Harshvardhan Saini

harshsaini10's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a dataset 5 days ago

LLM-Linearity/llm-linearity-activations

Updated 5 days ago • 84

published a dataset 5 days ago

LLM-Linearity/llm-linearity-activations

Updated 5 days ago • 84

upvoted a paper 3 months ago

When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models

Paper • 2605.08245 • Published Jun 23 • 1

upvoted 2 papers 4 months ago

Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients

Paper • 2606.18216 • Published Jun 16 • 65

Bridging Mechanistic Interpretability and Prompt Engineering with Gradient Ascent for Interpretable Persona Control

Paper • 2601.02896 • Published Apr 22 • 1