arxiv:2608.09888
Richard Z
chardizard
AI & ML interests
None yet
Recent Activity
authored a paper about 1 month ago
BDH-CQ: In-Context Learning with Recurrent Latent Reasoning upvoted a paper about 1 month ago
BDH-CQ: In-Context Learning with Recurrent Latent Reasoning updated a dataset 5 months ago
chardizard/SFTQwen3-8B-v1-10pct-Weak-ChatbotArena-CorrectOrganizations
models 10
chardizard/SFTQwen3-8B-OpenRubrics-v1-10pct-Weak
8B • Updated • 2
chardizard/SFTQwen3-8B-OpenRubrics-v1v2
8B • Updated • 4
chardizard/SFTQwen3-8B-OpenRubrics-v1
8B • Updated • 5
chardizard/Qwen2.5-7b-stock-DPO-Completeness-MinChosen8-MinDelta6
Updated • 5
chardizard/Qwen2.5-7b-DPO-Factuality-MinChosen9-MinDelta6
Text Generation • 333k • Updated • 6
chardizard/SmolLM-135M-DPO
Text Generation • 0.1B • Updated • 3
chardizard/tmp
Updated
chardizard/Pythia410mRE-WILD
Text Generation • 0.4B • Updated • 8
chardizard/DyTPythia410mRE-WILD2
Text Generation • 0.4B • Updated • 11
chardizard/DyTPythia410mRE-WILD
Text Generation • 0.4B • Updated • 8
datasets 15
chardizard/SFTQwen3-8B-v1-10pct-Weak-ChatbotArena-Correct
Viewer • Updated • 9.9k • 25
chardizard/OpenRubrics-Weak-v1v2
Viewer • Updated • 4.71k • 17
chardizard/SFTQwen8b-ChatbotArena-ARMJudge-Correct
Viewer • Updated • 9.98k • 18
chardizard/RubricARM-ChatbotArena-ARMJudge-Correct
Viewer • Updated • 12.9k • 43
chardizard/RubricARM-ChatbotArena-Llama-Correct
Viewer • Updated • 12.4k • 36
chardizard/RubricARM-ChatbotArena
Viewer • Updated • 23.6k • 12
chardizard/dpo-mix5-OpenInstruct-Llama3-Completeness-MinChosen6-MinDelta4
Viewer • Updated • 19k • 14
chardizard/dpo-mix5-OpenInstruct-Llama3-Completeness
Viewer • Updated • 204k • 40
chardizard/dpo-mix5-Llama3-Factuality-MinChosen9-MinDelta6
Viewer • Updated • 36.4k • 32
chardizard/dpo-mix5-Llama3-Factuality
Viewer • Updated • 561k • 50