Cog-DRIFT: Exploration on Adaptively Reformulated Instances Enables Learning from Hard Reasoning Problems
Paper • 2604.04767 • Published • 7
Justin Chen
dinobby
AI & ML interests
None yet
Recent Activity
submitted a paper about 1 month ago
Cog-DRIFT: Exploration on Adaptively Reformulated Instances Enables Learning from Hard Reasoning Problems updated a dataset about 1 month ago
dinobby/Cog-DRIFT-Dataset published a dataset about 1 month ago
dinobby/Cog-DRIFT-DatasetOrganizations
None yet
submitted a
paper to Daily Papers about 1 month ago
updated a
dataset about 1 month ago
published a
dataset about 1 month ago
updated a
model about 1 month ago
published a
model about 1 month ago
updated a
model about 1 month ago
published a
model about 1 month ago
upvoted a paper 3 months ago
updated a
dataset 3 months ago
published a
dataset 4 months ago
updated a
dataset 4 months ago
published a
dataset 4 months ago
updated a
dataset 5 months ago
published a
dataset 5 months ago
published 6
models 6 months ago
dinobby/OctoThinker-3B-Hybrid-Zero-NuRL-GPTo4-mini
4B • Updated • 1
dinobby/OctoThinker-3B-Hybrid-Zero-NuRL-Self
4B • Updated • 2
dinobby/OctoThinker-3B-Hybrid-Zero-GRPO
4B • Updated • 1
dinobby/Qwen3-4B-Instruct-2507-NuRL-GPTo4-mini
4B • Updated • 1
dinobby/Qwen3-4B-Instruct-2507-NuRL-Self
4B • Updated • 1
dinobby/Llama3.2-3B-Instruct-NuRL-GPTo4-mini
4B • Updated • 1