Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor | Paper Citation Record

Observation e8b87fd0-240e-418d-b6cf-8ec87ed4eb41 · outbound

This paper cites Eyes wide shut? exploring the visual shortcomings of multimodal llms,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Eyes wide shut? exploring the visual shortcomings of multimodal llms,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:39.207480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a12d77e5-20f2-4573-90e9-81ca44e1ab33 · outbound

This paper cites Learning transferable visual models from natural language supervision,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Learning transferable visual models from natural language supervision,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:39.197431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b602ef68-7beb-436a-b7af-92b84f6a69a2 · outbound

This paper cites DetailCLIP: Detail-Oriented CLIP for Fine-Grained Tasks.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor DetailCLIP: Detail-Oriented CLIP for Fine-Grained Tasks

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:31.581690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3734393-a69e-4769-a1e9-4e7e7c1d021c · outbound

This paper cites Is clip the main roadblock for fine-grained open-world perception?,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Is clip the main roadblock for fine-grained open-world perception?,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:39.187174Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 625bdc2b-6844-4ae1-ac8f-0e68ed309af3 · outbound

This paper cites Discffusion: Discriminative Diffusion Models as Few-shot Vision and Language Learners.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Discffusion: Discriminative Diffusion Models as Few-shot Vision and Language Learners

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-08-06T18:52:38.207894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation bf309773-992a-4ce3-a6c3-4332c53bc974 · outbound

This paper cites BRAVE: Broadening the visual encoding of vision-language models.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor BRAVE: Broadening the visual encoding of vision-language models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:31.767820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67cf8678-d817-4b9f-bb5c-00e6edf6170c · outbound

This paper cites Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:31.825326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea4cd2ef-2034-4a1b-8b7a-f9b908f0b8ea · outbound

This paper cites From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:31.897432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6fd8af5-b0b1-4324-8852-e6e4af2443fc · outbound

This paper cites Mini-gemini: Mining the potential of multi-modality vision language models,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Mini-gemini: Mining the potential of multi-modality vision language models,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:39.176426Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e9b9b89d-4508-462d-80ed-2c3b2ab5c80e · outbound

This paper cites Prismer: A Vision-Language Model with Multi-Task Experts.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Prismer: A Vision-Language Model with Multi-Task Experts

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:32.060515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cb52f24-dbbb-4ab1-81ec-a3d5c5cbafc0 · outbound

This paper cites Vcoder: Versatile vision encoders for multimodal large language models,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Vcoder: Versatile vision encoders for multimodal large language models,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:39.166549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b7103154-94f7-4435-bfa8-ac2c332fb38a · outbound

This paper cites Question aware vision transformer for multimodal reasoning,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Question aware vision transformer for multimodal reasoning,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:39.156651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7283de56-cd47-43d2-a110-a861513486d7 · outbound

This paper cites Api: Attention prompting on image for large vision-language models,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Api: Attention prompting on image for large vision-language models,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:39.146498Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation cefb533f-5313-443f-b4f5-cca3a74cf1db · outbound

This paper cites Instructblip: Towards general-purpose vision-language models with instruction tuning,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Instructblip: Towards general-purpose vision-language models with instruction tuning,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:32.475667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51279896-4373-4237-84bd-1fdf372892e6 · outbound

This paper cites Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:32.491396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df85e6de-4f47-4c97-afdc-2213358707fb · outbound

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

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor High-resolution image synthesis with latent diffusion models,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:32.533667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbcd5294-5e78-4b1c-bd97-3c5db57e9a4a · outbound

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

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Photorealistic text-to-image diffusion models with deep language understanding,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:39.116420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 296a3972-4983-498b-ad94-39a6c8bc9d1a · outbound

This paper cites Hierarchical text-conditional image generation with clip latents,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Hierarchical text-conditional image generation with clip latents,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:32.727639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0901327-ae10-4002-9c21-bba7c7ce2154 · outbound

This paper cites Sdxl: Improving latent diffusion models for high-resolution image synthesis,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Sdxl: Improving latent diffusion models for high-resolution image synthesis,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:39.097243Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 55412a86-d16b-48bd-a6f9-528b92f8f1d8 · outbound

This paper cites Prompt-to-prompt image editing with cross attention control,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Prompt-to-prompt image editing with cross attention control,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:39.086788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b99865be-9966-49d5-ae52-cd4fc760b7dc · outbound

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

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor What the daam: Interpreting stable diffusion using cross attention,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:39.077053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5715627b-f108-4911-a7ea-6493cff780c5 · outbound

This paper cites Towards understanding cross and self-attention in stable diffusion for text-guided image editing,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Towards understanding cross and self-attention in stable diffusion for text-guided image editing,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:39.067728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f68a552d-440a-4c04-83f3-8c6fe427aa1e · outbound

This paper cites Plug-and-play diffusion features for text-driven image- to-image translation,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Plug-and-play diffusion features for text-driven image- to-image translation,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:39.058139Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3de6ec26-b7fb-41ef-9c92-b1afb1298272 · outbound

This paper cites Diffusion Model is Secretly a Training-free Open Vocabulary Semantic Segmenter.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Diffusion Model is Secretly a Training-free Open Vocabulary Semantic Segmenter

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:33.421637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e32935a-f2fa-4f14-879f-b4239b68da79 · outbound

This paper cites Repurposing diffusion-based image generators for monocular depth estimation,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Repurposing diffusion-based image generators for monocular depth estimation,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:39.048007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4c4dce4f-505e-4580-bd26-cbd6e386ba1f · outbound

This paper cites Do text-free diffusion models learn discriminative visual representations?.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Do text-free diffusion models learn discriminative visual representations?

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:33.646987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44a895a7-2e78-42cf-bce6-5f52c4eb49a3 · outbound

This paper cites Deconstructing denoising diffusion models for self-supervised learning,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Deconstructing denoising diffusion models for self-supervised learning,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:39.038820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 98a009da-c65d-4f22-9c99-2857b6e2c9a8 · outbound

This paper cites Coca: Contrastive captioners are image-text foundation models,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Coca: Contrastive captioners are image-text foundation models,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:39.028681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 790d6f1e-5c0d-4a5c-9047-606095c7cbd9 · outbound

This paper cites Multimodal few-shot learning with frozen language models,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Multimodal few-shot learning with frozen language models,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:39.017462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e5a0be6c-107b-4935-9338-c4a9398dd94c · outbound

This paper cites Flamingo: a visual language model for few-shot learning,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Flamingo: a visual language model for few-shot learning,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:39.007156Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f20a7514-0702-4d53-ad7d-f58aaafc9dfa · outbound

This paper cites Visual instruction tuning,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Visual instruction tuning,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:38.996235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d0517812-1c5b-4029-9d48-4d901626aca3 · outbound

This paper cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:34.227206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cc71a27-f8e9-43c7-b0f5-e29d26238011 · outbound

This paper cites MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:34.315551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 556d3ef5-1f4b-4c51-aee0-77d103f946d8 · outbound

This paper cites OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:34.409335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 848a5aaa-b4e9-4115-82e6-decb4d529af6 · outbound

This paper cites Evaluating Object Hallucination in Large Vision-Language Models.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Evaluating Object Hallucination in Large Vision-Language Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:34.500395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54725c8f-4675-4ac8-abfb-c2e9f1e25b01 · outbound

This paper cites Multi-modal hallucination control by visual information grounding,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Multi-modal hallucination control by visual information grounding,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:38.986332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5f489965-c74f-4fb8-aa60-306084b23fae · outbound

This paper cites Detecting and preventing hallucinations in large vision language models,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Detecting and preventing hallucinations in large vision language models,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:38.976233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5b55157d-f698-4213-833c-1e1eefac95f1 · outbound

This paper cites A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:34.830166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36fe1c95-1620-4561-a3cd-5e6037917e1a · outbound

This paper cites HallE-Control: Controlling Object Hallucination in Large Multimodal Models.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor HallE-Control: Controlling Object Hallucination in Large Multimodal Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:34.896934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9bcfcae-e0d3-4335-bc9a-5553952852ae · outbound

This paper cites Aligning Large Multimodal Models with Factually Augmented RLHF.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Aligning Large Multimodal Models with Factually Augmented RLHF

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:34.983806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab5b5abd-9b09-4f0f-bccc-629838e11b29 · outbound

This paper cites BLINK: Multimodal Large Language Models Can See but Not Perceive.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor BLINK: Multimodal Large Language Models Can See but Not Perceive

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:35.095890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 201ad2db-d2af-4eb2-b99f-c19dc5e6cf4f · outbound

This paper cites Llava-next: Improved reasoning, ocr, and world knowledge,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Llava-next: Improved reasoning, ocr, and world knowledge,

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:35.206253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26b9cebe-850f-4bff-b75f-82e4460c81a5 · outbound

This paper cites MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:35.255074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a775c40-908f-4be4-97fc-d183c552ff0e · outbound

This paper cites Improved baselines with visual instruction tuning,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Improved baselines with visual instruction tuning,

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:35.415756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4aa7ebc1-2d2f-4923-9cc2-1c696551b0bf · outbound

This paper cites 4m: Massively multimodal masked modeling,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor 4m: Massively multimodal masked modeling,

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:38.952048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e08a5649-69ea-45a7-8806-6160ae111cfd · outbound

This paper cites 4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor 4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:35.658391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 958be85f-58a5-495e-b952-93836b10ad0a · outbound

This paper cites Llava-plus: Learning to use tools for creating multimodal agents,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Llava-plus: Learning to use tools for creating multimodal agents,

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:38.941704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 524a1413-4b8c-4d16-94c5-8e3364a96190 · outbound

This paper cites Visual programming: Compositional visual reasoning without training,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Visual programming: Compositional visual reasoning without training,

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:38.931881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation cd605569-c973-412d-a5ba-9693f9cea517 · outbound

This paper cites Spatialbot: Precise spatial understanding with vision language models,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Spatialbot: Precise spatial understanding with vision language models,

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:38.921200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation adba8552-2fb7-450e-9f5f-74e68331758f · outbound

This paper cites Your diffusion model is secretly a zero- shot classifier,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Your diffusion model is secretly a zero- shot classifier,

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:38.911539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6958a577-10b3-40c1-bfe4-a581be05c5bb · outbound

This paper cites Diffusion Models Beat GANs on Image Classification.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Diffusion Models Beat GANs on Image Classification

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:36.050247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 396ca2fd-a5fa-4ad7-9dc9-4f33babf60e7 · outbound

This paper cites Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:36.136857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57b935b2-94bf-41df-af2b-48c18dd48d23 · outbound

This paper cites Diffusion Models for Open-Vocabulary Segmentation.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Diffusion Models for Open-Vocabulary Segmentation

Reference 53

Resolution: verified exact; local_arxiv, observed 2026-08-06T18:52:37.892673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2801e47e-4379-472f-b257-71088ab13e4b · outbound

This paper cites Not all diffusion model activations have been evaluated as discriminative features,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Not all diffusion model activations have been evaluated as discriminative features,

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:38.901068Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7d74e8ff-50e6-4bf4-b698-08dacdd59fbb · outbound

This paper cites Dinov2: Learning robust visual features without supervision,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Dinov2: Learning robust visual features without supervision,

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:36.377242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00a9423d-718c-4cc2-8596-7644d85d2322 · outbound

This paper cites Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality,

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:38.883626Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3ea49173-02b8-4e6d-9f24-224ee2b21304 · outbound

This paper cites Naturalbench: Evaluating vision-language models on natural adversarial samples,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Naturalbench: Evaluating vision-language models on natural adversarial samples,

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:38.873717Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2f3f7607-0885-427b-932b-be059f4fe581 · outbound

This paper cites Openclip,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Openclip,

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:38.863477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6ffaac83-c65c-4172-b043-419a46750ca0 · outbound

This paper cites Sigmoid loss for language image pre-training,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Sigmoid loss for language image pre-training,

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:38.853467Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7e2d64dd-5c70-499f-b96d-4a57f5104283 · outbound

This paper cites Data filtering networks,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Data filtering networks,

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:38.843141Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 298bcc47-91a2-48c3-a73b-f196b9054cd7 · outbound

This paper cites Demystifying clip data,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Demystifying clip data,

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:38.833840Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f2e55f68-91ff-47ae-b704-e53d070df640 · outbound

This paper cites Eva-clip: Improved training techniques for clip at scale,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Eva-clip: Improved training techniques for clip at scale,

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:36.885560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e10e12ee-90e0-4599-8d23-15f3ac9f1acf · outbound

This paper cites Microsoft COCO Captions: Data Collection and Evaluation Server.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Microsoft COCO Captions: Data Collection and Evaluation Server

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:36.954496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d47a46a-4416-4d94-b899-9dc929b9eccc · outbound

This paper cites Accurate computation of the log-sum-exp and softmax functions,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Accurate computation of the log-sum-exp and softmax functions,

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:38.817386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f2f69d76-9387-498b-b3cd-f189c898635f · outbound

This paper cites Winoground: Probing vision and language models for visio-linguistic compositionality,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Winoground: Probing vision and language models for visio-linguistic compositionality,

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:38.806943Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e1eba4e4-6e52-40d7-b4ef-7a107f9ca734 · outbound

This paper cites Similarity of neural network representations revisited,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Similarity of neural network representations revisited,

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:38.796071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a693805c-afd9-4fbe-825d-cd9103233a47 · outbound

This paper cites Cider: Consensus-based image description evaluation,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Cider: Consensus-based image description evaluation,

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-06T18:52:37.250094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c03cdc7-06dd-4d99-8b0c-27ce0bf0c6ab · outbound

This paper cites Spice: Semantic propositional image caption evaluation,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Spice: Semantic propositional image caption evaluation,

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:52:38.741941Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 95b8348a-10c1-416b-a666-9ee0fe2a9ff0 · outbound

This paper cites Decoupled weight decay regularization,.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Decoupled weight decay regularization,

Reference 69

Resolution: malformed identifier; raw_fallback, observed 2026-08-06T18:52:37.725447Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation fdb9678a-2a92-4434-9134-38e0b3a60d74 · outbound

This paper cites Frisbees.

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor Frisbees

Reference 70

Resolution: malformed identifier; raw_fallback, observed 2026-08-06T18:52:38.503754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers