A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets | Paper Citation Record

Observation e541e223-0112-4f2b-bbc9-a9d01ba6a773 · outbound

This paper cites GPT-4 Technical Report.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T19:45:51.395705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 227d747f-b29e-408f-a3b9-4f62ce9cb1cb · outbound

This paper cites Vismin: Visual minimal-change understanding.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets Vismin: Visual minimal-change understanding

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:45:53.566352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3880f207-f9cf-4cb5-b486-27be3270d16f · outbound

This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T19:45:52.329853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c97579e-5679-49a4-bffb-f94465bededd · outbound

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

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T19:45:52.383239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a65d044-fa8b-44fe-9df2-d56f09da7c57 · outbound

This paper cites Clip2scene: Towards label-efficient 3d scene understanding by clip.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets Clip2scene: Towards label-efficient 3d scene understanding by clip

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:45:53.555147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 92458099-43b3-46b0-9043-596746f5c15e · outbound

This paper cites A simple framework for contrastive learning of visual representations.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets A simple framework for contrastive learning of visual representations

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:45:53.543996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3f519064-4f4e-4d59-9604-802108f68bf0 · outbound

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

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets Microsoft COCO Captions: Data Collection and Evaluation Server

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T19:45:52.563298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1ed6828-d923-4682-b1cd-7e32a88ecf1c · outbound

This paper cites InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T19:45:52.624039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 255f7f21-4cc0-4c52-b8bb-4f8f972f554a · outbound

This paper cites How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T19:45:52.695270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 907d0124-c006-4743-8192-02908b83132e · outbound

This paper cites Internvl: Scaling up vision foundation mod- els and aligning for generic visual-linguistic tasks.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets Internvl: Scaling up vision foundation mod- els and aligning for generic visual-linguistic tasks

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:45:53.531705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8fe1138b-f0b8-424d-8daf-e48f4b130349 · outbound

This paper cites InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T19:45:52.761831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2870a00f-fa24-45d3-8a1f-15b453fb94fe · outbound

This paper cites Dense and aligned captions (dac) promote compositional reasoning in vl models.Advances in Neural Information Processing Systems, 36:76137–76150, 2023.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets Dense and aligned captions (dac) promote compositional reasoning in vl models.Advances in Neural Information Processing Systems, 36:76137–76150, 2023

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:45:53.520358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 53581e1d-5568-463a-a2ed-2a178875b130 · outbound

This paper cites Teaching structured vision & language concepts to vision & language models.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets Teaching structured vision & language concepts to vision & language models

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:45:53.509035Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b3cbef5f-286e-4ca8-abc8-4dc10f2b40d7 · outbound

This paper cites Dense and aligned captions (dac) promote compositional reasoning in vl models.Advances in Neural Information Processing Systems, 36, 2024.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets Dense and aligned captions (dac) promote compositional reasoning in vl models.Advances in Neural Information Processing Systems, 36, 2024

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:45:53.497514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ff1e9ff5-461c-410f-99de-bdf4a9bf2b57 · outbound

This paper cites Scaling recti- fied flow transformers for high-resolution image synthesis.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets Scaling recti- fied flow transformers for high-resolution image synthesis

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:45:53.484864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bc526a0e-7a79-435c-b2c1-9d0b1222b699 · outbound

This paper cites Advances in deep concealed scene understanding.Visual Intelligence, 1(1):16,.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets Advances in deep concealed scene understanding.Visual Intelligence, 1(1):16,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:45:53.472951Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7883666e-4ec6-4b91-a616-a090dfa88957 · outbound

This paper cites Mini-InternVL: A Flexible-Transfer Pocket Multimodal Model with 5% Parameters and 90% Performance.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets Mini-InternVL: A Flexible-Transfer Pocket Multimodal Model with 5% Parameters and 90% Performance

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T19:45:52.913989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff800481-a222-45c8-80db-7d4383db1b2e · outbound

This paper cites Visual program- ming: Compositional visual reasoning without training.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets Visual program- ming: Compositional visual reasoning without training

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T19:45:52.917752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 034cbaee-71a7-48be-bae9-c85b71a30a3a · outbound

This paper cites Sugarcrepe: Fixing hackable benchmarks for vision-language compositionality.Advances in neural information processing systems, 36, 2024.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets Sugarcrepe: Fixing hackable benchmarks for vision-language compositionality.Advances in neural information processing systems, 36, 2024

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:45:53.453433Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 37d2f436-fce2-4aec-9234-3c5a9aa599ab · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets LoRA: Low-Rank Adaptation of Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T19:45:52.925907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 784193e0-7fa7-4c41-970e-390885a53cf6 · outbound

This paper cites Semantic to Structure: Learning Structural Representations for Infringement Detection.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets Semantic to Structure: Learning Structural Representations for Infringement Detection

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T19:45:52.929510Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56f713ab-86a7-4915-b5d1-57a18790bbda · outbound

This paper cites Secret lies in color: Enhancing ai-generated images detection with color distribution anal- ysis.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets Secret lies in color: Enhancing ai-generated images detection with color distribution anal- ysis

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:45:53.441738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d19b3da0-5082-4a78-aa13-25f335ec430d · outbound

This paper cites Elevater: A benchmark and toolkit for evaluating language-augmented visual models.Advances in Neural Information Processing Systems, 35:9287–9301,.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets Elevater: A benchmark and toolkit for evaluating language-augmented visual models.Advances in Neural Information Processing Systems, 35:9287–9301,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T19:45:52.936493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3398b2d4-3be4-426a-a529-90823f509958 · outbound

This paper cites Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T19:45:52.939887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0c50298-4162-40d0-a531-ad5605347184 · outbound

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

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:45:53.415920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8a3fd584-54a8-4495-8687-75df5a833d64 · outbound

This paper cites Vila: On pre-training for vi- sual language models.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets Vila: On pre-training for vi- sual language models

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:45:53.403872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e46b6ba9-fbad-431f-a29a-0b7d99b39aa6 · outbound

This paper cites Visual instruction tuning.Advances in neural information processing systems, 36, 2024.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets Visual instruction tuning.Advances in neural information processing systems, 36, 2024

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:45:53.392740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2280f4f3-b2b0-4be1-838b-7c667339728c · outbound

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

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T19:45:52.956170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c1b60e1-3386-462d-a2d7-9aa857a4ddf5 · outbound

This paper cites Synthesize diagnose and optimize: Towards fine- grained vision-language understanding.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets Synthesize diagnose and optimize: Towards fine- grained vision-language understanding

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:45:53.381845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d93327d3-3d0c-4963-85bc-6477f84f3fa1 · outbound

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

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T19:45:52.963677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66df1fac-28a3-490d-ab5e-9321e882a381 · outbound

This paper cites Learning transferable visual models from natural language supervi- sion.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets Learning transferable visual models from natural language supervi- sion

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:45:53.370750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5f425da8-9735-4cc6-9291-eed2103a7e35 · outbound

This paper cites LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T19:45:52.971449Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4bcd0cc-39f7-4c3a-9b0d-7c18cb48a168 · outbound

This paper cites Flava: A foundational language and vision alignment model.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets Flava: A foundational language and vision alignment model

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:45:53.359516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 76d185f6-1d9b-4154-9f2f-b3e45f382573 · outbound

This paper cites Yfcc100m: The new data in multimedia research.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets Yfcc100m: The new data in multimedia research

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:45:53.348027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 82a8c44b-5adc-4a9c-babc-da6136a43e44 · outbound

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

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets Winoground: Probing vision and language models for visio- linguistic compositionality

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:45:53.336292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d6a37b8d-b988-4cf3-8ecc-a2c11124e0e8 · outbound

This paper cites A picture is worth more than 77 text tokens: Evaluating clip-style models on dense captions.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets A picture is worth more than 77 text tokens: Evaluating clip-style models on dense captions

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:45:53.322934Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation eefbe169-f499-4469-9781-0b24b3d440ee · outbound

This paper cites xgen-mm (blip-3): A family of open large multimodal models.arXiv preprint arXiv:2408.08872, 2024.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets xgen-mm (blip-3): A family of open large multimodal models.arXiv preprint arXiv:2408.08872, 2024

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T19:45:52.989662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d2c2618-0cf4-4fb8-a16d-838f722ac5b8 · outbound

This paper cites What you see is what you read? improving text- image alignment evaluation.Advances in Neural Informa- tion Processing Systems, 36, 2024.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets What you see is what you read? improving text- image alignment evaluation.Advances in Neural Informa- tion Processing Systems, 36, 2024

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:45:53.311324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3b220d1b-48cf-46f1-8116-12b54b6a27ea · outbound

This paper cites When and why vision- language models behave like bags-of-words, and what to do about it? InThe Eleventh International Conference on Learning Representations, 2023.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets When and why vision- language models behave like bags-of-words, and what to do about it? InThe Eleventh International Conference on Learning Representations, 2023

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:45:53.299125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ed6d5e29-6cf9-4f0b-bf71-73cdb6b0e7d3 · outbound

This paper cites Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T19:45:53.000363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b14da76-f3fe-4ef7-9011-0ab3907d6449 · outbound

This paper cites Investigating compositional chal- lenges in vision-language models for visual grounding.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets Investigating compositional chal- lenges in vision-language models for visual grounding

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:45:53.287164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6bec6939-e9bd-4efe-a87d-d4f9fac82942 · outbound

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

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets Sigmoid loss for language image pre-training

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:45:53.274342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b54f18df-cf1d-496b-8186-365b28cf9c0a · outbound

This paper cites VL-CheckList: Evaluating Pre-trained Vision-Language Models with Objects, Attributes and Relations.

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets VL-CheckList: Evaluating Pre-trained Vision-Language Models with Objects, Attributes and Relations

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T19:45:53.011960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6faa031f-bd95-4ea0-9866-de705e61db24 · outbound

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

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T19:45:53.015838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers