Muneeza Azmat

Research eningeer@Red Hat, Inc.·美国·OpenReview

研究方向

Retrieval augmented generation · Domain specific LLMs · Alignment of LLMs · Climate smart agriculture · Medical imaging · Multimodal deep neural networks · Explainable AI

4.0

MEAL: A Multi-dimensional Evaluation of Alignment Techniques for LLMs

ICLR 2026Rejected

一作

-1

An Efficient and Modular Framework for Targeted Harm Mitigation in LLMs

ICLR 2026Withdrawn

三作

6.1

Speculate, then Collaborate: Fusing Knowledge of Language Models during Decoding

ICML 2025Poster

二作

5.7

Out-of-Distribution Detection using Synthetic Data Generation

COLM 2025Poster

二作

5.3

Speculate, then Collaborate: Fusing Knowledge of Language Models during Decoding

ICLR 2025Rejected

二作

4.8

SPRI: Aligning Large Language Models with Context-Situated Principles

ICML 2025Poster

二作

4.8

Out-of-Distribution Detection using Synthetic Data Generation

合作者 (20)

Rogério Abreu de Paula