Gabriel Synnaeve

Optimizing Language Models for Inference Time Objectives using Reinforcement Learning ICML 2025 RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning ICML 2025 SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains? ICLR 2025 TestGenEval: A Real World Unit Test Generation and Test Completion Benchmark ICLR 2025 The KoLMogorov Test: Compression by Code Generation ICLR 2025 Training compute-optimal transformer encoder models EMNLP 2025 What Makes Large Language Models Reason in (Multi-Turn) Code Generation? ICLR 2025 Better & Faster Large Language Models via Multi-token Prediction ICML 2024 CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution ICML 2024 Discrete Flow Matching NeurIPS 2024 Getting the most out of your tokenizer for pre-training and domain adaptation ICML 2024 Masked Audio Generation using a Single Non-Autoregressive Transformer ICLR 2024 A Data Source for Reasoning Embodied Agents AAAI 2023 AudioGen: Textually Guided Audio Generation ICLR 2023 Augmentation Invariant Discrete Representation for Generative Spoken Language Modeling ACL 2023 Code Translation with Compiler Representations ICLR 2023 Expresso: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis Interspeech 2023 From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion NeurIPS 2023 Generative Spoken Language Model based on continuous word-sized audio tokens EMNLP 2023 Simple and Controllable Music Generation NeurIPS 2023 Textually Pretrained Speech Language Models NeurIPS 2023 Flashlight: Enabling Innovation in Tools for Machine Learning ICML 2022 Gradient Matching for Domain Generalization ICLR 2022 Leveraging Automated Unit Tests for Unsupervised Code Translation ICLR 2022 Star Temporal Classification: Sequence Modeling with Partially Labeled Data NeurIPS 2022 CAPE: Encoding Relative Positions with Continuous Augmented Positional Embeddings NeurIPS 2021 Going Deeper With Image Transformers ICCV 2021 Hierarchical Skills for Efficient Exploration NeurIPS 2021 MDETR - Modulated Detection for End-to-End Multi-Modal Understanding ICCV 2021 Rethinking Evaluation in ASR: Are Our Models Robust Enough? Interspeech 2021 Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training Interspeech 2021 slimIPL: Language-Model-Free Iterative Pseudo-Labeling Interspeech 2021 XCiT: Cross-Covariance Image Transformers NeurIPS 2021 Contextualizing ASR Lattice Rescoring with Hybrid Pointer Network Language Model Interspeech 2020 End-to-End Object Detection with Transformers ECCV 2020 Growing Action Spaces ICML 2020 Iterative Pseudo-Labeling for Speech Recognition Interspeech 2020 Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameters Interspeech 2020 MLS: A Large-Scale Multilingual Dataset for Speech Research Interspeech 2020 Real Time Speech Enhancement in the Waveform Domain Interspeech 2020 Scaling Up Online Speech Recognition Using ConvNets Interspeech 2020 Word-Level Speech Recognition With a Letter to Word Encoder ICML 2020 A fully differentiable beam search decoder ICML 2019 A Structured Prediction Approach for Generalization in Cooperative Multi-Agent Reinforcement Learning NeurIPS 2019 Value Propagation Networks ICLR 2019 Who Needs Words? Lexicon-Free Speech Recognition Interspeech 2019 End-to-End Speech Recognition from the Raw Waveform Interspeech 2018 Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger NeurIPS 2018 Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play ICLR 2018 Joint Learning of Speaker and Phonetic Similarities with Siamese Networks Interspeech 2016 Jointly Learning to Locate and Classify Words Using Convolutional Networks Interspeech 2016 Prosodic boundary information helps unsupervised word segmentation NAACL 2015 Unsupervised Word Segmentation in Context COLING 2014