Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up
OLAResearchX 's Collections
SCARE
Label-Free Bias-Only Steering
MemoryATHENA
XMemTransfer

Label-Free Bias-Only Steering

updated Oct 1

Bias-only steering vectors from label-free test-time RL (GRPO, majority-vote reward). One repo per benchmark/base model.

Upvote
-

  • Label-free steering: Compressing test-time reinforcement learning into bias-only subspaces

    Paper • 2609.18587 • Published Sep 28 • 4

  • OLAResearchX/label-free-bias-steering-ai2d-qwen2.5-vl-7b

    Reinforcement Learning • Updated Sep 28

  • OLAResearchX/label-free-bias-steering-logicvista-qwen2.5-vl-7b

    Reinforcement Learning • Updated Sep 28

  • OLAResearchX/label-free-bias-steering-mathvista-qwen2.5-vl-7b

    Reinforcement Learning • Updated Sep 28

  • OLAResearchX/label-free-bias-steering-mmau-qwen2.5-omni-7b

    Reinforcement Learning • Updated Sep 28

  • OLAResearchX/label-free-bias-steering-math500-qwen2.5-7b

    Reinforcement Learning • Updated Sep 28

  • OLAResearchX/label-free-bias-steering-math500-qwen2.5-math-7b

    Reinforcement Learning • Updated Sep 28

  • OLAResearchX/label-free-bias-steering-checkpoints

    Reinforcement Learning • Updated Sep 28
Upvote
-
  • Collection guide
  • Browse collections
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs