[go: up one dir, main page]

Follow
Zachary Novack
Zachary Novack
CS PhD Student, UC - San Diego
Verified email at ucsd.edu - Homepage
Title
Cited by
Cited by
Year
Chils: Zero-shot image classification with hierarchical label sets
Z Novack, J McAuley, ZC Lipton, S Garg
International Conference on Machine Learning, 26342-26362, 2023
1372023
DITTO: Diffusion inference-time t-optimization for music generation
Z Novack, J McAuley, T Berg-Kirkpatrick, NJ Bryan
International Conference of Machine Learning (ICML), 2024
862024
DITTO-2: Distilled diffusion inference-time t-optimization for music generation
Z Novack, J McAuley, T Berg-Kirkpatrick, N Bryan
International Society of Music Information Retrieval (ISMIR), 2024
282024
Presto! Distilling Steps and Layers for Accelerating Music Generation
Z Novack, G Zhu, J Casebeer, J McAuley, T Berg-Kirkpatrick, NJ Bryan
International Conference on Learning Representations (ICLR), 2024
202024
Are you really listening? Boosting Perceptual Awareness in Music-QA Benchmarks
Y Zang, S O'Brien, T Berg-Kirkpatrick, J McAuley, Z Novack
International Society of Music Information Retrieval (ISMIR), 2025
132025
PDMX: A Large-Scale Public Domain MusicXML Dataset for Symbolic Music Processing
P Long, Z Novack, T Berg-Kirkpatrick, J McAuley
International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024
13*2024
Futga: Towards fine-grained music understanding through temporally-enhanced generative augmentation
J Wu, Z Novack, A Namburi, J Dai, HW Dong, Z Xie, C Chen, J McAuley
arXiv preprint arXiv:2407.20445, 2024
112024
Fast Text-to-Audio Generation with Adversarial Post-Training
Z Novack, Z Evans, Z Zukowski, J Taylor, CJ Carr, J Parker, A Al-Sinan, ...
IEEE Workshop on Applications of Signal Processing to Audio and Acoustics …, 2025
102025
Aligning Text-to-Music Evaluation with Human Preferences
Y Huang, Z Novack, K Saito, J Shi, S Watanabe, Y Mitsufuji, J Thickstun, ...
International Society of Music Information Retrieval (ISMIR), 2025
72025
FUTGA-MIR: Enhancing Fine-grained and Temporally-aware Music Understanding with Music Information Retrieval
J Wu, Z Novack, A Namburi, HW Dong, C Chen, J Dai, J McAuley
ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and …, 2025
62025
CoLLAP: Contrastive Long-form Language-Audio Pretraining with Musical Temporal Structure Augmentation
J Wu, W Li, Z Novack, A Namburi, C Chen, J McAuley
International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024
62024
Video-Guided Text-to-Music Generation Using Public Domain Movie Collections
H Kim, Z Novack, W Xu, J McAuley, HW Dong
International Society of Music Information Retrieval (ISMIR), 2025
42025
Zephyrus: An Agentic Framework for Weather Science
S Varambally, M Fisher, J Thakker, Y Chen, Z Xia, Y Jafari, R Niu, M Jain, ...
arXiv preprint arXiv:2510.04017, 2025
22025
WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning
G Mundada, Y Vishe, A Namburi, X Xu, Z Novack, J McAuley, J Wu
Empirical Methods in Natural Language Processing (EMNLP), Main Conference, 2025
22025
Repurposing Marigold for Zero-Shot Metric Depth Estimation via Defocus Blur Cues
C Talegaonkar, NG Suresh, Z Novack, Y Belhe, P Nagasamudra, ...
arXiv preprint arXiv:2505.17358, 2025
22025
Towards building multimodal weather LLMs
S Varambally, VV Manivannan, Y Jafari, L Han, Z Novack, Z Xia, ...
ICML 2025 Workshop on Assessing World Models, 2025
22025
Unsupervised Lead Sheet Generation via Semantic Compression
Z Novack, N Srivatsan, T Berg-Kirkpatrick, J McAuley
Audio Engineering Society (AES) Workshop on AI & the Musician, 2023
22023
Disentangling the Mechanisms Behind Implicit Regularization in SGD
Z Novack, S Kaur, T Marwah, S Garg, ZC Lipton
International Conference on Learning Representations (ICLR), 2022
22022
Musicrs: Benchmarking audio-centric conversational recommendation
R Surana, A Namburi, G Mundada, A Lal, Z Novack, J McAuley, J Wu
arXiv preprint arXiv:2509.19469, 2025
12025
Bob's Confetti: Phonetic Memorization Attacks in Music and Video Generation
J Roh, Z Novack, Y Peng, N Mireshghallah, T Berg-Kirkpatrick, ...
arXiv preprint arXiv:2507.17937, 2025
12025
The system can't perform the operation now. Try again later.
Articles 1–20