Elena Tutubalina

tlenusik's activity

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

authored 2 papers about 13 hours ago

Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?

Paper • 2602.14111 • Published 4 days ago • 51

RecVAE: a New Variational Autoencoder for Top-N Recommendations with Implicit Feedback

Paper • 1912.11160 • Published Dec 24, 2019 • 1

upvoted a paper about 13 hours ago

Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?

Paper • 2602.14111 • Published 4 days ago • 51

authored a paper 4 months ago

Global PIQA: Evaluating Physical Commonsense Reasoning Across 100+ Languages and Cultures

Paper • 2510.24081 • Published Oct 28, 2025 • 19

upvoted a paper 4 months ago

Global PIQA: Evaluating Physical Commonsense Reasoning Across 100+ Languages and Cultures

Paper • 2510.24081 • Published Oct 28, 2025 • 19

authored a paper 4 months ago

Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs

Paper • 2510.11288 • Published Oct 13, 2025 • 49

upvoted a paper 4 months ago

Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs

Paper • 2510.11288 • Published Oct 13, 2025 • 49

authored a paper 4 months ago

OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features

Paper • 2509.22033 • Published Sep 26, 2025 • 19

upvoted 2 papers 4 months ago

When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA

Paper • 2510.04849 • Published Oct 6, 2025 • 115

OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features

Paper • 2509.22033 • Published Sep 26, 2025 • 19

authored 2 papers 5 months ago

When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs

Paper • 2508.11383 • Published Aug 15, 2025 • 40

The Rogue Scalpel: Activation Steering Compromises LLM Safety

Paper • 2509.22067 • Published Sep 26, 2025 • 28

upvoted a paper 5 months ago

The Rogue Scalpel: Activation Steering Compromises LLM Safety

Paper • 2509.22067 • Published Sep 26, 2025 • 28

upvoted 2 papers 6 months ago

When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs

Paper • 2508.11383 • Published Aug 15, 2025 • 40

HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worlds

Paper • 2508.12782 • Published Aug 18, 2025 • 25

upvoted a paper 8 months ago

Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models

Paper • 2506.06751 • Published Jun 7, 2025 • 71

authored a paper 8 months ago

Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models

Paper • 2506.06751 • Published Jun 7, 2025 • 71

authored a paper 11 months ago

I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders

Paper • 2503.18878 • Published Mar 24, 2025 • 119

upvoted 2 papers 11 months ago

I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders

Paper • 2503.18878 • Published Mar 24, 2025 • 119

When Less is Enough: Adaptive Token Reduction for Efficient Image Representation

Paper • 2503.16660 • Published Mar 20, 2025 • 72