Paper Citation Record · LEDGER

VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization

As of 19 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 7 inbound Pith citation observations for arXiv:2505.10917.

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

pith.paper-citation-record.v1
2505.10917 v2

Coverage vector

measured 22 of 22 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T21:07:59.827793Z

measured 29 of 29 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 7 of 7 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T18:47:14.574922Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-30T18:45:00.174957Z

Reference resolution

22 of 22 outbound references displayed

verified exact0
verified fuzzy6
unresolved16
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation cd3bee83-896d-4216-8c3b-ddcd40ce3d0f · outbound

This paper cites Qwen2.5-VL Technical Report.

VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization Qwen2.5-VL Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T21:07:59.750212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 342fac08-527d-41f1-9fe7-e2b424d58ddb · outbound

This paper cites Locality Alignment Improves Vision-Language Models.

VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization Locality Alignment Improves Vision-Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T21:07:59.762345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 329ea386-3d6a-4592-aedb-2301564890e6 · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T21:07:59.765372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c7994bc-54a1-4c17-b3c2-0b80f0dc217c · outbound

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

VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T21:07:59.778856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bde1c36d-28a0-4fac-b6a3-6f62240ba564 · outbound

This paper cites Microsoft coco: Common objects in context.

VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization Microsoft coco: Common objects in context

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:08:00.076558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 83052d8e-d279-41be-bdba-76e4c43e60a4 · outbound

This paper cites Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMs.

VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMs

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T21:07:59.787597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c04ad6c-ac6e-40ff-9420-f6372fff69c4 · outbound

This paper cites MetaMorph: Multimodal Understanding and Generation via Instruction Tuning.

VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization MetaMorph: Multimodal Understanding and Generation via Instruction Tuning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T21:07:59.799314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d49ee1b3-6510-447e-a474-bce1d897dde8 · outbound

This paper cites Reconstructive Visual Instruction Tuning.

VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization Reconstructive Visual Instruction Tuning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T21:07:59.802425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05891336-2efd-4c02-8940-a9f9b5a05cb3 · outbound

This paper cites Accessed: 2025-01-.

VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization Accessed: 2025-01-

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:08:00.047059Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8fb35b7c-0c4d-425d-b401-c2eca526e82b · outbound

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

VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T21:07:59.813004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 835875ee-adc9-4e2b-90a5-24ec269979a2 · outbound

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

VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T21:07:59.815927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 601caa60-7141-4474-91d3-18c64dc2e16e · outbound

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

VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T21:07:59.819535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af89c01d-7931-4292-aa51-c115dad10ff8 · outbound

This paper cites an unresolved cited work.

VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:08:00.028481Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 67fd94ee-9da5-4dbd-b54e-bf48ab174532 · outbound

This paper cites MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI.

VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T21:07:59.809431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15a76928-e198-4444-8fac-33a077137e0d · outbound

This paper cites During fine-tuning, the batch size is halved to 16 to accommodate increased model complexity and dataset scale.

VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization During fine-tuning, the batch size is halved to 16 to accommodate increased model complexity and dataset scale

Reference 256

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:08:00.011517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ab2a4859-a5e2-46f3-b4e6-b34b5d06e44d · outbound

This paper cites A diagram is worth a dozen images.

VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization A diagram is worth a dozen images

Reference 2014

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:08:00.089592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0cf762b2-b22b-454f-ad3b-2c2397003bc1 · outbound

This paper cites Kimi-VL Technical Report.

VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization Kimi-VL Technical Report

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-15T21:07:59.795956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1692588c-b51e-4fdc-ae1b-c2cdc1f82b46 · outbound

This paper cites Multimodal Autoregressive Pre-training of Large Vision Encoders.

VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization Multimodal Autoregressive Pre-training of Large Vision Encoders

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-15T21:07:59.768232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b1c5bce-cc5b-4b38-ae96-e1a43230aa3c · outbound

This paper cites Ocr-vqa: Visual question answering by reading text in images.

VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization Ocr-vqa: Visual question answering by reading text in images

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:08:00.063149Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 95c087a8-7383-4bad-b687-73f6fde120a9 · outbound

This paper cites Referitgame: Referring to objects in photographs of natural scenes.

VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization Referitgame: Referring to objects in photographs of natural scenes

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:08:00.101799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3458492c-aa16-4c70-8214-bb981a6c7456 · outbound

This paper cites Gramian Multimodal Representation Learning and Alignment.

VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization Gramian Multimodal Representation Learning and Alignment

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-15T21:07:59.757737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9885729b-f0c2-42a1-91ad-f1aa82b1d2b3 · outbound

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

VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization Are We on the Right Way for Evaluating Large Vision-Language Models?

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-15T21:07:59.753923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 1a1910c1-7522-4081-8d32-e8820e2d1460 · inbound

From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents cites this paper.

From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T18:47:14.574922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e4f6cf0-67ff-405f-88ce-3095010eaaa4 · inbound

Fine-Grained Zero-Shot Object Detection cites this paper.

Fine-Grained Zero-Shot Object Detection VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T17:41:00.805264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67c046c7-93fe-4e25-8faf-bfd9bf4d1412 · inbound

MS-DETR: Towards Effective Video Moment Retrieval and Highlight Detection by Joint Motion-Semantic Learning cites this paper.

MS-DETR: Towards Effective Video Moment Retrieval and Highlight Detection by Joint Motion-Semantic Learning VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T17:01:52.569023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af063bff-0d23-43a7-bdbf-c9a6ab11253d · inbound

Vision Inference Former: Sustaining Visual Consistency in Multimodal Large Language Models cites this paper.

Vision Inference Former: Sustaining Visual Consistency in Multimodal Large Language Models VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-20T11:38:14.446584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c0ab3302-a89a-4ce4-8e50-5d72fee52e11 · inbound

Vision Inference Former: Sustaining Visual Consistency in Multimodal Large Language Models cites this paper.

Vision Inference Former: Sustaining Visual Consistency in Multimodal Large Language Models VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-06-30T18:45:00.177236Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation daa69f7a-4758-43b6-8c68-3db61f49861e · inbound

Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition cites this paper.

Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-06-28T17:42:26.088290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation badd34c8-4d75-4c39-b6c2-9bc6af3ccad1 · inbound

MIRROR: Aligning Semantic Relations from Language to Image via Gromov--Wasserstein cites this paper.

MIRROR: Aligning Semantic Relations from Language to Image via Gromov--Wasserstein VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-06-30T07:34:21.712771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.