Somshubra Majumdar
Identifiers
- name variant Somshubra Majumdar 0.60 · backfill
Papers (36)
- Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning cs.LG · 2026 · author #448
- From SWE-ZERO to SWE-HERO: Execution-free to Execution-based Fine-tuning for Software Engineering Agents cs.SE · 2026 · author #3
- NVIDIA Nemotron 3: Efficient and Open Intelligence cs.CL · 2025 · author #296
- Scaling Test-Time Compute to Achieve IOI Gold Medal with Open-Weight Models cs.LG · 2025 · author #6
- NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model cs.CL · 2025 · author #181
- OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critique cs.CL · 2025 · author #2
- From Output to Evaluation: Does Raw Instruction-Tuned Code LLMs Output Suffice for Fill-in-the-Middle Code Generation? cs.SE · 2025 · author #2
- SWAN-GPT: An Efficient and Scalable Approach for Long-Context Language Modeling cs.CL · 2025 · author #6
- OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs cs.SE · 2025 · author #6
- Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models cs.CL · 2025 · author #161
- OpenCodeReasoning: Advancing Data Distillation for Competitive Coding cs.CL · 2025 · author #3
- Scoring Verifiers: Evaluating Synthetic Verification for Code and Reasoning cs.AI · 2025 · author #2
- Resource-Efficient Adaptation of Speech Foundation Models for Multi-Speaker ASR eess.AS · 2024 · author #6
- Genetic Instruct: Scaling up Synthetic Generation of Coding Instructions for Large Language Models cs.CL · 2024 · author #1
- Less is More: Accurate Speech Recognition & Translation without Web-Scale Data cs.CL · 2024 · author #7
- Instruction Data Generation and Unsupervised Adaptation for Speech Language Models eess.AS · 2024 · author #3
- Nemotron-4 340B Technical Report cs.CL · 2024 · author #38
- Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognition cs.CL · 2023 · author #2
- Investigating End-to-End ASR Architectures for Long Form Audio Transcription eess.AS · 2023 · author #4
- Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition eess.AS · 2023 · author #4
- Efficient Sequence Transduction by Jointly Predicting Tokens and Durations eess.AS · 2023 · author #3
- Multi-blank Transducers for Speech Recognition eess.AS · 2022 · author #3
- Damage Control During Domain Adaptation for Transducer Based Automatic Speech Recognition cs.SD · 2022 · author #1
- CTC Variations Through New WFST Topologies eess.AS · 2021 · author #2
- CarneliNet: Neural Mixture Model for Automatic Speech Recognition eess.AS · 2021 · author #2
- SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognition cs.CL · 2021 · author #3
- Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognition eess.AS · 2021 · author #1
- MarbleNet: Deep 1D Time-Channel Separable Convolutional Neural Network for Voice Activity Detection eess.AS · 2020 · author #2
- Improving Noise Robustness of an End-to-End Neural Model for Automatic Speech Recognition eess.AS · 2020 · author #5
- MatchboxNet: 1D Time-Channel Separable Convolutional Neural Network Architecture for Speech Commands Recognition eess.AS · 2020 · author #1
- Insights into LSTM Fully Convolutional Networks for Time Series Classification cs.LG · 2019 · author #2
- Adversarial Attacks on Time Series cs.LG · 2019 · author #2
- Pathological Voice Classification Using Mel-Cepstrum Vectors and Support Vector Machine eess.AS · 2018 · author #3
- A Comprehensive Comparison between Neural Style Transfer and Universal Style Transfer cs.CV · 2018 · author #1
- Multivariate LSTM-FCNs for Time Series Classification cs.LG · 2018 · author #2
- LSTM Fully Convolutional Networks for Time Series Classification cs.LG · 2017 · author #2
Mentions
- 2504.03624 #161 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 2504.04030 #6 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 2502.13820 #2 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 2507.09075 #2 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 2505.18789 #2 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 2407.21077 #1 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 2504.08719 #6 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 2409.01438 #6 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 2406.11704 #38 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 2406.19674 #7 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 2406.12946 #3 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 2312.17279 #2 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 2211.03541 #3 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 2305.05084 #4 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 2309.09950 #4 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 2304.06795 #3 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 2210.03255 #1 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 2110.03098 #2 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 2004.08531 #1 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 2107.10708 #2 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 2104.02014 #3 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 2104.01721 #1 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 2010.13886 #2 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 2010.12715 #5 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 1902.10756 #2 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 1801.04503 #2 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 1902.10755 #2 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 1812.07729 #3 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 1806.00868 #1 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 1709.05206 #2 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 2508.14444 #181 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 2512.20856 #296 · arxiv_oai · confidence 0.70 Somshubra Majumdar
- 2504.01943 #3 · arxiv_oai · confidence 0.70 Somshubra Majumdar
Frequent Coauthors
- Boris Ginsburg 30 shared papers
- Vahid Noroozi 17 shared papers
- Aleksander Ficek 11 shared papers
- Jagadeesh Balam 11 shared papers
- Wasi Uddin Ahmad 11 shared papers
- Sean Narenthiran 9 shared papers
- Jocelyn Huang 8 shared papers
- Mehrzad Samadi 8 shared papers
- Vitaly Lavrukhin 8 shared papers
- Dima Rekesh 7 shared papers
- Fei Jia 7 shared papers
- Samuel Kriman 7 shared papers
- Oleksii Hrinchuk 6 shared papers
- Oleksii Kuchaiev 6 shared papers
- Siddhartha Jain 6 shared papers
- Ameya Sunil Mahabaleshwarkar 5 shared papers
- Ashwath Aithal 5 shared papers
- Ayush Dattagupta 5 shared papers
- Bryan Catanzaro 5 shared papers
- Christopher Parisien 5 shared papers