7 5 41

Anshuman Suri

iamgroot42

https://anshumansuri.com/

AI & ML interests

Privacy, Distribution Inference, Membership Inference

Recent Activity

liked a dataset 14 days ago

cfli/bge-full-data

liked a model 14 days ago

google/gemma-3-12b-it

new activity 14 days ago

mteb/arena:Arena is not accessible

View all activity

Organizations

iamgroot42's activity

liked a dataset 14 days ago

cfli/bge-full-data

Updated Oct 11, 2024 • 3.96k • 39

liked a model 14 days ago

google/gemma-3-12b-it

Image-Text-to-Text • Updated Mar 21 • 379k • • 400

New activity in mteb/arena 14 days ago

Arena is not accessible

#5 opened 7 months ago by

fedric95

liked a model 15 days ago

coqui/XTTS-v2

Text-to-Speech • Updated Dec 11, 2023 • 2.15M • 2.75k

liked 2 Spaces about 1 month ago

Refusal Censorship Steering

🦙

Generate text with controlled censorship

DeepSeek-R1 Censorship Steering

🐳

Generate text with customizable censorship steering

liked a dataset about 1 month ago

domenicrosati/TruthfulQA

Viewer • Updated Jul 1, 2022 • 817 • 1.35k • 14

upvoted a paper about 1 month ago

Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control

Paper • 2504.17130 • Published Apr 23 • 1

liked a dataset 3 months ago

wangrongsheng/HealthCareMagic-100k-en

Viewer • Updated May 7, 2023 • 112k • 189 • 18

upvoted a paper 3 months ago

2 OLMo 2 Furious

Paper • 2501.00656 • Published Dec 31, 2024 • 19

liked 2 datasets 3 months ago

allenai/tulu-3-sft-olmo-2-mixture

Viewer • Updated Dec 2, 2024 • 939k • 640 • 44

hendrycks/ethics

Viewer • Updated Apr 19, 2023 • 134k • 958 • 23

liked a Space 3 months ago

Exam 1 - Fundamentals of GRPO

🔥

Test your knowledge of GRPO, TRL, RL, and Deepseek R1.

liked a model 3 months ago

Qwen/QwQ-32B

Text Generation • Updated Mar 11 • 304k • • 2.77k

New activity in mteb/arena 3 months ago

Arena down?

#6 opened 4 months ago by

iamgroot42

updated a Space 4 months ago

First Agent Template

⚡

Get current time in a specified timezone

liked a model 4 months ago

jinaai/ReaderLM-v2

Text Generation • Updated Mar 4 • 17.6k • 646

authored a paper 4 months ago

Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation

Paper • 2502.00306 • Published Feb 1 • 5

commented a paper 4 months ago

Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation

Paper • 2502.00306 • Published Feb 1 • 5 •

upvoted a paper 4 months ago

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

Paper • 2502.02737 • Published Feb 4 • 232