Juan CM

jucamohedano's activity

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

updated a collection 8 days 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 8 days ago

updated a dataset 8 days ago

jucamohedano/oven-grpo-training-data

Viewer • Updated 7 days ago • 522k • 32

published a dataset 8 days ago

jucamohedano/oven-grpo-training-data

Viewer • Updated 7 days ago • 522k • 32

updated 2 collections 8 days 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 8 days ago

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 8 days ago

updated a dataset 8 days ago

jucamohedano/oven-qwen3-vl-eval-traces

Preview • Updated 8 days ago • 39

published a dataset 8 days ago

jucamohedano/oven-qwen3-vl-eval-traces

Preview • Updated 8 days ago • 39

updated a dataset 8 days ago

jucamohedano/oxford-pets-grpo-think

Viewer • Updated 8 days ago • 6.61k • 33

published a dataset 8 days ago

jucamohedano/oxford-pets-grpo-think

Viewer • Updated 8 days ago • 6.61k • 33

updated a dataset 8 days ago

jucamohedano/oxford-pets-grpo

Viewer • Updated 8 days ago • 6.61k • 36

published a dataset 8 days ago

jucamohedano/oxford-pets-grpo

Viewer • Updated 8 days ago • 6.61k • 36

updated a collection 8 days 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 8 days ago