arxiv:2610.19525
yoon
sangyon
AI & ML interests
None yet
Recent Activity
authored a paper 4 days ago
Diagnosing and Correcting Reward Hacking in Verifiable Instruction Following upvoted a paper 4 days ago
Diagnosing and Correcting Reward Hacking in Verifiable Instruction Following updated a dataset 4 days ago
sangyon/CALIFOrganizations
None yet
models 26
sangyon/llama31_tulu3_8b_dpo_grpo_nonthink_anchor_pyx01_b1024_c1_t1_2k_kl0
Updated
sangyon/qwen3_4b_grpo_think_pyx01_t4banchor_s4b_b1024_c1_kl0
Updated
sangyon/qwen3_17b_grpo_think_pyx01_t17banchor_s17b_b1024_c1_kl0
Updated
sangyon/qwen3_17b_grpo_nonthink_likelihood_pyx01_b1024_c1_e4_20260914_s1
Updated
sangyon/qwen3_4b_grpo_nonthink_pyx01_t4banchor_s4b_b1024_c1_kl0
Updated
sangyon/qwen3_4b_grpo_think_intentcheck_qwen3_4b_nonthink
4B • Updated • 3
sangyon/qwen3_17b_grpo_nonthink_pyx01_t17banchor_s17b_b1024_c1_kl0
Updated
sangyon/qwen3_17b_grpo_nonthink_constraint_only_b1024_c1_kl0_e4
Updated
sangyon/llama31_tulu3_8b_dpo_grpo_nonthink_intentcheck_tulu3_8b_dpo
Text Generation • 8B • Updated • 32
sangyon/qwen3_17b_grpo_think_t17banchor_pyx01_llmverifier_gptoss120b_fallback_bonus01_threshold42_v1_b10
Updated