Iftekhar Naim

Computer Science · Physical Sciences

13h-index753citations31works2.22yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Topic Modeling(15), Natural Language Processing Techniques(9), Multimodal Machine Learning Applications(6), Human Pose and Action Recognition(4), Bayesian Methods and Mixture Models(4)

Publications31 total

EmbeddingGemma: Powerful and Lightweight Text Representations
arXiv (Cornell University)·2025Open Access
On the Theoretical Limitations of Embedding-Based Retrieval
arXiv (Cornell University)·2025· 1 citedOpen Access
Gemini Embedding: Generalizable Embeddings from Gemini
arXiv (Cornell University)·2025Open Access
LOFT: Scalable and More Realistic Long-Context Evaluation
2025Open Access
Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?
arXiv (Cornell University)·2024· 3 citedOpen Access
Gecko: Versatile Text Embeddings Distilled from Large Language Models
arXiv (Cornell University)·2024· 9 citedOpen Access
Rethinking the Role of Token Retrieval in Multi-Vector Retrieval
arXiv (Cornell University)·2023· 7 citedOpen Access
TextMI: Textualize Multimodal Information for Integrating Non-verbal Cues in Pre-trained Language Models
arXiv (Cornell University)·2023· 6 citedOpen Access
How Does Beam Search improve Span-Level Confidence Estimation in Generative Sequence Labeling?
arXiv (Cornell University)·2022Open Access
Multi-Vector Retrieval as Sparse Alignment
arXiv (Cornell University)·2022· 4 citedOpen Access
Transforming Sequence Tagging Into A Seq2Seq Task
arXiv (Cornell University)·2022· 1 citedOpen Access
Transforming Sequence Tagging Into A Seq2Seq Task
2022· 12 citedOpen Access
Feature-Based Decipherment for Machine Translation
Computational Linguistics·2018· 3 citedOpen Access
Scribe
Communications of the ACM·2017· 21 cited
Aligning movies with scripts by exploiting temporal ordering constraints
2016· 6 cited
Automated Analysis and Prediction of Job Interview Performance
IEEE Transactions on Affective Computing·2016· 140 cited
ROC comment
2016· 3 cited
Unsupervised alignment of actions in video with text descriptions
International Joint Conference on Artificial Intelligence·2016· 32 cited
Feature-based Decipherment for Large Vocabulary Machine Translation
arXiv (Cornell University)·2015· 2 citedOpen Access
Automated prediction and analysis of job interview performance: The role of what you say and how you say it
2015· 124 cited
page 1 of 2Next →

Frequent Co-authors

Daniel Gildea(14), Jinhyuk Lee(7), Michael Boratko(6), Zhuyun Dai(5), Sai Meher Karthik Duddu(5), Henry Kautz(4), Jiebo Luo(4), Ming‐Wei Chang(4), Md. Iftekhar Tanveer(3), Tim R. Mosmann(3), Suprakash Datta(3), James S. Cavenaugh(3), Gaurav Sharma(3), Karthik Raman(3), Kazuma Hashimoto(3), Daniel Cer(3), Jeremy R. Cole(3), Gustavo Hernández Ábrego(3), Mohammed Ehsan Hoque(2), Jonathan A. Rebhahn(2)