Zhuolin Yang
@lucas110550
Followers
18
Following
100
Media
0
Statuses
14
Research Scientist @NVIDIA, Ph.D @UofIllinois. Words are my own.
Santa Clara
Joined February 2016
Our released evaluation toolkit can reproduce our AceReason-Nemotron models numbers (see below):. AceReason-Nemotron-1.0-7B:.LiveCodeBench (Avg@8): .* [05/23-05/24]: 72.0; [06/24-01/25]: 54.2.* release set v5: 51.2; release set v6: 44.4.AIME (Avg@64):.* AIME'24: 68.6; AIME'25:.
The first thing we did was to make sure the eval setup is correct!. We spend a lot of time to make sure our eval can. - accurately reproduce the DeepSeek-R1 numbers on AIME, LiveCodeBench. - it's IMPOSSIBLE to track the RL progress without a good eval set up (e.g., we see AIME up.
0
4
9
RT @zihan_johan_liu: With stronger SFT backbone, AceReason-Nemotron-1.1-7B significantly outperforms its predecessor and sets a record-high….
0
8
0
RT @ychenNLP: 📢We conduct a systematic study to demystify the synergy between SFT and RL for reasoning models. The result? We trained a 7B….
0
43
0
RT @_weiping: Introducing AceReason-Nemotron 1.1. Our previous release, AceReason-Nemotron-1.0, introduced a stage-wise RL recipe that was….
0
16
0