Michael Toker

6 papers · 2024–2026 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11)

Venues

ACL (2) ICLR (2) EACL (1) NAACL (1)

Top co-authors

Yonatan Belinkov (5) Hadas Orgad (3) Roi Reichart (2) Mor Ventura (2) Zorik Gekhman (2) Gal Chechik (1) Roy Schwartz (1) Benny Kimelfeld (1) Yonatan Bitton (1) Yoad Tewel (1)

Research topics

Artificial Intelligence (3) Computer Vision (3) Deep Learning (3) Core AI (3) Generation (3) Models (3) Machine Learning (2) Natural Language Processing (1) Application Areas (1) Applications (1) Core Methods (1) Learning Types (1)

Keywords

token representation (2) diffusion model (2) text classification (1) natural language inference (1) text-to-image generation (1) error detection (1) latent representation (1) text-to-image model (1) text-to-image diffusion (1) hallucination detection (1) multimodal reasoning (1) text encoder (1) abductive reasoning (1) information flow (1) internal representation (1) metaphor detection (1) visual language model (1) truthfulness encoding (1) attention pattern (1) large language model (1)

Papers

Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models ACL 2026 LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations ICLR 2025 NL-Eye: Abductive NLI For Images ICLR 2025 Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models NAACL 2025 A Dataset for Metaphor Detection in Early Medieval Hebrew Poetry EACL 2024 Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelines ACL 2024