SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models | Paper Citation Record

Observation 260c7929-66a1-46dc-886a-60cae45f37e9 · outbound

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

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Flamingo: a visual language model for few-shot learning

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.520874Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c7bc843e-ed67-49d5-b2b5-ee1778e69b07 · outbound

This paper cites Self-supervised learning from images with a joint-embedding predictive architecture.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Self-supervised learning from images with a joint-embedding predictive architecture

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.496360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5a27f76a-3d07-4553-94af-98249770fdaa · outbound

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

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-11T13:36:08.779407Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 678f4dde-8fc0-427c-b2fb-f565c4cac325 · outbound

This paper cites Qwen2.5-VL Technical Report.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Qwen2.5-VL Technical Report

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-11T13:36:08.759358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 519e7bb4-19da-4c46-995d-2253a66a0ee4 · outbound

This paper cites Beit: Bert pre-training of image transformers.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Beit: Bert pre-training of image transformers

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.543294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6de91f32-5026-4cbd-9d09-454f11cf5282 · outbound

This paper cites Lan- guage models are few-shot learners.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Lan- guage models are few-shot learners

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.500216Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1ba7cdb8-2fec-4404-a476-cc43c0cc9c8b · outbound

This paper cites Deep clustering for unsupervised learning of visual features.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Deep clustering for unsupervised learning of visual features

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.486793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 29c08d6f-4c75-4f23-8b65-9442b54d5e6e · outbound

This paper cites Unsupervised learn- ing of visual features by contrasting cluster assignments.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Unsupervised learn- ing of visual features by contrasting cluster assignments

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.481372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 893ee7a6-dac2-4328-a9d6-b79e94a853a9 · outbound

This paper cites Emerg- ing properties in self-supervised vision transformers.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Emerg- ing properties in self-supervised vision transformers

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.490749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1fe64c31-31d5-4297-8359-d454c9701b3a · outbound

This paper cites Are we on the right way for evaluating large vision-language models? InNeurIPS.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Are we on the right way for evaluating large vision-language models? InNeurIPS

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.507615Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 00797619-2f47-4ff5-bc5a-1123148b7e87 · outbound

This paper cites Generative pre- training from pixels.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Generative pre- training from pixels

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.373032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation dd787b00-f372-4301-ac3e-37847a5cfde3 · outbound

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

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models A simple framework for contrastive learning of visual representations

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.377078Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f4b18c12-05ee-4ddb-96b9-8a3b0ce58f19 · outbound

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

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Internvl: Scaling up vision foundation mod- els and aligning for generic visual-linguistic tasks

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.405150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation daa06f95-2bab-40aa-872a-89bedc694d43 · outbound

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

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Instructblip: Towards general-purpose vision-language models with instruction tuning

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.398759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0a7e73d1-be31-4e56-ab9b-096a84c2f5be · outbound

This paper cites Bert: Pre-training of deep bidirectional trans- formers for language understanding.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Bert: Pre-training of deep bidirectional trans- formers for language understanding

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.409457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation deb9e839-53b7-4a34-8173-beb01eb4a784 · outbound

This paper cites Unsuper- vised visual representation learning by context prediction.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Unsuper- vised visual representation learning by context prediction

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.469225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b950c390-7cfb-4074-bba5-af510f3531bc · outbound

This paper cites The Llama 3 Herd of Models.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models The Llama 3 Herd of Models

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-11T13:36:08.870137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b5840e98-8e44-4e93-be20-49f813b53cb8 · outbound

This paper cites Sugarcrepe++ dataset: Vision-language model sensitivity to semantic and lexical alterations.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Sugarcrepe++ dataset: Vision-language model sensitivity to semantic and lexical alterations

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.473309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 038b08ac-291e-422f-b352-997195d78f74 · outbound

This paper cites Eva: Exploring the limits of masked visual representa- tion learning at scale.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Eva: Exploring the limits of masked visual representa- tion learning at scale

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.512661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation cfa8c795-34ce-4f2c-8ea6-2b0b928eb6b9 · outbound

This paper cites Un- supervised representation learning by predicting image rota- tions.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Un- supervised representation learning by predicting image rota- tions

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.516466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 88020b11-fa72-4ea7-9fe6-3b6b80d346a8 · outbound

This paper cites Bootstrap your own latent: A new approach to self-supervised learning.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Bootstrap your own latent: A new approach to self-supervised learning

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.539508Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3b772da9-4a27-433f-9759-c0559c37e9f7 · outbound

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

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-05-11T13:36:08.659468Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2f04a502-80b2-4872-8fd8-e9d950ff0a1f · outbound

This paper cites SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-20T00:02:57.484204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ceb19fab-9b3d-4fa7-b481-43a4ba4d7ade · outbound

This paper cites Can mllms reason in multimodality? emma: An enhanced multimodal reasoning benchmark.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Can mllms reason in multimodality? emma: An enhanced multimodal reasoning benchmark

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.460941Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3e3c9789-eb81-4034-b0eb-06be2026dfe4 · outbound

This paper cites Momentum contrast for unsupervised visual rep- resentation learning.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Momentum contrast for unsupervised visual rep- resentation learning

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.457155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 794cfba8-0e6b-476a-9ee8-2df42d097097 · outbound

This paper cites Masked autoencoders are scalable vision learners.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Masked autoencoders are scalable vision learners

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.391003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5c412a58-09fd-4cb3-a362-de815ed439c8 · outbound

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

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-05-11T13:36:08.865648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0ecf6064-e608-47a3-ab62-4b1c0329d284 · outbound

This paper cites OpenAI o1 System Card.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models OpenAI o1 System Card

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-11T13:36:08.792449Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f74776ad-b8d7-4ed0-b424-ff7e276642ea · outbound

This paper cites Omnispatial: Towards comprehensive spatial reasoning benchmark for vision language models.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Omnispatial: Towards comprehensive spatial reasoning benchmark for vision language models

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:36:08.581149Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c9540e78-ff6a-44ec-85e5-7c9ad553a4bb · outbound

This paper cites Lisa: Reasoning segmenta- tion via large language model.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Lisa: Reasoning segmenta- tion via large language model

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.313330Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5479c03e-29b8-4f31-b514-cb40dfc63a56 · outbound

This paper cites Tulu 3: Pushing Frontiers in Open Language Model Post-Training.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Tulu 3: Pushing Frontiers in Open Language Model Post-Training

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-05-11T13:36:08.726255Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation da42ec44-bc0f-4b05-bf6f-be5f1de66c33 · outbound

This paper cites Otter: A Multi-Modal Model with In-Context Instruction Tuning.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Otter: A Multi-Modal Model with In-Context Instruction Tuning

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-15T02:43:48.053680Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 55580ff7-2933-4045-b829-1c30cf8c13e6 · outbound

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

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.317375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 61c047b1-c908-43ea-b229-df68a73628a5 · outbound

This paper cites Correlational image modeling for self-supervised visual pre-training.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Correlational image modeling for self-supervised visual pre-training

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.328458Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 75226c71-ce97-427c-87db-a0944021055f · outbound

This paper cites Improved Visual-Spatial Reasoning via R1-Zero-Like Training.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Improved Visual-Spatial Reasoning via R1-Zero-Like Training

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:36:08.748348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 45b8ad45-8804-4acc-b3b5-d38344be5b35 · outbound

This paper cites Microsoft coco: Common objects in context.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Microsoft coco: Common objects in context

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.362888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 450d6001-2a2b-410b-bb2a-dd023c5bc7b9 · outbound

This paper cites Visual spatial reasoning.TACL.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Visual spatial reasoning.TACL

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.324720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d6b3e8c3-86e2-4ae9-b711-646368e5ae17 · outbound

This paper cites Visual instruction tuning.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Visual instruction tuning

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.335615Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ab6c62c3-027b-4bfe-ad40-ed40e9a94902 · outbound

This paper cites Mmbench: Is your multi-modal model an all-around player? InECCV.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Mmbench: Is your multi-modal model an all-around player? InECCV

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.305499Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 27d1c04d-607c-4cbc-b8a3-76406c449774 · outbound

This paper cites Spatial-ssrl: Enhancing spatial understanding via self-supervised reinforcement learning.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Spatial-ssrl: Enhancing spatial understanding via self-supervised reinforcement learning

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:36:08.828062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2fc0114f-1199-4283-b7cf-ccb76b2ae1c5 · outbound

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

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Visual- rft: Visual reinforcement fine-tuning

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.301849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 809ac577-0d4a-4546-b8e2-90440b037115 · outbound

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

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models DeepSeek-VL: Towards Real-World Vision-Language Understanding

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-05-11T17:58:54.896552Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 27bbc79b-fc4e-4dad-a127-632a143ef0a3 · outbound

This paper cites Mathvista: Evaluating mathemat- ical reasoning of foundation models in visual contexts.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Mathvista: Evaluating mathemat- ical reasoning of foundation models in visual contexts

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.298257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d468757c-1a7d-4194-8c31-c2238b417063 · outbound

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

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:36:08.597995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e60766ee-691e-48d1-8319-6abe0e486a1d · outbound

This paper cites The llama 4 herd: The beginning of a new era of natively multimodal ai innovation.https://ai.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models The llama 4 herd: The beginning of a new era of natively multimodal ai innovation.https://ai

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.290848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e061e1d5-45bb-409c-becc-56d03b8844e8 · outbound

This paper cites Unsupervised learning of visual representations by solving jigsaw puzzles.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Unsupervised learning of visual representations by solving jigsaw puzzles

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.294569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f23922af-7a14-4dbe-92d3-277a2d355292 · outbound

This paper cites GPT-4 Technical Report.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models GPT-4 Technical Report

Reference 47

Resolution: verified exact; local_arxiv, observed 2026-05-11T13:36:08.810006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 13f89b78-6918-46b9-a6d3-6560fb050141 · outbound

This paper cites DINOv2: Learning Robust Visual Features without Supervision.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models DINOv2: Learning Robust Visual Features without Supervision

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-05-11T13:36:08.839114Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a6b55d36-e588-4736-8ad7-c97b7654a8af · outbound

This paper cites Training lan- guage models to follow instructions with human feedback.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Training lan- guage models to follow instructions with human feedback

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.309561Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2714f8db-d069-49b9-ad7d-35547320de7c · outbound

This paper cites Context encoders: Feature learning by inpainting.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Context encoders: Feature learning by inpainting

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.320920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 71d9472f-15b4-4786-aa7a-76748b494902 · outbound

This paper cites Learn- ing transferable visual models from natural language super- vision.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Learn- ing transferable visual models from natural language super- vision

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.465153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b26737de-543d-466c-b3d2-b6aaef3be2ee · outbound

This paper cites Proximal Policy Optimization Algorithms.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Proximal Policy Optimization Algorithms

Reference 52

Resolution: verified exact; local_arxiv, observed 2026-05-11T13:36:08.667118Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8b73a474-f45a-45f0-8bca-06235fbfd290 · outbound

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

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 53

Resolution: verified exact; local_arxiv, observed 2026-05-11T13:36:08.851864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 80ccf399-67a6-40e1-a917-5b01964db5d2 · outbound

This paper cites DINOv3.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models DINOv3

Reference 54

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T13:36:08.572435Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b9504a04-894b-4e5a-983c-b2da6a2847d1 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 55

Resolution: verified exact; local_arxiv, observed 2026-05-11T13:36:08.576979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 081620ee-690c-4fc0-86ae-b0827f3d1f50 · outbound

This paper cites Gemma 3 Technical Report.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Gemma 3 Technical Report

Reference 56

Resolution: verified exact; local_arxiv, observed 2026-05-11T13:36:08.844575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2ab89138-c7f7-427d-bbe9-9b69ab18d67b · outbound

This paper cites Kimi k1.5: Scaling Reinforcement Learning with LLMs.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 57

Resolution: verified exact; local_arxiv, observed 2026-05-11T13:36:08.822073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d035e965-e854-4323-89c1-d9a3953a5dc2 · outbound

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

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Winoground: Probing vision and language models for visio- linguistic compositionality

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.477546Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6253173f-d227-4eab-bff6-e5711facdd51 · outbound

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

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Eyes wide shut? exploring the visual shortcomings of multimodal llms

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.524656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8519b1fe-bf08-4257-a92d-1d8c83d7f77d · outbound

This paper cites SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Reference 60

Resolution: verified exact; local_arxiv, observed 2026-05-11T13:36:08.814689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4cb32b16-38b8-4bcf-bf2f-0811bdd26fe1 · outbound

This paper cites Pixel reasoner: Incentivizing pixel-space reasoning with curiosity-driven reinforcement learning.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Pixel reasoner: Incentivizing pixel-space reasoning with curiosity-driven reinforcement learning

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.535693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 70e5b200-4fd3-4d98-9252-9bc780772809 · outbound

This paper cites Mea- suring multimodal mathematical reasoning with math-vision dataset.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Mea- suring multimodal mathematical reasoning with math-vision dataset

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.453066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation aaf30619-55bd-4342-a66e-dad0355c4977 · outbound

This paper cites Divide, conquer and combine: A training-free framework for high-resolution image perception in multimodal large language models.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Divide, conquer and combine: A training-free framework for high-resolution image perception in multimodal large language models

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.445129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9a247ef6-a82d-46aa-b669-1071141cac14 · outbound

This paper cites LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model

Reference 64

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:36:08.805123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9e35c6d6-165c-4e4b-8bbd-2d5be9181d8b · outbound

This paper cites Vicrit: A verifiable rein- forcement learning proxy task for visual perception in vlms.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Vicrit: A verifiable rein- forcement learning proxy task for visual perception in vlms

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.531901Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4bbacae6-4a7b-4f3b-aaeb-2cb579d8f937 · outbound

This paper cites SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement

Reference 66

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:36:08.856150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1681915f-b3bf-406c-afdd-25718f8f9862 · outbound

This paper cites Jigsaw-r1: A study of rule-based visual reinforcement learning with jigsaw puzzles.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Jigsaw-r1: A study of rule-based visual reinforcement learning with jigsaw puzzles

Reference 67

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:36:08.652216Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bcb35224-6a9e-4f1d-bb75-7b1284dc1b73 · outbound

This paper cites Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs

Reference 68

Resolution: verified exact; arxiv_id, observed 2026-05-13T12:44:27.816864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6c7eda69-9da2-41ff-8dac-829d76e372ea · outbound

This paper cites V?: Guided visual search as a core mechanism in multimodal llms.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models V?: Guided visual search as a core mechanism in multimodal llms

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.528152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 305dcce8-101f-404f-b91b-67a4ccdb4fc1 · outbound

This paper cites Visual jigsaw post-training improves mllms.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Visual jigsaw post-training improves mllms

Reference 70

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:36:08.680333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 93ddcea5-acf8-4ffb-8237-018a3f76e2a3 · outbound

This paper cites MiMo-VL Technical Report.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models MiMo-VL Technical Report

Reference 71

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:36:08.615360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a3015ae6-3e4b-498f-b5e4-51e6e6d2875a · outbound

This paper cites Unsupervised object-level representation learning from scene images.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Unsupervised object-level representation learning from scene images

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.394749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d01f57a8-f546-4faf-8cae-b5d82cb33a44 · outbound

This paper cites Delving into inter-image invariance for unsupervised visual representations.IJCV.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Delving into inter-image invariance for unsupervised visual representations.IJCV

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.386791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9775d78e-cf60-4eda-bf4f-b5f9f2cfe3fb · outbound

This paper cites Masked frequency modeling for self-supervised visual pre-training.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Masked frequency modeling for self-supervised visual pre-training

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.441337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 98d290cd-b7d1-4857-a35b-5c5e73eca5f4 · outbound

This paper cites Depth any- thing v2.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Depth any- thing v2

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.449235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation af98848a-06ea-4dda-8b6c-663bf307169b · outbound

This paper cites How to evaluate the generalization of detection? a bench- mark for comprehensive open-vocabulary detection.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models How to evaluate the generalization of detection? a bench- mark for comprehensive open-vocabulary detection

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.425312Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 37c41524-cf77-4589-b7b7-e8f28b166e66 · outbound

This paper cites mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality

Reference 77

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:36:08.832543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 013d3648-2590-407f-9943-9e8bc8b7be78 · outbound

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

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Perception-R1: Pioneering Perception Policy with Reinforcement Learning

Reference 78

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:36:08.633735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 82fd2cc8-b1da-4349-97f8-e1b19fe59164 · outbound

This paper cites VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoning.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoning

Reference 79

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:36:08.628351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7897cae0-cbe9-414b-a511-49f6176688a4 · outbound

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

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for ex- pert agi

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.429163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 785a44ac-6f1c-4d8a-8882-d8bc0f501496 · outbound

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

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Sigmoid loss for language image pre-training

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.433096Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 66c10490-5f20-48f6-a458-0ac81f389d47 · outbound

This paper cites Online deep clustering for unsupervised representation learning.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Online deep clustering for unsupervised representation learning

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.437208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 18f68011-3757-4d0c-9051-27a9782c586f · outbound

This paper cites Mathverse: Does your multi-modal llm truly see the diagrams in visual math problems? In ECCV.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Mathverse: Does your multi-modal llm truly see the diagrams in visual math problems? In ECCV

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.413172Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 174fe4a7-f5dd-4cbe-b0d1-fcb98e2163d9 · outbound

This paper cites Mme-realworld: Could your multimodal llm challenge high-resolution real-world scenar- ios that are difficult for humans? InICLR.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models Mme-realworld: Could your multimodal llm challenge high-resolution real-world scenar- ios that are difficult for humans? InICLR

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.417301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 43e8db37-78f0-47b6-8ad9-cfb67458cd7c · outbound

This paper cites DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning

Reference 85

Resolution: verified exact; arxiv_id, observed 2026-05-11T14:42:57.181531Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c7adc2e5-d8fd-4fb6-a0af-f7b9fd059301 · outbound

This paper cites ibot: Image bert pre-training with online tokenizer.

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models ibot: Image bert pre-training with online tokenizer

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T09:37:50.421382Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8811d8eb-aa12-4f9c-971b-d2fd7cab62af · outbound

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

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 87

Resolution: verified exact; local_arxiv, observed 2026-05-11T13:36:08.610800Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c4efbcf1-98a0-4bfa-9c6e-6c4dd460d0ba · outbound

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

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 88

Resolution: malformed identifier; local_arxiv, observed 2026-05-11T13:36:08.587864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers