{"total":18,"rows":[{"id":"2211.14305","title":"SpaText: Spatio-Textual Representation for Controllable Image Generation","created":"2022-11-25","cited_by_count":217,"area":"diffusion"},{"id":"2403.13802","title":"ZigMa: A DiT-style Zigzag Mamba Diffusion Model","created":"2024-03-20","cited_by_count":84,"area":"diffusion"},{"id":"2502.04320","title":"ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features","created":"2025-02-06","cited_by_count":52,"area":"diffusion"},{"id":"2305.18729","title":"Real-World Image Variation by Aligning Diffusion Inversion Chain","created":"2023-05-30","cited_by_count":37,"area":"diffusion"},{"id":"2306.00966","title":"The Hidden Language of Diffusion Models","created":"2023-06-01","cited_by_count":34,"area":"diffusion"},{"id":"2310.06836","title":"A General Protocol to Probe Large Vision Models for 3D Physical Understanding","created":"2023-10-10","cited_by_count":32,"area":"diffusion"},{"id":"2410.18977","title":"Pay Attention and Move Better: Harnessing Attention for Interactive Motion Generation and Training-free Editing","created":"2024-10-24","cited_by_count":18,"area":"diffusion"},{"id":"2406.11643","title":"CustAny: Customizing Anything from A Single Example","created":"2024-06-17","cited_by_count":2,"area":"diffusion"},{"id":"2509.22650","title":"RefAM: Attention Magnets for Zero-Shot Referral Segmentation","created":"2025-09-26","cited_by_count":2,"area":"diffusion"},{"id":"2601.07287","title":"Focal Guidance: Unlocking Controllability from Semantic-Weak Layers in Video Diffusion Models","created":"2026-01-12","cited_by_count":1,"area":"diffusion"},{"id":"2604.20936","title":"AttentionBender: Manipulating Cross-Attention in Video Diffusion Transformers as a Creative Probe","created":"2026-04-22","cited_by_count":1,"area":"diffusion"},{"id":"2605.26460","title":"AnchorDiff: Training-Free Concept Grounding for MM-DiTs via Anchor-Based Graph Propagation","created":"2026-05-26","cited_by_count":1,"area":"diffusion"},{"id":"2509.05323","title":"Attention of a Kiss: Exploring Attention Maps in Video Diffusion for XAIxArts","created":"2025-08-30","cited_by_count":0,"area":"diffusion"},{"id":"2511.17766","title":"Deepfake Geography: Detecting AI-Generated Satellite Images","created":"2025-11-21","cited_by_count":0,"area":"diffusion"},{"id":"2601.20391","title":"Eliminating Hallucination in Diffusion-Augmented Interactive Text-to-Image Retrieval","created":"2026-01-28","cited_by_count":0,"area":"diffusion"},{"id":"2606.10046","title":"Inside the Latent Flow: Causal Deciphering of Attention Dynamics in Audio Separation Foundation Models","created":"2026-06-08","cited_by_count":0,"area":"diffusion"},{"id":"2607.03580","title":"When Geometry Aligns: Dihedral Hidden-State Transformations in UNet, ViT, and DiT Architectures","created":"2026-07-03","cited_by_count":0,"area":"diffusion"},{"id":"2608.05878","title":"MAVISEG: Manifold Propagation and Visual Prototypes for Zero-Shot Open-Vocabulary Segmentation in Diffusion Transformers","created":"2026-08-06","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}