Paper Citation Record · LEDGER

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

As of 7 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 27 inbound Pith citation observations for arXiv:2506.10967.

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

pith.paper-citation-record.v1
2506.10967 v2

Coverage vector

measured 34 of 34 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T04:20:33.522423Z

measured 61 of 61 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 27 of 27 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:11:49.179772Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T15:59:57.457886Z

Reference resolution

34 of 34 outbound references displayed

verified exact0
verified fuzzy4
unresolved30
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d9580dc0-9e63-41c9-860c-842923ee40f6 · outbound

This paper cites DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models.

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:30.500266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e25074c2-8e0b-46be-a3d5-4b0e7c0947ca · outbound

This paper cites Tri Dao, Dan Fu, Stefano Ermon, Atri Rudra, and Christopher Ré.

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs Tri Dao, Dan Fu, Stefano Ermon, Atri Rudra, and Christopher Ré

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:20:35.249313Z

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 bda22afa-70e1-4b24-b976-6ab55fef2e88 · outbound

This paper cites MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies.

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:31.095679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75faae6a-b724-4b8b-abd7-d58a1dbf889b · outbound

This paper cites Mistral 7B.

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs Mistral 7B

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:31.290255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb6f6bb3-cb43-4549-877f-ce54049d6d93 · outbound

This paper cites A diagram is worth a dozen images.

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs A diagram is worth a dozen images

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:31.400104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b5a60a5-a5be-480d-9837-88bf333bfa83 · outbound

This paper cites Video-LLaVA: Learning United Visual Representation by Alignment Before Projection.

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:31.581672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 880c77ef-a514-40ae-8dac-e2ee90fdcceb · outbound

This paper cites Microsoft coco: Common objects in context.

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs Microsoft coco: Common objects in context

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:20:34.975202Z

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 731567cb-7de2-446a-b222-3b662f87a2da · outbound

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

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:31.753984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f46ba898-242d-4dcc-a67e-660f1cd1d0a9 · outbound

This paper cites Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models.

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:31.837013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8783900-4263-4e24-8bf3-dfdd7c03543e · outbound

This paper cites Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs.

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:32.068161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d13ddfd-0112-46ce-bfb0-8a3a9baa8099 · outbound

This paper cites Gemma: Open Models Based on Gemini Research and Technology.

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs Gemma: Open Models Based on Gemini Research and Technology

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:32.245624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b416dba4-3258-4a0e-ae97-07e441622bd0 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs LLaMA: Open and Efficient Foundation Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:32.325718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2fd1dc9-808b-4d11-be3a-44643dea61ac · outbound

This paper cites Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem?.

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem?

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:32.526592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a32adc7-b150-4ae5-b10a-6b9661ed0910 · outbound

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

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:32.613673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c735d4a5-be86-430e-9d94-702ab8595c14 · outbound

This paper cites Qwen2.5 Technical Report.

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs Qwen2.5 Technical Report

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:32.701129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be676b47-8fa3-4528-acab-1b7fa509bc28 · outbound

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

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:32.927138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc8edb99-3740-495f-8468-1737e9cc18aa · outbound

This paper cites Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding.

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:33.004390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26b7f326-3691-4767-a429-eddfeaa91aef · outbound

This paper cites Long Context Transfer from Language to Vision.

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs Long Context Transfer from Language to Vision

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:33.079691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe9d77f7-1109-4755-be87-518e9ba954a8 · outbound

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

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:33.148022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8344eeb-4409-476e-8514-35f8472891fe · outbound

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

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:33.229755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2123e3a-1bd5-40af-9385-258fcf6886da · outbound

This paper cites Appendix B provides some details of the experimental setup, including information about model architectures, evaluation benchmarks, comparison methods and implemen- tation.

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs Appendix B provides some details of the experimental setup, including information about model architectures, evaluation benchmarks, comparison methods and implemen- tation

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:20:34.643823Z

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 ac6f7c56-d168-4c80-b242-6bc6aaf2d9a3 · outbound

This paper cites Therefore, the greedy algorithm runs in O(nm2) time.

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs Therefore, the greedy algorithm runs in O(nm2) time

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:20:34.442063Z

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 82d897ab-868b-4802-9c48-46acc1b2dfde · outbound

This paper cites an unresolved cited work.

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-07T04:20:34.277604Z

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 80118ccd-ae30-4541-b8f9-194c876cf8b5 · outbound

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

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning

Reference 1975

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:31.906806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e0c639a-dbd6-4e51-b060-7be707b167b8 · outbound

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

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs LLaVA-OneVision: Easy Visual Task Transfer

Reference 2012

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:31.510710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b2a4f8a-0bb3-4df5-b1a9-9275074cf3d4 · outbound

This paper cites Qwen Technical Report.

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs Qwen Technical Report

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:30.562632Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fccbff3-c235-473c-827c-647ccd7a1c5a · outbound

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

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:32.413526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38da4126-715b-4717-a507-f8506b4447bf · outbound

This paper cites LongVILA: Scaling Long-Context Visual Language Models for Long Videos.

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs LongVILA: Scaling Long-Context Visual Language Models for Long Videos

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:30.765313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e4ee5fe-b3d4-4fb5-864d-64b5088904fe · outbound

This paper cites Similarity-Aware Token Pruning: Your VLM but Faster.

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs Similarity-Aware Token Pruning: Your VLM but Faster

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:31.175344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2895cc3f-6db3-47f7-999b-8ece88d84bc0 · outbound

This paper cites Llava-prumerge: Adaptive token reduction for efficient large multimodal models.

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs Llava-prumerge: Adaptive token reduction for efficient large multimodal models

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:31.982439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7ffd2ae-9a9a-4e15-bd0c-5f1fa2a75316 · outbound

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

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:30.949286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 480d693e-9f13-40e3-96a6-4f0a64979a92 · outbound

This paper cites Qwen2.5-VL Technical Report.

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs Qwen2.5-VL Technical Report

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:30.635629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c99589e-8e7b-40ab-8eb9-0c9b25a35eea · outbound

This paper cites Mdp3: A training-free approach for list-wise frame selection in video-llms.

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs Mdp3: A training-free approach for list-wise frame selection in video-llms

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:32.151078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd123cd7-c6c9-4391-93fb-7314899df7ac · outbound

This paper cites InternLM2 Technical Report.

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs InternLM2 Technical Report

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:30.698008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 00c809f9-844e-4f80-8722-f6bc21ce394c · inbound

EgoPrune: Efficient Token Pruning for Egomotion Video Reasoning in Embodied Agent cites this paper.

EgoPrune: Efficient Token Pruning for Egomotion Video Reasoning in Embodied Agent Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-06T15:38:45.462835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6e1b3bf-d94e-4c4b-959d-e59484535d8d · inbound

A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models cites this paper.

A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T05:37:35.450623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb5cc1b2-a8b6-494d-ace8-c05441757435 · inbound

Towards Spatial Trace with Reasoning in Vision-Language Models for Robotics cites this paper.

Towards Spatial Trace with Reasoning in Vision-Language Models for Robotics Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Reference 122

Resolution: unresolved; no resolver link, observed 2026-08-03T16:27:34.271065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2867c7e5-692b-4aee-9976-eee272cbf749 · inbound

HAWK: Head Importance-Aware Visual Token Pruning in Multimodal Models cites this paper.

HAWK: Head Importance-Aware Visual Token Pruning in Multimodal Models Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Reference 44

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T07:01:05.867186Z

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 b952a8a0-3d83-4f70-b36c-5b1ea2f0bffe · inbound

Sink-Token-Aware Pruning for Fine-Grained Video Understanding in Efficient Video LLMs cites this paper.

Sink-Token-Aware Pruning for Fine-Grained Video Understanding in Efficient Video LLMs Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Reference 52

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T00:44:48.417048Z

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 5e597c98-ab8b-4547-8774-cd44bd08c998 · inbound

RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR Inference cites this paper.

RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR Inference Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T15:31:08.455532Z

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 23d1383c-d06e-4817-b8b6-88c678f3ea48 · inbound

RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR Inference cites this paper.

RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR Inference Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-12T03:21:19.376132Z

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 3490a9f9-7ee5-4a16-8cbe-0a9c697dee77 · inbound

RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR Inference cites this paper.

RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR Inference Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-22T10:31:25.772099Z

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 c50d254f-c09e-4cd1-872d-b44ea1beec21 · inbound

Focus-then-Context: Subject-Centric Progressive Visual Token Reduction for Vision-Language Models cites this paper.

Focus-then-Context: Subject-Centric Progressive Visual Token Reduction for Vision-Language Models Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T05:23:58.587932Z

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 70eb3121-3269-4247-8ead-97d6e6805ba0 · inbound

SAFE-Pruner: Semantic Attention-Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulation cites this paper.

SAFE-Pruner: Semantic Attention-Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulation Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Reference 47

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T08:43:14.998270Z

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 bb008883-066e-4558-af78-5629603e4af6 · inbound

SAFE-Pruner: Semantic Attention-Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulation cites this paper.

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-02T12:54:43.228543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fda3f518-4f09-46cc-95a7-8aa849d3982e · inbound

X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding cites this paper.

X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Reference 61

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T22:46:18.963802Z

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 edbc6b09-c160-4a09-9a4a-b6b3f11b6fc7 · inbound

X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding cites this paper.

X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Reference 64

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T10:44:36.407579Z

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 722a29f6-c5a9-4c48-847a-f1da057ebcbd · inbound

TGV-KV: Text-Grounded KV Eviction for Vision-Language Models cites this paper.

TGV-KV: Text-Grounded KV Eviction for Vision-Language Models Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Reference 24

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T02:16:26.715894Z

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 e6a61e6e-7b9c-428d-a4cc-5f379bf31ec5 · inbound

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

Spectral Evolution-Guided Token Pruning in Multimodal Large Language Models Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Reference 86

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T15:59:57.459369Z

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 3d777fc8-3027-41a4-9912-24a5f4ce079e · inbound

TOPS: First-Principles Visual Token Pruning via Constructing Token Optimal Preservation Sets for Efficient MLLM Inference cites this paper.

TOPS: First-Principles Visual Token Pruning via Constructing Token Optimal Preservation Sets for Efficient MLLM Inference Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Reference 58

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T14:09:53.798585Z

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 e7538e8f-8d90-4758-9d8c-e24379874ebc · inbound

Combating Textual Noise and Redundancy: Entropy-Aware Dense Visual Token Pruning cites this paper.

Combating Textual Noise and Redundancy: Entropy-Aware Dense Visual Token Pruning Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Reference 72

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T14:48:32.406972Z

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 af6ec779-02cc-4cd9-9823-eff642eca4cb · inbound

RADIO1D: Elastic Representations for Condensed Vision Modeling cites this paper.

RADIO1D: Elastic Representations for Condensed Vision Modeling Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Reference 51

Resolution: unresolved; no resolver link, observed 2026-07-12T01:07:20.766474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f15b7aa2-54f0-49dc-a303-7d5f893e19aa · inbound

IoU-PD: IoU-Aware Privileged Distillation for Visual Grounding with Multimodal Large Language Models cites this paper.

IoU-PD: IoU-Aware Privileged Distillation for Visual Grounding with Multimodal Large Language Models Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-01T22:32:25.110039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab72c83f-49fb-468a-906a-74a8aca1be14 · inbound

IoU-PD: IoU-Aware Privileged Distillation for Visual Grounding with Multimodal Large Language Models cites this paper.

IoU-PD: IoU-Aware Privileged Distillation for Visual Grounding with Multimodal Large Language Models Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-04T04:21:09.449182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d712359-c0ab-48d8-8081-4f12ab56b5ef · inbound

Structured Redundancy Modeling for Efficient Visual Token Pruning in High-Resolution MLLMs cites this paper.

Structured Redundancy Modeling for Efficient Visual Token Pruning in High-Resolution MLLMs Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T03:50:32.506198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 787a3619-c726-44eb-b279-9170356085bd · inbound

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation cites this paper.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-31T23:59:18.339215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c940e4a4-e27a-4e34-b139-3498d8d14cc3 · inbound

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation cites this paper.

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T04:01:48.622068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models cites this paper.

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 814f8c48-6d41-4d5d-8183-f3ad966214e2 · inbound

PhyCheck: Fine-Grained Evidence-Grounded Dataset for Physical Law Understanding in Video-LLMs cites this paper.

PhyCheck: Fine-Grained Evidence-Grounded Dataset for Physical Law Understanding in Video-LLMs Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-04T13:43:57.677655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b32330f0-3ef6-43b0-a933-40627f1db851 · inbound

PhyCheck: Fine-Grained Evidence-Grounded Dataset for Physical Law Understanding in Video-LLMs cites this paper.

PhyCheck: Fine-Grained Evidence-Grounded Dataset for Physical Law Understanding in Video-LLMs Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-07T00:11:49.179772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9355748a-d097-48c7-a5bc-667d093bcbcd · inbound

Hi-Token: Hierarchical Coordinate Tokenization for Generative Visual Grounding cites this paper.

Hi-Token: Hierarchical Coordinate Tokenization for Generative Visual Grounding Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-05T18:36:14.731592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.