Paper Citation Record · LEDGER

Visual-Advantage On-Policy Distillation for Vision-Language Models

As of 30 July 2026, this Paper Citation Record lists 33 of 33 outbound references and 1 inbound Pith citation observation for arXiv:2605.21924.

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

pith.paper-citation-record.v1
2605.21924 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-22T07:24:22.355378Z

measured 34 of 34 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-07-30T06:33:22.917629+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-30T05:51:18.037199Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-06-30T05:54:18.602535Z

Reference resolution

33 of 33 outbound references displayed

verified exact18
verified fuzzy15
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 57559873-2a57-4dc0-8753-5044f14c5556 · outbound

This paper cites On-policy distillation of language models: Learning from self-generated mistakes.

Visual-Advantage On-Policy Distillation for Vision-Language Models On-policy distillation of language models: Learning from self-generated mistakes

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:24:43.538432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation 013e0229-9e32-47fc-af7c-5315f2ddd62b · outbound

This paper cites Minillm: Knowledge distillation of large language models.

Visual-Advantage On-Policy Distillation for Vision-Language Models Minillm: Knowledge distillation of large language models

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:24:43.544402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation aa5096a4-7941-4869-95dd-7cba8386883a · outbound

This paper cites Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation.

Visual-Advantage On-Policy Distillation for Vision-Language Models Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:24:42.884307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation 7c5fbd27-8657-4e24-8198-00f7d6280272 · outbound

This paper cites DistiLLM: Towards Streamlined Distillation for Large Language Models.

Visual-Advantage On-Policy Distillation for Vision-Language Models DistiLLM: Towards Streamlined Distillation for Large Language Models

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-22T07:24:42.929750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation 888c5264-6fa5-44ce-986d-090b55c4b6e6 · outbound

This paper cites Qwen3-VL Technical Report.

Visual-Advantage On-Policy Distillation for Vision-Language Models Qwen3-VL Technical Report

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:24:42.939849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation aee4b324-9c80-4536-ba4f-e7242736c636 · outbound

This paper cites Inter-gps: Interpretable geometry problem solving with formal language and symbolic reasoning.

Visual-Advantage On-Policy Distillation for Vision-Language Models Inter-gps: Interpretable geometry problem solving with formal language and symbolic reasoning

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:24:43.534503Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation e01efe42-27d9-4c62-8c42-b61f8cee2516 · outbound

This paper cites VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning.

Visual-Advantage On-Policy Distillation for Vision-Language Models VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:24:42.961954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation 8005a4f9-3d78-45ee-9715-6d428831ed0e · outbound

This paper cites Distilling the Knowledge in a Neural Network.

Visual-Advantage On-Policy Distillation for Vision-Language Models Distilling the Knowledge in a Neural Network

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:24:42.973997Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation 8be8682c-5803-4ea4-97b1-6ef7587c8a4a · outbound

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

Visual-Advantage On-Policy Distillation for Vision-Language Models DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:24:42.968011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation 730a824b-9a15-4357-8ae9-130108c9edc3 · outbound

This paper cites Perception-Aware Policy Optimization for Multimodal Reasoning.

Visual-Advantage On-Policy Distillation for Vision-Language Models Perception-Aware Policy Optimization for Multimodal Reasoning

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:24:42.923599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation 1b19c7b6-e00e-4fa5-af0a-58120a41237f · outbound

This paper cites We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?.

Visual-Advantage On-Policy Distillation for Vision-Language Models We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:24:42.901472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation f76cbc4b-0cf9-4835-be48-443c2b0427ec · outbound

This paper cites MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts.

Visual-Advantage On-Policy Distillation for Vision-Language Models MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:24:42.945811Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation 5db27f69-3c9f-4d38-8b28-8cea840df618 · outbound

This paper cites Mathverse: Does your multi-modal llm truly see the diagrams in visual math problems? InEuropean Conference on Computer Vision, pages 169–186.

Visual-Advantage On-Policy Distillation for Vision-Language Models Mathverse: Does your multi-modal llm truly see the diagrams in visual math problems? InEuropean Conference on Computer Vision, pages 169–186

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:24:43.519778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation 00a5a185-29ef-4b77-bced-94cd9a4bfbf6 · outbound

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

Visual-Advantage On-Policy Distillation for Vision-Language Models Hallusionbench: an advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:24:43.527512Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation caf7152e-1ab1-48b8-b867-447713b8f377 · outbound

This paper cites A diagram is worth a dozen images.

Visual-Advantage On-Policy Distillation for Vision-Language Models A diagram is worth a dozen images

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:24:43.530864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation aa3e59f3-790a-4a9d-96cf-36596968c0fc · outbound

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

Visual-Advantage On-Policy Distillation for Vision-Language Models Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:24:43.558486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation e3750704-5ce0-4b95-b317-7ad0c7351e45 · outbound

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

Visual-Advantage On-Policy Distillation for Vision-Language Models Are we on the right way for evaluating large vision- language models?Advances in Neural Information Processing Systems, 37:27056–27087

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:24:43.562087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation ff1efb2c-c145-42b1-839e-568be0d64260 · outbound

This paper cites Ocrbench: on the hidden mystery of ocr in large multimodal models.Science China Information Sciences, 67(12):220102.

Visual-Advantage On-Policy Distillation for Vision-Language Models Ocrbench: on the hidden mystery of ocr in large multimodal models.Science China Information Sciences, 67(12):220102

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:24:43.570267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation c3462313-02a8-417a-911e-ae6131e2ce0a · outbound

This paper cites Multi-modal hallucination control by visual information grounding.

Visual-Advantage On-Policy Distillation for Vision-Language Models Multi-modal hallucination control by visual information grounding

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:24:43.565704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation e9832a10-f06f-496a-966b-f151860241c1 · outbound

This paper cites Mitigating object hallucinations in large vision-language models through visual contrastive decoding.

Visual-Advantage On-Policy Distillation for Vision-Language Models Mitigating object hallucinations in large vision-language models through visual contrastive decoding

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:24:43.555019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation 34958356-7e2e-4cce-951d-a757cadab9ac · outbound

This paper cites Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs.

Visual-Advantage On-Policy Distillation for Vision-Language Models Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-22T07:24:42.912926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation f803e542-6f41-4534-91c7-a63396146e47 · outbound

This paper cites V-dpo: Mitigating hallucination in large vision language models via vision-guided direct preference optimization.

Visual-Advantage On-Policy Distillation for Vision-Language Models V-dpo: Mitigating hallucination in large vision language models via vision-guided direct preference optimization

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:24:43.547814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation b8713252-d2d9-4d04-97b3-73766edbde3a · outbound

This paper cites Self-Rewarding Vision-Language Model via Reasoning Decomposition.

Visual-Advantage On-Policy Distillation for Vision-Language Models Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:24:42.889722Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation e246103d-1dfb-489a-a35f-d02c0f80c8f6 · outbound

This paper cites Mitigating hallucinations in large vision-language models with instruction contrastive decoding.

Visual-Advantage On-Policy Distillation for Vision-Language Models Mitigating hallucinations in large vision-language models with instruction contrastive decoding

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:24:43.551515Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation 5194f307-16ab-49f9-940c-f4bfb160999b · outbound

This paper cites Token preference optimization with self-calibrated visual-anchored rewards for hallucination mitigation.

Visual-Advantage On-Policy Distillation for Vision-Language Models Token preference optimization with self-calibrated visual-anchored rewards for hallucination mitigation

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-22T07:24:42.907761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation 921e3ae4-68e3-47cc-a0e5-8cc3f47e821c · outbound

This paper cites Spotlight on token perception for multimodal reinforcement learning.

Visual-Advantage On-Policy Distillation for Vision-Language Models Spotlight on token perception for multimodal reinforcement learning

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-22T07:24:42.918798Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation 5d371482-c469-4a26-8dab-dbb0b4d7fe08 · outbound

This paper cites Rethinking token-level policy optimization for multimodal chain-of-thought.

Visual-Advantage On-Policy Distillation for Vision-Language Models Rethinking token-level policy optimization for multimodal chain-of-thought

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-22T07:24:42.956937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation af1aefb4-1f19-4ef4-a049-9c6da5593db9 · outbound

This paper cites Noisyrollout: Reinforcing visual reasoning with data augmentation.

Visual-Advantage On-Policy Distillation for Vision-Language Models Noisyrollout: Reinforcing visual reasoning with data augmentation

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-22T07:24:42.895332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation 1a57432b-5303-4b59-a980-a052d79d3125 · outbound

This paper cites Rethinking kullback-leibler divergence in knowledge distillation for large language models.

Visual-Advantage On-Policy Distillation for Vision-Language Models Rethinking kullback-leibler divergence in knowledge distillation for large language models

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:24:43.523847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation 9d9cf732-09dd-4463-9940-65546755eadc · outbound

This paper cites Entropy-Aware On-Policy Distillation of Language Models.

Visual-Advantage On-Policy Distillation for Vision-Language Models Entropy-Aware On-Policy Distillation of Language Models

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-25T03:02:00.585154Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation 1b7bc637-9aed-4d75-b525-4857ce2f19a8 · outbound

This paper cites Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling.

Visual-Advantage On-Policy Distillation for Vision-Language Models Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-22T07:24:42.979381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation 6fc31c0c-aadc-4534-9ba9-eb0689295ab3 · outbound

This paper cites On-policy distillation.

Visual-Advantage On-Policy Distillation for Vision-Language Models On-policy distillation

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T07:24:43.541497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Observation ba133aa1-9274-48c1-862d-c427a72288bd · outbound

This paper cites Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning.

Visual-Advantage On-Policy Distillation for Vision-Language Models Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:24:42.951553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.

Pith citing papers

Observation 6ec24019-afb0-4680-98cf-7d0137eb90e3 · inbound

DOPD: Dual On-policy Distillation cites this paper.

DOPD: Dual On-policy Distillation Visual-Advantage On-Policy Distillation for Vision-Language Models

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-06-30T05:54:18.604225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-30T06:33:22.917629+00:00.