Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation
Paper • 2603.19220 • Published • 65
Eugene Oskin
eoskin
·
AI & ML interests
None yet
Recent Activity
updated a collection about 2 hours ago
impactful-papers upvoted a paper about 2 hours ago
Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation upvoted a collection about 2 hours ago
Gemma 4Organizations
None yet
upvoted a paper about 2 hours ago
upvoted a collection about 2 hours ago
upvoted a collection 2 days ago
upvoted a paper 3 days ago
upvoted a paper 5 days ago
upvoted 14
articles 10 days ago
Article
Build a Domain-Specific Embedding Model in Under a Day
•
62
Article
Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face
- +3
•
220
Article
MCP for Research: How to Connect AI to Research Tools
•
68
Article
Jupyter Agents: training LLMs to reason with notebooks
- +1
•
63
Article
Train AI models with Unsloth and Hugging Face Jobs for FREE
- +4
•
94
Article
Gemma 3n fully available in the open-source ecosystem!
- +6
•
121
Article
nanoVLM: The simplest repository to train your VLM in pure PyTorch
- +5
•
254
Article
Vision Language Models (Better, faster, stronger)
- +3
•
604
Article
The 5 Most Under-Rated Tools on Hugging Face
•
93
Article
Accelerating Qwen3-8B Agent on Intel® Core™ Ultra with Depth-Pruned Draft Models
- +3
•
25
Article
Holotron-12B - High Throughput Computer Use Agent
•
19
Article
State of Open Source on Hugging Face: Spring 2026
•
76
Article
What's New in Mellea 0.4.0 + Granite Libraries Release
•
8
Article
GGML and llama.cpp join HF to ensure the long-term progress of Local AI
- +4
•
491
upvoted a collection 10 days ago