arxiv:2604.08865
TIANYI
BIMU233
AI & ML interests
None yet
Recent Activity
upvoted a paper 10 days ago
Bridging the Agent-World Gap: Text World Models for LLM-based Agents upvoted a paper 16 days ago
MIRA: Mid-training Rubric Anchoring for Source-Aware Data Selection upvoted a paper about 1 month ago
Conditional Equivalence of DPO and RLHF: Implicit Assumption, Failure Modes, and Provable AlignmentOrganizations
None yet
models 13
BIMU233/GPT-2_agd
Updated
BIMU233/0.05_240
8B • Updated • 2
BIMU233/0.1_240
8B • Updated • 3
BIMU233/0.5_240
8B • Updated • 1
BIMU233/0.005_240
8B • Updated • 2
BIMU233/GPT-2_0.1p
0.4B • Updated • 1
BIMU233/GPT-2_0.0p
0.4B • Updated • 1
BIMU233/GPT-2_p0.0
Updated
BIMU233/SPPO_7B_small_critic
8B • Updated • 1
BIMU233/SPPO_7B
8B • Updated • 3
datasets 0
None public yet