Paper Citation Record · LEDGER

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models

As of 14 August 2026, this Paper Citation Record lists 72 of 72 outbound references and 1 inbound Pith citation observation for arXiv:2508.06895.

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

pith.paper-citation-record.v1
2508.06895 v1

Coverage vector

measured 72 of 72 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T22:35:51.006465Z

measured 73 of 73 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-27T15:05:31.609683Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T03:37:35.644847Z

Reference resolution

72 of 72 outbound references displayed

verified exact2
verified fuzzy33
unresolved37
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c70655ab-56a5-4c64-bcc4-f669907cb552 · outbound

This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:49.341044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8547c9d4-2611-4401-8dae-29d19e8c4628 · outbound

This paper cites Flamingo: a visual language model for few-shot learning.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Flamingo: a visual language model for few-shot learning

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:49.464613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f44d82c-5bda-47ac-a98c-b965b523c10e · outbound

This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:49.581640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a14b0dbd-b9c8-40c4-a722-e6160cca53aa · outbound

This paper cites BEiT: BERT Pre-Training of Image Transformers.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models BEiT: BERT Pre-Training of Image Transformers

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:49.678589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea69dbda-7193-4816-a5a4-94047e0dd567 · outbound

This paper cites Introducing our multimodal models, 2023.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Introducing our multimodal models, 2023

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:49.769760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 286fbd26-d5d9-43fe-83b7-8e642984c910 · outbound

This paper cites Eliciting Latent Predictions from Transformers with the Tuned Lens.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Eliciting Latent Predictions from Transformers with the Tuned Lens

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:49.861020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f00a6e90-2e19-4a0b-84b4-e36a274994d6 · outbound

This paper cites Mechanistic Interpretability for AI Safety -- A Review.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Mechanistic Interpretability for AI Safety -- A Review

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.042218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a42d0d58-e3d1-4327-8e32-c83934d265ab · outbound

This paper cites Towards monose- manticity: Decomposing language models with dictionary learning.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Towards monose- manticity: Decomposing language models with dictionary learning

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:52.299573Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9ba8def6-8af5-4b2a-b405-02d9322b37a7 · outbound

This paper cites InternLM2 Technical Report.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models InternLM2 Technical Report

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.328264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59c4c893-d02d-49c6-8c54-8133b029d34a · outbound

This paper cites Honeybee: Locality-enhanced projector for multimodal llm.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Honeybee: Locality-enhanced projector for multimodal llm

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:52.283743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4b911440-bcf0-4973-b37a-3b6aef5f396f · outbound

This paper cites Sssd: Self-supervised self distillation.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Sssd: Self-supervised self distillation

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:52.268603Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ee4f9e61-2f6d-45bf-bad7-0e323b25dc70 · outbound

This paper cites How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.687551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cd7704f-30a8-40e3-acfb-6aec47ff4019 · outbound

This paper cites Gonzalez, Ion Stoica, and Eric P.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Gonzalez, Ion Stoica, and Eric P

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:52.252412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8f132459-ad6d-407d-87dd-30b3199e6164 · outbound

This paper cites On the efficacy of knowledge distillation.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models On the efficacy of knowledge distillation

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.697046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d332bd6-792d-455c-ba7a-7026b82eb613 · outbound

This paper cites Towards automated circuit discovery for mechanistic interpretability.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Towards automated circuit discovery for mechanistic interpretability

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:52.228061Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 017ca2ca-ff9b-4ced-a391-915a93fb7aec · outbound

This paper cites Sparse Autoencoders Find Highly Interpretable Features in Language Models.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.705188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 875f8441-66d2-404c-8e1c-74d7c8e58839 · outbound

This paper cites an unresolved cited work.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-05T22:35:52.211942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2b905e90-76bd-496b-8670-40fdc7d8fa8c · outbound

This paper cites The Llama 3 Herd of Models.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models The Llama 3 Herd of Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.716976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c7af29b-8097-4160-b3e0-f1de8e5e0acc · outbound

This paper cites Softmax linear units.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Softmax linear units

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:52.196697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0035c43f-fdc4-476a-b219-aceb791b2b21 · outbound

This paper cites Making LLaMA SEE and Draw with SEED Tokenizer.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Making LLaMA SEE and Draw with SEED Tokenizer

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.726451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bf826e1-f8c1-471b-bedf-cc915a5c5e34 · outbound

This paper cites Knowledge distillation: A survey.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Knowledge distillation: A survey

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:52.182360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 54b1e966-2a24-4446-b3ca-c33e26b2df1d · outbound

This paper cites Making the v in vqa matter: Elevating the role of image understanding in visual question answer- ing.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Making the v in vqa matter: Elevating the role of image understanding in visual question answer- ing

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.735344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fbdd0df-74fe-4181-9627-58bccb00fc42 · outbound

This paper cites Vizwiz grand challenge: Answering visual questions from blind people.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Vizwiz grand challenge: Answering visual questions from blind people

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.739470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f680d928-24de-4382-9a90-8958094b680e · outbound

This paper cites Learning lightweight lane detection cnns by self at- 9 tention distillation.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Learning lightweight lane detection cnns by self at- 9 tention distillation

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:52.145624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation dd47919c-da0c-4988-9233-8b8ceb393723 · outbound

This paper cites Gqa: A new dataset for real-world visual reasoning and compositional question answering.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Gqa: A new dataset for real-world visual reasoning and compositional question answering

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:52.130633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1b1ba7eb-db2d-4bd7-a228-5d431c711bdc · outbound

This paper cites Perceiver: General perception with iterative attention.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Perceiver: General perception with iterative attention

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:52.115075Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2a8b29e0-8723-4413-a650-f7583765e77a · outbound

This paper cites Mistral 7B.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Mistral 7B

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.757110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ded257a3-9fba-4d08-a5ed-3f3158ee176e · outbound

This paper cites Unified language-vision pretraining in LLM with dynamic discrete visual tokenization.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Unified language-vision pretraining in LLM with dynamic discrete visual tokenization

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:52.100675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a57f0a1f-f9b1-4ae3-9aac-685e8ee71b3b · outbound

This paper cites Referitgame: Referring to objects in pho- tographs of natural scenes.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Referitgame: Referring to objects in pho- tographs of natural scenes

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.766968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4537c502-2c6d-4426-b379-d7e704f01182 · outbound

This paper cites Segment any- thing.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Segment any- thing

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.773397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 498e08ac-b26a-4e81-ba0a-72b9ea507b74 · outbound

This paper cites Obelics: An open web-scale filtered dataset of interleaved image-text documents.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Obelics: An open web-scale filtered dataset of interleaved image-text documents

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:52.067409Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation edc7b207-964e-4d94-a9a5-8430744b0757 · outbound

This paper cites Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:52.052441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation df31fd3d-5dac-45fa-b15f-679ae003b7a9 · outbound

This paper cites Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:52.035819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a9605a61-c8ae-41e0-9f4d-3d396002e224 · outbound

This paper cites Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.790592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc813285-dfe7-4fd3-b6f9-afb74af56bdd · outbound

This paper cites Improved baselines with visual instruction tuning.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Improved baselines with visual instruction tuning

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:52.018806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a7ecdcfe-9f6c-4459-bcf5-0db304b632f6 · outbound

This paper cites Visual instruction tuning.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Visual instruction tuning

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.799196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b83f99a5-dfb7-4b51-9a2e-7bcbb960c4fc · outbound

This paper cites Mmbench: Is your multi-modal model an all-around player? In European Conference on Computer Vision, pages 216–233.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Mmbench: Is your multi-modal model an all-around player? In European Conference on Computer Vision, pages 216–233

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:51.993626Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7ef00490-519f-4bce-84a9-5df723c612a7 · outbound

This paper cites Learn to explain: Multimodal reasoning via thought chains for science question answering.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Learn to explain: Multimodal reasoning via thought chains for science question answering

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.808685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59f2ed0c-4b47-41f5-a632-ef2eab90590a · outbound

This paper cites Generation and comprehension of unambiguous object descriptions.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Generation and comprehension of unambiguous object descriptions

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:51.965097Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a7f0785d-addd-4aad-a03f-f9616356999b · outbound

This paper cites Self-distillation amplifies regularization in hilbert space.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Self-distillation amplifies regularization in hilbert space

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:51.948884Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 39563cd3-562a-4d3a-9847-9331d19cfe9c · outbound

This paper cites DINOv2: Learning Robust Visual Features without Supervision.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models DINOv2: Learning Robust Visual Features without Supervision

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.823423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93ae3b32-05d0-4e7e-83d2-dc066eb27ba9 · outbound

This paper cites Towards vision-language mechanistic interpretabil- ity: A causal tracing tool for blip.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Towards vision-language mechanistic interpretabil- ity: A causal tracing tool for blip

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:51.931754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0c5dd1c1-844c-4056-9f6c-214e315a9eda · outbound

This paper cites Bridging Vision and Language Spaces with Assignment Prediction.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Bridging Vision and Language Spaces with Assignment Prediction

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-08-05T22:35:51.403848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c66dc27b-bfa2-4ccf-bf9d-768a8cde5a62 · outbound

This paper cites Relational knowledge distillation.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Relational knowledge distillation

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:51.913886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d40f46a3-2fcd-43af-843b-4ba4b19de5ea · outbound

This paper cites Multi-modal Auto-regressive Modeling via Visual Words.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Multi-modal Auto-regressive Modeling via Visual Words

Reference 45

Resolution: verified exact; local_arxiv, observed 2026-08-05T22:35:51.374658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1432a2b3-15ca-4824-b862-44626d0e0937 · outbound

This paper cites BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.855107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b928c81-94b3-42c5-a975-cd0bc3f77287 · outbound

This paper cites Distillation-based training for multi-exit architectures.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Distillation-based training for multi-exit architectures

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:51.898383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a6bff80d-3143-4c4f-b530-ad550e46d76f · outbound

This paper cites Learning transferable visual models from natural language supervi- sion.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Learning transferable visual models from natural language supervi- sion

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:51.880916Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 68fa1b46-277f-42de-b208-af31d40615e4 · outbound

This paper cites https://sharegpt.com/, 2023.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models https://sharegpt.com/, 2023

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:51.860116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ef80358d-b4f4-414a-8d08-98c36f3996a2 · outbound

This paper cites Self-distillation from the last mini-batch for consis- tency regularization.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Self-distillation from the last mini-batch for consis- tency regularization

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:51.839303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 78e534de-7b7c-455d-b174-b2fa44b71fb9 · outbound

This paper cites Towards vqa models that can read.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Towards vqa models that can read

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:51.822872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 28bec035-3033-42fb-9dc7-832a32c0e674 · outbound

This paper cites Emu: Generative pretraining in multimodality.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Emu: Generative pretraining in multimodality

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:51.807330Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 01e9b215-ee77-490e-acec-9ce79773feb5 · outbound

This paper cites Generative multimodal mod- els are in-context learners.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Generative multimodal mod- els are in-context learners

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.897216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e50e2f12-9afb-48f5-b7c9-d1becc473c62 · outbound

This paper cites Chameleon: Mixed-Modal Early-Fusion Foundation Models.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Chameleon: Mixed-Modal Early-Fusion Foundation Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.902847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1af2ba3a-de28-4cb2-a1b8-c5f2b482cd38 · outbound

This paper cites Gemma: Open Models Based on Gemini Research and Technology.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Gemma: Open Models Based on Gemini Research and Technology

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.908617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 881b7a09-e23e-4ea6-ba56-6da4a506c201 · outbound

This paper cites Neural discrete representation learning.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Neural discrete representation learning

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.913808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe509967-c08c-4440-95e7-08e51b647e00 · outbound

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

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.918910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b464dccf-82c5-415a-8e3b-7ee6c73ca14d · outbound

This paper cites CogVLM: Visual Expert for Pretrained Language Models.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models CogVLM: Visual Expert for Pretrained Language Models

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.925833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0343fc5b-0a5b-4893-a932-bfd7ec1bca87 · outbound

This paper cites Do Llamas Work in English? On the Latent Language of Multilingual Transformers.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Do Llamas Work in English? On the Latent Language of Multilingual Transformers

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.930906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 389002d3-9840-4f99-8139-c041a069e964 · outbound

This paper cites Libra: Building decoupled vision system on large lan- guage models.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Libra: Building decoupled vision system on large lan- guage models

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:51.768776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 350f9945-f90c-4fb9-b5a8-fd72c96c38ec · outbound

This paper cites Qwen2 Technical Report.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Qwen2 Technical Report

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.941886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0d7727e-d383-4be2-8759-0418ec76d26a · outbound

This paper cites Snapshot distillation: Teacher-student optimization in one generation.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Snapshot distillation: Teacher-student optimization in one generation

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:51.752840Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1c631496-3b3d-46f0-b4de-2b6e88a6785a · outbound

This paper cites mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.952229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ece70674-f426-4caa-8b23-94f5688ab990 · outbound

This paper cites Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.958123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd89176a-4563-4a09-954b-2777084513bc · outbound

This paper cites MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.965046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c98f7c46-dede-4b3b-8084-af4f288042b5 · outbound

This paper cites How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for Metric Learning.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for Metric Learning

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.970245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 254817d3-8c29-450d-8cc0-6a1244a2b763 · outbound

This paper cites Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-05T22:35:50.975513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cfbed7d-5065-4f0b-a67d-82dba9e00ade · outbound

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

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Sigmoid loss for language image pre-training

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:51.733114Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 107a0250-cf9a-4c02-9cad-a6a47b7d1a3f · outbound

This paper cites Be your own teacher: Improve the performance of convolutional neural networks via self distillation.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Be your own teacher: Improve the performance of convolutional neural networks via self distillation

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:51.717295Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5405491c-0ee7-4509-ac3e-1fe47aa53663 · outbound

This paper cites Self- distillation: Towards efficient and compact neural networks.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Self- distillation: Towards efficient and compact neural networks

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:51.702294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 16ed01c1-cdd9-4097-b31d-5e42bfcd5df1 · outbound

This paper cites Self-distillation as instance- specific label smoothing.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Self-distillation as instance- specific label smoothing

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:51.686436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation fee9d293-fe43-469a-8139-a64fb92017f2 · outbound

This paper cites Decoupled knowledge distillation.

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models Decoupled knowledge distillation

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:35:51.669092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Pith citing papers

Observation 7f1da0d9-bb6c-42ec-8773-cebbd1aa81f4 · inbound

RespiraMFM: A Multimodal Foundation Model with Contrastive Audio-Language Alignment for Respiratory Disease Identification cites this paper.

RespiraMFM: A Multimodal Foundation Model with Contrastive Audio-Language Alignment for Respiratory Disease Identification BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-07-03T03:37:35.646354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.