DiffPrune: differentiable information throttling for token pruning in vision-language models | Paper Citation Record

Observation e7ab9233-bfbc-4318-8d35-fd2e31bf2dbc · outbound

This paper cites Vita: An efficient video- to-text algorithm using vlm for rag-based video analysis system.

DiffPrune: differentiable information throttling for token pruning in vision-language models Vita: An efficient video- to-text algorithm using vlm for rag-based video analysis system

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.075499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3ce09f4-19d3-44b2-a558-6d085b77a783 · outbound

This paper cites Fastvlm: Efficient vision encoding for vision language models.

DiffPrune: differentiable information throttling for token pruning in vision-language models Fastvlm: Efficient vision encoding for vision language models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.080649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4166294a-5acf-4fa6-99ae-9a7d18aa5fc9 · outbound

This paper cites Mmtok: Multimodal coverage maximization for efficient inference of vlms.ICLR, 2026.

DiffPrune: differentiable information throttling for token pruning in vision-language models Mmtok: Multimodal coverage maximization for efficient inference of vlms.ICLR, 2026

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.085035Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e90af430-255c-4837-953d-3a601f785bc2 · outbound

This paper cites See what matters: Differentiable grid sample pruning for generalizable vision-language-action model.ICML, 2026.

DiffPrune: differentiable information throttling for token pruning in vision-language models See what matters: Differentiable grid sample pruning for generalizable vision-language-action model.ICML, 2026

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.090562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acbe806f-1b20-4e4b-a766-b8adb443d60e · outbound

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

DiffPrune: differentiable information throttling for token pruning in vision-language models Similarity-Aware Token Pruning: Your VLM but Faster

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.095066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2c9e02d-8997-4270-a005-044f4beb58a4 · outbound

This paper cites Fine-Grained VLM Fine-tuning via Latent Hierarchical Adapter Learning.

DiffPrune: differentiable information throttling for token pruning in vision-language models Fine-Grained VLM Fine-tuning via Latent Hierarchical Adapter Learning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.100395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 905fd507-6e98-444c-8906-6eb1d3ab4734 · outbound

This paper cites Dynamic Token Reduction during Generation for Vision Language Models.

DiffPrune: differentiable information throttling for token pruning in vision-language models Dynamic Token Reduction during Generation for Vision Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.105663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c393f4d7-e95b-4437-a5f1-19d52bfed842 · outbound

This paper cites Training data-efficient image transformers & distillation through attention.

DiffPrune: differentiable information throttling for token pruning in vision-language models Training data-efficient image transformers & distillation through attention

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.110570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40883bdc-2878-49e1-ae16-8f73ae319b5a · outbound

This paper cites Differentiable top-k operator with optimal transport.

DiffPrune: differentiable information throttling for token pruning in vision-language models Differentiable top-k operator with optimal transport

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.114879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 057b4bcc-8af9-440c-83f9-bdb8d32af8ba · outbound

This paper cites A survey of token compression for efficient multimodal large language models.Transactions on Machine Learning Research, 2025.

DiffPrune: differentiable information throttling for token pruning in vision-language models A survey of token compression for efficient multimodal large language models.Transactions on Machine Learning Research, 2025

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.119664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50b6c6b7-b07c-4c3e-b87c-5dceba29503f · outbound

This paper cites Towards efficient multimodal large language models: A survey on token compression.

DiffPrune: differentiable information throttling for token pruning in vision-language models Towards efficient multimodal large language models: A survey on token compression

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.123814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b57ef01e-7837-4369-9f93-f9d4290d1dc2 · outbound

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

DiffPrune: differentiable information throttling for token pruning in vision-language models An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.128248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 904491f9-3a2b-40b7-b3e9-3dcd2eef9d85 · outbound

This paper cites Sparsevlm: Visual token sparsification for efficient vision-language model inference.ICML, 2025.

DiffPrune: differentiable information throttling for token pruning in vision-language models Sparsevlm: Visual token sparsification for efficient vision-language model inference.ICML, 2025

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.132384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5b458d1-1faa-410b-b560-2b95be2ef930 · outbound

This paper cites [CLS] attention is all you need for training-free visual token pruning: Make VLM inference faster, 2024.

DiffPrune: differentiable information throttling for token pruning in vision-language models [CLS] attention is all you need for training-free visual token pruning: Make VLM inference faster, 2024

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.136191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 567d0701-0550-4c25-ac22-178d0978c75f · outbound

This paper cites Boosting multimodal large language models with visual tokens withdrawal for rapid inference.

DiffPrune: differentiable information throttling for token pruning in vision-language models Boosting multimodal large language models with visual tokens withdrawal for rapid inference

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.140082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b62e1afa-de98-4fef-a22e-1cc05a4b98fb · outbound

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

DiffPrune: differentiable information throttling for token pruning in vision-language models Hired: Attention-guided token dropping for efficient inference of high-resolution vision-language models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.143972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f52590df-372e-4c61-bc58-92d0deb26c18 · outbound

This paper cites Pyramiddrop: Accelerating your large vision-language models via pyramid visual redundancy reduction.CVPR, 2025.

DiffPrune: differentiable information throttling for token pruning in vision-language models Pyramiddrop: Accelerating your large vision-language models via pyramid visual redundancy reduction.CVPR, 2025

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.148073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb91a094-963a-43d1-8e3f-ebff4fd974d6 · outbound

This paper cites Topv: Compatible token pruning with inference time optimization for fast and low-memory multimodal vision language model.

DiffPrune: differentiable information throttling for token pruning in vision-language models Topv: Compatible token pruning with inference time optimization for fast and low-memory multimodal vision language model

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.152289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f2524a2-2331-42fd-af77-321f5d3640a0 · outbound

This paper cites Token merging: Your ViT but faster.

DiffPrune: differentiable information throttling for token pruning in vision-language models Token merging: Your ViT but faster

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.157900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91d7aa5b-c0c3-47d7-a564-13e1f6ed011c · outbound

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

DiffPrune: differentiable information throttling for token pruning in vision-language models Llava-prumerge: Adaptive token reduction for efficient large multimodal models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.162973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0ab578a-2df7-4c35-ae57-67216ea087e0 · outbound

This paper cites Visionzip: Longer is better but not necessary in vision language models.

DiffPrune: differentiable information throttling for token pruning in vision-language models Visionzip: Longer is better but not necessary in vision language models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.167162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fd8de38-6e94-4640-be2b-08b0f483585b · outbound

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

DiffPrune: differentiable information throttling for token pruning in vision-language models Fit and prune: Fast and training-free visual token pruning for multi-modal large language models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.171242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b635af1d-7e5c-49e8-ba33-ef790553ec37 · outbound

This paper cites Feather the throttle: Revisiting visual token pruning for vision-language model acceleration.

DiffPrune: differentiable information throttling for token pruning in vision-language models Feather the throttle: Revisiting visual token pruning for vision-language model acceleration

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.175607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd64416d-93eb-44b9-a497-e18fc75e2572 · outbound

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

DiffPrune: differentiable information throttling for token pruning in vision-language models Divprune: Diversity-based visual token pruning for large multimodal models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.179792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5824d6e-28be-41e8-9dbb-92409379ad42 · outbound

This paper cites important tokens.

DiffPrune: differentiable information throttling for token pruning in vision-language models important tokens

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.183933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 042cfef7-0ded-4af9-81d1-b825465f6119 · outbound

This paper cites highlighted tokens.

DiffPrune: differentiable information throttling for token pruning in vision-language models highlighted tokens

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.188152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c96544f-5311-41da-8d7b-43b2ed3ad803 · outbound

This paper cites Balanced token pruning: Accelerating vision language models beyond local optimization.

DiffPrune: differentiable information throttling for token pruning in vision-language models Balanced token pruning: Accelerating vision language models beyond local optimization

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.192539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee8db22d-d8b8-47ce-b797-417edbe7122f · outbound

This paper cites Prune redundancy, preserve essence: Vision token compression in vlms via synergistic importance-diversity.

DiffPrune: differentiable information throttling for token pruning in vision-language models Prune redundancy, preserve essence: Vision token compression in vlms via synergistic importance-diversity

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.196666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ede9d203-fe93-453d-b06f-ae74c47f3483 · outbound

This paper cites Vlm-pruner: Buffering for spatial sparsity in an efficient vlm centrifugal token pruning paradigm.CVPR 2026, 2025.

DiffPrune: differentiable information throttling for token pruning in vision-language models Vlm-pruner: Buffering for spatial sparsity in an efficient vlm centrifugal token pruning paradigm.CVPR 2026, 2025

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.200549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc4a4d78-3159-41fb-845a-70bb30ddb92f · outbound

This paper cites an unresolved cited work.

DiffPrune: differentiable information throttling for token pruning in vision-language models Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.204798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f487fb9-d7d1-4453-9b40-355601e8689d · outbound

This paper cites AgilePruner: An empirical study of attention and diversity for adaptive visual token pruning in large vision-language models.

DiffPrune: differentiable information throttling for token pruning in vision-language models AgilePruner: An empirical study of attention and diversity for adaptive visual token pruning in large vision-language models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.209493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6982661e-f6f2-496d-9c99-29a6b44e1794 · outbound

This paper cites Learnpruner: Rethinking attention-based token pruning in vision language models.ICLR 2026, 2026.

DiffPrune: differentiable information throttling for token pruning in vision-language models Learnpruner: Rethinking attention-based token pruning in vision language models.ICLR 2026, 2026

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.213721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cea724cb-c098-4da6-ba4a-9a8dd3b6c84f · outbound

This paper cites Object-centric vision token pruning for vision language models.

DiffPrune: differentiable information throttling for token pruning in vision-language models Object-centric vision token pruning for vision language models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.217842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b6a9edf-49e6-4116-b3cc-940a1dad2ede · outbound

This paper cites Dynamicvit: Efficient vision transformers with dynamic token sparsification.Advances in neural information processing systems, 34:13937–13949, 2021.

DiffPrune: differentiable information throttling for token pruning in vision-language models Dynamicvit: Efficient vision transformers with dynamic token sparsification.Advances in neural information processing systems, 34:13937–13949, 2021

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.221737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a91c95d-cd33-4c76-9f76-ac65b56dce80 · outbound

This paper cites ATP-LLaV A: Adaptive token pruning for large vision language models.

DiffPrune: differentiable information throttling for token pruning in vision-language models ATP-LLaV A: Adaptive token pruning for large vision language models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.226036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c89d468-262d-4d3f-a191-e44559ef87c4 · outbound

This paper cites Dynamic-llava: Efficient multimodal large language models via dynamic vision-language context sparsification.

DiffPrune: differentiable information throttling for token pruning in vision-language models Dynamic-llava: Efficient multimodal large language models via dynamic vision-language context sparsification

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.231051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 566bbb66-4186-4c11-a886-59ffb8d82118 · outbound

This paper cites The better you learn, the smarter you prune: Towards efficient vision-language-action models via differentiable token pruning.arXiv preprint arXiv:2509.12594, 2025.

DiffPrune: differentiable information throttling for token pruning in vision-language models The better you learn, the smarter you prune: Towards efficient vision-language-action models via differentiable token pruning.arXiv preprint arXiv:2509.12594, 2025

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.235350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40dc70a4-6a5b-48f7-935f-22f13dd64cb6 · outbound

This paper cites Shiva-dit: Residual-based differentiable top-k selection for efficient diffusion transformers.arXiv preprint arXiv:2602.05605, 2026.

DiffPrune: differentiable information throttling for token pruning in vision-language models Shiva-dit: Residual-based differentiable top-k selection for efficient diffusion transformers.arXiv preprint arXiv:2602.05605, 2026

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.239354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c496993-3fd2-41f1-842b-e378aac603b3 · outbound

This paper cites Growing a multi-head twig via distillation and reinforcement learning to accelerate large vision-language models, 2025.

DiffPrune: differentiable information throttling for token pruning in vision-language models Growing a multi-head twig via distillation and reinforcement learning to accelerate large vision-language models, 2025

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.243733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f62e263a-da1f-4626-b3f2-7ae0d99ef6ee · outbound

This paper cites Top-rl: Task-optimized progressive token pruning with reinforcement learning for vision language models.

DiffPrune: differentiable information throttling for token pruning in vision-language models Top-rl: Task-optimized progressive token pruning with reinforcement learning for vision language models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.247657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c9f9c71-7c4a-442e-b68a-e32e0cb1c9b4 · outbound

This paper cites Improving discrete optimisation via decoupled straight-through gumbel-softmax.arXiv preprint arXiv:2410.13331, 2024.

DiffPrune: differentiable information throttling for token pruning in vision-language models Improving discrete optimisation via decoupled straight-through gumbel-softmax.arXiv preprint arXiv:2410.13331, 2024

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.251926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a6de864-4960-4d41-895a-c957b9d45d6d · outbound

This paper cites Bias-variance tradeoffs in single-sample binary gradient estimators.

DiffPrune: differentiable information throttling for token pruning in vision-language models Bias-variance tradeoffs in single-sample binary gradient estimators

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.256293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6594bf2f-6e95-4257-8338-823e4b6b363d · outbound

This paper cites Bednarczyk, Igor T.

DiffPrune: differentiable information throttling for token pruning in vision-language models Bednarczyk, Igor T

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.260740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afd329fb-3ddd-4dfc-9803-f7aecc41c10e · outbound

This paper cites Denoising diffusion probabilistic models.

DiffPrune: differentiable information throttling for token pruning in vision-language models Denoising diffusion probabilistic models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.265570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e80635c-b9e1-4224-8e3d-db4e854108db · outbound

This paper cites Imagenet: A large-scale hierarchical image database.

DiffPrune: differentiable information throttling for token pruning in vision-language models Imagenet: A large-scale hierarchical image database

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.269978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 172eb3dc-0660-4eae-a0ca-ad1a1923f2b9 · outbound

This paper cites Imagenet-1k-vl-enriched, 2023.

DiffPrune: differentiable information throttling for token pruning in vision-language models Imagenet-1k-vl-enriched, 2023

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.274379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69fb3582-d08b-485d-ab6c-903f163041dc · outbound

This paper cites Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023.

DiffPrune: differentiable information throttling for token pruning in vision-language models Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.279245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d1b5490-b840-4020-baa1-da6e85c58010 · outbound

This paper cites p-mod: Building mixture-of-depths mllms via progressive ratio decay.

DiffPrune: differentiable information throttling for token pruning in vision-language models p-mod: Building mixture-of-depths mllms via progressive ratio decay

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.283933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4cc4923-512c-4583-95b4-c5a364e58971 · outbound

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

DiffPrune: differentiable information throttling for token pruning in vision-language models A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.288134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 342df929-1caa-4963-8aea-17c7990cae19 · outbound

This paper cites Gqa: A new dataset for real-world visual reasoning and com- positional question answering.

DiffPrune: differentiable information throttling for token pruning in vision-language models Gqa: A new dataset for real-world visual reasoning and com- positional question answering

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.292542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6958d870-ec55-4214-a0da-253bca53f93a · outbound

This paper cites Mmbench: Is your multi-modal model an all-around player? InEuropean conference on computer vision, pages 216–233.

DiffPrune: differentiable information throttling for token pruning in vision-language models Mmbench: Is your multi-modal model an all-around player? InEuropean conference on computer vision, pages 216–233

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.296595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93fec619-b46a-45ae-ade3-af1e62543a64 · outbound

This paper cites Mme: A comprehensive evaluation benchmark for multimodal large language models.NeurIPS, 2025.

DiffPrune: differentiable information throttling for token pruning in vision-language models Mme: A comprehensive evaluation benchmark for multimodal large language models.NeurIPS, 2025

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.300832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4835a83-2807-488f-8fd8-a2da84d10d71 · outbound

This paper cites Evaluating object hallucination in large vision-language models.

DiffPrune: differentiable information throttling for token pruning in vision-language models Evaluating object hallucination in large vision-language models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.305236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82a47b83-0c0a-4363-a71b-fd74527e2400 · outbound

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

DiffPrune: differentiable information throttling for token pruning in vision-language models Learn to explain: Multimodal reasoning via thought chains for science question answering

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.309536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64d1d17c-4049-4dbc-a5eb-57f9f7b2e1a8 · outbound

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

DiffPrune: differentiable information throttling for token pruning in vision-language models Making the v in vqa matter: Elevating the role of image understanding in visual question answering

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.313617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59093d5d-4da8-4ca8-82f6-ba0b68560495 · outbound

This paper cites Towards vqa models that can read.

DiffPrune: differentiable information throttling for token pruning in vision-language models Towards vqa models that can read

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.317590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5a6b520-ecc8-46ab-86f2-64269be89ced · outbound

This paper cites Seed-bench: Benchmarking multimodal large language models.

DiffPrune: differentiable information throttling for token pruning in vision-language models Seed-bench: Benchmarking multimodal large language models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.321611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ad26a32-b6f4-4283-95a9-b963857175a9 · outbound

This paper cites Vizwiz: nearly real-time answers to visual questions.

DiffPrune: differentiable information throttling for token pruning in vision-language models Vizwiz: nearly real-time answers to visual questions

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.325714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 628468e6-30c2-4d04-a1f5-935cca520ca4 · outbound

This paper cites Qwen2.5-vl technical report, 2025.

DiffPrune: differentiable information throttling for token pruning in vision-language models Qwen2.5-vl technical report, 2025

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.329882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83ea1c63-54c8-4b4d-91b9-301e17795949 · outbound

This paper cites One leaf reveals the season: Occlusion-based contrastive learning with semantic-aware views for efficient visual representation.

DiffPrune: differentiable information throttling for token pruning in vision-language models One leaf reveals the season: Occlusion-based contrastive learning with semantic-aware views for efficient visual representation

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.334149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 961a322c-f753-413b-b980-4aa903efa50f · outbound

This paper cites Fewer tokens, greater scaling: Self-adaptive visual bases for efficient and expansive representation learning.arXiv preprint arXiv:2511.19515, 2026.

DiffPrune: differentiable information throttling for token pruning in vision-language models Fewer tokens, greater scaling: Self-adaptive visual bases for efficient and expansive representation learning.arXiv preprint arXiv:2511.19515, 2026

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.338005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c39d067b-87ac-4f66-b702-68cb6f656cbb · outbound

This paper cites Scalar: Spatial- concept alignment for robust vision in harsh open world.Pattern Recognition, page 113203, 2026.

DiffPrune: differentiable information throttling for token pruning in vision-language models Scalar: Spatial- concept alignment for robust vision in harsh open world.Pattern Recognition, page 113203, 2026

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.341788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97e502d0-413b-4056-a63c-1bed66599ee8 · outbound

This paper cites Segmentation and vascular vectorization for coronary artery by geometry-based cascaded neural network.IEEE Transactions on Medical Imaging, 44(1):259–269, 2024.

DiffPrune: differentiable information throttling for token pruning in vision-language models Segmentation and vascular vectorization for coronary artery by geometry-based cascaded neural network.IEEE Transactions on Medical Imaging, 44(1):259–269, 2024

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.345884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b2835cc-cf58-46d2-9594-71b991ff6731 · outbound

This paper cites Geometry-based end-to-end segmentation of coronary artery in computed tomography angiography.

DiffPrune: differentiable information throttling for token pruning in vision-language models Geometry-based end-to-end segmentation of coronary artery in computed tomography angiography

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.349722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a626a9f0-5b9c-4957-9b0c-95931ce84b7c · outbound

This paper cites Tc-ssa: Token compression via semantic slot aggregation for gigapixel pathology reasoning.MICCAI, 2026.

DiffPrune: differentiable information throttling for token pruning in vision-language models Tc-ssa: Token compression via semantic slot aggregation for gigapixel pathology reasoning.MICCAI, 2026

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.353864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1eb1fb18-dfb0-43d9-b281-8b73de82113a · outbound

This paper cites Multimodal model for computational pathology: Representation learning and image compression.arXiv preprint arXiv:2603.18660, 2026.

DiffPrune: differentiable information throttling for token pruning in vision-language models Multimodal model for computational pathology: Representation learning and image compression.arXiv preprint arXiv:2603.18660, 2026

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.357948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee1efc6c-30f7-47e1-b734-37e530d55dfc · outbound

This paper cites A unified multi-task framework enables interpretable chest radiograph analysis.Med, 2026.

DiffPrune: differentiable information throttling for token pruning in vision-language models A unified multi-task framework enables interpretable chest radiograph analysis.Med, 2026

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.364815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3f8721b-d7d0-499e-997c-427e537ca456 · outbound

This paper cites Learning A Multi-Task Transformer Via Unified And Customized Instruction Tuning For Chest Radiograph Interpretation.

DiffPrune: differentiable information throttling for token pruning in vision-language models Learning A Multi-Task Transformer Via Unified And Customized Instruction Tuning For Chest Radiograph Interpretation

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.378524Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d41fddf2-6438-4ff3-b61f-5f0f148e643f · outbound

This paper cites MedViLaM: A multimodal large language model with advanced generalizability and explainability for medical data understanding and generation.

DiffPrune: differentiable information throttling for token pruning in vision-language models MedViLaM: A multimodal large language model with advanced generalizability and explainability for medical data understanding and generation

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.391750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5536d433-9bb5-41ee-a85e-075c1ecd6abf · outbound

This paper cites A foundation model for generalizable disease diagnosis in chest X-ray images.

DiffPrune: differentiable information throttling for token pruning in vision-language models A foundation model for generalizable disease diagnosis in chest X-ray images

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.403344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97405340-88b9-44d9-81e1-9057ee867f48 · outbound

This paper cites Efficient chest x-ray representation learning via semantic-partitioned contrastive learning.arXiv preprint arXiv:2603.07113, 2026.

DiffPrune: differentiable information throttling for token pruning in vision-language models Efficient chest x-ray representation learning via semantic-partitioned contrastive learning.arXiv preprint arXiv:2603.07113, 2026

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.416481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f64d019e-460b-4717-aea4-576551b0ad72 · outbound

This paper cites Beyond Surrogate Gradients: Fully Differentiable Token Pruning for Vision-Language Models.

DiffPrune: differentiable information throttling for token pruning in vision-language models Beyond Surrogate Gradients: Fully Differentiable Token Pruning for Vision-Language Models

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.429922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e90a018c-61c8-42d4-87db-cee1c59df241 · outbound

This paper cites The model knows which tokens matter:automatic token selection via noise gating.arXiv preprint arXiv:2603.07135, 2026.

DiffPrune: differentiable information throttling for token pruning in vision-language models The model knows which tokens matter:automatic token selection via noise gating.arXiv preprint arXiv:2603.07135, 2026

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.442868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08fd9115-9ea6-4bed-8564-90304362f42f · outbound

This paper cites Stepwise token selection for efficient multimodal large language models.

DiffPrune: differentiable information throttling for token pruning in vision-language models Stepwise token selection for efficient multimodal large language models

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.453946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5edc7764-fe6a-43ef-acb6-fc0a5df35b62 · outbound

This paper cites Learnable Token Sparsification for Efficient Gigapixel Whole Slide Image Reasoning.

DiffPrune: differentiable information throttling for token pruning in vision-language models Learnable Token Sparsification for Efficient Gigapixel Whole Slide Image Reasoning

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.464036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00836b36-0e4f-4756-8dee-4246054c7f18 · outbound

This paper cites PathSelect: Sequential Token Selection for Whole Slide Pathology.

DiffPrune: differentiable information throttling for token pruning in vision-language models PathSelect: Sequential Token Selection for Whole Slide Pathology

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.474432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec54d142-b6f8-4007-959e-9f7bdd02d711 · outbound

This paper cites Zerosense: How vision matters in long context compression.arXiv preprint arXiv:2603.11846, 2026.

DiffPrune: differentiable information throttling for token pruning in vision-language models Zerosense: How vision matters in long context compression.arXiv preprint arXiv:2603.11846, 2026

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-04T17:18:16.483944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers