When and why vision-language models behave like bags-of-words, and what to do about it? | Paper Citation Record

Observation 1c5deeee-8208-4051-8fa1-6835cb49f8d4 · inbound

Text Embedding is Not All You Need: Attention Control for Text-to-Image Semantic Alignment with Text Self-Attention Maps cites this paper.

Text Embedding is Not All You Need: Attention Control for Text-to-Image Semantic Alignment with Text Self-Attention Maps When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-12T15:08:54.627473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96a26a43-d54f-4170-b4aa-97439c27ece7 · inbound

Enhancing CLIP Conceptual Embedding through Knowledge Distillation cites this paper.

Enhancing CLIP Conceptual Embedding through Knowledge Distillation When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T22:24:06.780353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50cdc964-c232-4af0-8d39-bb20326e98bb · inbound

VladVA: Discriminative Fine-tuning of LVLMs cites this paper.

VladVA: Discriminative Fine-tuning of LVLMs When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-11T21:29:26.523972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 877fa6fe-ab78-42a7-8366-1b8646e0b093 · inbound

RelationField: Relate Anything in Radiance Fields cites this paper.

RelationField: Relate Anything in Radiance Fields When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-11T12:59:14.424665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c27b363-2f48-49de-8803-0715862d5e01 · inbound

ViGiL3D: A Linguistically Diverse Dataset for 3D Visual Grounding cites this paper.

ViGiL3D: A Linguistically Diverse Dataset for 3D Visual Grounding When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-10T22:32:38.758354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29cd9db1-eda2-4a78-ad7d-ccab212b63f4 · inbound

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency cites this paper.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-10T21:26:00.653529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a69c6cc-4c96-4ed1-b5c7-fb92fb010c16 · inbound

FLORA: Formal Language Model Enables Robust Training-free Zero-shot Object Referring Analysis cites this paper.

FLORA: Formal Language Model Enables Robust Training-free Zero-shot Object Referring Analysis When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-10T19:39:25.093138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a402747d-6017-4b4e-a935-9af29a8907bf · inbound

WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation cites this paper.

WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 58

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T16:24:27.539998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4323f224-8df8-4547-8e42-746b7bad621f · inbound

Decoupled Global-Local Alignment for Improving Compositional Understanding cites this paper.

Decoupled Global-Local Alignment for Improving Compositional Understanding When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-16T10:59:52.486750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44242c63-bf64-44cd-9389-36287455d129 · inbound

Multi-Modal Language Models as Text-to-Image Model Evaluators cites this paper.

Multi-Modal Language Models as Text-to-Image Model Evaluators When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-16T04:43:11.456920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d722abd3-f017-4e8d-a970-bc9b23a064c6 · inbound

Visually Guided Decoding: Gradient-Free Hard Prompt Inversion with Language Models cites this paper.

Visually Guided Decoding: Gradient-Free Hard Prompt Inversion with Language Models When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T21:55:28.262510Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dff164eb-6c6a-4acf-8cb4-bee651993ea6 · inbound

Visual Perturbation and Adaptive Hard Negative Contrastive Learning for Compositional Reasoning in Vision-Language Models cites this paper.

Visual Perturbation and Adaptive Hard Negative Contrastive Learning for Compositional Reasoning in Vision-Language Models When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T15:17:42.791864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b905e8a-b3f0-4abc-a0ef-56ac6cc61eab · inbound

TNG-CLIP:Training-Time Negation Data Generation for Negation Awareness of CLIP cites this paper.

TNG-CLIP:Training-Time Negation Data Generation for Negation Awareness of CLIP When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T14:35:00.457612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5978c2a7-5ae2-4d2b-a6dc-1796a0f67198 · inbound

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis cites this paper.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:12.731024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2650a0af-46a6-4c1d-a009-fa9c1ab10f53 · inbound

IKIWISI: An Interactive Visual Pattern Generator for Evaluating the Reliability of Vision-Language Models Without Ground Truth cites this paper.

IKIWISI: An Interactive Visual Pattern Generator for Evaluating the Reliability of Vision-Language Models Without Ground Truth When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-07T13:15:56.159838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21d5b03d-47ce-423f-916d-6834d1354101 · inbound

From Local Cues to Global Percepts: Emergent Gestalt Organization in Self-Supervised Vision Models cites this paper.

From Local Cues to Global Percepts: Emergent Gestalt Organization in Self-Supervised Vision Models When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T12:03:53.099753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ceca9211-8036-4760-80a7-1391c7ff2020 · inbound

CIVET: Systematic Evaluation of Understanding in VLMs cites this paper.

CIVET: Systematic Evaluation of Understanding in VLMs When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:36.339325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ed8fddf-ba6d-48cb-8c12-f3952ea698e1 · inbound

On the rankability of visual embeddings cites this paper.

On the rankability of visual embeddings When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-06T20:11:51.695389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48d636dd-8c85-446d-acd7-e7f440c730b8 · inbound

ADIEE: Automatic Dataset Creation and Scorer for Instruction-Guided Image Editing Evaluation cites this paper.

ADIEE: Automatic Dataset Creation and Scorer for Instruction-Guided Image Editing Evaluation When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-06T18:48:45.958345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e72a3b76-2f3c-414e-b73d-298ca1be321a · inbound

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models cites this paper.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:48.147656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 720d82eb-b1da-4161-9cf6-1fba16e76b26 · inbound

Advancing Multimodal LLMs by Large-Scale 3D Visual Instruction Dataset Generation cites this paper.

Advancing Multimodal LLMs by Large-Scale 3D Visual Instruction Dataset Generation When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-06T18:24:54.449939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d715b9ac-d1c6-4571-9849-5ace6a338478 · inbound

Response Wide Shut? Surprising Observations in Basic Vision Language Model Capabilities cites this paper.

Response Wide Shut? Surprising Observations in Basic Vision Language Model Capabilities When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T18:36:01.402381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 444a16d3-f9e4-41d5-9686-898887bac9e4 · inbound

Negation-Aware Test-Time Adaptation for Vision-Language Models cites this paper.

Negation-Aware Test-Time Adaptation for Vision-Language Models When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-15T18:08:58.775271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e3e5cde-ade4-4b49-9635-629d88a904b2 · inbound

Trade-offs in Image Generation: How Do Different Dimensions Interact? cites this paper.

Trade-offs in Image Generation: How Do Different Dimensions Interact? When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-06T12:08:01.848706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b0e5a8a-4ba5-4085-a5dc-479711bd9875 · inbound

MAG-Nav: Language-Driven Object Navigation Leveraging Memory-Reserved Active Grounding cites this paper.

MAG-Nav: Language-Driven Object Navigation Leveraging Memory-Reserved Active Grounding When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T23:40:01.070516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0787d3e-1fb8-4ba3-8582-6cbabf57d47e · inbound

Native Hierarchical and Compositional Representations with Subspace Embeddings cites this paper.

Native Hierarchical and Compositional Representations with Subspace Embeddings When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-05T17:45:39.596159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a406c379-ad15-4816-8977-5b9deee8d4c0 · inbound

Understanding Space Is Rocket Science -- Only Top Reasoning Models Can Solve Spatial Understanding Tasks cites this paper.

Understanding Space Is Rocket Science -- Only Top Reasoning Models Can Solve Spatial Understanding Tasks When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-05T11:56:10.958883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fca59d4c-535f-4bc2-94db-56f283c6cb16 · inbound

SPECS: Specificity-Enhanced CLIP-Score for Long Image Caption Evaluation cites this paper.

SPECS: Specificity-Enhanced CLIP-Score for Long Image Caption Evaluation When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-05T10:38:58.449457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8da70f2-04a0-4eb4-ad7a-0cb71a05e33c · inbound

Long Story Short: Disentangling Compositionality and Long-Caption Understanding in Contrastive VLMs cites this paper.

Long Story Short: Disentangling Compositionality and Long-Caption Understanding in Contrastive VLMs When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 45

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T14:41:30.190913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 50be0de3-0ac9-46a6-a88a-d9493641a75e · inbound

GRAPE: Let GRPO Supervise Query Rewriting by Ranking for Retrieval cites this paper.

GRAPE: Let GRPO Supervise Query Rewriting by Ranking for Retrieval When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T12:21:21.345749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a026177b-d17f-4e53-a456-1f2c21502a7a · inbound

TokenSwap: Backdoor Attack on the Compositional Understanding of Large Vision-Language Models cites this paper.

TokenSwap: Backdoor Attack on the Compositional Understanding of Large Vision-Language Models When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T13:52:17.224410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bac79f28-4979-4612-8ae4-10343a704e77 · inbound

Contrastive vision-language learning with paraphrasing and negation cites this paper.

Contrastive vision-language learning with paraphrasing and negation When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T21:09:38.983791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5df9f551-6620-434d-a92a-ae991542f506 · inbound

SPHINX: A Synthetic Environment for Visual Perception and Reasoning cites this paper.

SPHINX: A Synthetic Environment for Visual Perception and Reasoning When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 69

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T04:21:30.812869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 60f5526d-83ee-4184-8ab0-574212d155b7 · inbound

Sparse Neuron Ablation Triggers Catastrophic Collapse of the Language Core in Large Vision-Language Models cites this paper.

Sparse Neuron Ablation Triggers Catastrophic Collapse of the Language Core in Large Vision-Language Models When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-03T19:22:51.598480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22650ba6-8ce3-4633-843e-02d983482f9a · inbound

Adapting MLLMs for Nuanced Video Retrieval cites this paper.

Adapting MLLMs for Nuanced Video Retrieval When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 85

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T22:21:18.885153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation fd44e1be-d98f-4032-8e77-aff850b1e7f6 · inbound

LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation cites this paper.

LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:03.873100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba776f33-078c-43d5-a1df-22b946cefd29 · inbound

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

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:58.781116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f5f8a49-aa49-4479-a17f-bc0fdcfb7987 · inbound

Vision Language Models Cannot Reason About Physical Transformation cites this paper.

Vision Language Models Cannot Reason About Physical Transformation When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-15T13:27:51.848177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24ebf0a7-2571-49e4-beb6-ea2d10b44608 · inbound

To See or To Please: Uncovering Visual Sycophancy and Split Beliefs in VLMs cites this paper.

To See or To Please: Uncovering Visual Sycophancy and Split Beliefs in VLMs When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 35

Resolution: malformed identifier; arxiv_id, observed 2026-05-15T09:19:53.771783Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a984be64-eca3-412b-9df6-7fb35f0d700b · inbound

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning cites this paper.

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T19:48:11.172994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 11950544-6bb9-47fc-b7f1-1b33fdc3dfb5 · inbound

NSFL: A Post-Training Neuro-Symbolic Fuzzy Logic Framework for Boolean Operators in Neural Embeddings cites this paper.

NSFL: A Post-Training Neuro-Symbolic Fuzzy Logic Framework for Boolean Operators in Neural Embeddings When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:41:04.121070Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a31ff7df-3579-42df-8726-b996d065e135 · inbound

All in One: A Unified Synthetic Data Pipeline for Multimodal Video Understanding cites this paper.

All in One: A Unified Synthetic Data Pipeline for Multimodal Video Understanding When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 102

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T10:31:03.898475Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 8ab51118-45e0-44e5-985c-f3a8e5f74b6e · inbound

Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding cites this paper.

Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T10:36:04.871204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation cc21d4ef-fd35-4d23-8679-164dbccdc380 · inbound

AFMRL: Attribute-Enhanced Fine-Grained Multi-Modal Representation Learning in E-commerce cites this paper.

AFMRL: Attribute-Enhanced Fine-Grained Multi-Modal Representation Learning in E-commerce When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-10T00:59:49.741519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5fd61976-d684-4fb7-a2b1-815f2c3b182c · inbound

DCR: Counterfactual Attractor Guidance for Rare Compositional Generation cites this paper.

DCR: Counterfactual Attractor Guidance for Rare Compositional Generation When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 46

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T19:01:11.745909Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 8ac142af-b99a-4ded-bb73-7c7862bdc22d · inbound

Birds of a Feather Flock Together: Background-Invariant Representations via Linear Structure in VLMs cites this paper.

Birds of a Feather Flock Together: Background-Invariant Representations via Linear Structure in VLMs When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 45

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T07:27:29.700340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 29fa1dec-d6fb-4b8e-a0f3-2a0850ee0988 · inbound

A Composite Activation Function for Learning Stable Binary Representations cites this paper.

A Composite Activation Function for Learning Stable Binary Representations When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 80

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T02:07:07.934212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e9375fac-c45b-4910-824a-7ea38570c089 · inbound

Letting the neural code speak: Automated characterization of monkey visual neurons through human language cites this paper.

Letting the neural code speak: Automated characterization of monkey visual neurons through human language When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 104

Resolution: verified exact; arxiv_id, observed 2026-05-13T02:12:07.069071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation deb95c45-a754-48f7-aa21-abff4ff4c1fb · inbound

Letting the neural code speak: Automated characterization of monkey visual neurons through human language cites this paper.

Letting the neural code speak: Automated characterization of monkey visual neurons through human language When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 101

Resolution: verified exact; arxiv_id, observed 2026-05-20T21:19:02.977300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 74997e67-f9ae-4f3a-9c1a-35e44398aed0 · inbound

SMA: Submodular Modality Aligner For Data Efficient Multimodal Learning cites this paper.

SMA: Submodular Modality Aligner For Data Efficient Multimodal Learning When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:32:56.639657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 73d649b2-e73c-4c8d-961c-d21814af32b2 · inbound

Revealing the Gap in Human and VLM Scene Perception through Counterfactual Semantic Saliency cites this paper.

Revealing the Gap in Human and VLM Scene Perception through Counterfactual Semantic Saliency When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 64

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:39:27.778099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 69e4e4ef-8b55-4479-bf43-c039682694d7 · inbound

When Vision Speaks for Sound cites this paper.

When Vision Speaks for Sound When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 69

Resolution: verified exact; arxiv_id, observed 2026-05-20T22:13:46.772599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3beef4a7-9412-4812-8e8b-6b6c89f5b183 · inbound

See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding cites this paper.

See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 92

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T12:13:16.266930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 8d80a690-8f81-4c46-b93c-095273bc7ce0 · inbound

Advancing Creative Physical Intelligence in Large Multimodal Models cites this paper.

Advancing Creative Physical Intelligence in Large Multimodal Models When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 44

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T22:34:02.910384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 97ce575d-8ba8-4720-8fef-d05a526d1cd5 · inbound

A Systematic Study of Behavioral Cloning for Scientific Data Annotation cites this paper.

A Systematic Study of Behavioral Cloning for Scientific Data Annotation When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 238

Resolution: verified exact; arxiv_id, observed 2026-06-29T16:23:38.982894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 068f2855-f599-4563-8fce-1f71c2db2db8 · inbound

Compositionality Emerges in a Narrow Depth-Connectivity Regime: Architecture Constraints and Solution Manifolds cites this paper.

Compositionality Emerges in a Narrow Depth-Connectivity Regime: Architecture Constraints and Solution Manifolds When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 57

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T03:09:29.816466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0ec36d21-fe43-4b22-b26f-4a82aba2d2a5 · inbound

Evaluating and Enhancing Negation Comprehension in Remote Sensing MLLMs cites this paper.

Evaluating and Enhancing Negation Comprehension in Remote Sensing MLLMs When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-07-04T03:29:29.295857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 099a458a-b108-4c3e-a69f-0695d16a60e3 · inbound

ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP cites this paper.

ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 104

Resolution: verified exact; arxiv_id, observed 2026-07-04T13:39:50.738424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 855a6172-026e-477f-b46d-b12025a6dd25 · inbound

Open-Vocabulary and Referring Segmentation for 3D Gaussians Using 2D Detectors cites this paper.

Open-Vocabulary and Referring Segmentation for 3D Gaussians Using 2D Detectors When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-06-30T05:54:18.335565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3ee4f559-ea08-47b3-9dc0-b4a6325d463b · inbound

Sparse Attention for Dense Open-Vocabulary Prediction in CLIP cites this paper.

Sparse Attention for Dense Open-Vocabulary Prediction in CLIP When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-07-09T19:36:29.283063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 6a0b2fbd-b3b5-42cb-b2ee-62af29f5c5bd · inbound

Sparse Attention for Dense Open-Vocabulary Prediction in CLIP cites this paper.

Sparse Attention for Dense Open-Vocabulary Prediction in CLIP When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-14T15:51:57.429693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9105c657-07af-48d0-9cae-0870952e771e · inbound

CLIP-Guided Label-Free Discriminative Region Scoring for Fine-Grained Classification cites this paper.

CLIP-Guided Label-Free Discriminative Region Scoring for Fine-Grained Classification When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T05:13:02.469296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4164caff-3f99-47c4-8d2d-6a1baa7a8a81 · inbound

Trajectory-aware Cross-view Geo-localization with Sequential Observations cites this paper.

Trajectory-aware Cross-view Geo-localization with Sequential Observations When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-01T23:14:57.326327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27680bac-a6b1-4bf0-8faf-6e63a090ef6f · inbound

TPD: Temporal Prior Decoupling for Text-to-Video Diffusion Models cites this paper.

TPD: Temporal Prior Decoupling for Text-to-Video Diffusion Models When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-30T23:29:03.410996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40d68c93-ccc3-4738-8008-65f4bbac032b · inbound

Foveated Probes Recover Localized Binding Information in Vision Foundation Models cites this paper.

Foveated Probes Recover Localized Binding Information in Vision Foundation Models When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T15:24:47.569466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a9b5cbe-0297-4743-80ae-cc5f2ef9f23f · inbound

Mitigating Visual Degradation in MLLMs via Spatial-Spectral Visual Anchor Learning cites this paper.

Mitigating Visual Degradation in MLLMs via Spatial-Spectral Visual Anchor Learning When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-15T15:10:13.240029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d2b224c-6208-4a48-b279-761cbc5e347b · inbound

SVGEval: A Vision-Grounded Framework for Perceptual-Quality Benchmarking and Evaluation in Text-to-SVG Generation cites this paper.

SVGEval: A Vision-Grounded Framework for Perceptual-Quality Benchmarking and Evaluation in Text-to-SVG Generation When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T17:29:19.221100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2e2df52-ce0a-4a6e-95b3-26c4c3e16a94 · inbound

A Multimodal Automatic Redteaming Evaluation based on Atomic Jailbreak Strategy Decoupling and Combination cites this paper.

A Multimodal Automatic Redteaming Evaluation based on Atomic Jailbreak Strategy Decoupling and Combination When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:42.565379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7e661eb-b70a-42f9-85e1-b675b0a4ffa6 · inbound

Rethinking Text-Based Image Retrieval in Specific Domain cites this paper.

Rethinking Text-Based Image Retrieval in Specific Domain When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T14:23:02.412149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers