arXiv (All)
open access
Exploring Attention Sinks in Text-to-Image Transformers from Diffusion and Autoregressive Models
Attention sinks are tokens or positions that consistently receive disproportionate attention mass, often beyond what their semantic content would suggest. Despite extensive study in large language models, their behavior and functional relevance in text-to-image (T2I) Transformers remain largely unex
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Attention Sinks in Diffusion Transformers: A Causal Analysis#1187393
- One Geometry, Different Outcomes: Readout-Dependent Effects of the Modality Gap in Vision-Language Models#1130943
- N-gram-like Language Models Predict Naturalistic Reading Time Best#1078962
- Rethinking Memorization Mitigation in Diffusion Models: Reinforcing Text Conditioning#1156994
- Reading Right, Answering Wrong: How Visual Configuration Changes Affect Evidence Use in VLMs#1061402
Record · ID 1297689
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive