Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models | Paper Citation Record

Observation a205b59b-d940-44ec-b20b-b1ce05113763 · outbound

This paper cites GPT-4 Technical Report.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:42.783123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b68f802-f117-4d20-9c57-9b2f6fc45502 · outbound

This paper cites Qwen Technical Report.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Qwen Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:42.873209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc5380aa-495b-403f-b824-c951af462fd2 · outbound

This paper cites Qwen2.5-VL Technical Report.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Qwen2.5-VL Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:42.957030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a354a0fe-2f23-4469-9fb5-6d57164bfc21 · outbound

This paper cites MapQA: A Dataset for Question Answering on Choropleth Maps.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models MapQA: A Dataset for Question Answering on Choropleth Maps

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:43.047242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ba50aa3-3999-460d-a51b-f97816fe33cf · outbound

This paper cites ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Models.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:43.118516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c960d2c9-ada4-4dc6-b172-2fc19031cb0f · outbound

This paper cites UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expression.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expression

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:43.218009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4615098-7cfd-4dfc-abb7-03ccc8f23df0 · outbound

This paper cites GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:43.332355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 910e8922-4bdd-4d7c-95a5-cd450e5e09d3 · outbound

This paper cites R1-v: Reinforcing super generalization ability in vision-language models with less than $3.https://github.com/Deep-Agent/R1-V, 2025.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models R1-v: Reinforcing super generalization ability in vision-language models with less than $3.https://github.com/Deep-Agent/R1-V, 2025

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:37:56.305112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ad424351-a347-45cf-9118-0edb67921a5c · outbound

This paper cites Are We on the Right Way for Evaluating Large Vision-Language Models?.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Are We on the Right Way for Evaluating Large Vision-Language Models?

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:43.536170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82dd815f-cc4c-4aac-a85e-a3dd84af6992 · outbound

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

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:43.644290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1e9d65b-6059-4ad6-be0b-c45f35d4a376 · outbound

This paper cites Gonzalez, Ion Stoica, and Eric P.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Gonzalez, Ion Stoica, and Eric P

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:37:56.125085Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3531540a-cfb7-48ce-8f1b-fe894f167470 · outbound

This paper cites Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning, 2025.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning, 2025

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:37:55.949527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 271734de-2d98-44a3-b87c-25be0653fdd4 · outbound

This paper cites Patch n’pack: Navit, a vision transformer for any aspect ratio and resolution.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Patch n’pack: Navit, a vision transformer for any aspect ratio and resolution

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:37:55.748517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d29e0a8c-db58-4aaa-aa98-07b0f9a8dac0 · outbound

This paper cites Bert: Pre-training of deep bidirec- tional transformers for language understanding.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Bert: Pre-training of deep bidirec- tional transformers for language understanding

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:37:55.599809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1b27fa32-f58d-4a23-b944-4dd3a2c638d1 · outbound

This paper cites On Path to Multimodal Generalist: General-Level and General-Bench.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models On Path to Multimodal Generalist: General-Level and General-Bench

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:43.985549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa40b409-6c78-442b-84d4-fc1701f09a5a · outbound

This paper cites Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:44.072119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d9e2b31-4beb-472a-9052-bcc9a9d5f27c · outbound

This paper cites VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:44.110624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 701d8e6c-81b1-4d7a-85e4-20d51bce3fd2 · outbound

This paper cites Cantor: Inspiring multimodal chain-of-thought of mllm.ACM MM, 2024.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Cantor: Inspiring multimodal chain-of-thought of mllm.ACM MM, 2024

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:37:55.458081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ba33b5e7-45dd-4ffc-b33e-d25f34b1d1ed · outbound

This paper cites Hallusionbench: an advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Hallusionbench: an advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:37:55.289867Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0812ec8e-1fea-492a-9148-2110ca2e4d0d · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:44.393355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9848067d-40d2-44bd-a3a3-aac8c40b6c7f · outbound

This paper cites Free Video-LLM: Prompt-guided Visual Perception for Efficient Training-free Video LLMs.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Free Video-LLM: Prompt-guided Visual Perception for Efficient Training-free Video LLMs

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:44.473998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fa536d7-b889-42b8-afff-03f25b2f2e80 · outbound

This paper cites GPT-4o System Card.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models GPT-4o System Card

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:44.516429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1dc0482-7b39-4693-b682-578cc52782db · outbound

This paper cites Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:44.565913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 045da288-d805-43d5-872b-449c83ab6d74 · outbound

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

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Clevr: A diagnostic dataset for compositional language and elementary visual reasoning

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:37:55.115246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bacc674a-5048-48a6-8529-75e556c96760 · outbound

This paper cites FigureQA: An Annotated Figure Dataset for Visual Reasoning.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models FigureQA: An Annotated Figure Dataset for Visual Reasoning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:44.703110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0140bf2a-a5ea-4d8a-a649-d9bf3e65de77 · outbound

This paper cites A diagram is worth a dozen images.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models A diagram is worth a dozen images

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:37:54.951630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 080d880f-5ecb-4032-a0cc-3c6fb3a37e2f · outbound

This paper cites LLaVA-OneVision: Easy Visual Task Transfer.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models LLaVA-OneVision: Easy Visual Task Transfer

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:44.784518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb4f7a2e-b358-47af-b11e-7b046b6e82c5 · outbound

This paper cites SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:44.857093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ab70df7-2694-4d02-9eac-22b516c053c1 · outbound

This paper cites Mvbench: A comprehensive multi-modal video understanding benchmark.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Mvbench: A comprehensive multi-modal video understanding benchmark

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:37:54.794908Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 059e7857-0160-4348-a977-ab5a86d5b89e · outbound

This paper cites VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:44.976247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 311990ad-275b-4c1d-943d-b49c5c529f35 · outbound

This paper cites DeepSeek-V3 Technical Report.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models DeepSeek-V3 Technical Report

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:45.063410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3d474fd-64fa-4b36-b4b2-e8e5f73f7bed · outbound

This paper cites Visual spatial reasoning.TACL, 2023.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Visual spatial reasoning.TACL, 2023

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:37:54.625675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f8a42cc8-70a8-4716-91f5-9b8cd2cf7515 · outbound

This paper cites Improved baselines with visual instruction tuning.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Improved baselines with visual instruction tuning

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:37:54.441783Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 848b80bc-c73f-4377-93be-7c36b161b31b · outbound

This paper cites Visual instruction tuning.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Visual instruction tuning

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:45.234152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f937c7b9-8cfc-4f61-9ad7-50ae0c9f615b · outbound

This paper cites Mmbench: Is your multi-modal model an all-around player? In ECCV, 2024.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Mmbench: Is your multi-modal model an all-around player? In ECCV, 2024

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:37:54.262844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation aec24713-eebd-41a3-a6c3-f838f33c3b54 · outbound

This paper cites Ocrbench: on the hidden mystery of ocr in large multimodal models.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Ocrbench: on the hidden mystery of ocr in large multimodal models

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:37:54.130873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 49741e44-f24e-421a-9897-31100a89f9e4 · outbound

This paper cites DeepSeek-VL: Towards Real-World Vision-Language Understanding.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models DeepSeek-VL: Towards Real-World Vision-Language Understanding

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:45.787946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14856869-d85c-4176-9161-29c064ad3d38 · outbound

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

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:37:53.983355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6a495537-6ea1-4de9-9765-6701e7bbcf4e · outbound

This paper cites Learn to explain: Multimodal reasoning via thought chains for science question answering.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Learn to explain: Multimodal reasoning via thought chains for science question answering

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:37:53.808532Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4a02b294-cac4-4826-b864-84262d5b913c · outbound

This paper cites Cheap and quick: Efficient vision-language instruction tuning for large language models.NeurIPS, 2023.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Cheap and quick: Efficient vision-language instruction tuning for large language models.NeurIPS, 2023

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:37:53.634049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7d0232be-36ae-4f25-a436-a166fe6a183e · outbound

This paper cites Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:46.509499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90b0c37c-04c1-4dc9-93d3-0e3233b263b0 · outbound

This paper cites Video-rag: Visually-aligned retrieval-augmented long video comprehension.arXiv preprint arXiv:2411.13093, 2024.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Video-rag: Visually-aligned retrieval-augmented long video comprehension.arXiv preprint arXiv:2411.13093, 2024

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:46.617047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a972f16f-ab27-413d-8770-72947fbea608 · outbound

This paper cites MLLM-Selector: Necessity and Diversity-driven High-Value Data Selection for Enhanced Visual Instruction Tuning.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models MLLM-Selector: Necessity and Diversity-driven High-Value Data Selection for Enhanced Visual Instruction Tuning

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:46.790491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db05e5a2-683a-422b-9098-eb214b87e391 · outbound

This paper cites Generation and comprehension of unambiguous object descriptions.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Generation and comprehension of unambiguous object descriptions

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:37:53.474140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6aa570e5-7757-4a4d-9507-a2c62a29d32a · outbound

This paper cites ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:47.054610Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation feb65134-920d-4bf9-8fbb-cd50e46492e0 · outbound

This paper cites Infographicvqa.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Infographicvqa

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:37:53.318799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation eb606e72-c086-4dac-bfbc-73847b3c9101 · outbound

This paper cites Docvqa: A dataset for vqa on document images.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Docvqa: A dataset for vqa on document images

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:37:53.165749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a7e68bb9-1055-4b61-88d0-f5951e67213b · outbound

This paper cites MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:47.537408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d097eab-a669-4ed7-9c41-8431050b7f92 · outbound

This paper cites Training language models to follow instructions with human feedback.NeurIPS, 2022.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Training language models to follow instructions with human feedback.NeurIPS, 2022

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:37:52.920910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e11f3118-abc1-47d5-8ca4-0dd272df0855 · outbound

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

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Learning transferable visual models from natural language supervision

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:47.865340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0ff8c5d-9f1b-41e6-911a-855075ae6886 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.NeurIPS, 2023.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Direct preference optimization: Your language model is secretly a reward model.NeurIPS, 2023

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:37:52.695218Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 879f13ae-d0b9-4b5c-a844-38f843aaf72a · outbound

This paper cites Eve: Efficient Multimodal Vision Language Models with Elastic Visual Experts.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Eve: Efficient Multimodal Vision Language Models with Elastic Visual Experts

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:48.199482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 791d5a95-3c79-490a-b88c-e20176d1b599 · outbound

This paper cites Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:48.318387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8abd1ea-e136-48d5-a244-bb3c22e22062 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Proximal Policy Optimization Algorithms

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:48.437328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0afd5ec-f21b-4d35-8aca-16b8b8b998d0 · outbound

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

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:48.531778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75ff2723-9024-4e4a-883d-f23746d7593b · outbound

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

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:48.622594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2323e1fd-fc9b-4b47-9264-b649af1f9014 · outbound

This paper cites Long-vita: Scaling large multi-modal models to 1 million tokens with leading short-context accuray.arXiv preprint arXiv:2502.05177, 2025.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Long-vita: Scaling large multi-modal models to 1 million tokens with leading short-context accuray.arXiv preprint arXiv:2502.05177, 2025

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:48.691734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 020874f4-2c31-4234-a8ee-10e3083fa6cc · outbound

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

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Gemini: A Family of Highly Capable Multimodal Models

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:48.782938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13ea1e57-dedf-46a7-90b6-3388db6d6b98 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models LLaMA: Open and Efficient Foundation Language Models

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:48.877517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61cfd93d-8772-489c-9a56-e7c2efee99cf · outbound

This paper cites Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:48.974699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e22b9b99-6fa5-4feb-9213-419fb69ecb85 · outbound

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

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:49.073537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc7baed4-4b75-4a71-ad43-1f2c7c87d3b2 · outbound

This paper cites Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:49.199326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b330a79-d238-4eb8-889c-aa84aefb3fce · outbound

This paper cites Qwen2.5-1M Technical Report.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Qwen2.5-1M Technical Report

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:49.263799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9297dae2-6215-44be-8af7-ec6c6cb9706f · outbound

This paper cites R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:49.357574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 575783b0-dd21-4941-b5eb-464ca8c32aea · outbound

This paper cites MiniCPM-V: A GPT-4V Level MLLM on Your Phone.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models MiniCPM-V: A GPT-4V Level MLLM on Your Phone

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:49.453135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ee38d23-7e1c-47d9-9d2f-37e72a156375 · outbound

This paper cites MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:49.581401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20fefdf2-e833-4a4e-aee3-f6208b8e0f46 · outbound

This paper cites Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:49.696896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7099775a-08ff-495f-82ff-6a60aa94f3bf · outbound

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

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:37:52.485583Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7976af05-89f0-42e2-a8c6-20aa80e3b659 · outbound

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

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Sigmoid loss for language image pre-training

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:37:52.301424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9b77ae93-91de-49b5-8e52-1196ea0c1596 · outbound

This paper cites Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learning.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learning

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:50.037158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb348a27-c885-4a0a-9667-9fb0ed96adda · outbound

This paper cites LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:50.123928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71428098-f6cc-4eec-83ea-f68eedcd226a · outbound

This paper cites Omg-llava: Bridging image-level, object-level, pixel-level reasoning and understanding.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Omg-llava: Bridging image-level, object-level, pixel-level reasoning and understanding

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:37:52.132720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5984fb9c-150c-4bbd-9f4c-cb0289374dcf · outbound

This paper cites Pixel-SAIL: Single Transformer For Pixel-Grounded Understanding.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Pixel-SAIL: Single Transformer For Pixel-Grounded Understanding

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:50.273762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5be7b6d3-807f-4516-908c-2ae4f0eb2d20 · outbound

This paper cites Enhancing multimodal large language models complex reason via similarity computation.AAAI, 2024.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Enhancing multimodal large language models complex reason via similarity computation.AAAI, 2024

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:37:51.942715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3b8c0bd6-739c-4e66-bd74-6d7741264b85 · outbound

This paper cites MultiHiertt: Numerical reasoning over multi hierarchical tabular and textual data.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models MultiHiertt: Numerical reasoning over multi hierarchical tabular and textual data

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:37:51.749703Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 627beefb-2d62-4fc4-9721-e296d26b16a3 · outbound

This paper cites MLVU: Benchmarking Multi-task Long Video Understanding.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models MLVU: Benchmarking Multi-task Long Video Understanding

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:50.564213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1c18b3a-35d8-48a1-9128-c02701f41d19 · outbound

This paper cites Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:50.658662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea093f35-2b5b-40ce-9134-c4dd340489b8 · outbound

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

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:50.749824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9105b61a-f351-4ab7-be17-3628b1c0f762 · outbound

This paper cites Genimage: A million-scale benchmark for detecting ai-generated image.NeurIPS,.

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models Genimage: A million-scale benchmark for detecting ai-generated image.NeurIPS,

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:37:51.554229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers