Nan Xu

Affiliations:
  • University of Southern California, Department of Computer Science, Los Angeles, CA, USA


According to our database1, Nan Xu authored at least 17 papers between 2017 and 2025.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2025
FRIEDA: Benchmarking Multi-Step Cartographic Reasoning in Vision-Language Models.
CoRR, December, 2025

OmniStruct: Universal Text-to-Structure Generation across Diverse Schemas.
CoRR, November, 2025

Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability Theory.
CoRR, May, 2025

MetaScale: Test-Time Scaling with Evolving Meta-Thoughts.
CoRR, March, 2025

Semantic-Clipping: Efficient Vision-Language Modeling with Semantic-Guidedd Visual Selection.
CoRR, March, 2025

From Introspection to Best Practices: Principled Analysis of Demonstrations in Multimodal In-Context Learning.
Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, 2025

MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability Theory.
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

2024
Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking.
Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2024, 2024

AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

mDPO: Conditional Preference Optimization for Multimodal Large Language Models.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

Monotonic Paraphrasing Improves Generalization of Language Model Prompting.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

2023
Improving Zero-Shot Generalization for CLIP with Synthesized Prompts.
CoRR, 2023

Dense Retrieval as Indirect Supervision for Large-space Decision Making.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, 2023

Uncertainty-Guided Test-Time Training for Face Forgery Detection.
Proceedings of the Pattern Recognition - 7th Asian Conference, 2023

2022
Does Your Model Classify Entities Reasonably? Diagnosing and Mitigating Spurious Correlations in Entity Typing.
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022

2017
Joint Adaptive Neighbours and Metric Learning for Multi-view Subspace Clustering.
CoRR, 2017


  Loading...