View all publications on Google Scholar
|
2026 |
Agentic Discovery of Multi-Channel Bioacoustic Association Algorithms.
ICLR 2026 Workshop on Foundation Models for Science: Real-World Impact and Science-First Design. Google Scholar @inproceedings{mohapatraunknownagentic42,
title = {Agentic Discovery of Multi-Channel Bioacoustic Association Algorithms},
author = {Paramjyoti Mohapatra, Irina Tolkova, Akanksha Sarkar, Atharva Sehgal, Daniel P Salisbury, Andrew L Von Duyke, Léa Bouffaut, Holger Klinck, and Jennifer J Sun},
year = {2026},
booktitle = {ICLR 2026 Workshop on Foundation Models for Science: Real-World Impact and Science-First Design},
}
|
|
2026 |
Evaluating Agentic Optimization on Large Codebases.
arXiv preprint arXiv:2603.16011. PDF Google Scholar @article{sehgal2026evaluating35,
title = {Evaluating Agentic Optimization on Large Codebases},
author = {Atharva Sehgal, James Hou, Akanksha Sarkar, Ishaan Mantripragada, Swarat Chaudhuri, Jennifer J Sun, and Yisong Yue},
year = {2026},
}
|
|
2026 |
Simple Agents Outperform Experts in Biomedical Imaging Workflow Optimization.
CVPR 2026. Google Scholar @inproceedings{wang2026simple36,
title = {Simple Agents Outperform Experts in Biomedical Imaging Workflow Optimization},
author = {Xuefei Wang, Kai Horstmann, Ethan Lin, Jonathan Chen, Alexander Farhang, Sophia Stiles, Atharva Sehgal, Jonathan Light, David Van Valen, Yisong Yue, and Jennifer J Sun},
year = {2026},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages = {13680-13690},
}
|
|
2026 |
Live Interactive Training for Video Segmentation.
CVPR 2026. Google Scholar @inproceedings{yang2026live31,
title = {Live Interactive Training for Video Segmentation},
author = {Xinyu Yang, Haozheng Yu, Yihong Sun, Bharath Hariharan, and Jennifer J Sun},
year = {2026},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages = {39827-39837},
}
|
|
2026 |
Pre-training Limited Memory Language Models with Internal and External Knowledge.
ICLR 2026. Best Paper Runner-up, NeurIPS 2025 Workshop on Causal and Compositional Foundations of Language Models (CCFM) Project PDF Google Scholar @inproceedings{zhao2025pretraining22,
title = {Pre-training Limited Memory Language Models with Internal and External Knowledge},
author = {Linxi Zhao, Sofian Zalouk, Christian K Belardi, Justin Lovelace, Jin Peng Zhou, Ryan Thomas Noonan, Dongyoung Go, Kilian Q Weinberger, Yoav Artzi, and Jennifer J Sun},
year = {2026},
booktitle = {International Conference on Learning Representations (ICLR)},
note = {Best Paper Runner-up, NeurIPS 2025 Workshop on Causal and Compositional Foundations of Language Models (CCFM)},
url = {https://openreview.net/forum?id=cvztBvlglK},
}
|
|
2025 |
Pre-trained Large Language Models Learn to Predict Hidden Markov Models In-context.
NeurIPS 2025. Project PDF Google Scholar @article{dai2026pretrained34,
title = {Pre-trained Large Language Models Learn to Predict Hidden Markov Models In-context},
author = {Yijia Dai, Zhaolin Gao, Yahya Sattar, Sarah Dean, and Jennifer Sun},
year = {2025},
journal = {Advances in Neural Information Processing Systems},
volume = {38},
pages = {28877-28923},
url = {https://mlanthology.org/neurips/2025/dai2025neurips-pretrained/},
}
|
|
2025 |
Beyond Accuracy: Metrics that Uncover What Makes a'Good'Visual Descriptor.
CVPR 2025 Workshop on Visual Concepts (VisCon). Best Poster Award Project PDF Google Scholar @inproceedings{lin2025beyond32,
title = {Beyond Accuracy: Metrics that Uncover What Makes a'Good'Visual Descriptor},
author = {Ethan Lin, Linxi Zhao, Atharva Sehgal, and Jennifer J Sun},
year = {2025},
booktitle = {CVPR 2025 Workshop on Visual Concepts (VisCon)},
note = {Best Poster Award},
url = {https://ethan-y-lin.github.io/beyond-accuracy-project-page/},
}
|
|
2025 |
How many classes do we need to see for novel class discovery?.
CVPR 2025 Workshop on Domain Generalization: Evolution, Breakthroughs, and Future Horizons. PDF Google Scholar @inproceedings{sarkar2025how38,
title = {How many classes do we need to see for novel class discovery?},
author = {Akanksha Sarkar, Been Kim, and Jennifer J Sun},
year = {2025},
booktitle = {CVPR 2025 Workshop on Domain Generalization: Evolution, Breakthroughs, and Future Horizons},
}
|
|
2025 |
Tracking and understanding object transformations.
NeurIPS 2025. Project PDF Google Scholar @article{sun2026tracking30,
title = {Tracking and understanding object transformations},
author = {Yihong Sun, Xinyu Yang, Jennifer Sun, and Bharath Hariharan},
year = {2025},
journal = {Advances in Neural Information Processing Systems},
volume = {38},
pages = {81039-81065},
url = {https://openreview.net/forum?id=fz1mm2EsQ9},
}
|