICLR 2022 ∞-former: Infinite Memory Transformer ACL 2022 Modeling Structure with Undirected Neural Networks ICML 2022 Learning to Scaffold: Optimizing Model Explanations for Teaching NIPS 2022 Efficient Machine Translation Domain Adaptation ACL 2022 Quality-Aware Decoding for Neural Machine Translation NAACL 2022 Predicting Attention Sparsity in Transformers ACL 2022 Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity NIPS 2020 Sparse and Continuous Attention Mechanisms NIPS 2020 LP-SparseMAP: Differentiable Relaxed Optimization for Sparse Structured Prediction ICML 2020 Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers) ACL 2019 Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1) ACL 2019 Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2) ACL 2019 Learning Classifiers with Fenchel-Young Losses: Generalized Entropies, Margins, and Algorithms AISTATS 2019 Proceedings of the Third Workshop on Structured Prediction for NLP NAACL 2019 SparseMAP: Differentiable Sparse Structured Inference ICML 2018 Proceedings of the Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics EACL 2017 From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification ICML 2016 Orbit Regularization NIPS 2014 Fast and Robust Compressive Summarization with Dual Decomposition and Multi-Task Learning ACL 2013 Turning on the Turbo: Fast Third-Order Non-Projective Turbo Parsers ACL 2013 Structured Sparsity in Structured Prediction EMNLP 2011 Dual Decomposition with Many Overlapping Components EMNLP 2011 Turbo Parsers: Dependency Parsing by Approximate Variational Inference EMNLP 2010 Concise Integer Linear Programming Formulations for Dependency Parsing ACL 2009 Concise Integer Linear Programming Formulations for Dependency Parsing IJCNLP 2009