Paper Citation Record · LEDGER

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models

As of 9 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 0 inbound Pith citation observations for arXiv:2607.25818.

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

pith.paper-citation-record.v1
2607.25818 v1

Coverage vector

measured 25 of 25 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T01:26:51.082680Z

measured 25 of 25 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+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

25 of 25 outbound references displayed

verified exact0
verified fuzzy0
unresolved25
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 217938a5-dc6f-48ae-827c-0359c6c2cb76 · outbound

This paper cites GPT-4 Technical Report.

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T01:26:49.040376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7528e459-51df-42c7-a31f-d4efa9df8c32 · outbound

This paper cites Qwen2.5-VL Technical Report.

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models Qwen2.5-VL Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T01:26:49.087415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad930bb1-3186-4d39-9854-2e6770810ed4 · outbound

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

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T01:26:49.156022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d5d0b0c-a60c-43e7-b986-44de67cc35c9 · outbound

This paper cites Improved baselines with visual instruction tuning,.

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models Improved baselines with visual instruction tuning,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T01:26:49.238362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93a0201b-11cc-43bf-8462-0143430e69f8 · outbound

This paper cites Internlm-xcomposer2-4khd: A pioneering large vision-language model handling resolutions from 336 pixels to 4k HD,.

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models Internlm-xcomposer2-4khd: A pioneering large vision-language model handling resolutions from 336 pixels to 4k HD,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T01:26:49.340707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b71d865e-e830-4d5c-be0f-d5489301de35 · outbound

This paper cites Dynamicvit: Efficient vision transformers with dynamic token sparsification,.

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models Dynamicvit: Efficient vision transformers with dynamic token sparsification,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T01:26:49.457955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd3b5f41-2a64-46c0-892e-1757334b3692 · outbound

This paper cites An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models,.

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T01:26:49.568708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cab3c0a-6146-49ac-bb56-15432c60c487 · outbound

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

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T01:26:49.636465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a112fd40-00f6-496f-8688-8d9aafd0ea96 · outbound

This paper cites Llava-prumerge: Adaptive token reduction for efficient large multi- modal models,.

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models Llava-prumerge: Adaptive token reduction for efficient large multi- modal models,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T01:26:49.706989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c065bb2-9e5c-4683-b1bc-ede02df0ad86 · outbound

This paper cites Token Merging: Your ViT But Faster.

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models Token Merging: Your ViT But Faster

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T01:26:49.784716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c97e9a89-208e-4001-aa30-80bb68a92d10 · outbound

This paper cites Posprune: Visual token pruning with positional bias correction for efficient large vision-language models,.

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models Posprune: Visual token pruning with positional bias correction for efficient large vision-language models,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T01:26:49.905295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 316f3fca-4fb2-48a5-858b-c012fe4dc4be · outbound

This paper cites Lifting the veil on visual information flow in mllms: Unlocking pathways to faster inference,.

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models Lifting the veil on visual information flow in mllms: Unlocking pathways to faster inference,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T01:26:49.982696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 118afd50-33ea-4771-a9a6-8be482a8e3bb · outbound

This paper cites FlashAttention: Fast and memory-efficient exact attention with IO-awareness,.

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models FlashAttention: Fast and memory-efficient exact attention with IO-awareness,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T01:26:50.106589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6665121f-5166-40ef-b102-a58c734a063a · outbound

This paper cites FlashAttention-2: Faster attention with better parallelism and work partitioning,.

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models FlashAttention-2: Faster attention with better parallelism and work partitioning,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T01:26:50.149809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 667132df-c368-4c32-be2d-392c405d5b41 · outbound

This paper cites Divprune: Diversity-based visual token pruning for large multimodal models,.

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models Divprune: Diversity-based visual token pruning for large multimodal models,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T01:26:50.225381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22b19c55-7038-416e-969c-d448915a52bb · outbound

This paper cites Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More.

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T01:26:50.285248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21f39751-262d-4fae-b297-1fc8abcb2b31 · outbound

This paper cites Fit and prune: Fast and training-free visual token pruning for multi-modal large language models,.

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models Fit and prune: Fast and training-free visual token pruning for multi-modal large language models,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T01:26:50.393243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f836949a-bf70-4340-a192-55de70e61a77 · outbound

This paper cites SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference.

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T01:26:50.499048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d05624f-a8bc-480b-9d30-1829bd76b99e · outbound

This paper cites Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model.

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T01:26:50.559182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cee6e4c2-79fe-4b23-92b7-0362ca803d9b · outbound

This paper cites PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction.

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T01:26:50.663785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14a3eb1d-4fd8-4404-890d-7579fff8c686 · outbound

This paper cites Hired: Attention-guided token dropping for efficient inference of high-resolution vision-language models,.

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models Hired: Attention-guided token dropping for efficient inference of high-resolution vision-language models,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T01:26:50.773014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d99230ee-52b9-41a9-911f-f0300818985a · outbound

This paper cites Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs.

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T01:26:50.833164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76b05607-c089-4c72-95e8-7ae858aa0116 · outbound

This paper cites Filter, cor- relate, compress: Training-free token reduction for mllm acceleration,.

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models Filter, cor- relate, compress: Training-free token reduction for mllm acceleration,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T01:26:50.941399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 988d8154-1321-4fe3-bc40-6b36996c66b8 · outbound

This paper cites RoFormer: Enhanced Transformer with Rotary Position Embedding.

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models RoFormer: Enhanced Transformer with Rotary Position Embedding

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T01:26:50.999520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98243ab9-77d3-4036-b55f-56c5d3ae6542 · outbound

This paper cites Feather the Throttle: Revisiting Visual Token Pruning for Vision-Language Model Acceleration.

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models Feather the Throttle: Revisiting Visual Token Pruning for Vision-Language Model Acceleration

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T01:26:51.082680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.