Paper Citation Record · LEDGER

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models

As of 18 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 2 inbound Pith citation observations for arXiv:2505.19235.

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

pith.paper-citation-record.v1
2505.19235 v1

Coverage vector

measured 19 of 19 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:26:17.271389Z

measured 21 of 21 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-26T01:10:00.373247Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T15:59:57.441183Z

Reference resolution

19 of 19 outbound references displayed

verified exact2
verified fuzzy2
unresolved13
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 363fa428-9e58-4982-93c0-61d1468f4cde · outbound

This paper cites LLM in a flash: Efficient Large Language Model Inference with Limited Memory.

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models LLM in a flash: Efficient Large Language Model Inference with Limited Memory

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:17.201744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17d12eee-c0e0-48c2-9b01-acc626a45d1b · outbound

This paper cites Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification.

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:17.210434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3ebb722-0bd6-4819-9e16-e66099588199 · outbound

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

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models Evaluating Object Hallucination in Large Vision-Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:17.222667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 847a243a-9c9c-4f22-89d6-eae1454cc240 · outbound

This paper cites Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing.

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:26:17.428918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 69b87f83-9793-4573-9514-e99b11547a90 · outbound

This paper cites PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU.

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:17.238480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73c96792-fa40-40c6-b281-cf0d08d9d302 · outbound

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

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models LLaMA: Open and Efficient Foundation Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:17.242204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63e2338c-e391-4c6d-a94d-3b3bac0356ca · outbound

This paper cites CoreInfer: Accelerating Large Language Model Inference with Semantics-Inspired Adaptive Sparse Activation.

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models CoreInfer: Accelerating Large Language Model Inference with Semantics-Inspired Adaptive Sparse Activation

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:26:17.330358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 085c94df-aa16-4d8f-926b-7d6a5fec40e2 · outbound

This paper cites VoCo-LLaMA: Towards Vision Compression with Large Language Models.

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models VoCo-LLaMA: Towards Vision Compression with Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:17.253571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7261ab2b-1af0-436b-b90f-01406ffec30e · outbound

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

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:17.256913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de2889b6-1e29-4376-90cc-83afba36bce3 · outbound

This paper cites The document is organized as follows: •A- Related Work •B- Algorithm •C- Assumption Explanation •D- Experiments Settings •E- Additional Experiments •F- Visualization of Results A.

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models The document is organized as follows: •A- Related Work •B- Algorithm •C- Assumption Explanation •D- Experiments Settings •E- Additional Experiments •F- Visualization of Results A

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:26:17.615715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 925b7f91-2ca0-48ee-804d-cb98d7094966 · outbound

This paper cites For example, in the OPT-30B, a single token activates only approximately 10% of the neurons (Alizadeh et al., 2023).

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models For example, in the OPT-30B, a single token activates only approximately 10% of the neurons (Alizadeh et al., 2023)

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:26:17.605538Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 52ba59d7-3135-475e-9d01-410b2ed34eb6 · outbound

This paper cites CoreInfer identifies a set of core neurons that most frequently and strongly activated for each input sentence.

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models CoreInfer identifies a set of core neurons that most frequently and strongly activated for each input sentence

Reference 18

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T14:26:17.596385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e908ccf6-380b-4ca4-b6a4-82c934980c44 · outbound

This paper cites (18) which means∥y i∥= √η∥Ai∥.

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models (18) which means∥y i∥= √η∥Ai∥

Reference 19

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T14:26:17.585496Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8622f967-5baa-48a5-9900-8017aabc34f6 · outbound

This paper cites Language Models are Few-Shot Learners.

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models Language Models are Few-Shot Learners

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:17.206295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fc2dd48-1964-45ee-85bd-ceed7ccac036 · outbound

This paper cites H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking.

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:17.214742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1730d2e-3987-4037-950b-481a06676dd0 · outbound

This paper cites Dobi-svd: Differentiable svd for llm compression and some new perspectives.

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models Dobi-svd: Differentiable svd for llm compression and some new perspectives

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:17.235271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c2ae999-c555-43c2-ac74-490658923777 · outbound

This paper cites Hippomm: Hippocampal-inspired multimodal memory for long audiovisual event understanding.

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models Hippomm: Hippocampal-inspired multimodal memory for long audiovisual event understanding

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:17.227367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f5c1124-bece-4e9b-a235-fd754a1aaa5e · outbound

This paper cites PowerInfer-2: Fast Large Language Model Inference on a Smartphone.

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:17.250081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 968ccbce-b82b-4dd4-bebe-dd295d39af08 · outbound

This paper cites SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension.

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:17.218889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 983b60a4-d0bc-4255-ba7c-c9c910567d87 · inbound

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

Accelerating Multimodal Large Language Models with Prior-Corrected Token Reduction CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models

Reference 62

Resolution: verified exact; arxiv_id, observed 2026-07-04T15:59:56.742663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d213ce1e-51e3-4e07-9c40-c7843f744771 · inbound

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

Spectral Evolution-Guided Token Pruning in Multimodal Large Language Models CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models

Reference 62

Resolution: verified exact; arxiv_id, observed 2026-07-04T15:59:57.442445Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.