Pith. sign in

Paper Citation Record · LEDGER

MLLMs are Deeply Affected by Modality Bias

As of 15 August 2026, this Paper Citation Record lists 89 of 89 outbound references and 17 inbound Pith citation observations for arXiv:2505.18657.

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

pith.paper-citation-record.v1
2505.18657 v1

Coverage vector

measured 89 of 89 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:30:22.310402Z

measured 106 of 106 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 17 of 17 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-14T04:35:43.369407Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T11:59:50.223756Z

Reference resolution

89 of 89 outbound references displayed

  • verified exact0
  • verified fuzzy45
  • unresolved44
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation abadf357-7af2-4e8b-9948-53262f65cd1f · outbound

This paper cites Qwen2.5-VL Technical Report.

MLLMs are Deeply Affected by Modality Bias Qwen2.5-VL Technical Report

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:21.429352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:21.429352Z digest=sha256:b2db70d1e29da35bbfefe1a44021e0e0e0c623d7b0e77336a8862dda81a755c7

Observation de9914c2-3abb-45f0-ac95-d09d3c005fa0 · outbound

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

MLLMs are Deeply Affected by Modality Bias Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:21.459812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:21.459812Z digest=sha256:56f40c70e28f1ceaa11c5741a67dab7c61eb22073e702281289e264d4874b62b

Observation 1f977bd7-d0b0-4f54-af21-f70a07258c6f · outbound

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

MLLMs are Deeply Affected by Modality Bias InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:21.513272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:21.513272Z digest=sha256:d56c4212c5cdf077ebd7ddaa3576edfcc4957e96c52943fc6a5233f70ba409a7

Observation 84836bc0-651d-46b3-8fbf-c737d4b9694f · outbound

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

MLLMs are Deeply Affected by Modality Bias Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:21.584728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:21.584728Z digest=sha256:e53e8402c132bffcd0df15db0c787fa27971d5249fe3dd8e73bd0f0fdb5b4d7e

Observation 04bf98c0-6cca-40e7-8fd8-c244a6a200fe · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

MLLMs are Deeply Affected by Modality Bias Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:21.589921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:21.589921Z digest=sha256:4e0e377775161232e609f3fa89b95306e7409457147295c068147d3705a0f5ad

Observation b188da2d-cf46-4df9-b104-023a1c6c1498 · outbound

This paper cites GPT-4o System Card.

MLLMs are Deeply Affected by Modality Bias GPT-4o System Card

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:21.593162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:21.593162Z digest=sha256:931d52154c0ad320402e004808711bb2582cca8a400dbae70377057fca95c027

Observation fae684da-628a-46ff-8b47-8eb63d68578f · outbound

This paper cites Tactile sensing—from humans to humanoids,.

MLLMs are Deeply Affected by Modality Bias Tactile sensing—from humans to humanoids,

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:21.607933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:21.607933Z digest=sha256:dbd7bddb227463f12c46889f81644096fd516c40b97df42a1de562490cbd3d9a

Observation e8a1874e-b341-4cd8-bf36-191136222c82 · outbound

This paper cites Novel tactile sensor technology and smart tactile sensing systems: A review,.

MLLMs are Deeply Affected by Modality Bias Novel tactile sensor technology and smart tactile sensing systems: A review,

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:21.697018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:21.697018Z digest=sha256:c98f556c429d702cb7dd42bbed94e54e44b2a42e8941a23858bae5689de4e53c

Observation 3a8fc65a-4764-44a9-81ce-3d7e7ed403c0 · outbound

This paper cites Recent progress in technologies for tactile sensors,.

MLLMs are Deeply Affected by Modality Bias Recent progress in technologies for tactile sensors,

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:21.755734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:21.755734Z digest=sha256:c90ddcde4ec1c0cfa5468c301fbed983b4cc002bac3d8f6019f9c6897cf7e4cd

Observation c6b63d81-4111-4b67-8bc6-659793d4b861 · outbound

This paper cites Event-based vision: A survey,.

MLLMs are Deeply Affected by Modality Bias Event-based vision: A survey,

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:21.819291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:21.819291Z digest=sha256:481bac6b9510fd714d028237d605f146ba09716c7c3512e625ebcc0115e00521

Observation f1f0f181-d3aa-4f30-b2ed-01657d64df5f · outbound

This paper cites Deep Learning for Event-based Vision: A Comprehensive Survey and Benchmarks.

MLLMs are Deeply Affected by Modality Bias Deep Learning for Event-based Vision: A Comprehensive Survey and Benchmarks

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:21.878801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:21.878801Z digest=sha256:4db66ed7da8a0860e3d1f30c73cd611caae6ff65b298ead19df5c64bec0920c1

Observation 3d2aacf3-1a2b-4646-827a-f296279d0144 · outbound

This paper cites High speed and high dynamic range video with an event camera,.

MLLMs are Deeply Affected by Modality Bias High speed and high dynamic range video with an event camera,

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:21.976724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:21.976724Z digest=sha256:d6120e43732de1543b814af5f28fae0bbd47ae89817a7bf2bfa47cc4658691c9

Observation 8803649e-f34f-46a7-9ee5-7b12445399f1 · outbound

This paper cites 360sfuda++: Towards source-free uda for panoramic segmentation by learning reliable category prototypes,.

MLLMs are Deeply Affected by Modality Bias 360sfuda++: Towards source-free uda for panoramic segmentation by learning reliable category prototypes,

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.058249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.058249Z digest=sha256:1b06bf32aa0c0c772865da77503a8bf911c5b52456f61ee8df5384e8b5974794

Observation af7dc34a-6b02-4acd-8edf-02aad04864be · outbound

This paper cites Semantics distortion and style matter: Towards source-free uda for panoramic segmentation,.

MLLMs are Deeply Affected by Modality Bias Semantics distortion and style matter: Towards source-free uda for panoramic segmentation,

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.075625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.075625Z digest=sha256:9aa44db9ab42f679a0f79941b6811fe09deca973290fd87b13eb40abd608ea0a

Observation 368ebb22-04b4-414d-8dbf-4589bb639cce · outbound

This paper cites Omnisam: Omnidirectional segment anything model for uda in panoramic semantic segmentation,.

MLLMs are Deeply Affected by Modality Bias Omnisam: Omnidirectional segment anything model for uda in panoramic semantic segmentation,

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.078642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.078642Z digest=sha256:317843c98d67623786059e28b800b25457101c556fe92abd9acb744de2f5f033

Observation ad6c8bab-f38a-40d1-b620-5993180b1833 · outbound

This paper cites Mmbench: Is your multi-modal model an all-around player?,.

MLLMs are Deeply Affected by Modality Bias Mmbench: Is your multi-modal model an all-around player?,

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.081758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.081758Z digest=sha256:9fc5e9b26fcbb82dae0fe8597dbeddf10892e48b4a21764f7dd55dc53b9ac9bf

Observation 10368d55-3909-45c7-a04e-6ec4ff1c7b8f · outbound

This paper cites Mmbench-video: A long- form multi-shot benchmark for holistic video understanding,.

MLLMs are Deeply Affected by Modality Bias Mmbench-video: A long- form multi-shot benchmark for holistic video understanding,

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.084531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.084531Z digest=sha256:23be5745d156414711bac4f9b4d0c4de1b96c39f89a1667a8fe3663607a18a78

Observation 6d86b2eb-c66e-42bc-a795-70e1a17855fe · outbound

This paper cites Docvqa: A dataset for vqa on document images,.

MLLMs are Deeply Affected by Modality Bias Docvqa: A dataset for vqa on document images,

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:23.231183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.087528Z digest=sha256:8b68cd95980b6c3e25e2e05effa1bb759742b5efeb806a3c88397a1a430ff05a

Observation 0f72bb53-9575-40fc-8521-b66c9bf026c8 · outbound

This paper cites A Survey on Multimodal Benchmarks: In the Era of Large AI Models.

MLLMs are Deeply Affected by Modality Bias A Survey on Multimodal Benchmarks: In the Era of Large AI Models

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.090211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.090211Z digest=sha256:4a6171c6a31d9d9cb9f4b614b5c633c20223b8612ce42c5f5177fe8a76c72a57

Observation 7e2f3ed1-726d-445c-be3e-c0fba0554758 · outbound

This paper cites A Survey on Benchmarks of Multimodal Large Language Models.

MLLMs are Deeply Affected by Modality Bias A Survey on Benchmarks of Multimodal Large Language Models

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.093509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.093509Z digest=sha256:660f3faca500093ddae0e6df8c0dbe83b12ff3f1231ce5597320b6d660348166

Observation 22a4348b-32aa-45d7-840f-981ad9e234c0 · outbound

This paper cites Visual Prompting in Multimodal Large Language Models: A Survey.

MLLMs are Deeply Affected by Modality Bias Visual Prompting in Multimodal Large Language Models: A Survey

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.096111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.096111Z digest=sha256:dbc22e957b09884452bfd88b7071c09d821b1bcf2d843eccb6e1e5fd208e245b

Observation 240c9f7b-1905-4a45-85fa-6f8e67264a99 · outbound

This paper cites Survey of Adversarial Robustness in Multimodal Large Language Models.

MLLMs are Deeply Affected by Modality Bias Survey of Adversarial Robustness in Multimodal Large Language Models

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.098809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.098809Z digest=sha256:24298928b9983002712287c42460c4d637fc7f724383d79fb9aff4cc77af1c6c

Observation 5dd9b372-1165-4af8-9407-018a5b441505 · outbound

This paper cites When Continue Learning Meets Multimodal Large Language Model: A Survey.

MLLMs are Deeply Affected by Modality Bias When Continue Learning Meets Multimodal Large Language Model: A Survey

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.101577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.101577Z digest=sha256:b3341b8ff0389a74c7b17de343503192af1e1189c2ce5fbd4b22cece3dcb4c81

Observation 48a07fd0-6595-4230-a234-f4278ffaa336 · outbound

This paper cites Debiasing Multimodal Large Language Models via Penalization of Language Priors.

MLLMs are Deeply Affected by Modality Bias Debiasing Multimodal Large Language Models via Penalization of Language Priors

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.104648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.104648Z digest=sha256:bbb93c27778dc4c57ab80cb51e61eb88fc91851ed5efc1992d554c2dfd69c38d

Observation 930a19f3-df9e-4833-8bc6-83e4ba5c06bf · outbound

This paper cites Assessing modality bias in video question answering benchmarks with multimodal large language models,.

MLLMs are Deeply Affected by Modality Bias Assessing modality bias in video question answering benchmarks with multimodal large language models,

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:23.221346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.107563Z digest=sha256:67309f996c825eca1d381065d3b46c910f5c0fe7367fdb5623c2d4275147dd0e

Observation 75e16f0a-368a-4d2e-ade3-b2407f7b5c43 · outbound

This paper cites Eyes wide shut? exploring the visual shortcomings of multimodal llms,.

MLLMs are Deeply Affected by Modality Bias Eyes wide shut? exploring the visual shortcomings of multimodal llms,

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.110240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.110240Z digest=sha256:67c953f2767a21d442da106984920c95621dc6e6fef37e3c111fac6248bb0d6f

Observation bd31e67a-1889-4193-a03b-1846439542d8 · outbound

This paper cites Are We on the Right Way for Evaluating Large Vision-Language Models?.

MLLMs are Deeply Affected by Modality Bias Are We on the Right Way for Evaluating Large Vision-Language Models?

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.113116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.113116Z digest=sha256:b53260a76203e442a9946bcc4a95e5e6fe6d9e5e6d2fce8ce5387355a1a8ed91

Observation fdd05ac9-8660-40a5-8796-0e0a62eae093 · outbound

This paper cites Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective.

MLLMs are Deeply Affected by Modality Bias Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.115900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.115900Z digest=sha256:810994f4d6aa448792e9e97f2c2c2411123aaa7360dbc903063dd9e7de69369b

Observation 32ab4fa7-1ee6-4b7f-b712-ece5487f0cad · outbound

This paper cites MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark.

MLLMs are Deeply Affected by Modality Bias MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.118528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.118528Z digest=sha256:3fc8f3705718acbeb11c10bb8e44925c815777106a889df629d0323e8eff6b66

Observation e9eeb4cc-c199-42b3-a5d3-e11791352b31 · outbound

This paper cites Multimodal learning with transformers: A survey,.

MLLMs are Deeply Affected by Modality Bias Multimodal learning with transformers: A survey,

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:23.205609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.121281Z digest=sha256:e9fe1b39cd9e6970977494169703d20098fce9501b43d105507f4c8cb7046d37

Observation 785f5e72-992b-497b-9e28-1af5ce9120e7 · outbound

This paper cites A survey on deep multimodal learning for computer vision: advances, trends, applications, and datasets,.

MLLMs are Deeply Affected by Modality Bias A survey on deep multimodal learning for computer vision: advances, trends, applications, and datasets,

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:23.195082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.123962Z digest=sha256:5860cb5d457caa6c6bcc3b9e49cf5c9d97296f1d062fba9c7f5d18d81555c09c

Observation 1efb1648-6f3f-4ad4-9f34-c66904626dfd · outbound

This paper cites A review on methods and applications in multimodal deep learning,.

MLLMs are Deeply Affected by Modality Bias A review on methods and applications in multimodal deep learning,

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:23.183537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.127154Z digest=sha256:36bbfcacf273e5cf241593b0fa092dece6ee06075ba6cbbbabc90e7bb8948b84

Observation d748db31-5f83-40eb-996d-6fc45ace69dd · outbound

This paper cites Learning modality-agnostic representation for semantic segmentation from any modalities,.

MLLMs are Deeply Affected by Modality Bias Learning modality-agnostic representation for semantic segmentation from any modalities,

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:23.173138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.129748Z digest=sha256:56602cd9f04d7d7b1e8f3a1052b7599dbe74f39cc794167437f4a434cd1ab984

Observation 920b8fe1-f8ca-4dd9-bc5d-82c150b38cb0 · outbound

This paper cites MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation.

MLLMs are Deeply Affected by Modality Bias MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.133352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.133352Z digest=sha256:64dc2e0dd56959e4ea6a08539d825ab48dc12b3b809caf64905210acba6609d9

Observation d3cd5a6f-8cde-4b9e-9714-82afa793bde4 · outbound

This paper cites Cafuser: Condition-aware multimodal fusion for robust semantic perception of driving scenes,.

MLLMs are Deeply Affected by Modality Bias Cafuser: Condition-aware multimodal fusion for robust semantic perception of driving scenes,

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:23.162814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.136221Z digest=sha256:251e4425c2df4cde8dcf531f3557df10a25f41491de924d625a41720db274a09

Observation e6e58c7d-e301-4082-9d52-5b2b22c37770 · outbound

This paper cites Multimodality represen- tation learning: A survey on evolution, pretraining and its applications,.

MLLMs are Deeply Affected by Modality Bias Multimodality represen- tation learning: A survey on evolution, pretraining and its applications,

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:23.150498Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.139263Z digest=sha256:ade6e8acdec75115ddebbdf4b3ed8f59839ca4690821a9005c7a60d669fc52d6

Observation c4427475-67fb-4abf-a814-295a0c98e5d5 · outbound

This paper cites Enhancing multimodal cooperation via sample-level modality valuation,.

MLLMs are Deeply Affected by Modality Bias Enhancing multimodal cooperation via sample-level modality valuation,

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:23.138981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.142122Z digest=sha256:6ff1f586ccadf7deccfc1d92c59ccaf06ca8aaa81ae3c488700f69ed5135ec3d

Observation b25be5e1-2a98-4a37-8d5e-64e3a28b5c96 · outbound

This paper cites Centering the value of every modality: Towards efficient and resilient modality-agnostic semantic segmentation,.

MLLMs are Deeply Affected by Modality Bias Centering the value of every modality: Towards efficient and resilient modality-agnostic semantic segmentation,

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:23.127895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.144730Z digest=sha256:e15b9b9bd12ac5f8146b593bdbe5034c5be08254193d7db1f4ce8b2f5cb9d321

Observation 9eaf1cb3-d80c-4765-8697-b2d87d7cbae4 · outbound

This paper cites Reducing Unimodal Bias in Multi-Modal Semantic Segmentation with Multi-Scale Functional Entropy Regularization.

MLLMs are Deeply Affected by Modality Bias Reducing Unimodal Bias in Multi-Modal Semantic Segmentation with Multi-Scale Functional Entropy Regularization

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.147211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.147211Z digest=sha256:7f54eedd5f72df5bfa3db9325e6eb87ba5d871ee6fdcec2ecf7a8ffb8f273ece

Observation 32bd4f51-859d-493b-a30d-7056d89fb687 · outbound

This paper cites Learning Robust Anymodal Segmentor with Unimodal and Cross-modal Distillation.

MLLMs are Deeply Affected by Modality Bias Learning Robust Anymodal Segmentor with Unimodal and Cross-modal Distillation

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.150289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.150289Z digest=sha256:266e4925f9858690f3b9548fb450d27e88961dedbb02be2a4a76babd917d270c

Observation 4240287c-4dd6-43b6-9b7e-95bc67605209 · outbound

This paper cites Balanced multimodal learning via on-the-fly gradient modulation,.

MLLMs are Deeply Affected by Modality Bias Balanced multimodal learning via on-the-fly gradient modulation,

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:23.114742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.153165Z digest=sha256:6b8eb145a03a9241480f7872a32a8fc65a779808e6610ebe8843d925bb20070c

Observation 7f854eed-ce46-418b-a9f9-82957d64b9ec · outbound

This paper cites Clip the bias: How useful is balancing data in multimodal learning?,.

MLLMs are Deeply Affected by Modality Bias Clip the bias: How useful is balancing data in multimodal learning?,

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:23.103890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.155716Z digest=sha256:7833cb88b9aeee03e489165ddd1c6c08778724b801ccd4cf500749ebd395864c

Observation d983c414-9160-48e0-bcd9-99226fe98920 · outbound

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

MLLMs are Deeply Affected by Modality Bias Learning transferable visual models from natural language supervi- sion,

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.158369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.158369Z digest=sha256:e1ef9772ef25404e290f6187bc0cf032630815186c9b35f73ade6b31eac37fdd

Observation 5281160e-64e4-46c1-8726-11206bfeb0c3 · outbound

This paper cites Clippo: Image-and-language understanding from pixels only,.

MLLMs are Deeply Affected by Modality Bias Clippo: Image-and-language understanding from pixels only,

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:23.086597Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.161631Z digest=sha256:7881d7841cb20db5ea683049172d5979de7b0189543705d6064a2678409ab450

Observation 3863a0eb-aab7-41a9-b071-513a6915dc96 · outbound

This paper cites Clip-kd: An empirical study of clip model distillation,.

MLLMs are Deeply Affected by Modality Bias Clip-kd: An empirical study of clip model distillation,

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:23.075659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.164266Z digest=sha256:9dd9ce79c64779249b01da7c24ef27eef84e542e7443e8f28b8da138a09f49a4

Observation 17f011f8-4d95-4edc-9b26-86e7847d4924 · outbound

This paper cites Tinyclip: Clip distillation via affinity mimicking and weight inheritance,.

MLLMs are Deeply Affected by Modality Bias Tinyclip: Clip distillation via affinity mimicking and weight inheritance,

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:23.065651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.167042Z digest=sha256:6203f549c7e1f8fb9116f94ce66873841895fe7913bf7b7b7eab167a8f294c29

Observation 0565e097-cf6d-45be-9d94-5b72c4772f89 · outbound

This paper cites An inverse scaling law for clip training,.

MLLMs are Deeply Affected by Modality Bias An inverse scaling law for clip training,

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:23.055966Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.169708Z digest=sha256:7245384d485426e08c6f7bdf461696856cb368acbaf4b6467414dafc88ac7926

Observation eed1ba1d-0733-439f-838c-a82bbfebd2ce · outbound

This paper cites BalanceBenchmark: A Survey for Multimodal Imbalance Learning.

MLLMs are Deeply Affected by Modality Bias BalanceBenchmark: A Survey for Multimodal Imbalance Learning

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.172299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.172299Z digest=sha256:6f64dce890d6f7aff01328c9df204638be56b59cb169f23e1004a22701e3ba88

Observation 54f1252b-063a-4c80-abec-02d1ee4a54bc · outbound

This paper cites Facilitating multimodal classification via dynamically learning modality gap,.

MLLMs are Deeply Affected by Modality Bias Facilitating multimodal classification via dynamically learning modality gap,

Reference 49

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:23.045629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.175121Z digest=sha256:ec8618b4ba322421300478612a7ae14ac0e8ad5056574a4bcb37dc2ec162fd25

Observation 226d7d21-0215-4242-98e2-d50a08ebf7c9 · outbound

This paper cites Benchmarking Multi-modal Semantic Segmentation under Sensor Failures: Missing and Noisy Modality Robustness.

MLLMs are Deeply Affected by Modality Bias Benchmarking Multi-modal Semantic Segmentation under Sensor Failures: Missing and Noisy Modality Robustness

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.178436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.178436Z digest=sha256:ef4dea230f671703f5646aecc0aa4c53852b46e5551278aafa1006ce7edfeb5d

Observation a9af95a0-7df2-4c73-8114-69135c20ee99 · outbound

This paper cites The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio.

MLLMs are Deeply Affected by Modality Bias The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.181322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.181322Z digest=sha256:d9d21d6dcf7a3b524a86e4c41207e8143e6d04282abf3cde9d5ceff75deb7e4b

Observation eba14ae4-04a6-4dd1-8bd0-27b3e1fc5453 · outbound

This paper cites On modality bias recognition and reduction,.

MLLMs are Deeply Affected by Modality Bias On modality bias recognition and reduction,

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:23.035177Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.184498Z digest=sha256:984ab090a84c67b774bc5487a64633db51332bcbaadd262cd92ddcb65210637d

Observation 6c3f4aba-7103-404e-ad0e-401272a7a362 · outbound

This paper cites Cross modality bias in visual question answering: A causal view with possible worlds vqa,.

MLLMs are Deeply Affected by Modality Bias Cross modality bias in visual question answering: A causal view with possible worlds vqa,

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:23.024112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.187223Z digest=sha256:02ad4fae53fbbefb85fc73e5469f29b0f857755f58f808c1454baa7b2adef48e

Observation b1fb5883-1613-44da-b211-b78203584a3a · outbound

This paper cites Counterfactual vqa: A cause-effect look at language bias,.

MLLMs are Deeply Affected by Modality Bias Counterfactual vqa: A cause-effect look at language bias,

Reference 54

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:23.013324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.189752Z digest=sha256:33dbd6b88115d5a92542af6b67d02dcbfe1d330ba4a3d7cf224173591b4a7a01

Observation 5fd3e92d-26e7-48b8-8e13-a7016f6e868c · outbound

This paper cites Removing bias in multi-modal classifiers: Regularization by maximizing functional entropies,.

MLLMs are Deeply Affected by Modality Bias Removing bias in multi-modal classifiers: Regularization by maximizing functional entropies,

Reference 55

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:23.003308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.192626Z digest=sha256:affbcb4ee80dabb8b586c1885af49ea2c062f9fb3b289d8d86c7d15cedae6e1d

Observation 6c265d65-7454-45ba-939e-f633f23abb2d · outbound

This paper cites Overcoming language priors in visual question answering with adversarial regularization,.

MLLMs are Deeply Affected by Modality Bias Overcoming language priors in visual question answering with adversarial regularization,

Reference 56

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:22.992584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.195085Z digest=sha256:0dab7891e565e7a135639f1f3ec7387aa39464c5fde66943c55b68955b3be95a

Observation 95f1802f-089e-4d52-a589-a641b2e3f5bc · outbound

This paper cites VLind-Bench: Measuring Language Priors in Large Vision-Language Models.

MLLMs are Deeply Affected by Modality Bias VLind-Bench: Measuring Language Priors in Large Vision-Language Models

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.197925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.197925Z digest=sha256:8f30e8c0a55d8bde642dc679d265c7936a42c8b47359fec4baba343d74494725

Observation d09c89d4-3718-46f9-a9c6-a21ae99ffe63 · outbound

This paper cites Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMs.

MLLMs are Deeply Affected by Modality Bias Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMs

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.201170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.201170Z digest=sha256:2d366a57a9bcc941a25cdadbae89ca58e942e5c95ea1172de36d797fa43899d5

Observation ed7e82ee-c4df-406b-bb6d-e744c18b684d · outbound

This paper cites Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi,.

MLLMs are Deeply Affected by Modality Bias Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi,

Reference 59

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:22.982040Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.204220Z digest=sha256:1ad2d18072a87e5f50d997097b9005717c1615bd8d9b8e694bb46f7dc4c9b6a1

Observation bf7b0c12-2d21-4c55-8a2c-fd6b55594d57 · outbound

This paper cites Mmicl: Empowering vision-language model with multi-modal in-context learning,.

MLLMs are Deeply Affected by Modality Bias Mmicl: Empowering vision-language model with multi-modal in-context learning,

Reference 60

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:22.970869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.206978Z digest=sha256:eebd2777ca225e848a4fb5e68ce0a6c693f88f87508c18a7608ee97a543b74d4

Observation b2929ed7-5c6a-43f6-9111-44acd1117ea8 · outbound

This paper cites Strengthening multimodal large language model with bootstrapped preference optimization,.

MLLMs are Deeply Affected by Modality Bias Strengthening multimodal large language model with bootstrapped preference optimization,

Reference 61

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:22.958519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.209706Z digest=sha256:e529a6f1be7204d907abeac80bc47c17f1b2ed3c229c38bc158360c7f2b29b9b

Observation 145abb58-7810-4d10-9917-8b14b04e042c · outbound

This paper cites Paying more attention to image: A training-free method for alleviating hallucination in lvlms,.

MLLMs are Deeply Affected by Modality Bias Paying more attention to image: A training-free method for alleviating hallucination in lvlms,

Reference 62

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:22.946545Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.212686Z digest=sha256:f0bfb1a062c838f656026079576ed49e4e45ebabc6b422707d7b182dd2df7148

Observation 2793178a-cee2-4fa3-bc9a-0a090975cfb8 · outbound

This paper cites Looking Beyond Text: Reducing Language bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidance.

MLLMs are Deeply Affected by Modality Bias Looking Beyond Text: Reducing Language bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidance

Reference 63

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.216120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.216120Z digest=sha256:c8e4226eea424e40853599ed074935037154add11d2fd710ab73dd14c034ffcd

Observation aa27677a-e313-40c2-a46b-f9467ef70160 · outbound

This paper cites Debiasing Multimodal Large Language Models via Noise-Aware Preference Optimization.

MLLMs are Deeply Affected by Modality Bias Debiasing Multimodal Large Language Models via Noise-Aware Preference Optimization

Reference 64

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.219763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.219763Z digest=sha256:b04202e7d77d4f02cbf4e7f2fc4648195b3bfd826931890c169b84a9014e6d56

Observation 4b25bda4-5890-417e-abb3-c5147a9a2c1a · outbound

This paper cites The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models.

MLLMs are Deeply Affected by Modality Bias The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models

Reference 65

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.222904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.222904Z digest=sha256:d9f976f3ba4cbf0c9c5d94ea36fd554b775c16e9eb00bd069c8043fa17798836

Observation a66f15ad-6718-4f94-91b5-1bae655a8ab8 · outbound

This paper cites DeepSeek-V3 Technical Report.

MLLMs are Deeply Affected by Modality Bias DeepSeek-V3 Technical Report

Reference 66

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.226582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.226582Z digest=sha256:f7388a327c7d201829e409b86edea03b4767a1e56ecc34c21fcdef5c81ac78aa

Observation 24dbfffb-92e8-4f8b-96f4-5184825983ce · outbound

This paper cites DeepSeek LLM: Scaling Open-Source Language Models with Longtermism.

MLLMs are Deeply Affected by Modality Bias DeepSeek LLM: Scaling Open-Source Language Models with Longtermism

Reference 67

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.229737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.229737Z digest=sha256:a9126dfb03f8e7e8a8e522180899292e881484e1e4b99ecbbfd41defd7d67fba

Observation dcbe360a-bf55-4d60-bf25-1a2c58305fd8 · outbound

This paper cites A Comprehensive Overview of Large Language Models.

MLLMs are Deeply Affected by Modality Bias A Comprehensive Overview of Large Language Models

Reference 68

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.233235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.233235Z digest=sha256:361a751bf09ba742be5c74c33447c2a5cc91d3bf6be0d3579c5f7199466559f3

Observation f0b93cc6-1b3c-47e6-ae68-aaa8e7e9b50d · outbound

This paper cites Masked jigsaw puzzle: A versatile position embedding for vision transformers,.

MLLMs are Deeply Affected by Modality Bias Masked jigsaw puzzle: A versatile position embedding for vision transformers,

Reference 69

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:22.936660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.237361Z digest=sha256:9d24a0a45eb6538ce56d3da7a4140e9747797dc23a0031f153ddd5e63f5c0164

Observation 05080f11-c309-4a05-9822-8a3690c70c96 · outbound

This paper cites A survey on vision transformer,.

MLLMs are Deeply Affected by Modality Bias A survey on vision transformer,

Reference 70

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:22.926169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.240687Z digest=sha256:77ca7790c025338b982ddec504be95a1779856a6f2369c5915890c5d5cebbaac

Observation ac964b04-73d0-4318-bc75-bf67cf661dbf · outbound

This paper cites Bringing masked autoencoders explicit contrastive properties for point cloud self-supervised learning,.

MLLMs are Deeply Affected by Modality Bias Bringing masked autoencoders explicit contrastive properties for point cloud self-supervised learning,

Reference 71

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:22.916354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.243960Z digest=sha256:636ae7843ff8478e88d6446dd35bd831d9c52694f6b6258f6cee58d93ccbebf7

Observation c05644ac-d74b-40e8-849c-e84eeae62b23 · outbound

This paper cites Swin transformer: Hierarchical vision transformer using shifted windows,.

MLLMs are Deeply Affected by Modality Bias Swin transformer: Hierarchical vision transformer using shifted windows,

Reference 72

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.247725Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.247725Z digest=sha256:110121fd7d89c595a4f8f1839e93f75834075615d9b31adf0a4f0e2bed756989

Observation b6b99f08-5030-4543-9808-8fbf73ca4cab · outbound

This paper cites Sharing key semantics in transformer makes efficient image restoration,.

MLLMs are Deeply Affected by Modality Bias Sharing key semantics in transformer makes efficient image restoration,

Reference 73

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:22.900881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.250976Z digest=sha256:986789d6d917323d5fcd48dc98ff319a7ad5aa3d18798861d798cb80b60f3e4b

Observation f595a5dd-322b-441f-8fe8-2f54e1c5e178 · outbound

This paper cites Learning disentangled identifiers for action-customized text-to-image generation,.

MLLMs are Deeply Affected by Modality Bias Learning disentangled identifiers for action-customized text-to-image generation,

Reference 74

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:22.889983Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.255003Z digest=sha256:d40af6e907590a7809618fa10244b095dc23d456db6625d8edc983d06e1a9183

Observation 94e2c6fc-7000-47c3-ac38-11650580962c · outbound

This paper cites Languagebind: Extending video-language pretraining to n-modality by language-based semantic alignment,.

MLLMs are Deeply Affected by Modality Bias Languagebind: Extending video-language pretraining to n-modality by language-based semantic alignment,

Reference 75

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:22.877388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.259050Z digest=sha256:8cb990f003e746c435b84910459afcc4e4524dba059dfb7364df95a2de00648c

Observation b179d7a7-2263-4f13-963a-9ca3b55cd60e · outbound

This paper cites Unibind: Llm-augmented unified and balanced representation space to bind them all,.

MLLMs are Deeply Affected by Modality Bias Unibind: Llm-augmented unified and balanced representation space to bind them all,

Reference 76

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:22.865706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.262913Z digest=sha256:07abe40c81bedd435c044227c2090deb891b5a69a558134659f2d6e35fb1ce0a

Observation 8f91d17d-86f8-4764-b193-44e7b3378a20 · outbound

This paper cites Optimizing intersection-over-union in deep neural networks for image segmentation,.

MLLMs are Deeply Affected by Modality Bias Optimizing intersection-over-union in deep neural networks for image segmentation,

Reference 77

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:22.853693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.266455Z digest=sha256:066167521986f8a551d545ba24484f483d820e953cccde53092992cd059d9070

Observation 73692348-413f-4060-a6f0-372b6fd8976e · outbound

This paper cites Generalized inter- section over union: A metric and a loss for bounding box regression,.

MLLMs are Deeply Affected by Modality Bias Generalized inter- section over union: A metric and a loss for bounding box regression,

Reference 78

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:22.839603Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.270817Z digest=sha256:7f089c7bda4c219190b7ae9449ceb253735ec4a93ccf80e898fc464ef2dcb323

Observation e0ca48bf-d094-477e-96f4-6d9151494b36 · outbound

This paper cites Subjective and objective quality assessment for image restoration: A critical survey,.

MLLMs are Deeply Affected by Modality Bias Subjective and objective quality assessment for image restoration: A critical survey,

Reference 79

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:22.826616Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.274373Z digest=sha256:d36d17a18c04055d35873c1e308d8cd2e0417ca86edc3ad327ded89974ab744c

Observation 5d79f5b9-2bf3-49e1-8b1f-412a534e7363 · outbound

This paper cites Lvlm-ehub: A comprehensive evaluation benchmark for large vision-language models,.

MLLMs are Deeply Affected by Modality Bias Lvlm-ehub: A comprehensive evaluation benchmark for large vision-language models,

Reference 80

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:22.815042Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.278422Z digest=sha256:5c4c35b662e8275f4db8cd9d46fefae48042b315ee1a92946f78c04fe03ec621

Observation 99d06a1f-5917-49aa-a3b3-de98a6edb5aa · outbound

This paper cites Valor: Vision-audio-language omni-perception pretraining model and dataset,.

MLLMs are Deeply Affected by Modality Bias Valor: Vision-audio-language omni-perception pretraining model and dataset,

Reference 81

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:22.801518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.281980Z digest=sha256:b95711a616f35ef8e70c0186ee2bef98c8174dfa5760f977d318e99b4b3782e7

Observation e1842fcb-53cd-434f-a681-75f6eb0718f1 · outbound

This paper cites Multimodal visual-tactile representation learning through self-supervised contrastive pre-training,.

MLLMs are Deeply Affected by Modality Bias Multimodal visual-tactile representation learning through self-supervised contrastive pre-training,

Reference 82

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:22.789295Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.285837Z digest=sha256:0cd0d7deb81cdadc0f997211050afe70dc9d917ef740b549273a0b6bf5e56f4f

Observation cac625a7-724d-458f-9e85-53d7e383c7e6 · outbound

This paper cites OmniBind: Teach to Build Unequal-Scale Modality Interaction for Omni-Bind of All.

MLLMs are Deeply Affected by Modality Bias OmniBind: Teach to Build Unequal-Scale Modality Interaction for Omni-Bind of All

Reference 83

Resolution
unresolved
no resolver link, observed 2026-08-07T14:30:22.289194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:30:22.289194Z digest=sha256:0cc3c912d8ccbd7f90faedb4df283a667d63486222d790842a85bebee74644d3

Observation 47d56575-b2a1-4521-855c-d042382911fd · outbound

This paper cites Soft robotic hand with tactile palm-finger coordination,.

MLLMs are Deeply Affected by Modality Bias Soft robotic hand with tactile palm-finger coordination,

Reference 84

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:22.775871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.292730Z digest=sha256:353cb21838305510f979a405c9c1b6f65fab473b7cb053199efaa53b55217083

Observation 03946064-751d-4780-bb07-0fedf7bfaaa5 · outbound

This paper cites Categorizing robots by performance fitness into the tree of robots,.

MLLMs are Deeply Affected by Modality Bias Categorizing robots by performance fitness into the tree of robots,

Reference 85

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:22.762667Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.296123Z digest=sha256:2c0d56cffbd41848fd7984bb8375d4823bb3114af088cb4309f92ceb0a5aa542

Observation b8d77fdc-ab92-4c86-90f1-9c9553170a94 · outbound

This paper cites Vision-based tactile sensor design using physically based rendering,.

MLLMs are Deeply Affected by Modality Bias Vision-based tactile sensor design using physically based rendering,

Reference 86

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:22.751464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.299865Z digest=sha256:49c5acfef1be0cadb9396946115d82656dca2c7f58e03f19e4b65d655a6a5f7c

Observation 6f6640db-e917-4cd2-8627-48c3af45b849 · outbound

This paper cites Bi-vla: Vision-language-action model-based system for bimanual robotic dexterous manipulations,.

MLLMs are Deeply Affected by Modality Bias Bi-vla: Vision-language-action model-based system for bimanual robotic dexterous manipulations,

Reference 87

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:22.739766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.303293Z digest=sha256:4e23adcc9fccbea5d7de4a335f256026524038f8c665eee650610d6e7098940d

Observation 6cc13352-ba83-4d59-9730-629bee828a3b · outbound

This paper cites A practical tutorial on explainable ai techniques,.

MLLMs are Deeply Affected by Modality Bias A practical tutorial on explainable ai techniques,

Reference 88

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:22.728345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.307032Z digest=sha256:316df16da3658ab4ec9665567333bea64ffdc13ab035481da7e0df004f9ccbe2

Observation 27247ff8-dfd5-4b37-9541-3ca6845d5170 · outbound

This paper cites Explainable ai (xai): Core ideas, techniques, and solutions,.

MLLMs are Deeply Affected by Modality Bias Explainable ai (xai): Core ideas, techniques, and solutions,

Reference 89

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:30:22.716378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-07T14:30:22.310402Z digest=sha256:500ed0b5d7a1c5a774a6609e63e729d093f62d7f3a15a6ff9ab1ab21af8b1621

Pith citing papers

Observation 409490f8-ec1c-4261-8af4-a4482362a558 · inbound

Can Large Multimodal Models Actively Recognize Faulty Inputs? A Systematic Evaluation Framework of Their Input Scrutiny Ability cites this paper.

Can Large Multimodal Models Actively Recognize Faulty Inputs? A Systematic Evaluation Framework of Their Input Scrutiny Ability MLLMs are Deeply Affected by Modality Bias

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-06T01:00:28.861351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T01:00:28.861351Z digest=sha256:e6c71d78fc1351d233588994890b855389fb6f861f32727517c159027e33b09c

Observation 44f4ebe2-070c-4bb0-85d9-e8365943b253 · inbound

Omnidirectional Spatial Modeling from Correlated Panoramas cites this paper.

Omnidirectional Spatial Modeling from Correlated Panoramas MLLMs are Deeply Affected by Modality Bias

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-05T11:56:37.791379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T11:56:37.791379Z digest=sha256:7ca2e85f5772aca8b64e0dea50d95628cd4cd41aba2f57817780a3a20aec2030

Observation 163ddd2a-a86a-413e-84b0-168791481c7c · inbound

When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAs cites this paper.

When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAs MLLMs are Deeply Affected by Modality Bias

Reference 60

Resolution
unresolved
no resolver link, observed 2026-08-02T22:14:31.631473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T22:14:31.631473Z digest=sha256:4ba9530d6db0ee9af84adfe52cb8654fbb74b3e47e61b991e9b61366e3ebb941

Observation fbd1d54a-dd4f-4ddb-b55d-2cb5b89c675f · inbound

Token-Efficient Multimodal Reasoning via Image Prompt Packaging cites this paper.

Token-Efficient Multimodal Reasoning via Image Prompt Packaging MLLMs are Deeply Affected by Modality Bias

Reference 4

Resolution
verified exact
arxiv_id, observed 2026-05-13T21:53:19.601782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-05-13T21:52:25.713970Z digest=sha256:3999c09da3e0c00c51a9817e2c6d16b87eba72660483d293d13cfd46b3469aed

Observation f8d109ff-404d-49b4-b09b-18a6839cf17d · inbound

A Systematic Study of Cross-Modal Typographic Attacks on Audio-Visual Reasoning cites this paper.

A Systematic Study of Cross-Modal Typographic Attacks on Audio-Visual Reasoning MLLMs are Deeply Affected by Modality Bias

Reference 17

Resolution
verified exact
arxiv_id, observed 2026-05-13T17:38:02.902544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-05-13T17:34:10.089555Z digest=sha256:b278e4af55739dc5795c7e2ee5008d5745d35129854727753493aadc7db84d13

Observation b07b222e-4d13-46a3-a610-d57a13e7a1b0 · inbound

Beyond Text-Dominance: Understanding Modality Preference of Omni-modal Large Language Models cites this paper.

Beyond Text-Dominance: Understanding Modality Preference of Omni-modal Large Language Models MLLMs are Deeply Affected by Modality Bias

Reference 49

Resolution
verified exact
arxiv_id, observed 2026-05-10T07:11:53.732553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-05-10T07:02:02.752466Z digest=sha256:73987d712f180a95955389466431ee8f5b3e8cef6fdc5e508b9070c3933bcaa7

Observation 4a808afb-0e03-4f25-96d0-9de968dac8e9 · inbound

MiMIC: Mitigating Visual Modality Collapse in Universal Multimodal Retrieval While Avoiding Semantic Misalignment cites this paper.

MiMIC: Mitigating Visual Modality Collapse in Universal Multimodal Retrieval While Avoiding Semantic Misalignment MLLMs are Deeply Affected by Modality Bias

Reference 112

Resolution
verified exact
arxiv_id, observed 2026-05-11T14:21:07.562485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-05-09T21:56:38.004300Z digest=sha256:3e11f94d5de444bf8c98f120dfe283d65970701280452ff53f861fe72c8b458c

Observation 977cd533-9d06-4171-ad7e-30545c81c955 · inbound

Do Composed Image Retrieval Benchmarks Require Multimodal Composition? cites this paper.

Do Composed Image Retrieval Benchmarks Require Multimodal Composition? MLLMs are Deeply Affected by Modality Bias

Reference 13

Resolution
verified exact
arxiv_id, observed 2026-05-20T21:23:44.429486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-05-20T21:20:49.609788Z digest=sha256:9a9f27c421590ae742da1897f78a897c00fdc2f6ad18b4e2c71919dadf8a858f

Observation cc28aa76-c4c2-43ba-8e65-61703fccfcf6 · inbound

Semantic Generative Tuning for Unified Multimodal Models cites this paper.

Semantic Generative Tuning for Unified Multimodal Models MLLMs are Deeply Affected by Modality Bias

Reference 86

Resolution
metadata mismatch
arxiv_id, observed 2026-05-20T11:33:14.210167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-05-20T11:32:24.007847Z digest=sha256:a05efde69cdce5730791c93e230f6155e67797db8ba3eabb17b9b30797888a7b

Observation 69715a54-940a-4a56-bd7d-4de3a12c796a · inbound

Semantic Generative Tuning for Unified Multimodal Models cites this paper.

Semantic Generative Tuning for Unified Multimodal Models MLLMs are Deeply Affected by Modality Bias

Reference 86

Resolution
metadata mismatch
arxiv_id, observed 2026-06-30T18:35:00.347720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-06-30T18:31:10.578558Z digest=sha256:64cfbf3c6076d004004b2f7db18a2a3b23bba4f7ee08bd32d7c9f164248f6e9b

Observation 762b4ad1-b48e-40dd-95e3-99e53e76a9a2 · inbound

Measuring Cross-Modal Synergy: A Benchmark for VLM Explainability cites this paper.

Measuring Cross-Modal Synergy: A Benchmark for VLM Explainability MLLMs are Deeply Affected by Modality Bias

Reference 12

Resolution
verified exact
arxiv_id, observed 2026-05-22T06:06:08.750971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-05-22T06:05:34.039507Z digest=sha256:141bf0252fef25455d9932fcbe3efbe172871c880600b5698517b708db001df4

Observation 7a9952f2-aa1f-416c-a298-703ef7fd3898 · inbound

Sci-Rho: A Multilingual Visually-Grounded Symbolic Benchmark for STEM Problems cites this paper.

Sci-Rho: A Multilingual Visually-Grounded Symbolic Benchmark for STEM Problems MLLMs are Deeply Affected by Modality Bias

Reference 78

Resolution
verified exact
arxiv_id, observed 2026-07-02T20:47:22.882322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-06-27T20:11:02.445626Z digest=sha256:25498518c61a49bd53cbdff42d447c92a624606e1cd7d90d3ac978de3f759f43

Observation 4c0022df-3301-495b-a119-c24451d8c3f6 · inbound

Pareto LoRA: Mitigating Modality Imbalance in Unified Multimodal Models via Pareto-Optimal Gradient Integration cites this paper.

Pareto LoRA: Mitigating Modality Imbalance in Unified Multimodal Models via Pareto-Optimal Gradient Integration MLLMs are Deeply Affected by Modality Bias

Reference 46

Resolution
verified exact
arxiv_id, observed 2026-07-03T17:58:47.380374Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-06-27T03:31:02.911020Z digest=sha256:f65dd4f96195f062607dfffbaa4a4139111a457d30a70691886ad79318d82daa

Observation d21d4326-f5ba-4049-a2d6-e75804a0f5a1 · inbound

Vesta: A Generalist Embodied Reasoning Model cites this paper.

Vesta: A Generalist Embodied Reasoning Model MLLMs are Deeply Affected by Modality Bias

Reference 161

Resolution
verified exact
arxiv_id, observed 2026-07-04T04:29:35.710669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-06-26T16:55:12.518255Z digest=sha256:0fd18286de3754cf08449ba4ec26240479b9c0588b85e7b09d7785679a641282

Observation 9f8ed3fd-eddc-4c01-be3d-3b7158916600 · inbound

CAAD: Contrastive Audio-Aware Distillation for Efficient Speech Language Models cites this paper.

CAAD: Contrastive Audio-Aware Distillation for Efficient Speech Language Models MLLMs are Deeply Affected by Modality Bias

Reference 30

Resolution
verified exact
arxiv_id, observed 2026-07-04T11:59:50.226221Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-06-26T07:28:54.731659Z digest=sha256:a3223a50ca01d972c3fb228a9ed2e4c0c0a5105de4c2d5c59ef1feaf9f39a7f6

Observation 2428e129-1e3e-41a7-a55b-7e035829ebef · inbound

Allocation Before Ranking: Decoupled Token Compression for OmniLLMs cites this paper.

Allocation Before Ranking: Decoupled Token Compression for OmniLLMs MLLMs are Deeply Affected by Modality Bias

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-04T23:23:39.041606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T23:23:39.041606Z digest=sha256:4ad76d394f926ed0fc2da7cd4321ada7b50fc53692f2f5741c8bbb8d952882bf

Observation bd0c3c6f-90de-49e1-b67a-77a01b36c8f5 · inbound

Structure-Preserving Projection for Mitigating Modality Bias in LLM-Based Sequential Recommendation cites this paper.

Structure-Preserving Projection for Mitigating Modality Bias in LLM-Based Sequential Recommendation MLLMs are Deeply Affected by Modality Bias

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-14T04:35:43.369407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-14T04:35:43.369407Z digest=sha256:88853fc964fe4e8dbd2fbc1ba2c3e7d1e440f1f90783cab71723d779a14a4b31