BG
Boris Ginsburg
cs.CLeess.AScs.SDcs.LGcs.AIcs.SEcs.CVstat.MLcs.HCcs.MA
On Valency
published · living versionsW_f2a7whhj·v1 · currentpublished
Dory1.0-4B: A Looped Normalized-GPT
with Maxim Fishman, Simeng Sun, Shantanu Acharya, Faisal Ladhak +4
1 version
Preprints & journals
152 papers in the corpus · 2016–2026One Block Ahead: Promoting Sampler State in Diffusion Language Models2610.19510v1 · Yangyi Shen, Pin-Jui Ku, Nicolai Oswald et al.2026 · 0 citationsarXiv
Full-duplex Spoken Language Modeling with Discrete Diffusion2610.17780v1 · Chen Chen, Pin-Jui Ku, Ankita Pasad et al.2026 · 0 citationsarXiv
One Model to Loop Them All: Elastic Latent Recurrence for Language Models2610.12582v1 · Faisal Ladhak, Shantanu Acharya, Santiago Akle Serano et al.2026 · 0 citationsarXiv
UNREAL: Unifying Retrieval and Long-Context with a Single Model2610.08463v1 · Edan Kinderman, Elad Hoffer, Yochai Blau et al.2026 · 0 citationsarXiv
Staying on Task: Testing the Foundations of Long-Horizon Agent Reliability2609.38712v1 · Jeffrey Willette, Krishna C. Puvvada, Boris Ginsburg2026 · 0 citationsarXiv
NemotronLabs VoiceChat: An Open Full-duplex Speech-to-Speech Model with Tool Calling Capabilities2609.21967v2 · Jagadeesh Balam, Travis Bartley, Edresson Casanova et al.2026 · 0 citationsarXiv
Enabling Streaming User Transcription in Full-Duplex Speech-to-Speech Models2609.15759v1 · Ke Hu, Nourchene Ferchichi, Edresson Casanova et al.2026 · 0 citationsarXiv
Pushing the Boundaries of Streaming Multi-Speaker ASR: A Systematic Study of Architectural Trade-offs2609.10265v2 · Taejin Park, Ivan Medennikov, Kunal Dhawan et al.2026 · 0 citationsarXiv
Shortcutting the Fix: Identifying and Categorizing Agentic Exploits in Software Engineering Benchmarks2609.06780v2 · Nikolai Ludwig, Wasi Uddin Ahmad, Somshubra Majumdar et al.2026 · 0 citationsarXiv
Post-Training Language Models for Gold-Medal Performance in Coding Competitions2609.02849v2 · Aleksander Ficek, Sean Narenthiran, Mehrzad Samadi et al.2026 · 0 citationsarXiv
TurboBias 2.0: Streaming Context-Biasing for Production-Efficient ASR Systems2608.21343v1 · Vladimir Bataev, Lilit Grigoryan, Andrei Andrusenko et al.2026 · 0 citationsarXiv
Training nGPT2608.01284v3 · Ilya Loshchilov, Boris Ginsburg2026 · 0 citationsarXiv
Voice Memory for Agentic Speech Recognition2607.26410v1 · Chao-Han Huck Yang, Zih-Ching Chen, Piotr Zelasko et al.2026 · 0 citationsarXiv
Preference-ASR: A Preference-Aware Test Set for Benchmarking ASR in the Era of Speech LLMs2606.29534v1 · Nithin Rao Koluguri, Sasha Meister, Nikolay Karpov et al.2026 · 0 citationsarXiv
SHERLOC: Structured Diagnostic Localization for Code Repair Agents2606.24820v2 · Hovhannes Tamoyan, Sean Narenthiran, Erik Arakelyan et al.2026 · 1 citationarXiv
Open-SWE-Traces: Advancing Dual-Mode Multilingual Distillation for Software Engineering Agents2606.16038v1 · Wasi Uddin Ahmad, Nikolai Ludwig, Somshubra Majumdar et al.2026 · 1 citationarXiv
Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning2606.15007v1 · NVIDIA: Aaron Blakeman, Aaron Thomas, Aastha Jhunjhunwala et al.2026 · 0 citationsarXiv
Workspace Optimization: How to Train Your Agent2605.09650v1 · Elad Sarafian, Gal Kaplun, Ron Banner et al.2026 · 0 citationsarXiv
Retrieval from Within: An Intrinsic Capability of Attention-Based Models2605.05806v3 · Elad Hoffer, Yochai Blau, Edan Kinderman et al.2026 · 0 citationsarXiv
Normalized Architectures are Natively 4-Bit2605.06067v1 · Maxim Fishman, Brian Chmiel, Ron Banner et al.2026 · 0 citationsarXiv
Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence2604.24954v2 · NVIDIA: Amala Sanjay Deshmukh, Kateryna Chumachenko, Tuomas Rintamaki et al.2026 · 1 citationarXiv
Hierarchical Policy Optimization for Simultaneous Translation of Unbounded Speech2604.21045v1 · Siqi Ouyang, Shuoyang Ding, Oleksii Hrinchuk et al.2026 · 0 citationsarXiv
Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization2604.19079v1 · Andrei Andrusenko, Vladimir Bataev, Lilit Grigoryan et al.2026 · 0 citationsarXiv
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning2604.12374v1 · NVIDIA: Aakshita Chandiramani, Aaron Blakeman, Abdullahi Olaoye et al.2026 · 0 citationsarXiv
From SWE-ZERO to SWE-HERO: Execution-free to Execution-based Fine-tuning for Software Engineering Agents2604.01496v2 · Nikolai Ludwig, Wasi Uddin Ahmad, Somshubra Majumdar et al.2026 · 0 citationsarXiv
Speech-Hands: A Self-Reflection Voice Agentic Approach to Speech Recognition and Audio Reasoning with Omni Perception2601.09413v2 · Zhen Wan, Chao-Han Huck Yang, Jinchuan Tian et al.2026 · 0 citationsarXiv
NVIDIA Nemotron 3: Efficient and Open Intelligence2512.20856v1 · NVIDIA: Aaron Blakeman, Aaron Grattafiori, Aarti Basant et al.2025 · 1 citationarXiv
Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning2512.20848v1 · NVIDIA: Aaron Blakeman, Aaron Grattafiori, Aarti Basant et al.2025 · 0 citationsarXiv
Scaling Test-Time Compute to Achieve IOI Gold Medal with Open-Weight Models2510.14232v2 · Mehrzad Samadi, Aleksander Ficek, Sean Narenthiran et al.2025 · 0 citationsarXiv
Extending Automatic Machine Translation Evaluation to Book-Length Documents2509.17249v1 · Kuang-Da Wang, Shuoyang Ding, Chao-Han Huck Yang et al.2025 · 0 citationsarXiv
Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and AST2509.14128v2 · Monica Sekoyan, Nithin Rao Koluguri, Nune Tadevosyan et al.2025 · 0 citationsarXiv
NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model2508.14444v4 · NVIDIA: Aarti Basant, Abhijit Khairnar, Abhijit Paithankar et al.2025 · 0 citationsarXiv
FlexCTC: GPU-powered CTC Beam Decoding With Advanced Contextual Abilities2508.07315v2 · Lilit Grigoryan, Vladimir Bataev, Nikolay Karpov et al.2025 · 1 citationarXiv
TurboBias: Universal ASR Context-Biasing powered by GPU-accelerated Phrase-Boosting Tree2508.07014v2 · Andrei Andrusenko, Vladimir Bataev, Lilit Grigoryan et al.2025 · 1 citationarXiv
SPGISpeech 2.0: Transcribed multi-speaker financial audio for speaker-tagged transcription2508.05554v1 · Raymond Grossman, Taejin Park, Kunal Dhawan et al.2025 · 1 citationarXiv
NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference2508.05835v1 · Edresson Casanova, Paarth Neekhara, Ryan Langman et al.2025 · 4 citationsarXiv
Streaming Sortformer: Speaker Cache-Based Online Speaker Diarization with Arrival-Time Ordering2507.18446v1 · Ivan Medennikov, Taejin Park, Weiqing Wang et al.2025 · 3 citationsarXiv
Open Automatic Speech Recognition Models for Classical and Modern Standard Arabic2507.13977v1 · Lilit Grigoryan, Nikolay Karpov, Enas Albasiri et al.2025 · 2 citationsarXiv
The Challenge of Teaching Reasoning to LLMs Without RL or Distillation2507.09850v3 · Wei Du, Branislav Kisacanin, George Armstrong et al.2025 · 0 citationsarXiv
OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critique2507.09075v1 · Wasi Uddin Ahmad, Somshubra Majumdar, Aleksander Ficek et al.2025 · 0 citationsarXiv
DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment2507.02768v2 · Ke-Han Lu, Zhehuai Chen, Szu-Wei Fu et al.2025 · 6 citationsarXiv
Speaker Targeting via Self-Speaker Adaptation for Multi-talker ASR2506.22646v2 · Weiqing Wang, Taejin Park, Ivan Medennikov et al.2025 · 3 citationsarXiv
Pushing the Limits of Beam Search Decoding for Transducer-based ASR models2506.00185v1 · Lilit Grigoryan, Vladimir Bataev, Andrei Andrusenko et al.2025 · 2 citationsarXiv
NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decoding2505.22857v1 · Vladimir Bataev, Andrei Andrusenko, Lilit Grigoryan et al.2025 · 2 citationsarXiv
From Output to Evaluation: Does Raw Instruction-Tuned Code LLMs Output Suffice for Fill-in-the-Middle Code Generation?2505.18789v2 · Wasi Uddin Ahmad, Somshubra Majumdar, Boris Ginsburg2025 · 0 citationsarXiv
Word Level Timestamp Generation for Automatic Speech Recognition and Translation2505.15646v1 · Ke Hu, Krishna Puvvada, Elena Rastorgueva et al.2025 · 3 citationsarXiv
SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model2505.15670v4 · Ke Hu, Ehsan Hosseini-Asl, Chen Chen et al.2025 · 0 citationsarXiv
Granary: Speech Recognition and Translation Dataset in 25 European Languages2505.13404v2 · Nithin Rao Koluguri, Monica Sekoyan, George Zelenfroynd et al.2025 · 5 citationsarXiv
WIND: Accelerated RNN-T Decoding with Windowed Inference for Non-blank Detection2505.13765v1 · Hainan Xu, Vladimir Bataev, Lilit Grigoryan et al.2025 · 1 citationarXiv
Llama-Nemotron: Efficient Reasoning Models2505.00949v5 · Akhiad Bercovich, Itay Levy, Izik Golan et al.2025 · 1 citationarXiv
Career total: 188 works. 152 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.