Ahmad Beirami

papers

731

total citations

papers (12)

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

ICLR 2025arXiv

citations

InfAlign: Inference-aware language model alignment

ICML 2025arXiv

citations

Block Verification Accelerates Speculative Decoding

ICLR 2025arXiv

citations

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

CVPR 2025arXiv

citations

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

NEURIPS 2023arXiv

citations

Generalization and Robustness of the Tilted Empirical Risk

ICML 2025arXiv

citations

Enhancing Group Fairness in Online Settings Using Oblique Decision Forests

ICLR 2024arXiv

citations

FRAPPÉ: A Group Fairness Framework for Post-Processing Everything

ICML 2024

citations

Ahmad Beirami

papers (12)

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

SpecTr: Fast Speculative Decoding via Optimal Transport

Controlled Decoding from Language Models

Theoretical guarantees on the best-of-n alignment policy

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

InfAlign: Inference-aware language model alignment

Block Verification Accelerates Speculative Decoding

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

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

Generalization and Robustness of the Tilted Empirical Risk

Enhancing Group Fairness in Online Settings Using Oblique Decision Forests

FRAPPÉ: A Group Fairness Framework for Post-Processing Everything

papers (12)

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

SpecTr: Fast Speculative Decoding via Optimal Transport

Controlled Decoding from Language Models

Theoretical guarantees on the best-of-n alignment policy

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

InfAlign: Inference-aware language model alignment

Block Verification Accelerates Speculative Decoding

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

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

Generalization and Robustness of the Tilted Empirical Risk

Enhancing Group Fairness in Online Settings Using Oblique Decision Forests

FRAPPÉ: A Group Fairness Framework for Post-Processing Everything