Zachary Coalson

Orcid: 0009-0006-0821-3432

According to our database¹, Zachary Coalson authored at least 10 papers between 2023 and 2026.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of four.

Timeline

Legend:

Book In proceedings Article PhD thesis Dataset Other

Links

On csauthors.net:

Bibliography

2026

Asking Forever: Universal Activations Behind Turn Amplification in Conversational LLMs.

[BibT_eX]

[DOI]

Zachary Coalson

Bo Fang

Sanghyun Hong

CoRR, February, 2026

Discovering Universal Activation Directions for PII Leakage in Language Models.

[BibT_eX]

[DOI]

CoRR, February, 2026

Fail-Closed Alignment for Large Language Models.

[BibT_eX]

[DOI]

CoRR, February, 2026

2025

Hard Work Does Not Always Pay Off: On the Robustness of NAS to Data Poisoning.

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2025

Demystifying the Resilience of Large Language Model Inference: An End-to-End Perspective.

[BibT_eX]

[DOI]

Proceedings of the International Conference for High Performance Computing, 2025

IF-Guide: Influence Function-Guided Detoxification of LLMs.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Harnessing Input-Adaptive Inference for Efficient VLN.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

2024

PrisonBreak: Jailbreaking Large Language Models with Fewer Than Twenty-Five Targeted Bit-flips.

[BibT_eX]

[DOI]

CoRR, 2024

Hard Work Does Not Always Pay Off: Poisoning Attacks on Neural Architecture Search.

[BibT_eX]

[DOI]

CoRR, 2024

2023

BERT Lost Patience Won't Be Robust to Adversarial Slowdown.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Zachary Coalson

Timeline

Legend:

Links

On csauthors.net:

Bibliography

Loading...