TARDIS: Mitigating Temporal Misalignment via Representation Steering.
CoRR, March, 2025
Personalize Your LLM: Fake it then Align it.
Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2025, Albuquerque, New Mexico, USA, April 29, 2025
Weak-to-Strong Generalization Through the Data-Centric Lens.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025
Evaluating Language Model Context Windows: A "Working Memory" Test and Inference-time Correction.
CoRR, 2024
Is Free Self-Alignment Possible?
CoRR, 2024
OTTER: Improving Zero-Shot Classification via Optimal Transport.
CoRR, 2024
Multimodal Data Curation via Object Detection and Filter Ensembles.
CoRR, 2024
OTTER: Effortless Label Distribution Adaptation of Zero-shot Models.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
Zero-Shot Robustification of Zero-Shot Models.
Proceedings of the Twelfth International Conference on Learning Representations, 2024
Zero-Shot Robustification of Zero-Shot Models With Foundation Models.
CoRR, 2023
Mitigating Source Bias for Fairer Weak Supervision.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023
Universalizing Weak Supervision.
Proceedings of the Tenth International Conference on Learning Representations, 2022
Subtask Gated Networks for Non-Intrusive Load Monitoring.
Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, 2019
On the Statistical and Information-theoretic Characteristics of Deep Network Representations.
CoRR, 2018