Ahmad Beirami

beirami's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 3 papers 6 months ago

CoDe: Blockwise Control for Denoising Diffusion Models

Paper • 2502.00968 • Published Feb 3

Asymptotics of Language Model Alignment

Paper • 2404.01730 • Published Apr 2, 2024 • 1

Review, Refine, Repeat: Understanding Iterative Decoding of AI Agents with Dynamic Evaluation and Selection

Paper • 2504.01931 • Published Apr 2

authored 8 papers 10 months ago

Towards Robust Prompts on Vision-Language Models

Paper • 2304.08479 • Published Apr 17, 2023

Enhancing Group Fairness in Online Settings Using Oblique Decision Forests

Paper • 2310.11401 • Published Oct 17, 2023

Situated and Interactive Multimodal Conversations

Paper • 2006.01460 • Published Jun 2, 2020

A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models

Paper • 2307.12980 • Published Jul 24, 2023 • 1

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

Paper • 2411.18688 • Published Nov 27, 2024

InfAlign: Inference-aware language model alignment

Paper • 2412.19792 • Published Dec 27, 2024 • 1

Data-augmented phrase-level alignment for mitigating object hallucination

Paper • 2405.18654 • Published May 28, 2024

Theoretical guarantees on the best-of-n alignment policy

Paper • 2401.01879 • Published Jan 3, 2024

authored 2 papers over 1 year ago

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

Paper • 2406.05946 • Published Jun 10, 2024

Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment

Paper • 2404.12318 • Published Apr 18, 2024 • 15

authored 2 papers almost 2 years ago

Gradient-Based Language Model Red Teaming

Paper • 2401.16656 • Published Jan 30, 2024 • 1

Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking

Paper • 2312.09244 • Published Dec 14, 2023 • 10

authored a paper about 2 years ago

Controlled Decoding from Language Models

Paper • 2310.17022 • Published Oct 25, 2023 • 15