Hadas Orgad

hadasor's activity

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

upvoted a paper about 1 month ago

MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image

Paper • 2605.10616 • Published May 11 • 142

upvoted a paper 2 months ago

Large Language Models Generate Harmful Content Using a Distinct, Unified Mechanism

Paper • 2604.09544 • Published Apr 10 • 7

upvoted a paper 4 months ago

Empty Shelves or Lost Keys? Recall Is the Bottleneck for Parametric Factuality

Paper • 2602.14080 • Published Feb 15 • 23

upvoted an article 5 months ago

view article

Article

Friends and Grandmothers in Silico

• 

tux

•

Jan 24

• 10

upvoted a paper 8 months ago

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

Paper • 2510.15015 • Published Oct 16, 2025 • 11

upvoted a paper 9 months ago

Fine-Grained Detection of Context-Grounded Hallucinations Using LLMs

Paper • 2509.22582 • Published Sep 26, 2025 • 12

upvoted a paper 10 months ago

CRISP: Persistent Concept Unlearning via Sparse Autoencoders

Paper • 2508.13650 • Published Aug 19, 2025 • 16

upvoted 2 papers about 1 year ago

Effective Red-Teaming of Policy-Adherent Agents

Paper • 2506.09600 • Published Jun 11, 2025 • 39

TabSTAR: A Foundation Tabular Model With Semantically Target-Aware Representations

Paper • 2505.18125 • Published May 23, 2025 • 113

upvoted 5 papers over 1 year ago

Inside-Out: Hidden Factual Knowledge in LLMs

Paper • 2503.15299 • Published Mar 19, 2025 • 56

TokenVerse: Versatile Multi-concept Personalization in Token Modulation Space

Paper • 2501.12224 • Published Jan 21, 2025 • 48

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

Paper • 2501.06751 • Published Jan 12, 2025 • 32

NL-Eye: Abductive NLI for Images

Paper • 2410.02613 • Published Oct 3, 2024 • 23

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

Paper • 2410.02707 • Published Oct 3, 2024 • 47

upvoted a paper about 2 years ago

Make It Count: Text-to-Image Generation with an Accurate Number of Objects

Paper • 2406.10210 • Published Jun 14, 2024 • 78