Pith. sign in

Paper Citation Record · LEDGER

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning

As of 10 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 20 inbound Pith citation observations for arXiv:2507.03019.

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

pith.paper-citation-record.v1
2507.03019 v1

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T20:47:31.045451Z

measured 50 of 50 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 20 of 20 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-08T18:35:57.447384Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-11T03:17:51.718484Z

Reference resolution

30 of 30 outbound references displayed

  • verified exact0
  • verified fuzzy17
  • unresolved13
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 72268faf-069a-431f-b8e6-dffc9ba58fa1 · outbound

This paper cites The reasoning before the error step cannot be modified.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning The reasoning before the error step cannot be modified

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T20:47:31.494875Z

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.

source=pdf_text observed=2026-08-06T20:47:30.938496Z digest=sha256:b2c75cc4e336eae4487c0cca21c589019e840d7af082b94613e03a32c438f4c8

Observation a4170ffb-9e16-4ad6-be96-b2275cefb51a · outbound

This paper cites The reasoning process is not modified, just insert <back>.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning The reasoning process is not modified, just insert <back>

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T20:47:31.485898Z

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.

source=pdf_text observed=2026-08-06T20:47:30.976545Z digest=sha256:ff0828b1be11e526a79ca7b63d9d7facd2b64187702b7306b68150f3cab77cc7

Observation 316b64c2-2e40-4d95-8204-ccc4e44c92fa · outbound

This paper cites an unresolved cited work.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning Unresolved cited work

Reference 3

Resolution
unresolved
raw_fallback, observed 2026-08-06T20:47:31.477738Z

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.

source=pdf_text observed=2026-08-06T20:47:30.979628Z digest=sha256:57037af3b7019ed0f3386a273bdf376b12003d5c16c9c5d8d3daa85d7b61b2db

Observation eead73e6-af66-49e0-94fb-eb0beb6ebd7b · outbound

This paper cites We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-06T20:47:30.664463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:47:30.664463Z digest=sha256:f2bfeac6cec34241ab974d11d954c6c0a9b031191d45045ee871dfd84c3ce913

Observation c8651eda-4871-4952-b94e-e13f341ad969 · outbound

This paper cites messages.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning messages

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-06T20:47:30.852706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:47:30.852706Z digest=sha256:33aa42cd4f0caa4711c6e611464243785b2633acbc17b4c656a54b9f3468b066

Observation 7d44bd97-0220-45e7-a734-363ea0c07f54 · outbound

This paper cites After simplifying, we find that the ratio is 1 : 3.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning After simplifying, we find that the ratio is 1 : 3

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T20:47:31.383204Z

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.

source=pdf_text observed=2026-08-06T20:47:31.011459Z digest=sha256:a0d5b1c8c8d3b50961b59666642da3ddf4bb074494b77404a1750d4a43df5410

Observation 3847c8ad-c99a-460a-8dee-bce96500c5cd · outbound

This paper cites an unresolved cited work.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning Unresolved cited work

Reference 7

Resolution
unresolved
raw_fallback, observed 2026-08-06T20:47:31.284000Z

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.

source=pdf_text observed=2026-08-06T20:47:31.045451Z digest=sha256:3e7c6347c9bbd0369953f5596b1139d4fcb6527d0a511903254e3254953ad8ae

Observation 9c93a1ab-ccc0-4af9-abdc-35c9502593b8 · outbound

This paper cites Sentence 2 of reasoning.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning Sentence 2 of reasoning

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T20:47:31.469996Z

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.

source=pdf_text observed=2026-08-06T20:47:30.982356Z digest=sha256:da1cffc660ba7b2b701fd43307cdbf98d0a316a062de319f2697a5787869d4ec

Observation 313f719a-b3c2-44c6-8c05-d2cb1f4bbfcc · outbound

This paper cites And rethink and revise the reasoning and answer based on the content after </back>.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning And rethink and revise the reasoning and answer based on the content after </back>

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T20:47:31.461533Z

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.

source=pdf_text observed=2026-08-06T20:47:30.985099Z digest=sha256:569cfeaca8c2b86dd9a4750bdb8177f5ba008eb6e713c27b8ae464ec31a96cf5

Observation f6b1c32b-9d8c-4fcc-9074-6de663f01f3b · outbound

This paper cites And rethink and give the answer after </back>.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning And rethink and give the answer after </back>

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T20:47:31.451232Z

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.

source=pdf_text observed=2026-08-06T20:47:30.988103Z digest=sha256:c7214c226d3e1d8009ac41a3e23631b85a60c6c92025b3a20fa1beef8eb00fc8

Observation c09ed480-8db3-48b4-a59d-07696842c52f · outbound

This paper cites an unresolved cited work.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning Unresolved cited work

Reference 12

Resolution
unresolved
raw_fallback, observed 2026-08-06T20:47:31.442547Z

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.

source=pdf_text observed=2026-08-06T20:47:30.990988Z digest=sha256:0a917d2f0aa052c21f1d3789c6991fe70807bdebce4daa0725fed8eacd883462

Observation 1dc80504-6ca9-4f24-889a-56c0350d6fdd · outbound

This paper cites Sentence 2 of reasoning.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning Sentence 2 of reasoning

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T20:47:31.433859Z

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.

source=pdf_text observed=2026-08-06T20:47:30.993973Z digest=sha256:4212f72f04cc004eb3f098b49ef13bae3c694396bbe167e1a15cb1cbbd014987

Observation e8801faf-eea6-46b1-9815-b14741634d13 · outbound

This paper cites -- A square is drawn such that its vertices are at the centres of the four outer circles.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning -- A square is drawn such that its vertices are at the centres of the four outer circles

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T20:47:31.425989Z

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.

source=pdf_text observed=2026-08-06T20:47:30.996991Z digest=sha256:54c5b95e84d9cbaa047dbb52d27590b56b5fbb6828f30037072153fae1762b56

Observation b2c5f3c5-cb47-4c6d-af47-bd302941ceba · outbound

This paper cites -- The area of the square is (2r)2 = 4r2.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning -- The area of the square is (2r)2 = 4r2

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T20:47:31.418137Z

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.

source=pdf_text observed=2026-08-06T20:47:30.999645Z digest=sha256:26643663f624b417c692442e10e945b1b2128d7c61c71bfbb334e0d2eb78437a

Observation 24795798-e9ce-4018-a7bf-11c55303e088 · outbound

This paper cites -- Since there are five circles, the total area of the circles is 5πr2.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning -- Since there are five circles, the total area of the circles is 5πr2

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T20:47:31.409727Z

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.

source=pdf_text observed=2026-08-06T20:47:31.002688Z digest=sha256:5f2339933d7403e7062f9bea035ae06a6ddffe55dd5983f5afe7180a6a5a3bbb

Observation 33452066-64b7-426e-a04e-4863f2ff224a · outbound

This paper cites -- The unshaded parts are the areas of the circles that are covered by the square.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning -- The unshaded parts are the areas of the circles that are covered by the square

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T20:47:31.401013Z

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.

source=pdf_text observed=2026-08-06T20:47:31.006008Z digest=sha256:d3293b4578171c66a4c0a20bf62b2cf995a13cdf5f184f2f222620ffa7b87887

Observation 3a27c20d-4cda-4af0-a71f-08581c5d41bb · outbound

This paper cites -- The area of the unshaded parts is the area of the square.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning -- The area of the unshaded parts is the area of the square

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T20:47:31.391949Z

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.

source=pdf_text observed=2026-08-06T20:47:31.008830Z digest=sha256:29b52a9e35f9e10379704fab54b4b08ea7ccdbfec431b2cac3c9b267ce6bb404

Observation f1d2322d-ef69-4bab-a264-6b369ba98cae · outbound

This paper cites an unresolved cited work.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning Unresolved cited work

Reference 20

Resolution
unresolved
raw_fallback, observed 2026-08-06T20:47:31.374735Z

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.

source=pdf_text observed=2026-08-06T20:47:31.014141Z digest=sha256:ae8d270250f7ce8d181ff3a8557c9aad4b70d4025391ae09453368a8f4186ee9

Observation 5e38ddfe-ccba-42d7-b7ec-e71fcd97c3fa · outbound

This paper cites an unresolved cited work.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning Unresolved cited work

Reference 21

Resolution
unresolved
raw_fallback, observed 2026-08-06T20:47:31.366120Z

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.

source=pdf_text observed=2026-08-06T20:47:31.019638Z digest=sha256:40293543dd952683ccb5d9bf57741131f2040abdd86b7cd3a87818fd99694629

Observation a884af1b-d4db-4bc2-9f6e-8927f7765689 · outbound

This paper cites an unresolved cited work.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning Unresolved cited work

Reference 22

Resolution
unresolved
raw_fallback, observed 2026-08-06T20:47:31.357756Z

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.

source=pdf_text observed=2026-08-06T20:47:31.022206Z digest=sha256:1ed3eeccb83fb4e17c75fcbccc6590c68616979f69ba09d163fd85fddd6cf9eb

Observation 6dcdea34-8f86-40ce-a359-7692d2af23ed · outbound

This paper cites By observing the sequence, we can see that the dots are moving in a consistent direction.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning By observing the sequence, we can see that the dots are moving in a consistent direction

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T20:47:31.349398Z

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.

source=pdf_text observed=2026-08-06T20:47:31.025111Z digest=sha256:0ac335a618de9ef844c676de9ce5648dc2e380b41d43e74876ecc2f57a71bcdf

Observation 870401c0-d581-4652-8170-e61cdf40c2bc · outbound

This paper cites an unresolved cited work.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning Unresolved cited work

Reference 24

Resolution
unresolved
raw_fallback, observed 2026-08-06T20:47:31.341045Z

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.

source=pdf_text observed=2026-08-06T20:47:31.028214Z digest=sha256:8d0d8de0b6defd34cd0e37c8800100ee48b3a13319370a034de828e71d6b2a4d

Observation 0fb35419-d4ae-44eb-9ab6-f0714d8cb3e5 · outbound

This paper cites -- The measure of an angle formed by a tangent and a chord is equal to half the measure of the intercepted arc.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning -- The measure of an angle formed by a tangent and a chord is equal to half the measure of the intercepted arc

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T20:47:31.331363Z

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.

source=pdf_text observed=2026-08-06T20:47:31.030753Z digest=sha256:5c36f9a6ec7d383f17017a4454c86602ccd3716afdfbcef3bca81ea5d9d49d7f

Observation b0e90f09-baaa-4d16-a5fb-d9da4c825e82 · outbound

This paper cites -- Therefore, mdEB = 2× m∠EGB = 2× 52◦ = 104◦.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning -- Therefore, mdEB = 2× m∠EGB = 2× 52◦ = 104◦

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T20:47:31.319942Z

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.

source=pdf_text observed=2026-08-06T20:47:31.033451Z digest=sha256:b4dd3a1ad958516d7905a77b16e1a7b3e25f86a2112cdc69e7316a222f87412c

Observation 82d11871-e387-481f-ba30-2a5598b78427 · outbound

This paper cites -- Therefore, mdEB = 2× m∠EF B= 2× 30◦ = 60◦.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning -- Therefore, mdEB = 2× m∠EF B= 2× 30◦ = 60◦

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T20:47:31.310874Z

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.

source=pdf_text observed=2026-08-06T20:47:31.037572Z digest=sha256:07a78b6af27e06533fc3a4739985c04f379353299e74b5d8450c5f5ef0dbfcce

Observation 5e332506-330b-47a7-b0a1-ef5c8f485231 · outbound

This paper cites -- Therefore, mdCF = mdF E− mdEB = 118◦ − 60◦ = 58◦.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning -- Therefore, mdCF = mdF E− mdEB = 118◦ − 60◦ = 58◦

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T20:47:31.302131Z

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.

source=pdf_text observed=2026-08-06T20:47:31.040050Z digest=sha256:0f4d239f492a86ec2e0b11ec19270b2b428e000d64ce4c66701b3c166b7828b6

Observation a23ff69d-b599-4f8f-ab9b-606608499545 · outbound

This paper cites an unresolved cited work.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning Unresolved cited work

Reference 29

Resolution
unresolved
raw_fallback, observed 2026-08-06T20:47:31.293210Z

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.

source=pdf_text observed=2026-08-06T20:47:31.042929Z digest=sha256:a66da8e2da5576838267387ec7abe881fab443e5a9f483b03a0f9aead500ffa1

Observation 6b9d713f-51b3-4466-9c0f-dc826ec192b0 · outbound

This paper cites MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-06T20:47:30.353918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:47:30.353918Z digest=sha256:1c29b4ec1610ab875a64d5106ae37d5b0e48f012ac721e9048fbc695abe45da3

Observation aa578c03-8703-4fc1-93bd-46226221280f · outbound

This paper cites arXiv preprint arXiv:2412.05479.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning arXiv preprint arXiv:2412.05479

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-06T20:47:30.547413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:47:30.547413Z digest=sha256:a325194299f985eb31fecacaf67288d090ac18dc178f510273bcdaa17d9adacd

Observation 86a9adda-f003-4b5d-a23b-53cdc9b7dae8 · outbound

This paper cites v1: Learning to Point Visual Tokens for Multimodal Grounded Reasoning.

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning v1: Learning to Point Visual Tokens for Multimodal Grounded Reasoning

Reference 2025

Resolution
unresolved
no resolver link, observed 2026-08-06T20:47:30.268827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:47:30.268827Z digest=sha256:421d29ba5cb46693146576ce2af0408c10cf18f588033efc8b1bd623cbfce9e4

Pith citing papers

Observation a9c58a24-2ada-4ae2-bcc2-700e36a47aa9 · inbound

REVISOR: Beyond Textual Reflection, Towards Multimodal Introspective Reasoning in Long-Form Video Understanding cites this paper.

REVISOR: Beyond Textual Reflection, Towards Multimodal Introspective Reasoning in Long-Form Video Understanding Look-Back: Implicit Visual Re-focusing in MLLM Reasoning

Reference 54

Resolution
verified exact
arxiv_id, observed 2026-05-17T22:20:22.876107Z

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.

source=pdf_text observed=2026-05-17T22:19:36.366837Z digest=sha256:d15939cc7ec53aefa8e5d263266f1c1325a8c49619e98a2365e91cae116b583a

Observation 6ddd8f7e-d16c-47b1-b6f4-56a0019124f3 · inbound

Mimic Human Cognition, Master Multi-Image Reasoning: A Meta-Action Framework for Enhanced Visual Understanding cites this paper.

Mimic Human Cognition, Master Multi-Image Reasoning: A Meta-Action Framework for Enhanced Visual Understanding Look-Back: Implicit Visual Re-focusing in MLLM Reasoning

Reference 78

Resolution
unresolved
no resolver link, observed 2026-08-03T11:13:16.948001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:13:16.948001Z digest=sha256:a4d4f43a5113a846e9f11cfac491a0b7ab6be4800add51d0f1c50727e994a58c

Observation 739bef0c-6e6e-489c-aa56-af425ef1773b · inbound

Spotlight and Shadow: Attention-Guided Dual-Anchor Introspective Decoding for MLLM Hallucination Mitigation cites this paper.

Spotlight and Shadow: Attention-Guided Dual-Anchor Introspective Decoding for MLLM Hallucination Mitigation Look-Back: Implicit Visual Re-focusing in MLLM Reasoning

Reference 45

Resolution
verified exact
arxiv_id, observed 2026-05-11T07:35:57.360254Z

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.

source=arxiv_source observed=2026-05-10T17:07:09.330134Z digest=sha256:f0dd748b99bfd026da1830eb4de4a7515b3c5716104cc0008db61e38f3cdc398

Observation 2a4d0106-50b7-4e5c-afde-4eaed69507a4 · inbound

Visual Enhanced Depth Scaling for Multimodal Latent Reasoning cites this paper.

Visual Enhanced Depth Scaling for Multimodal Latent Reasoning Look-Back: Implicit Visual Re-focusing in MLLM Reasoning

Reference 69

Resolution
verified exact
arxiv_id, observed 2026-05-11T08:11:04.154430Z

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.

source=pdf_text observed=2026-05-10T16:46:36.010169Z digest=sha256:1c63b05479f4a3c9c0f1eaec43a3afbd10d7f3d7aac14ebce897c6b42b1b1ad7

Observation 7eabfee9-cb52-46e3-bfe8-374ed209bb44 · inbound

Visual Enhanced Depth Scaling for Multimodal Latent Reasoning cites this paper.

Visual Enhanced Depth Scaling for Multimodal Latent Reasoning Look-Back: Implicit Visual Re-focusing in MLLM Reasoning

Reference 69

Resolution
verified exact
arxiv_id, observed 2026-05-12T06:06:24.059935Z

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.

source=pdf_text observed=2026-05-12T04:38:06.774877Z digest=sha256:37add17c47fed1301d0a0508d728413526b4a7d118158ae71ca16365de65b044

Observation 30c6268b-57c1-4bda-a947-504f65936629 · inbound

Visual Enhanced Depth Scaling for Multimodal Latent Reasoning cites this paper.

Visual Enhanced Depth Scaling for Multimodal Latent Reasoning Look-Back: Implicit Visual Re-focusing in MLLM Reasoning

Reference 69

Resolution
verified exact
arxiv_id, observed 2026-05-13T07:27:29.283449Z

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.

source=pdf_text observed=2026-05-13T07:26:59.917150Z digest=sha256:c6b55a25250d01e59ba2b1bae8a3f0bcad83f3cefb1f3f8f5d0f4fe02b1f1c78

Observation be0b6ae5-dff0-4d24-955b-4d72ec3f7925 · inbound

Visual Reasoning through Tool-supervised Reinforcement Learning cites this paper.

Visual Reasoning through Tool-supervised Reinforcement Learning Look-Back: Implicit Visual Re-focusing in MLLM Reasoning

Reference 31

Resolution
verified exact
arxiv_id, observed 2026-05-11T12:46:03.088560Z

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.

source=pdf_text observed=2026-05-10T03:05:21.688216Z digest=sha256:965efa2813cd9440cf08a25611cfd3097678ba75a414d6955f881156db4e6bf4

Observation e8d60e04-7225-49d7-9159-1c49dec744b0 · inbound

From Failure to Feedback: Group Revision Unlocks Hard Cases in Object-Level Grounding cites this paper.

From Failure to Feedback: Group Revision Unlocks Hard Cases in Object-Level Grounding Look-Back: Implicit Visual Re-focusing in MLLM Reasoning

Reference 86

Resolution
verified exact
arxiv_id, observed 2026-05-20T18:43:38.812017Z

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.

source=pdf_text observed=2026-05-20T18:39:11.904941Z digest=sha256:1c738b68da2a9bc14c1c4d8e57aa94558dacb50020ecdc9cf5fde94272a7e06f

Observation 8ef41ebd-c14c-474d-9182-b12c7adb8acd · inbound

RAVE: Re-Allocating Visual Attention in Large Multimodal Models cites this paper.

RAVE: Re-Allocating Visual Attention in Large Multimodal Models Look-Back: Implicit Visual Re-focusing in MLLM Reasoning

Reference 11

Resolution
verified exact
arxiv_id, observed 2026-05-20T11:13:13.474746Z

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.

source=pdf_text observed=2026-05-20T11:10:58.225078Z digest=sha256:06efc97de7ec0bb344c1ee973664a6bad028f3ee11c4539a65bc113b07880c73

Observation 19db35b0-c239-44dc-8591-1107bb084684 · inbound

RAVE: Re-Allocating Visual Attention in Large Multimodal Models cites this paper.

RAVE: Re-Allocating Visual Attention in Large Multimodal Models Look-Back: Implicit Visual Re-focusing in MLLM Reasoning

Reference 11

Resolution
verified exact
arxiv_id, observed 2026-07-01T14:55:48.349609Z

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.

source=pdf_text observed=2026-06-30T18:36:56.248838Z digest=sha256:53da9af4b69e2d61bb7b692b089b03189aa83be85b6684e3be5f68c2d9b9bc2a

Observation f341be0b-c6cf-4f68-a3c9-1e5985358497 · inbound

Reasoning Portability: Guiding Continual Learning for MLLMs in the RLVR Era cites this paper.

Reasoning Portability: Guiding Continual Learning for MLLMs in the RLVR Era Look-Back: Implicit Visual Re-focusing in MLLM Reasoning

Reference 56

Resolution
verified exact
arxiv_id, observed 2026-05-20T13:33:19.320896Z

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.

source=pdf_text observed=2026-05-20T13:29:11.509966Z digest=sha256:e653b77dedc10cba8018486c91a686d355b1dd28facbe4c7776fd6236d28d9e1

Observation 141616eb-2574-40b2-8685-dae74dd5d590 · inbound

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning cites this paper.

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning Look-Back: Implicit Visual Re-focusing in MLLM Reasoning

Reference 19

Resolution
metadata mismatch
arxiv_id, observed 2026-06-29T00:12:50.591396Z

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.

source=pdf_text observed=2026-06-28T23:13:15.593994Z digest=sha256:7d899f12bf481d0ee373b14fa5005c0a2b40f46628a29530a8f37d87d1c35f83

Observation 891b51ad-ca93-420d-87d8-b5ec2a5425ec · inbound

Attention-guided Fine-tuning of Multimodal Large Language Models Improves Chain-of-Thought Reasoning cites this paper.

Attention-guided Fine-tuning of Multimodal Large Language Models Improves Chain-of-Thought Reasoning Look-Back: Implicit Visual Re-focusing in MLLM Reasoning

Reference 63

Resolution
metadata mismatch
arxiv_id, observed 2026-07-01T22:06:16.593338Z

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.

source=arxiv_source observed=2026-06-28T15:45:26.891621Z digest=sha256:831471132065da8287de6703279d54ac52fe4946a0c3b5b97f58f82dd876aca4

Observation 8b27f944-ebaf-40ac-a3f1-30c2bf4ac92e · inbound

V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning cites this paper.

V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning Look-Back: Implicit Visual Re-focusing in MLLM Reasoning

Reference 61

Resolution
verified exact
arxiv_id, observed 2026-07-04T19:20:07.215544Z

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.

source=arxiv_source observed=2026-06-25T21:23:10.051805Z digest=sha256:0b53abc6f3cde35181701913a525d8e629f94a2cf623f9c2300ef396a174c9b5

Observation 3e3a7d14-92ee-4bf8-a3c5-42c5fb8be946 · inbound

From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models cites this paper.

From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models Look-Back: Implicit Visual Re-focusing in MLLM Reasoning

Reference 212

Resolution
verified exact
arxiv_id, observed 2026-07-04T15:09:54.955641Z

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.

source=pdf_text observed=2026-06-26T01:50:54.242508Z digest=sha256:8d3184ebcfb1236f0bca55c9a79767310cfbf4f7a75423ce82c91fb8db501446

Observation 3604d31a-385a-4662-88c9-2eeade474ff8 · inbound

LASER: A Corrective Lens for LVLMs via Visual Attention Preservation and Sink Suppression cites this paper.

LASER: A Corrective Lens for LVLMs via Visual Attention Preservation and Sink Suppression Look-Back: Implicit Visual Re-focusing in MLLM Reasoning

Reference 67

Resolution
metadata mismatch
arxiv_id, observed 2026-07-03T16:58:42.487515Z

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.

source=pdf_text observed=2026-07-03T16:53:43.427625Z digest=sha256:b78348fc6260be0a89a289c40d559138452366df2df5f85e53ca6d1e97ed0217

Observation eda8b0fd-22a3-4750-8306-4da2106792c9 · inbound

H-OPD: Confidence Aware Heterogeneous Multi-Teacher Multimodal On-policy Distillation cites this paper.

H-OPD: Confidence Aware Heterogeneous Multi-Teacher Multimodal On-policy Distillation Look-Back: Implicit Visual Re-focusing in MLLM Reasoning

Reference 37

Resolution
unresolved
no resolver link, observed 2026-07-12T09:29:14.105502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-12T09:29:14.105502Z digest=sha256:179ff84ecdd922f5979496db9ead38241245a8ac5ff997087afb198ce4a32636

Observation 73092337-5df1-42f8-ac0f-79d486b5cfa2 · inbound

Scene Graph Thinking: Reinforcing Structured Visual Reasoning for Multimodal Large Language Models cites this paper.

Scene Graph Thinking: Reinforcing Structured Visual Reasoning for Multimodal Large Language Models Look-Back: Implicit Visual Re-focusing in MLLM Reasoning

Reference 23

Resolution
verified exact
local_arxiv, observed 2026-07-11T03:17:51.747056Z

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.

source=pdf_text observed=2026-07-11T03:11:49.713677Z digest=sha256:80cc9dbf16272875cec1d580453c51fedbdcffbe50279dc2f0892818fa342889

Observation e2d3edb7-b771-4f98-82f2-678bc8a38447 · inbound

Scene Graph Thinking: Reinforcing Structured Visual Reasoning for Multimodal Large Language Models cites this paper.

Scene Graph Thinking: Reinforcing Structured Visual Reasoning for Multimodal Large Language Models Look-Back: Implicit Visual Re-focusing in MLLM Reasoning

Reference 23

Resolution
unresolved
no resolver link, observed 2026-07-14T16:12:58.882161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-14T16:12:58.882161Z digest=sha256:efb16f16f92fa3b2f34e0d873ee9748b6835cbf6cda6b613556fbe262fa2c16d

Observation ffec8a5e-e26f-44ad-8867-0d67c196613b · inbound

ReGround: Restoring Visual Grounding in Multi-Step Reasoning through Self-Diagnosis and Visual Re-Examination cites this paper.

ReGround: Restoring Visual Grounding in Multi-Step Reasoning through Self-Diagnosis and Visual Re-Examination Look-Back: Implicit Visual Re-focusing in MLLM Reasoning

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-08T18:35:57.447384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T18:35:57.447384Z digest=sha256:ee7ad3397985a9018e22ddc36c5a3dc0790b10afc32710346111f3360a639e7a