Paper Citation Record · LEDGER

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying

As of 18 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 5 inbound Pith citation observations for arXiv:2506.02020.

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

pith.paper-citation-record.v1
2506.02020 v1

Coverage vector

measured 29 of 29 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:18:49.815677Z

measured 34 of 34 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T20:43:17.336608Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-13T17:08:01.148592Z

Reference resolution

29 of 29 outbound references displayed

verified exact1
verified fuzzy12
unresolved16
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6a06e7c1-ffc4-4f6e-af91-519c5b807b3b · outbound

This paper cites Notellm: A retrievable large language model for note recommendation.

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying Notellm: A retrievable large language model for note recommendation

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:18:54.052728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation be9e6f38-c610-4e59-869c-60cdcce966a5 · outbound

This paper cites NoteLLM-2: Multimodal Large Representation Models for Recommendation.

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying NoteLLM-2: Multimodal Large Representation Models for Recommendation

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T13:18:46.934462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d23551af-ff17-475e-bbfd-8ffa72c03980 · outbound

This paper cites VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents.

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T13:18:47.055743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adcef878-068b-44f0-b6fb-54145652c77b · outbound

This paper cites VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents.

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:18:50.597400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2c2f5a19-c0bf-4ee3-aed9-7786dc748ecf · outbound

This paper cites Mmsearch: Unveiling the potential of large models as multi-modal search engines.

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying Mmsearch: Unveiling the potential of large models as multi-modal search engines

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:18:53.861947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2037f4b4-297b-4860-bb3e-a92d987b8487 · outbound

This paper cites Learning transferable visual models from natural language supervision.

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying Learning transferable visual models from natural language supervision

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:18:53.676270Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 14e6952a-8e20-493a-91aa-5e8d7d655adf · outbound

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

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying Sigmoid loss for language image pre-training

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:18:53.437440Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0a91747f-1661-496a-b348-79ad926b19d3 · outbound

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

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T13:18:47.517568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ac52ac6-a3b7-487b-a43c-42578b84fa9e · outbound

This paper cites EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters.

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T13:18:47.669708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb7201fc-68ed-48cb-a5a9-fcd83ad30f09 · outbound

This paper cites Visual instruction tuning.

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying Visual instruction tuning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T13:18:47.878642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6c8825a-e942-4e43-b3f1-634b507bed65 · outbound

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

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying LLaVA-OneVision: Easy Visual Task Transfer

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T13:18:48.004899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ab308f6-09dc-4d04-b326-0d4a9db9c0ee · outbound

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

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T13:18:48.083695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56948934-2ff3-42cf-864d-e24574e7f022 · outbound

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

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T13:18:48.190114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 037c4ad1-3a29-4627-bfdf-dc47b9027368 · outbound

This paper cites Representation Learning with Contrastive Predictive Coding.

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying Representation Learning with Contrastive Predictive Coding

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T13:18:48.258280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2be151e4-ec62-4bb7-87f6-124e6a02f149 · outbound

This paper cites Girshick.

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying Girshick

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:18:53.298401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d441546d-9309-4228-aa4c-577ebfe4ec70 · outbound

This paper cites an unresolved cited work.

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:18:53.011925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4c19eca1-f0ba-40ad-b4ca-06503607c333 · outbound

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

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying Llave: Large language and vision embedding models with hardness-weighted contrastive learning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T13:18:48.530572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00e5072e-34de-4be2-9027-b8dee6685881 · outbound

This paper cites Scaling deep contrastive learning batch size under memory limited setup.

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying Scaling deep contrastive learning batch size under memory limited setup

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:18:52.834999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 49a68cbb-a738-4763-95d9-2707a5e1a146 · outbound

This paper cites Sfr- embedding-mistral:enhance text retrieval with transfer learning.

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying Sfr- embedding-mistral:enhance text retrieval with transfer learning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T13:18:48.770440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f3336d7-15d2-4268-9806-eb28c1f95d34 · outbound

This paper cites Nv-embed: Improved techniques for training llms as generalist embedding models.

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying Nv-embed: Improved techniques for training llms as generalist embedding models

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:18:52.517561Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 345308d0-a43d-404a-b265-7841355c0144 · outbound

This paper cites Breaking the batch barrier (b3) of contrastive learning via smart batch mining.

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying Breaking the batch barrier (b3) of contrastive learning via smart batch mining

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T13:18:49.092184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d89fa713-000a-45eb-9f28-1d446614dc2f · outbound

This paper cites Vlm2vec: Training vision-language models for massive multimodal embedding tasks.

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying Vlm2vec: Training vision-language models for massive multimodal embedding tasks

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:18:52.225357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b4e7e494-9df5-40aa-9749-773e8d3af88c · outbound

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

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying E5-V: Universal Embeddings with Multimodal Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T13:18:49.328229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b65eaf56-3c4b-4acb-997d-4790aa3dcfea · outbound

This paper cites Breaking the modality barrier: Universal embedding learning with multimodal llms.

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying Breaking the modality barrier: Universal embedding learning with multimodal llms

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T13:18:49.443909Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 308e107d-fa79-4f6c-84c7-45123b663d45 · outbound

This paper cites Reproducible scaling laws for contrastive language-image learning.

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying Reproducible scaling laws for contrastive language-image learning

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:18:51.937499Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 708161ca-e7cd-48d9-a6f3-4bdee685bc79 · outbound

This paper cites Magiclens: Self-supervised image retrieval with open-ended instructions.

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying Magiclens: Self-supervised image retrieval with open-ended instructions

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:18:51.561668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 19ae5c26-5713-43b7-afa7-63d3567a26e9 · outbound

This paper cites an unresolved cited work.

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:18:51.301046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c14177af-8e87-46ca-855b-8011d54ec94e · outbound

This paper cites Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C.

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:18:51.092200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d7e0e637-e7e5-4135-8f6d-12939a687a7a · outbound

This paper cites Visual news: Benchmark and challenges in news image captioning.

Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying Visual news: Benchmark and challenges in news image captioning

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:18:50.865936Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Pith citing papers

Observation e645e263-3f3f-4f85-b91b-a49573b0af2c · inbound

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs cites this paper.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:58.191649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5019370f-b1a0-4032-a9cf-39ea744575e5 · inbound

Tencent Advertising Algorithm Challenge 2025: All-Modality Generative Recommendation cites this paper.

Tencent Advertising Algorithm Challenge 2025: All-Modality Generative Recommendation Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying

Reference 61

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:08:01.150217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 09101564-083c-4c12-a45b-25aa8df6c83c · inbound

Evaluation of Embedding-Based and Generative Methods for LLM-Driven Document Classification: Opportunities and Challenges cites this paper.

Evaluation of Embedding-Based and Generative Methods for LLM-Driven Document Classification: Opportunities and Challenges Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-13T10:23:38.252227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5e448f3-ec66-479c-bf7d-a6621149975d · inbound

Enhancing Multimodal In-Context Learning via Inductive-Deductive Reasoning cites this paper.

Enhancing Multimodal In-Context Learning via Inductive-Deductive Reasoning Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-09T05:55:31.217933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d2e52caf-a117-4d20-864f-ee1847e6c1db · inbound

Illuminating Visual Identity in Universal Multimodal Embeddings cites this paper.

Illuminating Visual Identity in Universal Multimodal Embeddings Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:17.336608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.