1.5k citations · 3k across the 43 of their papers we have counts for
44 papers
Shortcutting the Fix: Identifying and Categorizing Agentic Exploits in Software Engineering Benchmarks
Nikolai Ludwig, Wasi Uddin Ahmad, Somshubra Majumdar +1
High software engineering benchmark scores often mask exploitative shortcuts, such as retrieving upstream solutions, exploiting local Git histories, or recalling memorized code. We…
Post-Training Language Models for Gold-Medal Performance in Coding Competitions
Aleksander Ficek, Sean Narenthiran, Mehrzad Samadi +2
Competitive programming has become a key test of large language model reasoning, with international competitions such as IOI and ICPC representing its most challenging settings. We…
Open-SWE-Traces: Advancing Dual-Mode Multilingual Distillation for Software Engineering Agents
Wasi Uddin Ahmad, Nikolai Ludwig, Somshubra Majumdar +1
The path toward autonomous software engineering is currently bottlenecked by a severe deficit of diverse, large-scale trajectory data. We address this by introducing \ourdataset, a…
Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
NVIDIA, :, Aaron Blakeman +572
We introduce Nemotron 3 Ultra, a 550 billion total and 55 billion active parameter Mixture-of-Experts Hybrid Mamba-Attention language model. We pre-trained Nemotron 3 Ultra on 20 t…
From SWE-ZERO to SWE-HERO: Execution-free to Execution-based Fine-tuning for Software Engineering Agents
Nikolai Ludwig, Wasi Uddin Ahmad, Somshubra Majumdar +1
We introduce SWE-ZERO to SWE-HERO, a two-stage SFT recipe that achieves state-of-the-art results on SWE-bench by distilling open-weight frontier LLMs. Our pipeline replaces resourc…
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
NVIDIA, :, Aakshita Chandiramani +544
We describe the pre-training, post-training, and quantization of Nemotron 3 Super, a 120 billion (active 12 billion) parameter hybrid Mamba-Attention Mixture-of-Experts model. Nemo…
Learning Generative Selection for Best-of-N
Shubham Toshniwal, Aleksander Ficek, Siddhartha Jain +5
Scaling test-time compute via parallel sampling can substantially improve LLM reasoning, but is often limited by Best-of-N selection quality. Generative selection methods, such as…
NVIDIA Nemotron 3: Efficient and Open Intelligence
NVIDIA, :, Aaron Blakeman +356
We introduce the Nemotron 3 family of models - Nano, Super, and Ultra. These models deliver strong agentic, reasoning, and conversational capabilities. The Nemotron 3 family uses a…
Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
NVIDIA, :, Aaron Blakeman +311
We present Nemotron 3 Nano 30B-A3B, a Mixture-of-Experts hybrid Mamba-Transformer language model. Nemotron 3 Nano was pretrained on 25 trillion text tokens, including more than 3 t…
Scaling Test-Time Compute to Achieve IOI Gold Medal with Open-Weight Models
Mehrzad Samadi, Aleksander Ficek, Sean Narenthiran +5
Competitive programming has become a rigorous benchmark for evaluating the reasoning and problem-solving capabilities of large language models (LLMs). The International Olympiad in…
Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation
Vaibhav Srivastav, Steven Zheng, Eric Bezzam +6
We present the Open ASR Leaderboard, a reproducible benchmarking platform with community contributions from academia and industry. It compares 86 open-source and proprietary system…
NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model
NVIDIA, :, Aarti Basant +214
We introduce Nemotron-Nano-9B-v2, a hybrid Mamba-Transformer language model designed to increase throughput for reasoning workloads while achieving state-of-the-art accuracy compar…
A Study on Regularization-Based Continual Learning Methods for Indic ASR
Gokul Adethya T, S. Jaya Nirmala
Indias linguistic diversity poses significant challenges for developing inclusive Automatic Speech Recognition (ASR) systems. Traditional multilingual models, which require simulta…
OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critique
Wasi Uddin Ahmad, Somshubra Majumdar, Aleksander Ficek +6
Recent advancements in reasoning-based Large Language Models (LLMs), particularly their potential through test-time scaling, have created significant opportunities for distillation…
From Output to Evaluation: Does Raw Instruction-Tuned Code LLMs Output Suffice for Fill-in-the-Middle Code Generation?
Wasi Uddin Ahmad, Somshubra Majumdar, Boris Ginsburg
Post-processing is crucial for the automatic evaluation of LLMs in fill-in-the-middle (FIM) code generation due to the frequent presence of extraneous code in raw outputs. This ext…
Llama-Nemotron: Efficient Reasoning Models
Akhiad Bercovich, Itay Levy, Izik Golan +132
We introduce the Llama-Nemotron series of models, an open family of heterogeneous reasoning models that deliver exceptional reasoning capabilities, inference efficiency, and an ope…
SWAN-GPT: An Efficient and Scalable Approach for Long-Context Language Modeling
Krishna C. Puvvada, Faisal Ladhak, Santiago Akle Serrano +8
We present a decoder-only Transformer architecture that robustly generalizes to sequence lengths substantially longer than those seen during training. Our model, SWAN-GPT, interlea…
OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs
Wasi Uddin Ahmad, Aleksander Ficek, Mehrzad Samadi +4
Large Language Models (LLMs) have transformed software development by enabling code generation, automated debugging, and complex reasoning. However, their continued advancement is…
Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models
NVIDIA, :, Aaron Blakeman +198
As inference-time scaling becomes critical for enhanced reasoning capabilities, it is increasingly becoming important to build models that are efficient to infer. We introduce Nemo…
OpenCodeReasoning: Advancing Data Distillation for Competitive Coding
Wasi Uddin Ahmad, Sean Narenthiran, Somshubra Majumdar +5
Since the advent of reasoning-based large language models, many have found great success from distilling reasoning capabilities into student models. Such techniques have significan…
Scoring Verifiers: Evaluating Synthetic Verification for Code and Reasoning
Aleksander Ficek, Somshubra Majumdar, Vahid Noroozi +1
Synthetic verification techniques such as generating test cases and reward modelling are common ways to enhance the coding capabilities of large language models (LLM) beyond predef…
Resource-Efficient Adaptation of Speech Foundation Models for Multi-Speaker ASR
Weiqing Wang, Kunal Dhawan, Taejin Park +6
Speech foundation models have achieved state-of-the-art (SoTA) performance across various tasks, such as automatic speech recognition (ASR) in hundreds of languages. However, multi…
Genetic Instruct: Scaling up Synthetic Generation of Coding Instructions for Large Language Models
Somshubra Majumdar, Vahid Noroozi, Mehrzad Samadi +6
Large Language Models (LLMs) require high quality instruction data for effective alignment, particularly in code generation tasks where expert curated datasets are expensive to pro…
Instruction Data Generation and Unsupervised Adaptation for Speech Language Models
Vahid Noroozi, Zhehuai Chen, Somshubra Majumdar +3
In this paper, we propose three methods for generating synthetic samples to train and evaluate multimodal large language models capable of processing both text and speech inputs. A…