Nathan Susanj

29 papers A* 2A 5C 1Misc 5Journal 11Unranked 5
YearRankTypeTitle / Venue / Authors
2025 J jnl
Activation-Informed Pareto-Guided Low-Rank Compression for Efficient LLM/VLM.
CoRR
Ryan Solgi, Parsa Madinei, Jiayi Tian, Rupak Vignesh Swaminathan, Jing Liu, Nathan Susanj, Zheng Zhang
2025 A conf
Context-Driven Dynamic Pruning for Large Speech Foundation Models.
INTERSPEECH
Masao Someki, Shikhar Bharadwaj, Atharva Anand Joshi, Chyi-Jiunn Lin, Jinchuan Tian, Jee-weon Jung, Markus Müller, Nathan Susanj, Jing Liu, Shinji Watanabe
2025 A* conf
MaZO: Masked Zeroth-Order Optimization for Multi-Task Fine-Tuning of Large Language Models.
EMNLP
Zhen Zhang, Yifan Yang, Kai Zhen, Nathan Susanj, Athanasios Mouchtaris, Siegfried Kunzmann, Zheng Zhang
2025 J jnl
MaZO: Masked Zeroth-Order Optimization for Multi-Task Fine-Tuning of Large Language Models.
CoRR
Zhen Zhang, Yifan Yang, Kai Zhen, Nathan Susanj, Athanasios Mouchtaris, Siegfried Kunzmann, Zheng Zhang
2025 — conf
Saten: Sparse Augmented Tensor Networks for Post-Training Compression of Large Language Models.
EMNLP (Findings)
Ryan Solgi, Kai Zhen, Rupak Vignesh Swaminathan, Nathan Susanj, Athanasios Mouchtaris, Siegfried Kunzmann, Zheng Zhang
2025 J jnl
Saten: Sparse Augmented Tensor Networks for Post-Training Compression of Large Language Models.
CoRR
Ryan Solgi, Kai Zhen, Rupak Vignesh Swaminathan, Nathan Susanj, Athanasios Mouchtaris, Siegfried Kunzmann, Zheng Zhang
2025 J jnl
SharpZO: Hybrid Sharpness-Aware Vision Language Model Prompt Tuning via Forward-Only Passes.
CoRR
Yifan Yang, Zhen Zhang, Rupak Vignesh Swaminathan, Jing Liu, Nathan Susanj, Zheng Zhang
2025 — conf
Wanda++: Pruning Large Language Models via Regional Gradients.
ACL (Findings)
Yifan Yang, Kai Zhen, Bhavana Ganesh, Aram Galstyan, Goeric Huybrechts, Markus Müller, Jonas M. Kübler, Rupak Vignesh Swaminathan, Athanasios Mouchtaris, Sravan Babu Bodapati, Nathan Susanj, Zheng Zhang, Jack FitzGerald, Abhishek Kumar
2025 J jnl
Wanda++: Pruning Large Language Models via Regional Gradients.
CoRR
Yifan Yang, Kai Zhen, Bhavana Ganesh, Aram Galstyan, Goeric Huybrechts, Markus Müller, Jonas M. Kübler, Rupak Vignesh Swaminathan, Athanasios Mouchtaris, Sravan Babu Bodapati, Nathan Susanj, Zheng Zhang, Jack FitzGerald, Abhishek Kumar
2024 Misc conf
Max-Margin Transducer Loss: Improving Sequence-Discriminative Training Using a Large-Margin Learning Strategy.
ICASSP
Rupak Vignesh Swaminathan, Grant P. Strimel, Ariya Rastrow, Sri Harish Mallidi, Kai Zhen, Hieu Duy Nguyen, Nathan Susanj, Athanasios Mouchtaris
2023 J jnl
Accelerator-Aware Training for Transducer-Based Speech Recognition.
CoRR
Suhaila M. Shakiah, Rupak Vignesh Swaminathan, Hieu Duy Nguyen, Raviteja Chinta, Tariq Afzal, Nathan Susanj, Athanasios Mouchtaris, Grant P. Strimel, Ariya Rastrow
2023 A conf
Conmer: Streaming Conformer Without Self-attention for Interactive Voice Assistants.
INTERSPEECH
Martin Radfar, Paulina Lyskawa, Brandon Trujillo, Yi Xie, Kai Zhen, Jahn Heymann, Denis Filimonov, Grant P. Strimel, Nathan Susanj, Athanasios Mouchtaris
2023 Misc conf
Gated Contextual Adapters For Selective Contextual Biasing In Neural Transducers.
ICASSP
Anastasios Alexandridis, Kanthashree Mysore Sathyendra, Grant P. Strimel, Feng-Ju Chang, Ariya Rastrow, Nathan Susanj, Athanasios Mouchtaris
2023 Misc conf
Multilingual End-To-End Spoken Language Understanding For Ultra-Low Footprint Applications.
ICASSP
Markus Müller, Anastasios Alexandridis, Zach Trozenski, Joel Whiteman, Grant P. Strimel, Nathan Susanj, Athanasios Mouchtaris, Siegfried Kunzmann
2022 Misc conf
A Neural Prosody Encoder for End-to-End Dialogue Act Classification.
ICASSP
Kai Wei, Dillon Knox, Martin Radfar, Thanh Tran, Markus Müller, Grant P. Strimel, Nathan Susanj, Athanasios Mouchtaris, Maurizio Omologo
2022 J jnl
A neural prosody encoder for end-ro-end dialogue act classification.
CoRR
Kai Wei, Dillon Knox, Martin Radfar, Thanh Tran, Markus Müller, Grant P. Strimel, Nathan Susanj, Athanasios Mouchtaris, Maurizio Omologo
2022 — conf
Accelerator-Aware Training for Transducer-Based Speech Recognition.
SLT
Suhaila M. Shakiah, Rupak Vignesh Swaminathan, Hieu Duy Nguyen, Raviteja Chinta, Tariq Afzal, Nathan Susanj, Athanasios Mouchtaris, Grant P. Strimel, Ariya Rastrow
2022 A* conf
Adaptive Global-Local Context Fusion for Multi-Turn Spoken Language Understanding.
AAAI
Thanh Tran, Kai Wei, Weitong Ruan, Ross McGowan, Nathan Susanj, Grant P. Strimel
2022 A conf
ConvRNN-T: Convolutional Augmented Recurrent Neural Network Transducers for Streaming Speech Recognition.
INTERSPEECH
Martin Radfar, Rohit Barnwal, Rupak Vignesh Swaminathan, Feng-Ju Chang, Grant P. Strimel, Nathan Susanj, Athanasios Mouchtaris
2022 J jnl
ConvRNN-T: Convolutional Augmented Recurrent Neural Network Transducers for Streaming Speech Recognition.
CoRR
Martin Radfar, Rohit Barnwal, Rupak Vignesh Swaminathan, Feng-Ju Chang, Grant P. Strimel, Nathan Susanj, Athanasios Mouchtaris
2022 A conf
Knowledge Distillation via Module Replacing for Automatic Speech Recognition with Recurrent Neural Network Transducer.
INTERSPEECH
Kaiqi Zhao, Hieu Nguyen, Animesh Jain, Nathan Susanj, Athanasios Mouchtaris, Lokesh Gupta, Ming Zhao
2022 A conf
Sub-8-Bit Quantization Aware Training for 8-Bit Neural Network Accelerator with On-Device Speech Recognition.
INTERSPEECH
Kai Zhen, Hieu Duy Nguyen, Raviteja Chinta, Nathan Susanj, Athanasios Mouchtaris, Tariq Afzal, Ariya Rastrow
2022 J jnl
Sub-8-Bit Quantization Aware Training for 8-Bit Neural Network Accelerator with On-Device Speech Recognition.
CoRR
Kai Zhen, Hieu Duy Nguyen, Raviteja Chinta, Nathan Susanj, Athanasios Mouchtaris, Tariq Afzal, Ariya Rastrow
2022 — conf
Sub-8-Bit Quantization for On-Device Speech Recognition: A Regularization-Free Approach.
SLT
Kai Zhen, Martin Radfar, Hieu Duy Nguyen, Grant P. Strimel, Nathan Susanj, Athanasios Mouchtaris
2022 J jnl
Sub-8-bit quantization for on-device speech recognition: a regularization-free approach.
CoRR
Kai Zhen, Martin Radfar, Hieu Duy Nguyen, Grant P. Strimel, Nathan Susanj, Athanasios Mouchtaris
2022 Misc conf
Tie Your Embeddings Down: Cross-Modal Latent Spaces for End-to-end Spoken Language Understanding.
ICASSP
Bhuvan Agrawal, Markus Müller, Samridhi Choudhary, Martin Radfar, Athanasios Mouchtaris, Ross McGowan, Nathan Susanj, Siegfried Kunzmann
2021 C conf
Attentive Contextual Carryover for Multi-Turn End-to-End Spoken Language Understanding.
ASRU
Kai Wei, Thanh Tran, Feng-Ju Chang, Kanthashree Mysore Sathyendra, Thejaswi Muniyappa, Jing Liu, Anirudh Raju, Ross McGowan, Nathan Susanj, Ariya Rastrow, Grant P. Strimel
2021 J jnl
Attentive Contextual Carryover for Multi-Turn End-to-End Spoken Language Understanding.
CoRR
Kai Wei, Thanh Tran, Feng-Ju Chang, Kanthashree Mysore Sathyendra, Thejaswi Muniyappa, Jing Liu, Anirudh Raju, Ross McGowan, Nathan Susanj, Ariya Rastrow, Grant P. Strimel
2021 — conf
Revisiting Pretraining with Adapters.
RepL4NLP@ACL-IJCNLP
Seungwon Kim, Alex Shum, Nathan Susanj, Jonathan Hilgart