Paper Citation Record · LEDGER

FreeRet: MLLMs as Training-Free Retrievers

As of 11 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 2 inbound Pith citation observations for arXiv:2509.24621.

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

pith.paper-citation-record.v1
2509.24621 v3

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T13:51:48.175750Z

measured 34 of 34 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T00:44:49.894408Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-05-16T22:21:18.877497Z

Reference resolution

32 of 32 outbound references displayed

verified exact0
verified fuzzy0
unresolved32
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4cd1bd75-29ad-4a32-8c27-50a4a634ee09 · outbound

This paper cites GPT-4 Technical Report.

FreeRet: MLLMs as Training-Free Retrievers GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:43.859969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c7d23bc-7776-4f42-8dcf-3d7edd7c68be · outbound

This paper cites E5-V: Universal Embeddings with Multimodal Large Language Models.

FreeRet: MLLMs as Training-Free Retrievers E5-V: Universal Embeddings with Multimodal Large Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:44.906899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53c0bd72-bc9e-42d9-87d1-38ee6fc94016 · outbound

This paper cites Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval.

FreeRet: MLLMs as Training-Free Retrievers Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:45.017918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6390c5b-ccb4-4480-815f-a73ce239e35a · outbound

This paper cites Llave: Large language and vision embedding models with hardness-weighted contrastive learning.arXiv preprint arXiv:2503.04812,.

FreeRet: MLLMs as Training-Free Retrievers Llave: Large language and vision embedding models with hardness-weighted contrastive learning.arXiv preprint arXiv:2503.04812,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:45.134226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e1d7afa-ed1c-4a16-9b7a-f31d127d8c52 · outbound

This paper cites Meta-Task Prompting Elicits Embeddings from Large Language Models.

FreeRet: MLLMs as Training-Free Retrievers Meta-Task Prompting Elicits Embeddings from Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:45.243145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98be9408-7cbe-4b49-a090-bce47863e48a · outbound

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

FreeRet: MLLMs as Training-Free Retrievers LLaVA-OneVision: Easy Visual Task Transfer

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:45.405402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26fba614-591f-48ed-8ef3-7fa053f843ee · outbound

This paper cites Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free.

FreeRet: MLLMs as Training-Free Retrievers Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:45.593825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9d4bee7-5631-4a32-8c17-ee87f78270b7 · outbound

This paper cites MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs.

FreeRet: MLLMs as Training-Free Retrievers MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:45.715775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 331d8613-da27-4bc8-9de0-a339b1e35f7e · outbound

This paper cites IDMR: Towards Instance-Driven Precise Visual Correspondence in Multimodal Retrieval.

FreeRet: MLLMs as Training-Free Retrievers IDMR: Towards Instance-Driven Precise Visual Correspondence in Multimodal Retrieval

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:45.837477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c283fa7-683b-44cf-b708-c95e3bc8b952 · outbound

This paper cites PUMA: Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning.

FreeRet: MLLMs as Training-Free Retrievers PUMA: Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:46.051954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99bbb62d-bba3-49db-a400-10abc6f28b64 · outbound

This paper cites VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents.

FreeRet: MLLMs as Training-Free Retrievers VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:46.190342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfb23136-d37a-4820-86c5-b3cd861dac8b · outbound

This paper cites ABC: Achieving Better Control of Multimodal Embeddings using VLMs.

FreeRet: MLLMs as Training-Free Retrievers ABC: Achieving Better Control of Multimodal Embeddings using VLMs

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:46.300749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fadf603e-6e5a-49cb-b848-29bb5654fa24 · outbound

This paper cites Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG.

FreeRet: MLLMs as Training-Free Retrievers Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:46.487847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8716cb6-480b-48bb-ae76-b9d70901cb20 · outbound

This paper cites Repetition Improves Language Model Embeddings.

FreeRet: MLLMs as Training-Free Retrievers Repetition Improves Language Model Embeddings

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:46.748960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 917f7d0a-cc6d-4d83-a965-69ea11d1b269 · outbound

This paper cites EVA-CLIP: Improved Training Techniques for CLIP at Scale.

FreeRet: MLLMs as Training-Free Retrievers EVA-CLIP: Improved Training Techniques for CLIP at Scale

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:46.961197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bade4ad-4e8a-4c62-b53f-eca4b9a6df2b · outbound

This paper cites GenEOL: Harnessing the Generative Power of LLMs for Training-Free Sentence Embeddings.

FreeRet: MLLMs as Training-Free Retrievers GenEOL: Harnessing the Generative Power of LLMs for Training-Free Sentence Embeddings

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:47.066669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90df73cf-6061-4400-807e-e75bd64ae71f · outbound

This paper cites Qwen2.5-Omni Technical Report.

FreeRet: MLLMs as Training-Free Retrievers Qwen2.5-Omni Technical Report

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:47.410013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b1ae8c2-680d-4d1b-b0d2-8cf5074c2f69 · outbound

This paper cites CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning.

FreeRet: MLLMs as Training-Free Retrievers CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:47.574156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70403970-c00e-475d-81aa-ec3fa4377d6e · outbound

This paper cites GME: Improving Universal Multimodal Retrieval by Multimodal LLMs.

FreeRet: MLLMs as Training-Free Retrievers GME: Improving Universal Multimodal Retrieval by Multimodal LLMs

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:47.730305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49f655dc-7e36-47b8-9731-419e8a38a5ce · outbound

This paper cites Guiding cross-modal represen- tations with mllm priors via preference alignment.arXiv preprint arXiv:2506.06970,.

FreeRet: MLLMs as Training-Free Retrievers Guiding cross-modal represen- tations with mllm priors via preference alignment.arXiv preprint arXiv:2506.06970,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:47.807060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbf44705-8aec-4727-975c-e52fb73c1668 · outbound

This paper cites MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval.

FreeRet: MLLMs as Training-Free Retrievers MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:47.927031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 544ab897-e1ad-4293-9bc8-97d4de8e7ca5 · outbound

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

FreeRet: MLLMs as Training-Free Retrievers InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:48.060652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e34eae24-0db7-4b14-956d-bd1bd47e9cc8 · outbound

This paper cites Reply only with ‘Yes’ or ‘No’.

FreeRet: MLLMs as Training-Free Retrievers Reply only with ‘Yes’ or ‘No’

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:48.175750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7800cf64-9e88-4bfe-8760-d704bfa0cde8 · outbound

This paper cites mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data.

FreeRet: MLLMs as Training-Free Retrievers mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data

Reference 2005

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:44.103590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 255c323b-f667-4d5a-9ada-2c6cf0d17b70 · outbound

This paper cites Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs.

FreeRet: MLLMs as Training-Free Retrievers Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs

Reference 2009

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:44.359594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db38e351-0130-4a4e-b987-7e9619bb7c80 · outbound

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

FreeRet: MLLMs as Training-Free Retrievers Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:47.222387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c58442a-7344-4c20-834a-a54508027b37 · outbound

This paper cites Scaling Sentence Embeddings with Large Language Models.

FreeRet: MLLMs as Training-Free Retrievers Scaling Sentence Embeddings with Large Language Models

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:44.769800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1005f206-1afe-437d-84d6-da0b33b01268 · outbound

This paper cites MIEB: Massive Image Embedding Benchmark.

FreeRet: MLLMs as Training-Free Retrievers MIEB: Massive Image Embedding Benchmark

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:47.306583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a9c248f-2f8c-4930-9554-b1f8988f838b · outbound

This paper cites Qwen2.5-VL Technical Report.

FreeRet: MLLMs as Training-Free Retrievers Qwen2.5-VL Technical Report

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:43.963065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7d1b244-391c-4b06-b716-aec09917d6f1 · outbound

This paper cites Breaking the modality barrier: Universal em- bedding learning with multimodal llms.arXiv preprint arXiv:2504.17432,.

FreeRet: MLLMs as Training-Free Retrievers Breaking the modality barrier: Universal em- bedding learning with multimodal llms.arXiv preprint arXiv:2504.17432,

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:44.618861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcc43ec4-cbb2-4f65-8bc0-a8c1e1d99ce5 · outbound

This paper cites Retrieval-Augmented Generation for Large Language Models: A Survey.

FreeRet: MLLMs as Training-Free Retrievers Retrieval-Augmented Generation for Large Language Models: A Survey

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:44.489689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1f08b03-5330-4c86-b60f-c1888a4036b9 · outbound

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

FreeRet: MLLMs as Training-Free Retrievers Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:44.206465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation a24e8ce2-005e-45c7-aa2b-16511eac61f2 · inbound

Adapting MLLMs for Nuanced Video Retrieval cites this paper.

Adapting MLLMs for Nuanced Video Retrieval FreeRet: MLLMs as Training-Free Retrievers

Reference 91

Resolution: verified exact; local_arxiv, observed 2026-05-16T22:21:18.879203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 16bcb70a-b636-4490-9e5d-1904c9346190 · inbound

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding cites this paper.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding FreeRet: MLLMs as Training-Free Retrievers

Reference 102

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:49.894408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.