75 citations · 174 across the 19 of their papers we have counts for
21 papers
Unified Audio Intelligence Without Regressing on Text Intelligence
Zhifeng Kong, Sang-gil Lee, Jaehyeon Kim +17
Audio intelligence involves understanding, reasoning about, and generating both audio and speech. In this work, we introduce Nemotron-Labs-Audex-30B-A3B (Audex), a unified audio-te…
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…
Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation
Zhuolin Yang, Zihan Liu, Yang Chen +14
We introduce Nemotron-Cascade 2, an open 30B MoE model with 3B activated parameters that delivers best-in-class reasoning and strong agentic capabilities. Despite its compact size,…
Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
Boxin Wang, Chankyu Lee, Nayeon Lee +9
Building general-purpose reasoning models with reinforcement learning (RL) entails substantial cross-domain heterogeneity, including large variation in inference-time response leng…
NVIDIA Nemotron Nano V2 VL
NVIDIA, :, Amala Sanjay Deshmukh +121
We introduce Nemotron Nano V2 VL, the latest model of the Nemotron vision-language series designed for strong real-world document understanding, long video comprehension, and reaso…
From 128K to 4M: Efficient Training of Ultra-Long Context Large Language Models
Chejian Xu, Wei Ping, Peng Xu +5
Long-context capabilities are essential for a wide range of applications, including document and video understanding, in-context learning, and inference-time scaling, all of which…
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…
Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning
NVIDIA, :, Alisson Azzolini +51
Physical AI systems need to perceive, understand, and perform complex actions in the physical world. In this paper, we present the Cosmos-Reason1 models that can understand the phy…
NVLM: Open Frontier-Class Multimodal LLMs
Wenliang Dai, Nayeon Lee, Boxin Wang +7
We introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks, rivaling the leading propr…
RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs
Yue Yu, Wei Ping, Zihan Liu +5
Large language models (LLMs) typically utilize the top-k contexts from a retriever in retrieval-augmented generation (RAG). In this work, we propose a novel instruction fine-tuning…
Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications
Fengqing Jiang, Zhangchen Xu, Luyao Niu +4
Large language models (LLMs) are increasingly deployed as the service backend for LLM-integrated applications such as code completion and AI-powered search. LLM-integrated applicat…
InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining
Boxin Wang, Wei Ping, Lawrence McAfee +4
Pretraining auto-regressive large language models~(LLMs) with retrieval demonstrates better perplexity and factual accuracy by leveraging external databases. However, the size of e…
Certifying Out-of-Domain Generalization for Blackbox Functions
Maurice Weber, Linyi Li, Boxin Wang +3
Certifying the robustness of model performance under bounded data distribution drifts has recently attracted intensive interest under the umbrella of distributional robustness. How…
Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models
Boxin Wang, Chejian Xu, Shuohang Wang +5
Large-scale pre-trained language models have achieved tremendous success across a wide range of natural language understanding (NLU) tasks, even surpassing human performance. Howev…
Counterfactual Adversarial Learning with Representation Interpolation
Wei Wang, Boxin Wang, Ning Shi +4
Deep learning models exhibit a preference for statistical fitting over logical reasoning. Spurious correlations might be memorized when there exists statistical bias in training da…
Incorporating External POS Tagger for Punctuation Restoration
Ning Shi, Wei Wang, Boxin Wang +3
Punctuation restoration is an important post-processing step in automatic speech recognition. Among other kinds of external information, part-of-speech (POS) taggers provide inform…
DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation
Boxin Wang, Fan Wu, Yunhui Long +3
Recent success of deep neural networks (DNNs) hinges on the availability of large-scale dataset; however, training on such dataset often poses privacy risks for sensitive training…
Uncovering the Connections Between Adversarial Transferability and Knowledge Transferability
Kaizhao Liang, Jacky Y. Zhang, Boxin Wang +3
Knowledge transferability, or transfer learning, has been widely adopted to allow a pre-trained model in the source domain to be effectively adapted to downstream tasks in the targ…
Revisit Systematic Generalization via Meaningful Learning
Ning Shi, Boxin Wang, Wei Wang +2
Humans can systematically generalize to novel compositions of existing concepts. Recent studies argue that neural networks appear inherently ineffective in such cognitive capacity,…
Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms
Ruoxi Jia, David Dao, Boxin Wang +6
Given a data set containing millions of data points and a data consumer who is willing to pay for $ to train a machine learning (ML) model over , how…
G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators
Yunhui Long, Boxin Wang, Zhuolin Yang +4
Recent advances in machine learning have largely benefited from the massive accessible training data. However, large-scale data sharing has raised great privacy concerns. In this w…