Finding the Sweet Spot: Preference Data Construction for Scaling Preference Optimization
Paper
•
2502.16825
•
Published
•
6
Hai Ye
oceanpty
AI & ML interests
None yet
Recent Activity
commented on
a paper
11 days ago
Finding the Sweet Spot: Preference Data Construction for Scaling
Preference Optimization
authored
a paper
2 months ago
Test-time Computing: from System-1 Thinking to System-2 Thinking
Organizations
None yet
oceanpty's activity
upvoted
a
paper
11 days ago
commented
a
paper
11 days ago
authored
a
paper
2 months ago
upvoted
a
paper
2 months ago
updated
2
models
2 months ago
authored
3
papers
2 months ago
Preference-Guided Reflective Sampling for Aligning Language Models
Paper
•
2408.12163
•
Published
Self-Judge: Selective Instruction Following with Alignment Self-Evaluation
Paper
•
2409.00935
•
Published
Multi-Agent Sampling: Scaling Inference Compute for Data Synthesis with Tree Search-Based Agentic Collaboration
Paper
•
2412.17061
•
Published
•
1
updated
6
models
2 months ago
oceanpty/Self-J-lla31-8b-inst-base-mis-7b-v02-threshold-1
Updated
•
21
oceanpty/Self-J-lla31-8b-inst-ref-lla31-70b-base-mis-7b-v02-threshold-1
Updated
•
35
oceanpty/Self-J-lla31-8b-inst-base-qwen2-7b-inst-threshold-1
Updated
•
18
oceanpty/Self-J-lla31-8b-inst-ref-lla31-70b-base-qwen2-7b-inst-threshold-1
Updated
•
23
oceanpty/Self-J-lla31-8b-inst-ref-lla31-70b-base-qwen2-7b-inst-threshold-1
Updated
•
23
oceanpty/Self-J-lla31-8b-inst-base-lla31-8b-inst-threshold-1
Updated
•
14
updated
a
collection
2 months ago