H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning | Paper Citation Record

Observation 02b8d00c-4f93-4420-83ac-e36dd654eddb · outbound

This paper cites Don’t just assume; look and answer: Overcoming priors for visual question answering.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Don’t just assume; look and answer: Overcoming priors for visual question answering

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2005225-0a92-4941-b183-d69a499f2df9 · outbound

This paper cites Neural module networks.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Neural module networks

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee40dcdc-5370-4c95-a3d8-967bd50e467a · outbound

This paper cites Vqa: Visual question answering.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Vqa: Visual question answering

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 304897c1-bffe-4823-93be-ce55427eff1c · outbound

This paper cites Qwen2.5-VL Technical Report.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Qwen2.5-VL Technical Report

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:14:22.073999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d7f7db7e-3c3f-49a4-9b6e-ff5569249d74 · outbound

This paper cites SAM 3: Segment Anything with Concepts.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning SAM 3: Segment Anything with Concepts

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-06-30T06:24:19.583033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 27fd4ac7-7e01-4009-a5d2-eb51a41c2ce3 · outbound

This paper cites Are we on the right way for evaluating large vision-language models?Advances in Neural Information Processing Systems, 37:27056–27087, 2024.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Are we on the right way for evaluating large vision-language models?Advances in Neural Information Processing Systems, 37:27056–27087, 2024

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 381137bd-9993-4a30-837d-a17fd62a0a69 · outbound

This paper cites Beyond question-based biases: Assessing multimodal shortcut learning in visual question answering.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Beyond question-based biases: Assessing multimodal shortcut learning in visual question answering

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 567c85f0-f740-458e-9cdb-ab0859677745 · outbound

This paper cites Gemini 3 flash: High-efficiency agentic multimodal understanding.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Gemini 3 flash: High-efficiency agentic multimodal understanding

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 681706ef-c37d-430e-a621-b8633a67aebd · outbound

This paper cites Deepseek-r1 incentivizes reasoning in llms through reinforcement learning.Nature, 645(8081):633–638, 2025.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Deepseek-r1 incentivizes reasoning in llms through reinforcement learning.Nature, 645(8081):633–638, 2025

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a41934e7-2ede-4f66-a00b-f76a93870f80 · outbound

This paper cites Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:14:22.071060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9cb8e320-72d3-4e2f-9a86-0ee4dd2e9462 · outbound

This paper cites Hudson and Christopher D.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Hudson and Christopher D

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8a852af-ba1f-4046-b480-da8f5a67508c · outbound

This paper cites GPT-4o System Card.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning GPT-4o System Card

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-06-30T06:24:19.584388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cee35312-3f35-48a6-b8d7-35a4c954a5f3 · outbound

This paper cites Raven progressive matrices.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Raven progressive matrices

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77debea3-3348-4396-bc2c-d0d78d85c398 · outbound

This paper cites Clevr: A diagnostic dataset for compositional language and elementary visual reasoning.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Clevr: A diagnostic dataset for compositional language and elementary visual reasoning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc695b8e-3edf-47f5-b018-e49f0a68ec03 · outbound

This paper cites Visual genome: Connecting language and vision using crowdsourced dense image annotations.International journal of computer vision, 123(1):32–73, 2017.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Visual genome: Connecting language and vision using crowdsourced dense image annotations.International journal of computer vision, 123(1):32–73, 2017

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c59b158b-a7c3-4a51-b698-9e6950b63d02 · outbound

This paper cites Imore: Implicit program-guided reasoning for human motion q&a.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Imore: Implicit program-guided reasoning for human motion q&a

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68e336e7-f3a2-4420-ac31-b599f80d5a74 · outbound

This paper cites Vision-sr1: Self-rewarding vision-language model via reasoning decomposition and multi-reward policy optimization.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Vision-sr1: Self-rewarding vision-language model via reasoning decomposition and multi-reward policy optimization

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fccf2cf1-8ace-4b76-a479-ee35882b6513 · outbound

This paper cites Visual-rft: Visual reinforcement fine-tuning.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Visual-rft: Visual reinforcement fine-tuning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca8cded6-2d71-4a6c-8461-950e1b81a47f · outbound

This paper cites Learn to explain: Multimodal reasoning via thought chains for science question answering.Advances in neural information processing systems, 35:2507–2521, 2022.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Learn to explain: Multimodal reasoning via thought chains for science question answering.Advances in neural information processing systems, 35:2507–2521, 2022

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bfd8663-6812-4d8c-a8e8-ff796bca7233 · outbound

This paper cites Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08a5f508-d2ce-4c02-bce3-ef8ce740177d · outbound

This paper cites A computational investigation into the human representation and processing of visual information.WH San Francisco: Freeman and Company, San Francisco, 1(1):4, 1982.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning A computational investigation into the human representation and processing of visual information.WH San Francisco: Freeman and Company, San Francisco, 1(1):4, 1982

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33942dd2-30ed-426a-acdc-5777d7bab885 · outbound

This paper cites SmolVLM: Redefining small and efficient multimodal models.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning SmolVLM: Redefining small and efficient multimodal models

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-06-30T06:24:19.588487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1f35ee56-26f9-4737-8384-360dc2ed56b0 · outbound

This paper cites Ok-vqa: A visual question answering benchmark requiring external knowledge.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Ok-vqa: A visual question answering benchmark requiring external knowledge

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59f4b493-5f3e-45a1-9c08-676339e7dbae · outbound

This paper cites Pkr-qa: A benchmark for procedural knowledge reasoning with knowledge module learning.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Pkr-qa: A benchmark for procedural knowledge reasoning with knowledge module learning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf751ef3-1174-4d11-b2c2-3d524abe4764 · outbound

This paper cites an unresolved cited work.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Unresolved cited work

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccbc4a4e-de5e-42a3-a945-99785e6dda8b · outbound

This paper cites Grounding multimodal large language models to the world.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Grounding multimodal large language models to the world

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e974d39-0d41-4161-a197-8def928049a4 · outbound

This paper cites Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-06-30T06:24:19.585935Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 96d199c0-0ddf-41ce-be50-f39ca01f802b · outbound

This paper cites Sentence-bert: Sentence embeddings using siamese bert-networks.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Sentence-bert: Sentence embeddings using siamese bert-networks

Reference 28

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6c63f4b-5c70-4a23-962e-6d5d7467de5c · outbound

This paper cites an unresolved cited work.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8ad17e8-4c85-44a1-bf44-cc49afe30d08 · outbound

This paper cites Grounded reinforcement learning for visual reasoning.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Grounded reinforcement learning for visual reasoning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 324d5f17-1452-403d-810d-b9ed2a1b16ee · outbound

This paper cites A-okvqa: A benchmark for visual question answering using world knowledge.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning A-okvqa: A benchmark for visual question answering using world knowledge

Reference 31

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a146134-7fb7-4d46-a9fd-869d1b678983 · outbound

This paper cites an unresolved cited work.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee428d28-21d9-4781-98d6-00f5aed48bb6 · outbound

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

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-06-30T06:24:19.577448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation beb3ca3b-32e5-4dfb-9342-9ab25c3dc33e · outbound

This paper cites Vlm-r1: A stable and generalizable r1-style large vision-language model.arXiv e-prints, pages arXiv–2504, 2025.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Vlm-r1: A stable and generalizable r1-style large vision-language model.arXiv e-prints, pages arXiv–2504, 2025

Reference 34

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3817647c-3a84-414f-ad02-75b509cb8a2b · outbound

This paper cites Language prior is not the only shortcut: A benchmark for shortcut learning in VQA.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Language prior is not the only shortcut: A benchmark for shortcut learning in VQA

Reference 35

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8492fe8-ccf3-4c5d-babe-8f2ea424a8b6 · outbound

This paper cites Robospatial: Teaching spatial understanding to 2d and 3d vision-language models for robotics.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Robospatial: Teaching spatial understanding to 2d and 3d vision-language models for robotics

Reference 36

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8edf08a1-565c-4f43-8536-fbd4300c7b4f · outbound

This paper cites Aligning large multimodal models with factually augmented rlhf.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Aligning large multimodal models with factually augmented rlhf

Reference 37

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6c2f491-059a-47b0-bc86-75c48693c019 · outbound

This paper cites Reason-rft: Reinforcement fine-tuning for visual reasoning of vision language models.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Reason-rft: Reinforcement fine-tuning for visual reasoning of vision language models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df0e8031-8d0b-4862-becf-f94c559ca7b0 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Gemini: A Family of Highly Capable Multimodal Models

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-06-30T06:24:19.592194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d76f3881-784c-40ee-96e9-31edee27a189 · outbound

This paper cites Gemini Robotics: Bringing AI into the Physical World.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Gemini Robotics: Bringing AI into the Physical World

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-06-30T06:24:19.581646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4ef73406-d8cf-452a-bf48-4a59a9975570 · outbound

This paper cites Qwen3.5-Omni Technical Report.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Qwen3.5-Omni Technical Report

Reference 41

Resolution: verified exact; local_arxiv, observed 2026-06-30T06:24:19.590819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9f84fce8-0f5a-44ee-a14e-82980fd649b9 · outbound

This paper cites Vl-rethinker: Incentivizing self-reflection of vision-language models with reinforcement learning.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Vl-rethinker: Incentivizing self-reflection of vision-language models with reinforcement learning

Reference 42

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1bc2cc3-8b94-4cda-897f-1267bc9e62b6 · outbound

This paper cites Procedures as a representation for data in a computer program for understanding natural language.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Procedures as a representation for data in a computer program for understanding natural language

Reference 43

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a06c8446-a93e-497e-abd8-c75bdbe0a6fa · outbound

This paper cites Learning structural descriptions from examples.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Learning structural descriptions from examples

Reference 44

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4642844-0455-4f73-8e94-04cae7b4956a · outbound

This paper cites STAR: A Benchmark for Situated Reasoning in Real-World Videos.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning STAR: A Benchmark for Situated Reasoning in Real-World Videos

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-06-30T06:24:19.569669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5ea1c24a-e558-4ac0-877b-e6af5a798835 · outbound

This paper cites Realworldqa: A benchmark for real-world spatial understanding.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Realworldqa: A benchmark for real-world spatial understanding

Reference 46

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40a64413-d951-4af7-bb72-51832351807d · outbound

This paper cites Next-qa: Next phase of question- answering to explaining temporal actions.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Next-qa: Next phase of question- answering to explaining temporal actions

Reference 47

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad88ec18-9174-4c7f-abe2-bb20bd58f2d1 · outbound

This paper cites Neural- symbolic vqa: Disentangling reasoning from vision and language understanding.Advances in neural information processing systems, 31, 2018.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Neural- symbolic vqa: Disentangling reasoning from vision and language understanding.Advances in neural information processing systems, 31, 2018

Reference 48

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation deaf51d4-4060-4d61-b0d3-0f4199430f68 · outbound

This paper cites Rlhf-v: Towards trustworthy mllms via behavior alignment from fine-grained correctional human feedback.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Rlhf-v: Towards trustworthy mllms via behavior alignment from fine-grained correctional human feedback

Reference 49

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fa4283e-d302-4393-83fb-ed25a5e22a12 · outbound

This paper cites Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi

Reference 50

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25ac8f50-9b0e-4b04-aeef-587f5588266e · outbound

This paper cites Raven: A dataset for relational and analogical visual reasoning.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Raven: A dataset for relational and analogical visual reasoning

Reference 51

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d838940-73f2-49c8-87ed-0113bd0f5b32 · outbound

This paper cites Mitigating Easy Option Bias in Multiple-Choice Question Answering.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Mitigating Easy Option Bias in Multiple-Choice Question Answering

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-06-30T06:24:19.587769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 00e4f341-87a6-4d92-97a7-6bf27303ca4a · outbound

This paper cites R1-vl: Learning to reason with multimodal large language models via step-wise group relative policy optimization.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning R1-vl: Learning to reason with multimodal large language models via step-wise group relative policy optimization

Reference 53

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1df64fe7-114f-4e9d-97c2-1dd1c9a1d1e2 · outbound

This paper cites Physreason: A comprehensive benchmark towards physics-based reasoning.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Physreason: A comprehensive benchmark towards physics-based reasoning

Reference 54

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87f9e699-cdf2-4b17-80b9-ca1a51bfb1f1 · outbound

This paper cites Multimodal chain-of-thought reasoning in language models.Transactions on Machine Learning Research, 2024, 2024.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Multimodal chain-of-thought reasoning in language models.Transactions on Machine Learning Research, 2024, 2024

Reference 55

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb99c87c-ba04-4766-b386-b18c03a4e5dc · outbound

This paper cites Visual7w: Grounded question answering in images.

H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning Visual7w: Grounded question answering in images

Reference 56

Resolution: unresolved; no resolver link, observed 2026-06-30T06:16:51.452335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers