Amit Levi

Affiliations:

Technion - Israel Institute of Technology, Department of Computer Science, Haifa, Israel

According to our database¹, Amit Levi authored at least 8 papers between 2025 and 2026.

Collaborative distances:

Dijkstra number² of five.
Erdős number³ of four.

Timeline

Legend:

Book In proceedings Article PhD thesis Dataset Other

Bibliography

2026

Extracting Recurring Vulnerabilities from Black-Box LLM-Generated Software.

[BibT_eX]

[DOI]

CoRR, February, 2026

Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models.

[BibT_eX]

[DOI]

CoRR, February, 2026

Silenced Biases: The Dark Side LLMs Learned to Refuse.

[BibT_eX]

[DOI]

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025

Activation Steering for Masked Diffusion Language Models.

[BibT_eX]

[DOI]

CoRR, December, 2025

You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations.

[BibT_eX]

[DOI]

CoRR, November, 2025

Silent Tokens, Loud Effects: Padding in LLMs.

[BibT_eX]

[DOI]

CoRR, October, 2025

Enhancing Jailbreak Attacks via Compliance-Refusal-Based Initialization.

[BibT_eX]

[DOI]

CoRR, February, 2025

Jailbreak Attack Initializations as Extractors of Compliance Directions.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

Amit Levi

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...