Dhananjay Ram

26 papers A* 2A 4B 1C 1Journal 14Unranked 4
YearRankTypeTitle / Venue / Authors
2026 J jnl
Reinforcement-aware Knowledge Distillation for LLM Reasoning.
CoRR
Zhaoyang Zhang, Shuli Jiang, Yantao Shen, Yuting Zhang, Dhananjay Ram, Shuo Yang, Zhuowen Tu, Wei Xia, Stefano Soatto
2025 J jnl
Learning to Focus: Focal Attention for Selective and Scalable Transformers.
CoRR
Dhananjay Ram, Wei Xia, Stefano Soatto
2025 — conf
Sequence-level Large Language Model Training with Contrastive Preference Optimization.
NAACL (Findings)
Zhili Feng, Dhananjay Ram, Cole Hawkins, Aditya Rawal, Jinman Zhao, Sheng Zha
2025 J jnl
Sequence-level Large Language Model Training with Contrastive Preference Optimization.
CoRR
Zhili Feng, Dhananjay Ram, Cole Hawkins, Aditya Rawal, Jinman Zhao, Sheng Zha
2024 A* conf
DEM: Distribution Edited Model for Training with Mixed Data Distributions.
EMNLP
Dhananjay Ram, Aditya Rawal, Momchil Hardalov, Nikolaos Pappas, Sheng Zha
2024 J jnl
DEM: Distribution Edited Model for Training with Mixed Data Distributions.
CoRR
Dhananjay Ram, Aditya Rawal, Momchil Hardalov, Nikolaos Pappas, Sheng Zha
2024 B conf
HLAT: High-quality Large Language Model Pre-trained on AWS Trainium.
IEEE Big Data
Haozheng Fan, Hao Zhou, Guangtai Huang, Parameswaran Raman, Xinwei Fu, Gaurav Gupta, Dhananjay Ram, Yida Wang, Jun Huan
2024 J jnl
HLAT: High-quality Large Language Model Pre-trained on AWS Trainium.
CoRR
Haozheng Fan, Hao Zhou, Guangtai Huang, Parameswaran Raman, Xinwei Fu, Gaurav Gupta, Dhananjay Ram, Yida Wang, Jun Huan
2023 — conf
Efficient Long-Range Transformers: You Need to Attend More, but Not Necessarily at Every Layer.
EMNLP (Findings)
Qingru Zhang, Dhananjay Ram, Cole Hawkins, Sheng Zha, Tuo Zhao
2023 J jnl
Efficient Long-Range Transformers: You Need to Attend More, but Not Necessarily at Every Layer.
CoRR
Qingru Zhang, Dhananjay Ram, Cole Hawkins, Sheng Zha, Tuo Zhao
2020 J jnl
Neural Network Based End-to-End Query by Example Spoken Term Detection.
IEEE ACM Trans. Audio Speech Lang. Process.
Dhananjay Ram, Lesly Miculicich, Hervé Bourlard
2019 C conf
Multilingual Bottleneck Features for Query by Example Spoken Term Detection.
ASRU
Dhananjay Ram, Lesly Miculicich, Hervé Bourlard
2019 J jnl
Multilingual Bottleneck Features for Query by Example Spoken Term Detection.
CoRR
Dhananjay Ram, Lesly Miculicich, Hervé Bourlard
2019 J jnl
Neural Network based End-to-End Query by Example Spoken Term Detection.
CoRR
Dhananjay Ram, Lesly Miculicich, Hervé Bourlard
2018 A conf
CNN Based Query by Example Spoken Term Detection.
INTERSPEECH
Dhananjay Ram, Lesly Miculicich, Hervé Bourlard
2018 A* conf
Document-Level Neural Machine Translation with Hierarchical Attention Networks.
EMNLP
Lesly Miculicich, Dhananjay Ram, Nikolaos Pappas, James Henderson
2018 J jnl
Document-Level Neural Machine Translation with Hierarchical Attention Networks.
CoRR
Lesly Miculicich, Dhananjay Ram, Nikolaos Pappas, James Henderson
2018 J jnl
Phonetic subspace features for improved query by example spoken term detection.
Speech Commun.
Dhananjay Ram, Afsaneh Asaei, Hervé Bourlard
2018 A conf
Phonological Posterior Hashing for Query by Example Spoken Term Detection.
INTERSPEECH
Afsaneh Asaei, Dhananjay Ram, Hervé Bourlard
2018 — conf
Self-Attentive Residual Decoder for Neural Machine Translation.
NAACL-HLT
Lesly Miculicich Werlen, Nikolaos Pappas, Dhananjay Ram, Andrei Popescu-Belis
2018 J jnl
Sparse Subspace Modeling for Query by Example Spoken Term Detection.
IEEE ACM Trans. Audio Speech Lang. Process.
Dhananjay Ram, Afsaneh Asaei, Hervé Bourlard
2017 J jnl
Global-Context Neural Machine Translation through Target-Side Attentive Residual Connections.
CoRR
Lesly Miculicich Werlen, Nikolaos Pappas, Dhananjay Ram, Andrei Popescu-Belis
2016 J jnl
A Bayesian Approach to Estimation of Speaker Normalization Parameters.
CoRR
Dhananjay Ram, Debasis Kundu, Rajesh M. Hegde
2016 A conf
Subspace Detection of DNN Posterior Probabilities via Sparse Representation for Query by Example Spoken Term Detection.
INTERSPEECH
Dhananjay Ram, Afsaneh Asaei, Hervé Bourlard
2015 A conf
Sparse modeling of posterior exemplars for keyword detection.
INTERSPEECH
Dhananjay Ram, Afsaneh Asaei, Pranay Dighe, Hervé Bourlard
2014 — conf
A Bayesian approach to speaker normalization using vowel formant frequency.
NCC
Dhananjay Ram, Debasis Kundu, Rajesh M. Hegde