Persona Dosing: Calibrated Activation Steering for Graded Trait Control
Paper • 2609.36388 • Published • 48
👋 Open to Work
Zehao Jin
Lunamos
AI & ML interests
None yet
Recent Activity
upvoted a paper 2 days ago
Persona Dosing: Calibrated Activation Steering for Graded Trait Control submitted a paper 2 days ago
Persona Dosing: Calibrated Activation Steering for Graded Trait Control upvoted a paper 2 days ago
Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes ItOrganizations
upvoted a paper 2 days ago
submitted a
paper to Daily Papers 2 days ago
upvoted a paper 2 days ago
submitted a
paper to Daily Papers 2 days ago
upvoted 3
papers 28 days ago
S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?
Paper • 2608.31100 • Published • 148
Aspire: Can Models Self-Evolve from Vague Goals?
Paper • 2608.31111 • Published • 274
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?
Paper • 2609.01437 • Published • 567
updated a
Space 3 months ago
liked a
model 3 months ago
Add persona examples (validated v1 PERSONA concepts)
#16 opened 4 months ago
by Lunamos
liked 2
models 4 months ago
Add Gemma-4-12B-IT (gemma4_unified): transformers main + flas checkpoint20260605
#15 opened 4 months ago
by Lunamos
updated 7
models 4 months ago
flas-ai/flas-gemma-3-4b-pt
Updated • 19 • 1
flas-ai/flas-gemma-3-4b-it
Updated • 7
flas-ai/flas-llama-3.1-8b
Updated • 7
flas-ai/flas-llama-3.1-8b-instruct
Updated • 10
flas-ai/flas-qwen3-8b-base
Updated • 7
flas-ai/flas-qwen3-8b
Updated • 20 • 2
flas-ai/flas-gemma-4-12b-it
Updated • 25 • 2