arxiv:2604.05336
Hangoo Kang
Hkang
·
AI & ML interests
None yet
Recent Activity
authored a paper 18 days ago
TRACE: Capability-Targeted Agentic Training upvoted a paper about 1 month ago
TRACE: Capability-Targeted Agentic Training upvoted a paper about 2 months ago
SEVerA: Verified Synthesis of Self-Evolving AgentsOrganizations
models 22
Hkang/Qwen3-4B-Instruct-2507-untied
Text Generation • 4B • Updated
Hkang/Pythia1b-oai-summary-PETRM
Text Generation • 1B • Updated
Hkang/PPO_IMDB_BON_0KL_2048
Text Generation • 0.8B • Updated
Hkang/PPO_IMDB_BON_0KL_1792
Text Generation • 0.8B • Updated
Hkang/PPO_IMDB_BON_0KL_1536
Text Generation • 0.8B • Updated • 1
Hkang/PPO_IMDB_BON_0KL_1280
Text Generation • 0.8B • Updated
Hkang/PPO_IMDB_BON_0KL_1K
Text Generation • 0.8B • Updated • 1
Hkang/PPO_IMDB_BON_0KL_700
Text Generation • 0.8B • Updated
Hkang/PPO_IMDB_BON_0KL_500
Text Generation • 0.8B • Updated
Hkang/PPO_IMDB_BON_0KL_200
Text Generation • 0.8B • Updated • 2
datasets 151
Hkang/summarize_sft-test_lm-EleutherAI_pythia-1b_seed-42_numex-250_BON-n256RM-BON_256
Viewer • Updated • 250 • 131
Hkang/imdb_sft-test_lm-PPO_IMDB_BON_0KL_500_seed-42_numex-250
Viewer • Updated • 250 • 52
Hkang/imdb_sft-test_lm-PPO_IMDB_BON_0KL_700_seed-42_numex-250
Viewer • Updated • 250 • 169
Hkang/imdb_sft-test_lm-PPO_IMDB_BON_0KL_200_seed-42_numex-250
Viewer • Updated • 250 • 29
Hkang/summarize_sft-test_lm-EleutherAI_pythia-1b_seed-42_numex-250_orgRM-BON_512
Viewer • Updated • 250 • 113
Hkang/summarize_sft-test_lm-EleutherAI_pythia-1b_seed-42_numex-250_PETRM-BON_512
Viewer • Updated • 250 • 189
Hkang/summarize_sft-test_lm-EleutherAI_pythia-1b_seed-42_numex-250_origRM-BON_256
Viewer • Updated • 250 • 170
Hkang/summarize_sft-test_lm-EleutherAI_pythia-1b_seed-20_numex-250_origRM-BON_256
Viewer • Updated • 250 • 157
Hkang/summarize_sft-test_lm-PPO_BON_wKL_seed20_baseline_seed-42_numex-250
Viewer • Updated • 250 • 29
Hkang/summarize_sft-test_lm-PPO_BON_0KL_seed20_seed-42_numex-250
Viewer • Updated • 250 • 68