Paper Citation Record · LEDGER

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression

As of 7 August 2026, this Paper Citation Record lists 67 of 67 outbound references and 5 inbound Pith citation observations for arXiv:2509.00419.

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

pith.paper-citation-record.v1
2509.00419 v1

Coverage vector

measured 67 of 67 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T13:42:29.264825Z

measured 72 of 72 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T05:03:26.782904Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T15:59:57.422464Z

Reference resolution

67 of 67 outbound references displayed

verified exact1
verified fuzzy0
unresolved65
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e39a8bf1-6a96-4633-a840-16d2d58e8397 · outbound

This paper cites online" 'onlinestring :=.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression online" 'onlinestring :=

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:22.672491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9af7304-6f1e-4b75-93f5-cf7be541e311 · outbound

This paper cites write newline.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:22.774072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f5f2323-fbf7-48d4-b866-c3214d6797bf · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:38.342321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d7f06c1f-40ff-48c0-80e1-ca68a43e3c98 · outbound

This paper cites HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:22.903167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 603fcc49-fa2b-4b00-8795-4c2462b8697c · outbound

This paper cites Qwen2.5-VL Technical Report.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Qwen2.5-VL Technical Report

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:22.989120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 347f759e-8492-48c5-84ef-6dfbb74b682a · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:23.065410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19f6daa0-b112-4d0b-8739-d3cb0e016320 · outbound

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

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Are We on the Right Way for Evaluating Large Vision-Language Models?

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:23.148844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df1e7d22-0ce9-428d-aadb-65a68c83b5fa · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:38.139124Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7dd90ed1-4f5f-402c-b270-bec831610849 · outbound

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

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:23.334060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b71f6f9e-8bbd-488c-af92-ebd5aa486989 · outbound

This paper cites The Llama 3 Herd of Models.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression The Llama 3 Herd of Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:23.415022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 560f4c9c-079f-44b7-8539-577a27236f78 · outbound

This paper cites Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:23.508694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f23f3775-03fd-4e32-a21e-5b146cf594ea · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 12

Resolution: verified exact; doi, observed 2026-08-05T13:42:29.439727Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1147cb59-830a-408f-99b9-19c28faace18 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:37.952475Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 71527a54-85a4-408a-a8cc-59a865b404be · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 14

Resolution: metadata mismatch; raw_fallback, observed 2026-08-05T13:42:31.030779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a885e856-5489-4b10-a5b8-8f1246dbcfe6 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:37.764141Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ae53f67d-1f4c-43a2-b450-9aa43406ddc4 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:37.533292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c74e6b7b-d87b-4c18-a689-7a8d5c6b64e9 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:37.330147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2dc21c2c-f757-4c8f-8ff8-2dacefe3fbdc · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:37.092695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 15e204f8-d967-4db2-8f4e-5215cf798120 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:36.854096Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 88adabbc-f3bd-4964-881c-21c49781875d · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:36.663296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7942e703-e04c-4a86-9248-d90e23cb6765 · outbound

This paper cites Mixtral of Experts.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Mixtral of Experts

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:24.024369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a371c47-94e7-4010-9ec6-7bcc63c35797 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:24.135702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d9b0595-6538-432c-8b88-2af5e8c6db83 · outbound

This paper cites Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:24.274676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9184c06d-1e16-43a5-a5a6-8298c04848e3 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:36.459732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d544c8a8-2608-4435-bd7b-f86a3f2ebff6 · outbound

This paper cites A Study on Token Pruning for ColBERT.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression A Study on Token Pruning for ColBERT

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:24.576796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80d32214-cd9b-4680-a3e2-3236d9848557 · outbound

This paper cites LLaVA-OneVision: Easy Visual Task Transfer.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression LLaVA-OneVision: Easy Visual Task Transfer

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:24.706806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fcfaf2a-5b8b-41b2-990d-0e07150b2d22 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:36.283379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a4a0ee39-230b-4234-bb61-943f16198377 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:35.997122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 64bdbd4b-cafd-471f-b876-bb7f4949788d · outbound

This paper cites BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:25.233873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87b720a0-3bce-4fe3-9172-8b2ce2411744 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:35.792606Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6c4ce98d-5f94-448c-8c52-98e5e06645e4 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:35.620346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8f897563-0faf-4608-9fef-cee0c1953d83 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:25.812634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3cfce5f-6fc0-463c-b5ae-ba57ba05aea9 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:25.955338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df2cab8c-e828-45da-a04b-041ab567f309 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:35.338419Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b3f3b9b4-3496-4f5f-88e8-c0ad221b67bb · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:26.269777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8602b363-94c4-44e2-92b9-90a272b24cf9 · outbound

This paper cites ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:26.378907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fff648c-754a-4a65-abf4-58b9a9a03746 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:35.148319Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7c1019a9-df2d-4491-9132-b0c54f8e5909 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:34.933892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 54933ae2-6ad6-44e0-ac61-f8078488fb40 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 39

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:34.637417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 572a5fd9-9bb5-413f-b21d-fc320bcca9a9 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:34.408199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 268c6568-f2c4-4d78-b141-00cc5df95e19 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:34.175479Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6310c7f4-3ba8-4fc0-bcd0-e43273fb5e01 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:33.957244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5a75df77-d674-49af-8aa5-1a7007c24541 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 43

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:33.775286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1858da30-ad44-4644-b2d6-33a296c7664e · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:27.219802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e33b9e5b-8a14-45c9-91e5-185a5831f4fc · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 45

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:33.550312Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5f53bc73-532b-48fd-a632-d703e01c71ba · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 46

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:33.367520Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b94b5cbe-cc0b-4558-9749-fdc79c3181a6 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 47

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:33.240837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a5556458-4547-43b2-8622-19b6cc050ee1 · outbound

This paper cites MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:27.635378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2891eb46-dd02-4ca6-83e6-12703098abad · outbound

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

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:27.728036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0f5980a-123e-4b83-b2c3-a3d69785e456 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:27.805437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5d9b632-2d99-4c96-bc62-58df3fb18d29 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 51

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:33.035275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 10561fb1-d74c-4e84-a724-da5e72d258e5 · outbound

This paper cites LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:27.944783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45b5c767-8842-4af4-8e06-31814c83e787 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 53

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:32.875298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bd5ad8e8-fc81-48ee-a34e-24501979196a · outbound

This paper cites Qwen2.5 Technical Report.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Qwen2.5 Technical Report

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:28.151533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e564b3d-cf4c-499e-ac67-fe18c1b5b0d0 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 55

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:32.740147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 89509a5e-4f84-4017-9308-07e483a219ee · outbound

This paper cites LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understanding.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understanding

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:28.293970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 049c161e-8a49-4b47-9290-ff795abedf9a · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:28.410082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6f26fe0-4e32-421e-a57d-cf143ef66f24 · outbound

This paper cites MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:28.502423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6531b8d-3542-4a86-9833-35c90dc321a1 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 59

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:32.576905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2c558228-3dce-432e-9d48-c7a5414d3206 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 60

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:32.417911Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5538dd61-e472-4646-a6fe-73bfb96e193a · outbound

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

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:28.758540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb9953f2-7e5b-4906-b8aa-4cfbb8fb392a · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 62

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:32.133485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a8b6add4-2c32-4340-9e76-eb965d4975ed · outbound

This paper cites Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:28.922349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d467945-0623-4172-9ce8-608ec0c12b99 · outbound

This paper cites Token-level Correlation-guided Compression for Efficient Multimodal Document Understanding.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Token-level Correlation-guided Compression for Efficient Multimodal Document Understanding

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:29.008171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 559511f1-0a75-4938-ab81-a3d6c7986e18 · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 65

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:31.870651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5e0251c3-181a-43d3-8741-1daedf4f0dba · outbound

This paper cites an unresolved cited work.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Unresolved cited work

Reference 66

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:42:31.511234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2f0c0531-01f2-4bf4-8299-2aec7fa82cd7 · outbound

This paper cites MLVU: Benchmarking Multi-task Long Video Understanding.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression MLVU: Benchmarking Multi-task Long Video Understanding

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:29.264825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation a3a4f5ed-3447-4948-8f42-5d316adb27df · inbound

HybridKV: Hybrid KV Cache Compression for Efficient Multimodal Large Language Model Inference cites this paper.

HybridKV: Hybrid KV Cache Compression for Efficient Multimodal Large Language Model Inference LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:20:48.354550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cfbce84e-0766-4d32-b12b-649646c1da17 · inbound

CIVIC: End-to-End Sequence Compactness for Efficient Vision-Language Models cites this paper.

CIVIC: End-to-End Sequence Compactness for Efficient Vision-Language Models LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T12:13:26.454047Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f36012ed-4480-4707-9ac7-e2c97e48ee7b · inbound

Accelerating Multimodal Large Language Models with Prior-Corrected Token Reduction cites this paper.

Accelerating Multimodal Large Language Models with Prior-Corrected Token Reduction LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression

Reference 26

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T15:59:56.765099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation be980c68-f51c-42f2-9eb3-a29cbae6d681 · inbound

Spectral Evolution-Guided Token Pruning in Multimodal Large Language Models cites this paper.

Spectral Evolution-Guided Token Pruning in Multimodal Large Language Models LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression

Reference 30

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T15:59:57.423842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d13bbfb4-1f49-43db-b16c-80d33edd3730 · inbound

Attention-Free and Lightweight Token Reduction for Efficient Vision-Language Models cites this paper.

Attention-Free and Lightweight Token Reduction for Efficient Vision-Language Models LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T05:03:26.782904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.