HyunseokLee

hyunseoki's activity

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

updated a collection 3 days ago

Meta-Harness v1b: Policy x Harness Co-Evolution

Collection

Co-evolution GRPO (verl, Qwen3.5): shared policy = grader/solver + harness-editor. IMO/paper-review/math. bf16 checkpoints + evolved scaffolds. • 20 items • Updated 3 days ago

updated a model 3 days ago

hyunseoki/mh-v1b-imo-9b-reclaim-bestonly

Text Generation • 9B • Updated 3 days ago • 10

published a model 3 days ago

hyunseoki/mh-v1b-imo-9b-reclaim-bestonly

Text Generation • 9B • Updated 3 days ago • 10

updated 2 datasets 4 days ago

hyunseoki/rltr-data

Updated 4 days ago • 45

hyunseoki/mh-v1b-scaffolds

Updated 4 days ago • 36

updated a model 4 days ago

hyunseoki/rltr-qwen3-8b-to-gemma4b-polaris

Updated 4 days ago

updated a collection 5 days ago

Meta-Harness v1b: Policy x Harness Co-Evolution

Collection

Co-evolution GRPO (verl, Qwen3.5): shared policy = grader/solver + harness-editor. IMO/paper-review/math. bf16 checkpoints + evolved scaffolds. • 20 items • Updated 3 days ago

updated a model 5 days ago

hyunseoki/mh-v1b-imo-9b-t20

Text Generation • 9B • Updated 5 days ago • 22

published a model 5 days ago

hyunseoki/mh-v1b-imo-9b-t20

Text Generation • 9B • Updated 5 days ago • 22

updated a collection 5 days ago

RLTR: Learning Robust Reasoning via Transfer

Collection

Checkpoints (bf16, 50-step) + train/eval data for RLTR (transfer-reward RL) incl. cross-family (gemma) receiver. • 7 items • Updated 5 days ago

published a dataset 5 days ago

hyunseoki/rltr-data

Updated 4 days ago • 45

updated a collection 5 days ago

RLTR: Learning Robust Reasoning via Transfer

Collection

Checkpoints (bf16, 50-step) + train/eval data for RLTR (transfer-reward RL) incl. cross-family (gemma) receiver. • 7 items • Updated 5 days ago

published a model 5 days ago

hyunseoki/rltr-qwen3-8b-to-gemma4b-polaris

Updated 4 days ago

updated a collection 5 days ago

RLTR: Learning Robust Reasoning via Transfer

Collection

Checkpoints (bf16, 50-step) + train/eval data for RLTR (transfer-reward RL) incl. cross-family (gemma) receiver. • 7 items • Updated 5 days ago

updated a model 5 days ago

hyunseoki/rltr-qwen3-4b-polaris-baseline

Updated 5 days ago

published a model 5 days ago

hyunseoki/rltr-qwen3-4b-polaris-baseline

Updated 5 days ago

updated a model 5 days ago

hyunseoki/rltr-qwen3-4b-to-1p7b-polaris

Updated 5 days ago

updated a collection 5 days ago

RLTR: Learning Robust Reasoning via Transfer

Collection

Checkpoints (bf16, 50-step) + train/eval data for RLTR (transfer-reward RL) incl. cross-family (gemma) receiver. • 7 items • Updated 5 days ago

published a model 5 days ago

hyunseoki/rltr-qwen3-4b-to-1p7b-polaris

Updated 5 days ago

updated a collection 5 days ago

RLTR: Learning Robust Reasoning via Transfer

Collection

Checkpoints (bf16, 50-step) + train/eval data for RLTR (transfer-reward RL) incl. cross-family (gemma) receiver. • 7 items • Updated 5 days ago