Profiles2023-2026
Zhaozhuo Xu
Stevens Institute of Technology
10Papers
4Last author
20Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers10
- Randomized Antipodal Search Done Right for Data Pareto Improvement of LLM UnlearningAuthor 8 of 8ICLR 2026 · 2 citations
- Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable SparsityAuthor 10 of 10ICLR 2026 · 1 citation
- Scout Before You Attend: Sketch-and-Walk Sparse Attention for Efficient LLM InferenceAuthor 5 of 6ICML 2026
- Zeroth-Order Fine-Tuning of LLMs with Transferable Static SparsityAuthor 12 of 12ICLR 2025
- KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled QuantizationAuthor 3 of 4NeurIPS 2024 · 97 citations
- SIRIUS : Contexual Sparisty with Correction for Efficient LLMsAuthor 3 of 5NeurIPS 2024 · 8 citations
- Knowledge Graphs Can be Learned with Just Intersection FeaturesAuthor 7 of 7ICML 2024 · 3 citations
- Do LLMs Know to Respect Copyright Notice?Author 3 of 4EMNLP 2024 · 1 citation
- TVE: Learning Meta-attribution for Transferable Vision ExplainerAuthor 8 of 11ICML 2024 · 1 citation
- One-Pass Distribution Sketch for Measuring Data Heterogeneity in Federated LearningAuthor 2 of 4NeurIPS 2023 · 19 citations
