Juan CM

jucamohedano's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a Space 11 days ago

Running

8

Simulation RL Environments

🚢

8

Turning real-world work into RL environments: PortSimEnv v1

liked a Space 17 days ago

Running

265

The ultimate guide to multi-harness RL

🔀

265

Train open models with RL inside real agent harnesses

liked a model 18 days ago

EvanOLeary/laguna-xs2-dense-k8-kernelmix

Text Generation • 3B • Updated May 30 • 81 • 1

updated a model 23 days ago

jucamohedano/rlm-laguna-xs2-dense-3b-v0.1

Text Generation • 3B • Updated 23 days ago • 456 • 1

published a model 23 days ago

jucamohedano/rlm-laguna-xs2-dense-3b-v0.1

Text Generation • 3B • Updated 23 days ago • 456 • 1

published a dataset 2 months ago

jucamohedano/experts-ml-selfcond-result

Updated Aug 18 • 17

updated a dataset 2 months ago

jucamohedano/experts-ml-selfcond-result

Updated Aug 18 • 17

updated a collection 3 months ago

OVEN GRPO sweep (Qwen3-VL-4B)

Collection

GRPO LoRA fine-tunes of Qwen3-VL-4B on OVEN (verl), from my MSc thesis. Mostly negative results across reward, prompt, and data axes. • 14 items • Updated Jul 29

updated a dataset 3 months ago

jucamohedano/oven-grpo-training-data

Viewer • Updated Jul 29 • 522k • 168

published a dataset 3 months ago

jucamohedano/oven-grpo-training-data

Viewer • Updated Jul 29 • 522k • 168

updated 2 collections 3 months ago

Open-world classification — GRPO experiments

Collection

GRPO training datasets for open-world image classification (Oxford-IIIT Pet): direct and structured-reasoning variants. From my lmms-owc work. • 2 items • Updated Jul 29

OVEN Qwen3-VL — evaluation traces

Collection

Qwen3-VL (2B/4B/8B/32B) rollouts + LM-judge verdicts on OVEN, from my MSc thesis. • 1 item • Updated Jul 29

updated a dataset 3 months ago

jucamohedano/oven-qwen3-vl-eval-traces

Preview • Updated Jul 29 • 92

published a dataset 3 months ago

jucamohedano/oven-qwen3-vl-eval-traces

Preview • Updated Jul 29 • 92

updated a dataset 3 months ago

jucamohedano/oxford-pets-grpo-think

Viewer • Updated Jul 29 • 6.61k • 13

published a dataset 3 months ago

jucamohedano/oxford-pets-grpo-think

Viewer • Updated Jul 29 • 6.61k • 13

updated a dataset 3 months ago

jucamohedano/oxford-pets-grpo

Viewer • Updated Jul 29 • 6.61k • 30

published a dataset 3 months ago

jucamohedano/oxford-pets-grpo

Viewer • Updated Jul 29 • 6.61k • 30

updated a collection 3 months ago

OVEN GRPO sweep (Qwen3-VL-4B)

Collection

GRPO LoRA fine-tunes of Qwen3-VL-4B on OVEN (verl), from my MSc thesis. Mostly negative results across reward, prompt, and data axes. • 14 items • Updated Jul 29