6 papers
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…
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,…
On Data Engineering for Scaling LLM Terminal Capabilities
Renjie Pi, Grace Lam, Mohammad Shoeybi +3
Despite rapid recent progress in the terminal capabilities of large language models, the training data strategies behind state-of-the-art terminal agents remain largely undisclosed…
Beyond Accuracy: Evaluating Grounded Visual Evidence in Thinking with Images
Xuchen Li, Xuzhao Li, Renjie Pi +3
Despite the remarkable progress of Vision-Language Models (VLMs) in adopting "Thinking-with-Images" capabilities, accurately evaluating the authenticity of their reasoning process…
Look Less, Reason More: Rollout-Guided Adaptive Pixel-Space Reasoning
Xuchen Li, Xuzhao Li, Jiahui Gao +3
Vision-Language Models (VLMs) excel at many multimodal tasks, yet they frequently struggle with tasks requiring precise understanding and handling of fine-grained visual elements.…
MR. Judge: Multimodal Reasoner as a Judge
Renjie Pi, Felix Bai, Qibin Chen +4
The paradigm of using Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) as evaluative judges has emerged as an effective approach in RLHF and inference-time…