Paper Citation Record · LEDGER

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues

As of 3 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 1 inbound Pith citation observation for arXiv:2604.24036.

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

pith.paper-citation-record.v1
2604.24036 v2

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-08T04:38:06.673737Z

measured 41 of 41 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-03T06:30:56.289259+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-08T04:38:06.673737Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-05-11T21:41:15.213547Z

Reference resolution

40 of 40 outbound references displayed

verified exact9
verified fuzzy30
unresolved1
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a0160b1f-a493-4f02-a325-c6c6d50c4ffa · outbound

This paper cites Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-11T21:41:15.218723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 51a0d5df-3597-41c9-9e7a-55d007143218 · outbound

This paper cites vehicle” “motorcycle.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues vehicle” “motorcycle

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.446195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 313f9921-d4a7-4613-8f09-c53351899905 · outbound

This paper cites The pedestrians carrying umbrellas.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues The pedestrians carrying umbrellas

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.451353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation eb4f5b00-c628-4f00-976a-1f8831e0e61a · outbound

This paper cites These modules derive and integrate lingusitic semantic pri- ors, enhancing grounding robustness against occlusion and small objects in crowded scenes.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues These modules derive and integrate lingusitic semantic pri- ors, enhancing grounding robustness against occlusion and small objects in crowded scenes

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.459086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 69f883f4-cc5a-4f24-9031-9f3686e96ce6 · outbound

This paper cites Additionally, the supercomputing resource was partially supported by KSC (KSC-2025-CRE-0090).

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Additionally, the supercomputing resource was partially supported by KSC (KSC-2025-CRE-0090)

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.463736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 5607226b-0c6e-4fb5-985c-eb6e444d81d7 · outbound

This paper cites an unresolved cited work.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-05-26T20:43:02.477340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 9b7c3978-2d3a-44ea-8062-ed68e294e9b3 · outbound

This paper cites Qwen2.5-VL Technical Report.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Qwen2.5-VL Technical Report

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-11T21:41:15.245554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 2af1c8ad-4229-40d8-ba8e-fbd58212eb24 · outbound

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

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-11T21:41:15.229293Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 1594cc31-2fa4-4b68-ab46-ff4fe70cb395 · outbound

This paper cites Visionllm: Large language model is also an open-ended decoder for vision-centric tasks.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Visionllm: Large language model is also an open-ended decoder for vision-centric tasks

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.536078Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 075897bc-3e6b-45bc-a436-4dc6bebf38a9 · outbound

This paper cites Kosmos-2: Grounding multimodal large lan- guage models to the world.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Kosmos-2: Grounding multimodal large lan- guage models to the world

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.489266Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation e05854a1-b585-478d-8d30-6cd280b73dc1 · outbound

This paper cites Ferret: Refer and ground anything anywhere at any granularity.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Ferret: Refer and ground anything anywhere at any granularity

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.572753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation b2911d23-037c-4e7a-ac5e-65966a6b8be9 · outbound

This paper cites Groma: Localized visual tokenization for grounding multimodal large language models.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Groma: Localized visual tokenization for grounding multimodal large language models

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.560532Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation c0b42aca-156c-4d4e-a81d-bc1744630647 · outbound

This paper cites ChatRex: Taming Multimodal LLM for Joint Perception and Understanding.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues ChatRex: Taming Multimodal LLM for Joint Perception and Understanding

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:41:15.238967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation deb17694-42ca-4949-b855-cc9c97cd2f28 · outbound

This paper cites Modeling context in referring expressions.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Modeling context in referring expressions

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.564282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 97cd706b-5a73-49eb-b496-2d4d3ea7d2c9 · outbound

This paper cites Generation and comprehension of unambigu- ous object descriptions.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Generation and comprehension of unambigu- ous object descriptions

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.548023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 424a1474-5d98-4aab-9ebe-021720792dc2 · outbound

This paper cites CrowdHuman: A Benchmark for Detecting Human in a Crowd.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues CrowdHuman: A Benchmark for Detecting Human in a Crowd

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:41:15.263199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 6371b8be-e3dd-4598-819a-d2e945f019dc · outbound

This paper cites Visdrone-det2019: The vision meets drone object detection in image challenge results.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Visdrone-det2019: The vision meets drone object detection in image challenge results

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.555748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 7e47a030-e1bc-4f9a-91ef-7531033e1482 · outbound

This paper cites The unmanned aerial vehicle benchmark: Object detection and tracking.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues The unmanned aerial vehicle benchmark: Object detection and tracking

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.552013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 16bb2646-2a81-4f26-b1fb-5ea59daa723f · outbound

This paper cites Refdrone: A challenging benchmark for referring expression comprehension in drone scenes.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Refdrone: A challenging benchmark for referring expression comprehension in drone scenes

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:41:15.255524Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 5f92e2cd-f9bf-4b65-92bb-076b74dbe8db · outbound

This paper cites Language can boost otherwise unseen ob- jects into visual awareness.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Language can boost otherwise unseen ob- jects into visual awareness

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.568845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 24d41887-ea99-42ba-a59d-dd05ed048dce · outbound

This paper cites Words jump-start vision: A label advan- tage in object recognition.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Words jump-start vision: A label advan- tage in object recognition

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.544060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation b74d33f4-b2de-44d5-97d3-2993e3db0e06 · outbound

This paper cites Weather-aware drone-view object detection via environmental context understanding.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Weather-aware drone-view object detection via environmental context understanding

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.576533Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation f0dcedd0-f893-41c4-8377-4992dee0d7f9 · outbound

This paper cites Language-guided Learning for Object Detection Tackling Multiple Variations in Aerial Images.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Language-guided Learning for Object Detection Tackling Multiple Variations in Aerial Images

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:41:15.271640Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation b9fed8b5-a027-4db1-8d40-e578a2e802e5 · outbound

This paper cites Moai: Mixture of all intelligence for large language and vision models.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Moai: Mixture of all intelligence for large language and vision models

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.524479Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 5311179a-7c25-436c-aee7-3aca1bc96c42 · outbound

This paper cites Citypersons: A diverse dataset for pedestrian detection.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Citypersons: A diverse dataset for pedestrian detection

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.509617Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation f93928b3-f4c2-4bda-8db9-1aa041d2afa3 · outbound

This paper cites Widerperson: A diverse dataset for dense pedestrian detection in the wild.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Widerperson: A diverse dataset for dense pedestrian detection in the wild

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.441073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 24dec3c1-7d14-433d-a09a-39ed426da67e · outbound

This paper cites HazyDet: Open-Source Benchmark for Drone-View Object Detection with Depth-Cues in Hazy Scenes.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues HazyDet: Open-Source Benchmark for Drone-View Object Detection with Depth-Cues in Hazy Scenes

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:41:15.210278Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 0648ae53-a755-4d55-a2e0-bdcdd6f58c4b · outbound

This paper cites An image is worth 16x16 words: Trans- formers for image recognition at scale.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues An image is worth 16x16 words: Trans- formers for image recognition at scale

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.481858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 80c2269c-3dd6-4558-b319-dce2eee5d0fd · outbound

This paper cites A convnet for the 2020s.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues A convnet for the 2020s

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.500008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation e40e722b-a530-41d3-ab55-797e51f27aea · outbound

This paper cites Vicuna: An open-source chatbot impress- ing gpt-4 with 90%* chatgpt quality.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Vicuna: An open-source chatbot impress- ing gpt-4 with 90%* chatgpt quality

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.505626Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 53bd0878-64a5-4ce5-92ce-cd644cd29651 · outbound

This paper cites T-rex2: Towards generic object detection via text-visual prompt synergy.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues T-rex2: Towards generic object detection via text-visual prompt synergy

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.515368Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation ad6756e3-f0fe-46da-848d-3f0252bd96d0 · outbound

This paper cites Detrs beat yolos on real-time object detection.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Detrs beat yolos on real-time object detection

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.519975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 6fd53837-d088-40b8-8399-cc30fc18e4f4 · outbound

This paper cites Mask r-cnn.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Mask r-cnn

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.531625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation a266671a-b802-4be4-82ed-250b452d2cde · outbound

This paper cites Gaussian Error Linear Units (GELUs).

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Gaussian Error Linear Units (GELUs)

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-05-11T21:41:15.279343Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 27ad2295-0e18-44ee-a99b-70fb74035341 · outbound

This paper cites Clip-convnextlarge d 320.laion2b-s29b-b131k- ft-soup.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Clip-convnextlarge d 320.laion2b-s29b-b131k- ft-soup

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.485502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation c4c26015-5085-4464-95b8-8d89801e34dd · outbound

This paper cites Attention is all you need.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Attention is all you need

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.493347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 6af14882-c6dc-47a1-95b6-13f418da74bb · outbound

This paper cites Microsoft coco: Common objects in context.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Microsoft coco: Common objects in context

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.539823Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 017d1ecf-4746-40f5-b112-dc4639dcbb57 · outbound

This paper cites Decoupled weight decay regularization.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Decoupled weight decay regularization

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.467564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 0119df1a-7a5d-42b1-8612-20e74770b16b · outbound

This paper cites Meteor: An automatic metric for mt evalu- ation with improved correlation with human judgments.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Meteor: An automatic metric for mt evalu- ation with improved correlation with human judgments

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.471494Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 84533ec3-5232-4497-a586-e40ab5bb527d · outbound

This paper cites Cider: Consensus-based image descrip- tion evaluation.

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues Cider: Consensus-based image descrip- tion evaluation

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T20:43:02.436924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Pith citing papers

Observation a0160b1f-a493-4f02-a325-c6c6d50c4ffa · inbound