Nemotron Math & Reasoning Collection Datasets for building models that excel at math reasoning, proofs, and quantitative problem-solving. Covers SFT, RL, and pretraining data. • 23 items • Updated about 1 month ago • 16
Nemotron Chat & Instruction Following Collection Datasets for building helpful, multi-turn, instruction-following conversational models across single and multi-turn settings. • 19 items • Updated about 1 month ago • 10
Open-SWE-Traces Collection Open-SWE-Traces: Advancing Dual-Mode Multilingual Distillation for Software Engineering Agents • 3 items • Updated about 1 month ago • 5
Nemotron Supervised Fine-Tuning Collection SFT datasets covering math, code, chat, safety, agentic, VLM, multilingual, and specialized domains. • 44 items • Updated about 1 month ago • 21
Nemotron Code & SWE Collection Datasets for building models that write, debug, and reason about code. Covers competitive programming, software engineering, and code pretraining. • 14 items • Updated about 1 month ago • 9
Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation Paper • 2507.10524 • Published Jul 14, 2025 • 76
VL-JEPA: Joint Embedding Predictive Architecture for Vision-language Paper • 2512.10942 • Published Dec 11, 2025 • 64
SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers Paper • 2609.01343 • Published 10 days ago • 100