publications
2025
- NeurIPS 2025NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV CacheIn Advances in Neural Information Processing Systems (NeurIPS), 2025
2024
- Preprint
2023
- WSDM 2023 (Oral)Reliable decision from multiple subtasks through threshold optimization: Content moderation in the wildIn Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining (WSDM), 2023
- OOD-CV@ICCV23Gradient estimation for unseen domain risk minimization with pre-trained modelsIn Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023
- JCSELooking to personalize gaze estimation using transformersJournal of Computing Science and Engineering, 2023