RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension | Paper Citation Record

Observation da3a10ce-0c00-41d9-9d98-3bd16ecac0bc · outbound

This paper cites Flamingo: a visual language model for few-shot learning.NeurIPS, 35: 23716–23736, 2022.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Flamingo: a visual language model for few-shot learning.NeurIPS, 35: 23716–23736, 2022

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:04.539569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ac081a8-7e28-4f8c-bf34-9c7875622ae9 · outbound

This paper cites LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:04.579056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 967822dd-61a2-4198-9923-dc5f5a705185 · outbound

This paper cites Qwen3-VL Technical Report.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Qwen3-VL Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:04.635320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf67dab3-b5cb-428a-89e3-45a7a8e5868f · outbound

This paper cites Qwen2.5-VL Technical Report.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Qwen2.5-VL Technical Report

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:04.693023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f24a486f-9919-4c6f-9c83-b659c5184936 · outbound

This paper cites UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:04.760809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4432b674-c5e6-4f3b-8cd3-af77f1dad750 · outbound

This paper cites Revisiting referring expression comprehension eval- uation in the era of large multimodal models.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Revisiting referring expression comprehension eval- uation in the era of large multimodal models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:04.818019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d9db02b-185a-4933-8366-79daa45afdce · outbound

This paper cites Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:04.895286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b8fed1a-db9e-4431-99f9-2085bc73bb16 · outbound

This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:04.999810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78ef50aa-7bb2-4199-bf2e-a4359ee1dfa4 · outbound

This paper cites Molmo and pixmo: Open weights and open data for state-of-the-art multimodal models.arXiv e-prints, pages arXiv–2409, 2024.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Molmo and pixmo: Open weights and open data for state-of-the-art multimodal models.arXiv e-prints, pages arXiv–2409, 2024

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:05.037620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3945e791-9831-4f40-aeb9-39e4a7ffbf6a · outbound

This paper cites GREC: Generalized Referring Expression Comprehension.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension GREC: Generalized Referring Expression Comprehension

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:05.093422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c0a1b47-97c7-49b6-aa46-3b38fbb24aeb · outbound

This paper cites GPT-4o System Card.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension GPT-4o System Card

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:05.144797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21bcd62c-d96f-4fc7-a957-29b10de5adb9 · outbound

This paper cites ChatRex: Taming Multimodal LLM for Joint Perception and Understanding.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension ChatRex: Taming Multimodal LLM for Joint Perception and Understanding

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:05.207146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 681d3c20-3ae6-471f-993a-9a2a81638482 · outbound

This paper cites Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:05.261966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 731f7b62-d644-49a6-9fc5-c6e0bae9b1d1 · outbound

This paper cites Referring to Any Person.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Referring to Any Person

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:05.304394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db7e48df-b46e-4f64-bfdf-b05045bf3f46 · outbound

This paper cites Referitgame: Referring to objects in pho- tographs of natural scenes.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Referitgame: Referring to objects in pho- tographs of natural scenes

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:05.368756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3603a2e-65cf-45c4-8f50-e6e53fa82e62 · outbound

This paper cites LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:05.459491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63fd2520-a011-4839-b7eb-25fdabc0b8cb · outbound

This paper cites Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:05.561502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9838a444-74c6-4038-9c95-699c7b9eb291 · outbound

This paper cites Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Models.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:05.687979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10e38b7f-9bbb-4f7b-8d35-e8a5196e304c · outbound

This paper cites Microsoft coco: Common objects in context.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Microsoft coco: Common objects in context

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:05.753276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bdff3cf-8f46-4932-b4a7-efc5fd55bbdc · outbound

This paper cites Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:05.829843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecb8f732-52e8-46c7-aa42-0f369074d339 · outbound

This paper cites FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:05.876710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3744472-e751-4988-81d6-484f0af9c3e6 · outbound

This paper cites Grounding dino: Marrying dino with grounded pre-training for open-set object detection.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Grounding dino: Marrying dino with grounded pre-training for open-set object detection

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:05.928558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61ee1c29-9b90-442f-8d90-54e4bd3ce969 · outbound

This paper cites Visual-RFT: Visual Reinforcement Fine-Tuning.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Visual-RFT: Visual Reinforcement Fine-Tuning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:06.001283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d081467a-fba5-47ed-8fed-6128430195bb · outbound

This paper cites Ovis: Structural Embedding Alignment for Multimodal Large Language Model.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Ovis: Structural Embedding Alignment for Multimodal Large Language Model

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:06.083870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f99a459e-4aaf-4b83-95b3-b768bf4252aa · outbound

This paper cites Ovis2.5 Technical Report.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Ovis2.5 Technical Report

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:06.151054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 402deff4-801e-4ee6-91ed-d8bc3fdcabcc · outbound

This paper cites Multi-task collabora- tive network for joint referring expression comprehension and segmentation.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Multi-task collabora- tive network for joint referring expression comprehension and segmentation

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:06.211228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a3c09eb-8af5-4315-b4ac-7e70bc71651c · outbound

This paper cites Groma: Localized visual tokenization for grounding multimodal large language models.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Groma: Localized visual tokenization for grounding multimodal large language models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:06.257337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70e0be89-3c71-40ce-ada3-b967ab81f5c2 · outbound

This paper cites Generation and comprehension of unambiguous object descriptions.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Generation and comprehension of unambiguous object descriptions

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:06.316009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0f64d39-28e0-4eb7-bc2c-991d0754030b · outbound

This paper cites Generation and comprehension of unambiguous object descriptions.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Generation and comprehension of unambiguous object descriptions

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:06.430995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f3d6205-ec34-4f98-bc2e-16293ae0aac1 · outbound

This paper cites Gpt-4v(ision) system card.https://cdn.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Gpt-4v(ision) system card.https://cdn

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:06.490275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8f49206-0282-4865-84ca-bbbb87e053f2 · outbound

This paper cites Gpt-5 system card.https://cdn.openai.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Gpt-5 system card.https://cdn.openai

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:06.546252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65a78f74-539f-4987-9c7f-731bc1de8bd8 · outbound

This paper cites Referring ex- pression comprehension: A survey of methods and datasets.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Referring ex- pression comprehension: A survey of methods and datasets

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:06.662874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9dfdd7a3-e0de-4829-8d46-949032369237 · outbound

This paper cites Visual cot: Unleashing chain-of-thought reasoning in multi-modal language models.CoRR, 2024.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Visual cot: Unleashing chain-of-thought reasoning in multi-modal language models.CoRR, 2024

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:06.774752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 576bdeb4-f9b7-4bf8-b7f6-5f07d1c93721 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:06.876514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1296e17-1939-44a6-8446-7d675f11bdad · outbound

This paper cites VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:06.983726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6a80eed-482d-4ae2-84cc-0d40b7fb4b12 · outbound

This paper cites Patch-as-decodable-token: Towards uni- fied multi-modal vision tasks in mllms.arXiv preprint arXiv:2510.01954, 2025.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Patch-as-decodable-token: Towards uni- fied multi-modal vision tasks in mllms.arXiv preprint arXiv:2510.01954, 2025

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:07.060034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b4a338a-fb29-4a97-9e22-fac40314b0b3 · outbound

This paper cites Glm-4.5v and glm-4.1v-thinking: Towards versatile multi- modal reasoning with scalable reinforcement learning, 2025.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Glm-4.5v and glm-4.1v-thinking: Towards versatile multi- modal reasoning with scalable reinforcement learning, 2025

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:07.259707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3db9db6f-fcf0-4c3e-880a-67a7059bf4f5 · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:07.458967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ccea993-3747-459f-8f58-8bd87257ca8d · outbound

This paper cites Cogvlm: Visual expert for pretrained language models.Advances in Neural Information Processing Sys- tems, 37:121475–121499, 2024.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Cogvlm: Visual expert for pretrained language models.Advances in Neural Information Processing Sys- tems, 37:121475–121499, 2024

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:07.601795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da076246-6d8d-4668-bfce-913e2385243b · outbound

This paper cites InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:07.683207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 729569c2-b377-4281-b81b-4f524fefe190 · outbound

This paper cites General object foundation model for images and videos at scale.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension General object foundation model for images and videos at scale

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:07.787595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d93ed22-5206-4c68-a1ce-0505f0e0f35e · outbound

This paper cites DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:07.837162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db9bcf32-653c-4f92-a650-2d55ad2f5251 · outbound

This paper cites MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:07.935450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74f776f6-90cd-48e2-86b5-fdc20ff0c53a · outbound

This paper cites FG-CLIP: Fine-grained visual and textual alignment.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension FG-CLIP: Fine-grained visual and textual alignment

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:08.030855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2dd413a9-b3c8-492c-8eac-b7f26b238764 · outbound

This paper cites Perception-R1: Pioneering Perception Policy with Reinforcement Learning.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Perception-R1: Pioneering Perception Policy with Reinforcement Learning

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:08.183639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1bce0ce-06fb-40a6-a8ac-362c4126733b · outbound

This paper cites Modeling context in referring expres- sions.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Modeling context in referring expres- sions

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:08.325970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b00f6ce-5600-4dd7-999f-6f8b1b032c79 · outbound

This paper cites Modeling context in referring expres- sions.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Modeling context in referring expres- sions

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:08.404859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69e15d4d-0cf5-44f3-a7dd-28377eee06ed · outbound

This paper cites Revisiting counterfactual prob- lems in referring expression comprehension.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Revisiting counterfactual prob- lems in referring expression comprehension

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:08.514856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b08e51da-35fe-47f9-8f01-f04124ecdad7 · outbound

This paper cites Referring expression comprehension with semantic visual relationship and word mapping.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Referring expression comprehension with semantic visual relationship and word mapping

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:08.637873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81826f37-eb77-4845-9ef3-01f6a68d07a8 · outbound

This paper cites MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:08.771844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fc71d84-4992-4e43-ac5e-d1b650761d0a · outbound

This paper cites Towards Unifying Reference Expression Generation and Comprehension.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Towards Unifying Reference Expression Generation and Comprehension

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:08.894756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e41f54f7-240d-482c-b270-6870ee617ea7 · outbound

This paper cites InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:08.960506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fb223f4-bf55-4590-a199-7f87fab54bbb · outbound

This paper cites an unresolved cited work.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Unresolved cited work

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:09.052966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8ea21a0-2dee-4786-a61f-ce9642f5adc9 · outbound

This paper cites We filtered the images based on their resolution, retaining only those within the range of 1024x1024 to 2048x2048 pixels.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension We filtered the images based on their resolution, retaining only those within the range of 1024x1024 to 2048x2048 pixels

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:09.163085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a106fe0a-25e5-4c9c-9802-0fac829d2afb · outbound

This paper cites The improve- ments are most pronounced in Compositional Reasoning, especially within the Relation sub-category.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension The improve- ments are most pronounced in Compositional Reasoning, especially within the Relation sub-category

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:09.279542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96c0b0bf-4123-4843-bae8-cc54859bf5b7 · outbound

This paper cites These fig- ures provide a visual comparison of several representative models across challenging examples from all six categories.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension These fig- ures provide a visual comparison of several representative models across challenging examples from all six categories

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:09.349920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2859ab34-9466-434b-b8bd-1486a9a53c2e · outbound

This paper cites Assign a clear and concise class label to each object (e.g., 'person', 'laptop', 'coffee mug', 'dog').

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Assign a clear and concise class label to each object (e.g., 'person', 'laptop', 'coffee mug', 'dog')

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:09.425170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b8032cb-9060-45fc-8df1-7153f10f2f0f · outbound

This paper cites Each instance requires its own property dictionary.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Each instance requires its own property dictionary

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:09.505935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7f42b7d-661b-4196-91ce-c0d280ed4473 · outbound

This paper cites Populate this object with all observable visual properties.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension Populate this object with all observable visual properties

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:09.567300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c28d9f9f-0d1f-481e-9069-a7098eb5704a · outbound

This paper cites to the left of the monitor.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension to the left of the monitor

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:09.636249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b4d2d47-3db9-4cb0-9e7d-7d8426063bf7 · outbound

This paper cites a white ceramic mug filled with dark coffee.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension a white ceramic mug filled with dark coffee

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:09.715916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37078029-0070-4c8d-a347-1af69d0f174c · outbound

This paper cites scene_properties.

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension scene_properties

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-03T18:15:09.777799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers