arxiv:2504.17950
Isadora White
izzcw
AI & ML interests
LLMs, Reinforcement Learning, agents, embodiment, multi-agent collaboration
Recent Activity
published
a model
2 days ago
izzcw/dpo_model_3.1_8k
updated
a model
6 days ago
izzcw/qwen_large_crafting_sft_success
published
a model
6 days ago
izzcw/qwen_large_crafting_sft_success
Organizations
Papers
3
models
26
izzcw/dpo_model_3.1_8k
Updated
izzcw/qwen_large_crafting_sft_success
Text Generation
•
Updated
•
81
izzcw/large_crafting_sft_success
Text Generation
•
Updated
•
97
izzcw/trajectory_crafting_dpo_pairs
Updated
izzcw/trajectory_crafting_dpo_pairs.json
Updated
izzcw/llama_3.1_large_crafting_sft_success
Text Generation
•
Updated
•
28
izzcw/llama_3b_crafting_sft_success_new_mem
Text Generation
•
Updated
•
6
izzcw/mini_llama_crafting_sft_success_new_mem
Text Generation
•
Updated
•
457
izzcw/cooking_sft_fail_new_mem
Text Generation
•
Updated
•
62
izzcw/crafting_sft_fail_new_mem
Text Generation
•
Updated
•
8
datasets
6
izzcw/trajectory_crafting_dpo_pairs
Viewer
•
Updated
•
244
•
72
izzcw/dpo_pairs_crafting_filtered
Viewer
•
Updated
•
876
•
144
izzcw/cooking-filtered
Updated
•
57
izzcw/minecollab_filtered_construction_data
Viewer
•
Updated
•
9.23k
•
46
izzcw/minecollab_filtered_crafting
Viewer
•
Updated
•
3.57k
•
45
izzcw/minecollab_filtered_cooking
Viewer
•
Updated
•
3.98k
•
40