arxiv:2504.17950
Isadora White
izzcw
AI & ML interests
LLMs, Reinforcement Learning, agents, embodiment, multi-agent collaboration
Recent Activity
updated a model about 22 hours ago
izzcw/fingerprint_raw_conversations published a model about 22 hours ago
izzcw/fingerprint_raw_conversations upvoted a paper about 1 month ago
Efficient RL Training for LLMs with Experience ReplayOrganizations
models 27
izzcw/fingerprint_raw_conversations
Updated
izzcw/dpo_model_3.1_8k
Updated
izzcw/qwen_large_crafting_sft_success
Text Generation • 2B • Updated • 3
izzcw/large_crafting_sft_success
Text Generation • 2B • Updated • 5
izzcw/trajectory_crafting_dpo_pairs
Updated
izzcw/trajectory_crafting_dpo_pairs.json
Updated
izzcw/llama_3.1_large_crafting_sft_success
Text Generation • 8B • Updated • 3
izzcw/llama_3b_crafting_sft_success_new_mem
Text Generation • 3B • Updated • 2
izzcw/mini_llama_crafting_sft_success_new_mem
Text Generation • 1B • Updated • 1 •
izzcw/cooking_sft_fail_new_mem
Text Generation • 8B • Updated
datasets 6
izzcw/trajectory_crafting_dpo_pairs
Viewer • Updated • 244 • 10
izzcw/dpo_pairs_crafting_filtered
Viewer • Updated • 876 • 7
izzcw/cooking-filtered
Updated • 4
izzcw/minecollab_filtered_construction_data
Viewer • Updated • 9.23k • 30 • 1
izzcw/minecollab_filtered_crafting
Viewer • Updated • 3.57k • 11
izzcw/minecollab_filtered_cooking
Viewer • Updated • 3.98k • 13