Jiangshan's Personal Website
HomeBlogArchivesCategoriesTagsAbout
  • Tags
  • Experiment
Posted 2026-06-29Updated 2026-07-02Study6 minutes read (About 918 words)

2026-06-29-SlimeSearchR1Example

Training and evaluation of the slime Search-R1-trained Qwen2.5-3B model on NQ and HotpotQA.
Read more
Posted 2026-06-10Updated 2026-07-15Study16 minutes read (About 2454 words)

PPO vs GRPO — Post-Training Qwen2.5-0.5B-Instruct on GSM8K with veRL

Comparing PPO and GRPO for post-training Qwen2.5-0.5B-Instruct on GSM8K with veRL.
Read more
Posted 2026-06-03Updated 2026-07-02Study13 minutes read (About 1982 words)

2026-06-03-SwingUpCartpole

From CartPole-v1 to CartPole Swing-Up
Read more
Posted 2026-06-01Updated 2026-07-02Research9 minutes read (About 1401 words)

2026-06-01-Slahmr_examples

slahmr examples
Read more
Jiangshan Gong

Jiangshan Gong

University of Illinois at Urbana-Champaign

Posts

31

Categories

3

Tags

22

Follow

Links

  • Hexohexo.io
  • Bulmabulma.io

Categories

  • Life9
  • Research1
  • Study21

Recents

2026-06-29

2026-06-29-QWenVL

Study

2026-06-29

2026-06-29-SlimeSearchR1Example

Study

2026-06-10

PPO vs GRPO — Post-Training Qwen2.5-0.5B-Instruct on GSM8K with veRL

Study

2026-06-07

2026-06-07-RLClassic

Study

2026-06-06

2026-06-06-RLPre

Study

Archives

  • 202610
  • 20253
  • 20238
  • 202210

Tags

BASH1
COOKING1
CUDA3
DATABASE1
DATASTRUCTURE4
Experiment6
GRPO2
LINUX1
LLM2
LLMTRAINING2
PARALLELPROGRAMMING3
PPO2
Qwen-VL2
RL5
SLAHMR1
TRAVEL1
VLM2
WEBDEV1
WEBSITE5
qwen2.5-3B2
search-r12
slime2
Jiangshan's Personal Website

© 2026 Jiangshan Gong  Powered by Hexo & Icarus

© 2019

×