Ahmad Beirami

10

Papers

454

Total Citations

Papers (10)

Safety Alignment Should be Made More Than Just a Few Tokens Deep

Theoretical guarantees on the best-of-n alignment policy

On Optimal Generalizability in Parametric Learning

NeurIPS 2017arXiv

Block Verification Accelerates Speculative Decoding

Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignment

Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment

FRAPPÉ: A Group Fairness Framework for Post-Processing Everything

Controlled Decoding from Language Models

SpecTr: Fast Speculative Decoding via Optimal Transport

Uncovering the Hidden Dynamics of Video Self-supervised Learning under Distribution Shifts