Michael Toker PRO

tokeron's activity

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

upvoted a paper 19 days ago

DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models

Paper • 2510.15015 • Published 26 days ago • 10

upvoted a paper 3 months ago

CRISP: Persistent Concept Unlearning via Sparse Autoencoders

Paper • 2508.13650 • Published Aug 19 • 15

upvoted a paper 5 months ago

RefVNLI: Towards Scalable Evaluation of Subject-driven Text-to-image Generation

Paper • 2504.17502 • Published Apr 24 • 55

upvoted 2 papers 6 months ago

Multi-Domain Explainability of Preferences

Paper • 2505.20088 • Published May 26 • 20

SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders

Paper • 2501.18052 • Published Jan 29 • 8

upvoted a paper 7 months ago

Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models

Paper • 2504.01137 • Published Apr 1 • 21

upvoted 2 papers 8 months ago

AdaptiVocab: Enhancing LLM Efficiency in Focused Domains through Lightweight Vocabulary Adaptation

Paper • 2503.19693 • Published Mar 25 • 76

Inside-Out: Hidden Factual Knowledge in LLMs

Paper • 2503.15299 • Published Mar 19 • 55

upvoted a paper 10 months ago

Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models

Paper • 2501.06751 • Published Jan 12 • 32

upvoted 8 papers about 1 year ago

GLEE: A Unified Framework and Benchmark for Language-based Economic Environments

Paper • 2410.05254 • Published Oct 7, 2024 • 84

LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations

Paper • 2410.02707 • Published Oct 3, 2024 • 48

Customizing Text-to-Image Models with a Single Image Pair

Paper • 2405.01536 • Published May 2, 2024 • 22

Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs

Paper • 2406.20086 • Published Jun 28, 2024 • 6

NNsight and NDIF: Democratizing Access to Foundation Model Internals

Paper • 2407.14561 • Published Jul 18, 2024 • 35

Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models

Paper • 2311.12092 • Published Nov 20, 2023 • 23

NL-Eye: Abductive NLI for Images

Paper • 2410.02613 • Published Oct 3, 2024 • 23

Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelines

Paper • 2403.05846 • Published Mar 9, 2024 • 1

upvoted an article about 1 year ago

view article

Article

Introducing the Open Leaderboard for Hebrew LLMs!

May 5, 2024

• 52

upvoted a paper about 1 year ago

Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model

Paper • 2408.11039 • Published Aug 20, 2024 • 63

upvoted a paper over 1 year ago

Simulating Classroom Education with LLM-Empowered Agents

Paper • 2406.19226 • Published Jun 27, 2024 • 32