@misc{sobrenome2026sharp,
  title  = {Sharp Routers, Flat Experts: Probing the Loss Landscape of Mixture-of-Experts Models},
  author = {Sobrenome, Nome and Petrova, Inessa and Mensah, Kukua},
  year   = {2026},
  url    = {https://example.org/papers/moe-landscape-2026.pdf},
  note   = {Preprint},
}

@inproceedings{sobrenome2025descending,
  title     = {Descending Gently: Curvature-Aware Warmup for Large-Batch Training},
  author    = {Sobrenome, Nome and Tanaka, L{\'\i}via and Okafor, Munachiso},
  booktitle = {Advances in Neural Information Processing Systems},
  year      = {2025},
  url       = {https://example.org/papers/curvature-warmup-2025.pdf},
}

@article{sobrenome2024schedules,
  title   = {Step-Size Schedules as Control Policies: A Unified View of Warmup, Decay and Restarts},
  author  = {Sobrenome, Nome and Moreau, Cyprien},
  journal = {Transactions on Machine Learning Research},
  year    = {2024},
  url     = {https://example.org/papers/schedules-control-2024.pdf},
}

@inproceedings{sobrenome2024distilling,
  title     = {Distilling Long Context into Compact Students for Retrieval-Heavy Tasks},
  author    = {Sobrenome, Nome and Weber, Hilke and Duarte, Graziela and Tanaka, L{\'\i}via},
  booktitle = {Annual Meeting of the Association for Computational Linguistics},
  year      = {2024},
  url       = {https://example.org/papers/long-context-distillation-2024.pdf},
}

@inproceedings{sobrenome2024paraphrase,
  title     = {Paraphrase Drift: Stress-Testing Language Model Evaluations with Controlled Rewrites},
  author    = {Sobrenome, Nome and Haddad, Suhail},
  booktitle = {Workshop at the Conference on Neural Information Processing Systems},
  year      = {2024},
  url       = {https://example.org/papers/paraphrase-drift-2024.pdf},
}

@inproceedings{ribeiro2023gradient,
  title     = {Gradient Noise as a Thermometer: Estimating the Effective Temperature of {SGD}},
  author    = {Ribeiro, Anselmo and Sobrenome, Nome and Lindqvist, Jonna},
  booktitle = {International Conference on Machine Learning},
  year      = {2023},
  url       = {https://example.org/papers/gradient-noise-2023.pdf},
}

@inproceedings{brandao2023lowbit,
  title     = {Low-Bit, High Fidelity: Quantization-Aware Distillation for {Portuguese} Language Models},
  author    = {Brand{\~a}o, Telma and Sobrenome, Nome and Castro, Firmino},
  booktitle = {Conference on Empirical Methods in Natural Language Processing},
  year      = {2023},
  url       = {https://example.org/papers/low-bit-portuguese-2023.pdf},
}

@inproceedings{iyer2022contrastive,
  title     = {Contrastive Views from Weak Supervision: Learning Representations from Noisy Metadata},
  author    = {Iyer, Revathi and Sobrenome, Nome and Novak, Eneja and Haddad, Suhail},
  booktitle = {International Conference on Learning Representations},
  year      = {2022},
  url       = {https://example.org/papers/weak-contrastive-2022.pdf},
}

@article{okafor2022calibration,
  title   = {Calibration Under Shift: A Benchmark and Protocol for Uncertainty in Deployed Classifiers},
  author  = {Okafor, Munachiso and Sobrenome, Nome and Nakamura, Bunta},
  journal = {Journal of Machine Learning Research},
  year    = {2022},
  url     = {https://example.org/papers/calibration-shift-2022.pdf},
}

@inproceedings{sobrenome2021agreeing,
  title     = {Agreeing on Parts: Patch-Level Consistency for Self-Supervised Dense Features},
  author    = {Sobrenome, Nome and Almeida, Pl{\'a}cido and Kowalski, Dobromir},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2021},
  url       = {https://example.org/papers/patch-consistency-2021.pdf},
}