arxiv:2510.18135
Daniel Khashabi
danyaljj
AI & ML interests
None yet
Recent Activity
upvoted a paper about 14 hours ago
Trust Functions: Near-Lossless Weak-to-Strong Generalization by Learning When to Trust the Weak Teacher upvoted a paper 6 days ago
DAR: Deontic Reasoning with Agentic Harnesses upvoted a paper 23 days ago
Steered LLM Activations are Non-SurjectiveOrganizations
models 16
danyaljj/gpt-j-6B-step-384500
Text Generation • Updated • 5
danyaljj/gpt-j-6B-step-383500
Text Generation • Updated • 2
danyaljj/gpt-j-6B-step-382500
Text Generation • Updated • 1
danyaljj/gpt-j-6B-step-358500
Text Generation • Updated • 7
danyaljj/gpt-j-6B-step-338500
Text Generation • Updated • 1
danyaljj/gpt-j-6B-step-318500
Text Generation • Updated • 2
danyaljj/gpt-j-6B-step-384000
Text Generation • Updated • 4
danyaljj/gpt-j-6B-step-383000
Text Generation • Updated • 2
danyaljj/gpt-j-6B-step-378500
Text Generation • Updated • 1
danyaljj/gpt-j-6B-step-348500
Text Generation • Updated • 2
datasets 0
None public yet