Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders | Paper Citation Record

Observation 482a1999-05f5-455d-a698-e15895792ca2 · outbound

This paper cites Sora: Creating video from text, 2024.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Sora: Creating video from text, 2024

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:22.477040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 097c51b4-4b52-437c-8279-2b03ec7f035b · outbound

This paper cites Scalable diffusion models with transformers.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Scalable diffusion models with transformers

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:22.596245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53325ac9-28d7-416b-a2c3-e34f1bdb750f · outbound

This paper cites Zero-shot text-to-image generation.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Zero-shot text-to-image generation

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:22.636395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5943a50c-58e7-4a0b-9140-f52b3e659be9 · outbound

This paper cites Photorealistic text-to-image diffusion models with deep language understanding.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Photorealistic text-to-image diffusion models with deep language understanding

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:22.675389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51d635d3-4590-4ed7-b9a7-9879f7f76ad7 · outbound

This paper cites GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:22.688145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32be373c-6b5b-4351-9328-7f3ef2a03463 · outbound

This paper cites GECO: Generative Image-to-3D within a SECOnd.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders GECO: Generative Image-to-3D within a SECOnd

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:22.694879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd7630b7-2605-4b14-9cd6-01ea20fcff77 · outbound

This paper cites DreamFusion: Text-to-3D using 2D Diffusion.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders DreamFusion: Text-to-3D using 2D Diffusion

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:22.702017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fedaefb3-01a6-4ca5-97be-a63da88d2114 · outbound

This paper cites Texture: Text-guided texturing of 3d shapes.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Texture: Text-guided texturing of 3d shapes

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:22.743271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1c521b8-f241-4a09-8270-c3978692abb6 · outbound

This paper cites High-resolution image synthesis with latent diffusion models.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders High-resolution image synthesis with latent diffusion models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:22.822752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07ee73d6-6c8c-44ae-873d-142a9333441e · outbound

This paper cites Do As I Can, Not As I Say: Grounding Language in Robotic Affordances.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Do As I Can, Not As I Say: Grounding Language in Robotic Affordances

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:22.872363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7464c206-802b-4b05-b288-b5c8dcd29e57 · outbound

This paper cites Inner Monologue: Embodied Reasoning through Planning with Language Models.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Inner Monologue: Embodied Reasoning through Planning with Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:22.892187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 203e24c2-406a-4292-8474-040b2e296d34 · outbound

This paper cites Language models as zero-shot planners: Extracting actionable knowledge for embodied agents.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Language models as zero-shot planners: Extracting actionable knowledge for embodied agents

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:22.898729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e36853f-070a-468d-93a2-c283c486f18f · outbound

This paper cites Text-guided controllable mesh refinement for interactive 3d modeling.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Text-guided controllable mesh refinement for interactive 3d modeling

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:22.904222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10f5f498-774e-45c4-b906-76e0df7b4d24 · outbound

This paper cites Smoodi: Stylized motion diffusion model.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Smoodi: Stylized motion diffusion model

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:22.910423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50647a37-f5f5-43db-87f9-f26e91d2f09f · outbound

This paper cites Meshgpt: Generating triangle meshes with decoder-only transformers.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Meshgpt: Generating triangle meshes with decoder-only transformers

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:22.916259Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a94a36d2-667e-4d46-861a-a450fe187753 · outbound

This paper cites A very preliminary analysis of DALL-E 2.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders A very preliminary analysis of DALL-E 2

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:23.000282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf94b759-3514-4d1f-a04c-d5aac5f74637 · outbound

This paper cites Discovering and validating ai errors with crowdsourced failure reports.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Discovering and validating ai errors with crowdsourced failure reports

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:23.067556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 763e0925-04b4-42a8-8bf5-6ca474bec4e6 · outbound

This paper cites Generative artificial intelligence in creative contexts: a systematic review and future research agenda.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Generative artificial intelligence in creative contexts: a systematic review and future research agenda

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:23.112411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7239a24b-92c2-4a6f-964b-230c12b39753 · outbound

This paper cites Discovering Failure Modes of Text-guided Diffusion Models via Adversarial Search.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Discovering Failure Modes of Text-guided Diffusion Models via Adversarial Search

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:23.128482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c8c7bcc-e0ad-405e-b032-af87ffd03753 · outbound

This paper cites Relations, Negations, and Numbers: Looking for Logic in Generative Text-to-Image Models.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Relations, Negations, and Numbers: Looking for Logic in Generative Text-to-Image Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:23.136521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a5801f5-75cc-4e5b-b73a-e33eb3716944 · outbound

This paper cites HandRefiner: Re- fining malformed hands in generated images by diffusion-based conditional inpainting.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders HandRefiner: Re- fining malformed hands in generated images by diffusion-based conditional inpainting

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:23.176933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9355aecc-e75b-4d64-8874-57a32efb0089 · outbound

This paper cites HanDiffuser: Text-to-image generation with realistic hand appearances.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders HanDiffuser: Text-to-image generation with realistic hand appearances

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:23.219023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22a1ae46-7e84-49e2-981e-9cd6dc223087 · outbound

This paper cites Layout-agnostic scene text image synthesis with diffusion models.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Layout-agnostic scene text image synthesis with diffusion models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:23.297920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18efadc1-4b30-4088-856f-8beabf1c8dd6 · outbound

This paper cites TextInVision: Text and Prompt Complexity Driven Visual Text Generation Benchmark.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders TextInVision: Text and Prompt Complexity Driven Visual Text Generation Benchmark

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-08-15T18:33:28.631972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 738b6139-8566-4f80-b0fd-7a03ac1ec247 · outbound

This paper cites Text-to-image diffusion models cannot count, and prompt refinement cannot help.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Text-to-image diffusion models cannot count, and prompt refinement cannot help

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:23.351542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 142b95eb-967f-472d-87c6-685f55ea4239 · outbound

This paper cites Testing Relational Understanding in Text-Guided Image Generation.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Testing Relational Understanding in Text-Guided Image Generation

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:23.358089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffeeb73b-ae1e-4be2-9450-fec44fa592e6 · outbound

This paper cites Blindspot: Hidden biases of good people.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Blindspot: Hidden biases of good people

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:23.364488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f488886a-a8cc-498f-a30c-5ac98830754f · outbound

This paper cites Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:23.415410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab1abbaf-6f03-45bd-b167-cef766eda60e · outbound

This paper cites A study of the evaluation metrics for generative images containing combinational creativity.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders A study of the evaluation metrics for generative images containing combinational creativity

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:23.500318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e42e6034-5890-48f9-bece-42a40141a3eb · outbound

This paper cites Gans trained by a two time-scale update rule converge to a local nash equilibrium.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Gans trained by a two time-scale update rule converge to a local nash equilibrium

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:23.552184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a6fb29c-0f5f-4e26-b02f-81519bcaeea2 · outbound

This paper cites Clipscore: A reference-free evaluation metric for image captioning.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Clipscore: A reference-free evaluation metric for image captioning

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:23.588084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76d981a2-766b-4e69-85c3-7b5e1a911103 · outbound

This paper cites Image Generation Diversity Issues and How to Tame Them.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Image Generation Diversity Issues and How to Tame Them

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-08-15T18:33:28.428735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9ab62e29-01b4-4676-bb16-8f6073b271c9 · outbound

This paper cites Anomaly score: Evaluating generative models and individual generated images based on complexity and vulnerability.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Anomaly score: Evaluating generative models and individual generated images based on complexity and vulnerability

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:23.607946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b1bc46e-dfab-468e-a93d-7bfd06477a69 · outbound

This paper cites A note on the evaluation of generative models.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders A note on the evaluation of generative models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:23.614873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8328dc55-c33f-4532-95c6-52e2199a18eb · outbound

This paper cites Reliable fidelity and diversity metrics for generative models.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Reliable fidelity and diversity metrics for generative models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:23.622722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8148ee44-c185-445d-adfb-6b4437f0173f · outbound

This paper cites Human Evaluation of Text-to-Image Models on a Multi-Task Benchmark.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Human Evaluation of Text-to-Image Models on a Multi-Task Benchmark

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:23.673214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aec9a3bb-2fb0-4ff0-bad6-209fccab286d · outbound

This paper cites Imagereward: Learning and evaluating human preferences for text-to-image generation.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Imagereward: Learning and evaluating human preferences for text-to-image generation

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:23.740755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 484dda56-7a7b-4d8e-b40e-61722ff2b054 · outbound

This paper cites Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:23.764374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96aef2c8-7ba1-45c1-83c3-b73bf3c2e998 · outbound

This paper cites Seeing what a GAN cannot generate.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Seeing what a GAN cannot generate

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:23.772199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3267aa8-e6e2-4e54-a336-ff94c62e1113 · outbound

This paper cites Deep inside convolutional networks: Visualising image classification models and saliency maps.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Deep inside convolutional networks: Visualising image classification models and saliency maps

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:23.779436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f18ce2c4-361a-47be-a929-3ee40f922382 · outbound

This paper cites Axiomatic attribution for deep networks.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Axiomatic attribution for deep networks

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:23.853434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d23988e4-13a9-4cf3-bb31-326b3c687859 · outbound

This paper cites Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:23.888453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57cdcb95-d44e-4ed0-9de8-7e8e7dbe45d7 · outbound

This paper cites Sanity checks for saliency maps.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Sanity checks for saliency maps

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:23.897581Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de6d1643-ca20-4e4c-9bbc-09a30a7e4e0a · outbound

This paper cites Interpretation of neural networks is fragile.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Interpretation of neural networks is fragile

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:23.988090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a229a3d6-c7cd-4406-96bb-37fdf09f4953 · outbound

This paper cites an unresolved cited work.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Unresolved cited work

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.022190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae9908be-2b88-41ab-9151-63d7f695553f · outbound

This paper cites Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav).

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav)

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.044994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf506858-a230-4d99-8dda-3bec12dd0844 · outbound

This paper cites Network dissec- tion: Quantifying interpretability of deep visual representations.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Network dissec- tion: Quantifying interpretability of deep visual representations

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.051015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9acdc07e-d552-48b9-a92a-724fe1d91399 · outbound

This paper cites Craft: Concept recursive activation factorization for explainability.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Craft: Concept recursive activation factorization for explainability

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.056752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2626aa0d-686d-449f-80d9-584bac746125 · outbound

This paper cites Understanding video transformers via universal concept discovery.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Understanding video transformers via universal concept discovery

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.062338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fa1018b-2fe4-49d9-947e-6aecf72d3002 · outbound

This paper cites Sparse autoencoders find highly interpretable features in language models.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Sparse autoencoders find highly interpretable features in language models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.114677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13445960-c2ca-466e-a26a-7e71aa1fa8bb · outbound

This paper cites Towards monosemanticity: Decomposing language models with dictionary learning.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Towards monosemanticity: Decomposing language models with dictionary learning

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.184942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26a4bb2f-dedf-4028-99f7-c78d8758ce06 · outbound

This paper cites A holistic approach to unifying automatic concept extraction and concept importance estimation.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders A holistic approach to unifying automatic concept extraction and concept importance estimation

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.215459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7196a3d-b097-427d-8bab-498a8f589b58 · outbound

This paper cites A is for absorption: Studying feature splitting and absorption in sparse autoencoders.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders A is for absorption: Studying feature splitting and absorption in sparse autoencoders

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.230818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b4e9208-e078-4d82-b127-98eacd3a34f1 · outbound

This paper cites Relational composition in neural networks: A survey and call to action.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Relational composition in neural networks: A survey and call to action

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.238588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c07af7cc-3d07-49e0-8628-e00b269a68ee · outbound

This paper cites Towards unifying interpretability and control: Evaluation via intervention.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Towards unifying interpretability and control: Evaluation via intervention

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.248444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2815a0b4-533c-4cfa-8748-1d12383bc195 · outbound

This paper cites Archetypal SAE: Adaptive and stable dictionary learning for concept extraction in large vision models.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Archetypal SAE: Adaptive and stable dictionary learning for concept extraction in large vision models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.303830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f28e8aa-6510-4f27-a9e4-ccec007d8cbc · outbound

This paper cites Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.363074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6cfaf60-a5cd-42b3-9009-d867ac9dc7cb · outbound

This paper cites GAN dissection: Visualizing and understanding generative adversarial networks.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders GAN dissection: Visualizing and understanding generative adversarial networks

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.419998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72842019-5626-49ad-9ce4-5431335e78e0 · outbound

This paper cites What the DAAM: Interpreting stable diffusion using cross attention.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders What the DAAM: Interpreting stable diffusion using cross attention

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.455734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 396c2a20-cb5f-4df9-97e5-706a1d5b92d3 · outbound

This paper cites Qualitative failures of image generation models and their application in detecting deepfakes.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Qualitative failures of image generation models and their application in detecting deepfakes

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.462688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 816d4ac2-58d9-4291-acc3-bedfc53749a6 · outbound

This paper cites Hierarchical Text-Conditional Image Generation with CLIP Latents.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Hierarchical Text-Conditional Image Generation with CLIP Latents

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.468612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6db6f65f-3b2e-4fd9-9dcd-0f11ade1f305 · outbound

This paper cites Score-Based Generative Modeling through Stochastic Differential Equations.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Score-Based Generative Modeling through Stochastic Differential Equations

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.475458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 131f2991-6d0e-44ea-81a5-9beee39a87a2 · outbound

This paper cites Consistency models.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Consistency models

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.481506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 230f8b6b-1a4f-4356-ab10-edf0df4f1532 · outbound

This paper cites Improved denoising diffusion probabilistic models.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Improved denoising diffusion probabilistic models

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.569218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c9817a8-ef66-41f4-89f6-92788bc1c898 · outbound

This paper cites Video diffusion models.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Video diffusion models

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.670178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c89dfc9-b965-4dcd-8f9c-03bd02f17ebb · outbound

This paper cites VDT: General-purpose Video Diffusion Transformers via Mask Modeling.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders VDT: General-purpose Video Diffusion Transformers via Mask Modeling

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.715527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2a100be-e907-4666-b9aa-0fc786035038 · outbound

This paper cites ModelScope Text-to-Video Technical Report.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders ModelScope Text-to-Video Technical Report

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.735030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc68f085-c1c4-4780-9e81-7cc00e77c78c · outbound

This paper cites AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.751864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcc86b88-6899-49d4-b50d-4ffeac2085b4 · outbound

This paper cites AnimateDiff-Lightning: Cross-Model Diffusion Distillation.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders AnimateDiff-Lightning: Cross-Model Diffusion Distillation

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.769557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfbd9dbe-b01e-4dfe-ae85-691bc24dc638 · outbound

This paper cites CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.776424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 521dc25f-1697-4af5-9538-64e77e458891 · outbound

This paper cites VideoCrafter1: Open Diffusion Models for High-Quality Video Generation.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders VideoCrafter1: Open Diffusion Models for High-Quality Video Generation

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.781838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31d1dc30-278e-438d-858a-fa15ec4de45a · outbound

This paper cites Tune-a-video: One-shot tuning of image diffusion models for text-to-video generation.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Tune-a-video: One-shot tuning of image diffusion models for text-to-video generation

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.787805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c08b538-256a-4c06-9468-02edc36e557e · outbound

This paper cites Magic3D: High-resolution text-to-3d content creation.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Magic3D: High-resolution text-to-3d content creation

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.870472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea612781-1c10-43fc-a2c5-6a350117191e · outbound

This paper cites Shap-E: Generating Conditional 3D Implicit Functions.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Shap-E: Generating Conditional 3D Implicit Functions

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.944024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4cf1d53-7d0f-4d97-b2e7-4143686c5587 · outbound

This paper cites Score jacobian chaining: Lifting pretrained 2d diffusion models for 3d generation.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Score jacobian chaining: Lifting pretrained 2d diffusion models for 3d generation

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.973933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f33ae7d-4840-4e36-89d1-5db350df25ff · outbound

This paper cites Denoising diffusion probabilistic models.Advances in neural information processing systems, 33:6840–6851, 2020.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Denoising diffusion probabilistic models.Advances in neural information processing systems, 33:6840–6851, 2020

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.980516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e685852c-4089-4562-af3f-d3309ce84d02 · outbound

This paper cites Denoising Diffusion Implicit Models.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Denoising Diffusion Implicit Models

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.992206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb1ae87e-3846-4de1-9d1d-1d7349e525eb · outbound

This paper cites Stable Diffusion 2.0 Release, 2022.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Stable Diffusion 2.0 Release, 2022

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:24.998749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1bf2a8d-cfc5-42b0-a0a4-0e30e2d958ed · outbound

This paper cites Introducing Stable Diffusion 3, 2024.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Introducing Stable Diffusion 3, 2024

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:25.004763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 833d4d16-685c-4492-ad50-3a575f5a3093 · outbound

This paper cites SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:25.011962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c552e18c-2a06-4041-a4b7-1fdbbdb7a0ca · outbound

This paper cites StyleDrop: Text-to-Image Generation in Any Style.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders StyleDrop: Text-to-Image Generation in Any Style

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:25.018215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e3a92f4-b73f-4e88-b283-cc30cbd12d3a · outbound

This paper cites Arbitrary style guidance for enhanced diffusion-based text-to-image generation.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Arbitrary style guidance for enhanced diffusion-based text-to-image generation

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:25.027064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc2ab56e-49d3-40b0-82ef-29613818485b · outbound

This paper cites Adding conditional control to text-to-image diffusion models.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Adding conditional control to text-to-image diffusion models

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:25.087626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1777202-08a9-4f25-8e0b-1016536e45ca · outbound

This paper cites DreamBooth: Fine tuning text-to-image diffusion models for subject-driven generation.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders DreamBooth: Fine tuning text-to-image diffusion models for subject-driven generation

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:25.163342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f4f0b60-8dbb-4cd6-8ce3-3a032a255901 · outbound

This paper cites Id-booth: Identity-consistent face generation with diffusion models.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Id-booth: Identity-consistent face generation with diffusion models

Reference 85

Resolution: verified exact; raw_fallback, observed 2026-08-15T18:33:27.995939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 72416d79-9f08-4960-ae4d-aa4be1688a43 · outbound

This paper cites Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:25.260932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ec9da0b-f35c-4fe5-b8f2-6867e2794c25 · outbound

This paper cites PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:25.267579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c3d7e5e-e187-4dad-bdd7-8cc39dad3930 · outbound

This paper cites DeepFloyd IF: A Powerful Open-Source Text-to-Image Model, 2023.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders DeepFloyd IF: A Powerful Open-Source Text-to-Image Model, 2023

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:25.274173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c75b6423-e15b-42ce-985a-1c3cb46000db · outbound

This paper cites Announcing Black Forest Labs, 2024.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Announcing Black Forest Labs, 2024

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:25.280303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35e9ccd5-3cf0-4d5b-99a2-620bf6fe26db · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders An image is worth 16x16 words: Transformers for image recognition at scale

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:25.309868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffa28fea-949d-48c8-8cad-c4c3fca4ff1d · outbound

This paper cites Scaling Autoregressive Models for Content-Rich Text-to-Image Generation.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Scaling Autoregressive Models for Content-Rich Text-to-Image Generation

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:25.391904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b406070-bf53-4646-a923-e473159d086c · outbound

This paper cites Deep Learning Scaling is Predictable, Empirically.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Deep Learning Scaling is Predictable, Empirically

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:25.520016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e87cdaef-56d8-4493-86bc-21ea6e6078e3 · outbound

This paper cites LAION-5B: An open large-scale dataset for training next generation image-text models.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders LAION-5B: An open large-scale dataset for training next generation image-text models

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:25.553567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f152598-3726-4196-87c0-27637ef0df29 · outbound

This paper cites Common crawl corpus.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Common crawl corpus

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:25.558830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4fe50d8-6ccb-4fe9-b17a-9b0b81476642 · outbound

This paper cites COYO-700M: Image-text pair dataset, 2022.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders COYO-700M: Image-text pair dataset, 2022

Reference 95

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:33:30.908054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 718690a0-d9d1-4d86-8404-7cd4cb05ac01 · outbound

This paper cites Conceptual Captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Conceptual Captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning

Reference 96

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:33:30.843698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation de735147-3211-40e4-a2aa-48094493b42a · outbound

This paper cites Into the LAION’s den: Investigating hate in multimodal datasets.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Into the LAION’s den: Investigating hate in multimodal datasets

Reference 97

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:33:30.800656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3ebced64-79d2-4c65-a924-8c64a7abddc6 · outbound

This paper cites The dark side of dataset scaling: Evaluating racial classification in multimodal models.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders The dark side of dataset scaling: Evaluating racial classification in multimodal models

Reference 98

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:33:30.779233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 96c61e2b-100e-415b-8dc5-07f24501f699 · outbound

This paper cites The Bias Amplification Paradox in Text-to-Image Generation.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders The Bias Amplification Paradox in Text-to-Image Generation

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:25.708005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87570b4a-ab18-481e-bc99-c95500a713ac · outbound

This paper cites Multimodal datasets: misogyny, pornography, and malignant stereotypes.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders Multimodal datasets: misogyny, pornography, and malignant stereotypes

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-15T18:33:25.803378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers