Paper Citation Record · LEDGER

Hyper-ICL: Attention Calibration with Hyperbolic Anchor Distillation for Multimodal In-Context Learning

As of 11 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 0 inbound Pith citation observations for arXiv:2606.04434.

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

pith.paper-citation-record.v1
2606.04434 v1

Coverage vector

measured 12 of 12 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-28T07:23:19.428348Z

measured 12 of 12 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

12 of 12 outbound references displayed

verified exact3
verified fuzzy0
unresolved7
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a34620c4-621d-41be-add0-18f4cf4f846c · outbound

This paper cites D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al.

Hyper-ICL: Attention Calibration with Hyperbolic Anchor Distillation for Multimodal In-Context Learning D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-28T07:23:19.428348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18962731-fec3-402e-ad46-32fd6f744e9d · outbound

This paper cites Microsoft COCO Captions: Data Collection and Evaluation Server.

Hyper-ICL: Attention Calibration with Hyperbolic Anchor Distillation for Multimodal In-Context Learning Microsoft COCO Captions: Data Collection and Evaluation Server

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-02T06:36:43.899682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 5ad2a012-096e-4974-b3ff-675f5d1328cb · outbound

This paper cites A survey on in- context learning.

Hyper-ICL: Attention Calibration with Hyperbolic Anchor Distillation for Multimodal In-Context Learning A survey on in- context learning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-28T07:23:19.428348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f587a21-25df-494d-aced-2ff4860eee1d · outbound

This paper cites SEED-Bench: Benchmarking multimodal large language models.

Hyper-ICL: Attention Calibration with Hyperbolic Anchor Distillation for Multimodal In-Context Learning SEED-Bench: Benchmarking multimodal large language models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-28T07:23:19.428348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 404f11fc-5863-4101-9d6b-32507e697605 · outbound

This paper cites B., Carin, L., and Chen, W.

Hyper-ICL: Attention Calibration with Hyperbolic Anchor Distillation for Multimodal In-Context Learning B., Carin, L., and Chen, W

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-28T07:23:19.428348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd89840e-8c0f-42d1-ae9c-b9b74dc55f22 · outbound

This paper cites Efficient Multi-modal Long Context Learning for Training-free Adaptation.

Hyper-ICL: Attention Calibration with Hyperbolic Anchor Distillation for Multimodal In-Context Learning Efficient Multi-modal Long Context Learning for Training-free Adaptation

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-07-02T06:36:43.893801Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation defdc462-4b8c-4e0b-89aa-4fa6c166045d · outbound

This paper cites Object Hallucination in Image Captioning.

Hyper-ICL: Attention Calibration with Hyperbolic Anchor Distillation for Multimodal In-Context Learning Object Hallucination in Image Captioning

Reference 7

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T06:36:43.897031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation c48426de-3fca-4ba1-a5d9-27c991cf4b10 · outbound

This paper cites Beyond task performance: evaluating and reducing the flaws of large multimodal models with in-context-learning.

Hyper-ICL: Attention Calibration with Hyperbolic Anchor Distillation for Multimodal In-Context Learning Beyond task performance: evaluating and reducing the flaws of large multimodal models with in-context-learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-28T07:23:19.428348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 462a3921-e45c-4ec8-ac0c-c719e8742145 · outbound

This paper cites Function Vectors in Large Language Models.

Hyper-ICL: Attention Calibration with Hyperbolic Anchor Distillation for Multimodal In-Context Learning Function Vectors in Large Language Models

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-07-02T06:36:43.902685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 587d5529-e6de-4240-bad0-d0663b087e45 · outbound

This paper cites These results further demonstrate that the proposed logit-level attention calibration and hyperbolic distillation generalize effectively across diverse MLLM architectures.

Hyper-ICL: Attention Calibration with Hyperbolic Anchor Distillation for Multimodal In-Context Learning These results further demonstrate that the proposed logit-level attention calibration and hyperbolic distillation generalize effectively across diverse MLLM architectures

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-28T07:23:19.428348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79e75153-06e1-4f82-bd86-a3bd9d7c698d · outbound

This paper cites For a fair comparison, the 8-shot ICL baseline also uses demonstrations drawn from the source dataset rather than the target dataset.

Hyper-ICL: Attention Calibration with Hyperbolic Anchor Distillation for Multimodal In-Context Learning For a fair comparison, the 8-shot ICL baseline also uses demonstrations drawn from the source dataset rather than the target dataset

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-28T07:23:19.428348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e729799a-5b72-4e62-b4fe-f8a71fdd65d4 · outbound

This paper cites First, we compute the mean gate value in early layers(0-7) and late layers (24-31), together with the average per-layer standard deviation over heads and query tokens.

Hyper-ICL: Attention Calibration with Hyperbolic Anchor Distillation for Multimodal In-Context Learning First, we compute the mean gate value in early layers(0-7) and late layers (24-31), together with the average per-layer standard deviation over heads and query tokens

Reference 12

Resolution: malformed identifier; no resolver link, observed 2026-06-28T07:23:19.428348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.