Paper Citation Record · LEDGER

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning

As of 8 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 1 inbound Pith citation observation for arXiv:2505.19714.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2505.19714 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:14:02.334299Z

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T04:17:28.017071Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

38 of 38 outbound references displayed

verified exact0
verified fuzzy15
unresolved23
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7b9d031e-9169-4714-a0ac-1e375370713e · outbound

This paper cites Improving end-to-end text image translation from the auxiliary text translation task.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning Improving end-to-end text image translation from the auxiliary text translation task

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:14:05.437206Z

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 a297e907-4ceb-4b7f-bdaa-4bad07857890 · outbound

This paper cites Exploring better text image translation with multimodal codebook.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning Exploring better text image translation with multimodal codebook

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:14:05.230742Z

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 8d0289b7-7e2d-46d4-a8b8-2a9463734673 · outbound

This paper cites Document image machine translation with dynamic multi-pre-trained models assembling.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning Document image machine translation with dynamic multi-pre-trained models assembling

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:14:04.999357Z

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 4bfba9eb-207b-4f5a-9427-16ead2573713 · outbound

This paper cites X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T14:13:58.918731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c29c512-5d09-4072-8db4-4edac912a1d6 · outbound

This paper cites TEaR: Improving LLM-based Machine Translation with Systematic Self-Refinement.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning TEaR: Improving LLM-based Machine Translation with Systematic Self-Refinement

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T14:13:58.952388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2db436a2-94c8-4f04-a1e7-f478d1825759 · outbound

This paper cites Towards fully automated manga translation.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning Towards fully automated manga translation

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:14:04.822417Z

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 b88b2cfb-05ff-4100-b79b-c6f58616f4e2 · outbound

This paper cites Doc-handler: Document scanner, manipulator, and translator based on image and natural language processing.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning Doc-handler: Document scanner, manipulator, and translator based on image and natural language processing

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:14:04.602806Z

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 fcbd4c83-9b94-4581-8147-d3779a3ffeb4 · outbound

This paper cites A novel dataset and benchmark analysis on document image translation.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning A novel dataset and benchmark analysis on document image translation

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:14:04.437848Z

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 84599604-fd47-42d1-80e3-94fe0accb12b · outbound

This paper cites Understand layout and translate text: Unified feature-conductive end-to-end document image translation.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning Understand layout and translate text: Unified feature-conductive end-to-end document image translation

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:14:04.266082Z

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 fa117ddf-2327-4491-8ab4-d939013c384e · outbound

This paper cites Peit: bridging the modality gap with pre-trained models for end-to-end image translation.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning Peit: bridging the modality gap with pre-trained models for end-to-end image translation

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:14:04.142137Z

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 7eb808bc-a1d9-4499-83d1-9063bd20ccbd · outbound

This paper cites Born a babynet with hierarchical parental supervision for end-to-end text image machine translation.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning Born a babynet with hierarchical parental supervision for end-to-end text image machine translation

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:14:03.928447Z

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 f2fd6f25-9fe1-4f6d-b18a-b04a8c1aefe9 · outbound

This paper cites Umtit: Unifying recognition, translation, and generation for multimodal text image translation.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning Umtit: Unifying recognition, translation, and generation for multimodal text image translation

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:14:03.772522Z

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 7db1058f-f4c4-492b-bc71-e42c40294a12 · outbound

This paper cites Qwen2.5-VL Technical Report.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning Qwen2.5-VL Technical Report

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T14:13:59.814191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bf1845f-f9b1-4086-930c-d38c6ee018da · outbound

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

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T14:13:59.949559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 011e98e9-b803-431d-82c9-185df12c0503 · outbound

This paper cites Qvq: To see the world with wisdom, December 2024.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning Qvq: To see the world with wisdom, December 2024

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T14:14:00.084026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f47fd1cf-41f0-418d-b310-a04514489007 · outbound

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

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T14:14:00.195720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9f90ec2-3c9e-46b9-b572-a7f041e22ada · outbound

This paper cites Kimi k1.5: Scaling reinforcement learning with llms.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning Kimi k1.5: Scaling reinforcement learning with llms

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:14:03.612372Z

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 0bd6ec55-df4d-4264-8d83-b82c5cc732ea · outbound

This paper cites Qwq-32b: Embracing the power of reinforcement learning, March 2025 b.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning Qwq-32b: Embracing the power of reinforcement learning, March 2025 b

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T14:14:00.396181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5f2a814-4646-4e86-909d-c9f07717bcc1 · outbound

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

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T14:14:00.498814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3398ef41-7d5f-4aed-8636-b2a1051d9b93 · outbound

This paper cites R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T14:14:00.582740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 747cb31e-cc82-47f3-81d3-efbbbd61326d · outbound

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

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T14:14:00.742150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc78ef3e-8682-4e19-a0e3-0d45b7c6a15e · outbound

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

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning Visual-RFT: Visual Reinforcement Fine-Tuning

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T14:14:00.855627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fa60082-4020-47cd-b5bb-c0f92981b7ad · outbound

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

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T14:14:00.965350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 843b5793-aed7-4f43-b81c-4b2f26517bdc · outbound

This paper cites R1-v: Reinforcing super generalization ability in vision-language models with less than \ 3.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning R1-v: Reinforcing super generalization ability in vision-language models with less than \ 3

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T14:14:01.061657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94e68b34-4a67-44e6-b338-989af900c6ee · outbound

This paper cites MIT-10M: A Large Scale Parallel Corpus of Multilingual Image Translation.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning MIT-10M: A Large Scale Parallel Corpus of Multilingual Image Translation

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T14:14:01.162482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42d4d390-4d3c-4478-8d98-9318e8527c08 · outbound

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

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T14:14:01.267361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bb5ca55-f5fb-441c-a276-f01b8b9e0538 · outbound

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

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T14:14:01.404958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a06f41ee-f846-40e9-bd74-d419b355d93a · outbound

This paper cites an unresolved cited work.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:14:03.447765Z

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 9bfd95f3-3fcb-46c7-be81-a6b2b414545c · outbound

This paper cites Results of WMT 23 metrics shared task: Metrics might be guilty but references are not innocent.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning Results of WMT 23 metrics shared task: Metrics might be guilty but references are not innocent

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T14:14:01.629109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25423da9-622c-4e82-b194-c93f4694c9a8 · outbound

This paper cites MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T14:14:01.716379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a70b5dee-780a-4925-ba71-b32baa6ae6a3 · outbound

This paper cites an unresolved cited work.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning Unresolved cited work

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T14:14:01.816152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 814b935f-bf68-4e35-a9bc-0bb090857f4f · outbound

This paper cites A call for clarity in reporting BLEU scores.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning A call for clarity in reporting BLEU scores

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:14:03.300772Z

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 80f028a1-8817-42d7-bc7e-81395417c64e · outbound

This paper cites chrf++: words helping character n-grams.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning chrf++: words helping character n-grams

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:14:03.129649Z

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 fbcc3b8e-3264-4326-8858-a49a43a0420d · outbound

This paper cites Meteor: An automatic metric for mt evaluation with improved correlation with human judgments.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning Meteor: An automatic metric for mt evaluation with improved correlation with human judgments

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:14:02.982521Z

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 b1ba5894-f2a8-4e0a-96b1-97ec66c90f86 · outbound

This paper cites OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T14:14:02.099149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5967fad5-0f27-4407-8282-6a21ff33cf33 · outbound

This paper cites Proximal Policy Optimization Algorithms.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning Proximal Policy Optimization Algorithms

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T14:14:02.163845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4990aa5c-23f1-4509-ab9d-3c5349673d46 · outbound

This paper cites No Language Left Behind: Scaling Human-Centered Machine Translation.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning No Language Left Behind: Scaling Human-Centered Machine Translation

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T14:14:02.254773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea34ad3b-0316-42a7-a15a-ce7bdd82a941 · outbound

This paper cites Deep nn for nsfw detection.

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning Deep nn for nsfw detection

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:14:02.804453Z

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.

Pith citing papers

Observation f7a59fed-1928-45ab-8d96-c5839908803a · inbound

Multi-Task GRPO: Reliable LLM Reasoning Across Tasks cites this paper.

Multi-Task GRPO: Reliable LLM Reasoning Across Tasks MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-03T04:17:28.017071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.