Introducing AceReason-Nemotron: Advancing math and code reasoning through reinforcement learning (RL). We propose conducting RL on math-only prompts first, then on code-only prompts. Our key findings include:.- Math-only RL significantly boosts both math and code benchmarks!.-

RT @lucas110550: Our released evaluation toolkit can reproduce our AceReason-Nemotron models numbers (see below):. AceReason-Nemotron-1.0-7….

RT @ychenNLP: 📢We conduct a systematic study to demystify the synergy between SFT and RL for reasoning models. The result? We trained a 7B….

RT @zihan_johan_liu: With stronger SFT backbone, AceReason-Nemotron-1.1-7B significantly outperforms its predecessor and sets a record-high….

RT @MohammadShoeybi: Checkout our detailed study on advancing math and code reasoning using SFT and RL.

Introducing AceReason-Nemotron 1.1. Our previous release, AceReason-Nemotron-1.0, introduced a stage-wise RL recipe that was applied sequentially to math-only and code-only prompts, demonstrating both high efficiency and strong effectiveness. Here, we systematically investigate

RT @GavinNewsom: If they can handcuff a U.S. Senator for asking a question, imagine what they will do to you.

RT @mli0603: Cosmos-Reason1 has exciting updates 💡.Now it understands physical reality — judging videos as real or fake! Check out the reso….

RT @kuchaev: New reasoning Nemotron-H models are now publicly available. These models are based on hybrid architecture! .47B and 8B in BF….

Pass@1024 results of our RL model (AceReason-Nemotron-7B) and its starting SFT model (DeepSeek-R1-Distill-Qwen-7B) on LiveCodeBench-v6, which features a large answer space and high-quality test cases that are difficult to solve through 'guessing', even with extensive sampling.

👍👍.

RT @_akhaliq: Nvidia just dropped AceReason-Nemotron on Hugging Face. Advancing Math and Code Reasoning through Reinforcement Learning http….

RT @zihan_johan_liu: Check out our AceReason-Nemotron-14B. 🤗We start with RL training using math-only prompts, the….

RT @StringChaos: Lots of good analysis in here!.

RT @ychenNLP: with just math-RL, AceReason-Nemotron-14B surpass DeepCoder-14B on LiveCodeBench v5. we then did code-RL and found training….

RT @NVIDIAAIDev: 📣 Introducing AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning (RL). Starting from the….

RT @kuchaev: Llama-Nemotron-v1 technical report is now available on arxiv

RT @Alibaba_Qwen: Introducing Qwen3! . We release and open-weight Qwen3, our latest large language models, including 2 MoE models and 6 den….

RT @zihan_johan_liu: Introducing AceMath-RL-Nemotron-7B, a math reasoning model trained entirely through reinforcement learning from DeepSe….

RT @ychenNLP: Had a lot of fun to scale up RL to improve math reasoning!. Excited to introduce AceMath-RL-Nemotron-7B with a scalable train….