Paper Citation Record · LEDGER

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression

As of 9 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 0 inbound Pith citation observations for arXiv:2507.20613.

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

pith.paper-citation-record.v1
2507.20613 v1

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T13:30:43.161888Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

36 of 36 outbound references displayed

verified exact1
verified fuzzy21
unresolved14
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation cdf01905-5def-41d3-a335-98eb60a01886 · outbound

This paper cites Mistral 7B.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression Mistral 7B

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T13:30:42.804887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee72836e-d53f-44e3-8084-3344d37c347f · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T13:30:42.818922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76e04a05-3988-4000-ad42-35a10a60b91f · outbound

This paper cites Visual Instruction Tuning.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression Visual Instruction Tuning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T13:30:42.830113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b53ea00-5b6d-4bc8-a389-8fda88643ab1 · outbound

This paper cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T13:30:42.835441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08a05469-5afa-4b1b-a210-d604c3ce094a · outbound

This paper cites Detkds: Knowledge distillation search for object detectors,.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression Detkds: Knowledge distillation search for object detectors,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:30:44.564011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b00d138d-d1e7-42b1-aa05-4f384ca7dda1 · outbound

This paper cites Kd-zero: Evolving knowledge distiller for any teacher-student pairs,.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression Kd-zero: Evolving knowledge distiller for any teacher-student pairs,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:30:44.504365Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6bc3437b-95bd-4437-91f6-17a4d352250f · outbound

This paper cites Diswot: Student architecture search for distillation without training,.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression Diswot: Student architecture search for distillation without training,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:30:44.481187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5c3634d0-805f-40c1-9b16-7a142ce2564a · outbound

This paper cites Automated knowl- edge distillation via monte carlo tree search,.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression Automated knowl- edge distillation via monte carlo tree search,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:30:44.458637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 30a7d02f-3c98-4aa6-afc8-91d37284b4a4 · outbound

This paper cites Norm: Knowledge distillation via n-to-one representation matching,.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression Norm: Knowledge distillation via n-to-one representation matching,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:30:44.424740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 44690b78-098d-483f-96e6-04a1cf32dd4c · outbound

This paper cites Self-regulated feature learning via teacher-free feature distillation,.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression Self-regulated feature learning via teacher-free feature distillation,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:30:44.395837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e5f5ec44-c517-427b-b91e-8cbfbd6d4253 · outbound

This paper cites Attnzero: efficient attention discovery for vision transformers,.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression Attnzero: efficient attention discovery for vision transformers,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:30:44.348391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation af463892-66e4-4904-b57e-6206f954b3c3 · outbound

This paper cites Auto-gas: Automated proxy discovery for training-free generative architecture search,.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression Auto-gas: Automated proxy discovery for training-free generative architecture search,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:30:44.316113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0bd06b3c-4571-4d1b-b54d-4eb843d0e6a3 · outbound

This paper cites Discovering sparsity allocation for layer-wise pruning of large language models,.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression Discovering sparsity allocation for layer-wise pruning of large language models,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:30:44.281817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f973f67c-2c8f-42b1-9d52-217e93f28980 · outbound

This paper cites Als: Adaptive layer sparsity for large language models via activation correlation assessment,.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression Als: Adaptive layer sparsity for large language models via activation correlation assessment,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:30:44.250051Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 59f1ad14-95a1-4808-9923-36e1529f45bc · outbound

This paper cites Pruner-zero: Evolving symbolic pruning metric from scratch for large language models,.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression Pruner-zero: Evolving symbolic pruning metric from scratch for large language models,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:30:44.219538Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 18b23f2f-8d47-4c27-bb43-70182d023917 · outbound

This paper cites Gpt-4 technical report,.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression Gpt-4 technical report,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T13:30:42.987883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0b3b97a-4dfd-4d33-90a9-d17ef05d05f3 · outbound

This paper cites A Survey on Multimodal Large Language Models.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression A Survey on Multimodal Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T13:30:42.992956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcd21370-34b8-465e-b48a-c9e6d7f23fde · outbound

This paper cites MM-LLMs: Recent Advances in MultiModal Large Language Models.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression MM-LLMs: Recent Advances in MultiModal Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T13:30:42.998293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9923c97-ad20-4ae3-82c5-2a9dab66f20f · outbound

This paper cites SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T13:30:43.003466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0faf0ac8-3e2c-4cd0-9e9f-25b3603d3bec · outbound

This paper cites A simple and effective pruning approach for large language models,.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression A simple and effective pruning approach for large language models,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:30:44.155052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f2d54b24-6f97-4cc4-8a80-9fbb479816d7 · outbound

This paper cites LLM-Pruner: On the Structural Pruning of Large Language Models.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression LLM-Pruner: On the Structural Pruning of Large Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T13:30:43.024746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b1e39e2-0511-4df5-baec-b541a4928c86 · outbound

This paper cites EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-08-06T13:30:43.438184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ac3a04cf-5ebe-4896-8822-7e0bd39d986d · outbound

This paper cites Stbllm: Breaking the 1-bit barrier with structured binary llms,.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression Stbllm: Breaking the 1-bit barrier with structured binary llms,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:30:44.126834Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d3fc8da3-71dd-4de2-9dad-c79de0617d28 · outbound

This paper cites Quantization and training of neural networks for efficient integer- arithmetic-only inference,.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression Quantization and training of neural networks for efficient integer- arithmetic-only inference,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:30:44.089521Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e9a7c1fc-1d1d-4332-b169-efcceb261fe6 · outbound

This paper cites Tree-Structured Parzen Estimator: Understanding Its Algorithm Components and Their Roles for Better Empirical Performance.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression Tree-Structured Parzen Estimator: Understanding Its Algorithm Components and Their Roles for Better Empirical Performance

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T13:30:43.067164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ab89baa-e06b-4dcd-b7ca-8de29aed7b1a · outbound

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

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T13:30:43.074900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64d66b4e-b3d5-4e2a-82a3-153fa88c4895 · outbound

This paper cites Instructblip: Towards general-purpose vision-language models with instruction tuning,.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression Instructblip: Towards general-purpose vision-language models with instruction tuning,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:30:44.048696Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 007fcc78-5189-4675-9292-a30cca02c11b · outbound

This paper cites Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T13:30:43.097201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5131ace4-7dca-40ab-b163-ec079b984a33 · outbound

This paper cites Introducing idefics: An open reproduction of state-of-the-art visual language model,.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression Introducing idefics: An open reproduction of state-of-the-art visual language model,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:30:44.021511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 35f1e5dc-0271-429a-982b-be695bf1c1d7 · outbound

This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T13:30:43.115817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09e0b65b-74cd-468f-8ae7-20dc420a63bd · outbound

This paper cites Improved baselines with visual instruction tuning,.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression Improved baselines with visual instruction tuning,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:30:43.976289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 231d81d1-1a62-48dc-9187-53818ebfa90b · outbound

This paper cites Making the v in vqa matter: Elevating the role of image understanding in visual question answering,.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression Making the v in vqa matter: Elevating the role of image understanding in visual question answering,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:30:43.930249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4ddcab95-3a88-47f2-93e2-3e8e6f01496f · outbound

This paper cites Learn to explain: Multimodal reasoning via thought chains for science question answering,.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression Learn to explain: Multimodal reasoning via thought chains for science question answering,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:30:43.884804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c0e2264f-066b-4b86-9a53-4fd91feaf5aa · outbound

This paper cites Towards vqa models that can read,.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression Towards vqa models that can read,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:30:43.859286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c43d2c17-4b78-4c1c-a36d-db4b97d7bb6d · outbound

This paper cites Evaluating Object Hallucination in Large Vision-Language Models.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression Evaluating Object Hallucination in Large Vision-Language Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T13:30:43.156497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abfca8b3-18f9-4ca2-858c-8900646299d9 · outbound

This paper cites Pointer sentinel mixture models,.

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression Pointer sentinel mixture models,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T13:30:43.822970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Pith citing papers

No inbound Pith citation observations are available.