Paper Citation Record · LEDGER

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression

As of 22 August 2026, this Paper Citation Record lists 81 of 81 outbound references and 3 inbound Pith citation observations for arXiv:2505.19602.

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

pith.paper-citation-record.v1
2505.19602 v1

Coverage vector

measured 81 of 81 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:16:20.927090Z

measured 84 of 84 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T06:03:03.062322Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-20T07:58:07.594523Z

Reference resolution

81 of 81 outbound references displayed

verified exact0
verified fuzzy6
unresolved75
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 293a0609-f139-43f6-8037-2b43a274623d · outbound

This paper cites Longformer: The Long-Document Transformer.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Longformer: The Long-Document Transformer

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:12.031316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6f5049a-cb1c-4012-92fc-54079f5ef1b7 · outbound

This paper cites Improving image generation with better captions.Computer Science.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Improving image generation with better captions.Computer Science

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:12.089620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dffea209-3858-47ca-a9a0-3affff8ba103 · outbound

This paper cites PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:12.217814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9ea3931-fa9a-4d77-8236-6c48319287f0 · outbound

This paper cites Maskgit: Masked generative image transformer.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Maskgit: Masked generative image transformer

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:12.340496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 646555be-1f9c-4df6-9c80-d2e0bfdc8a28 · outbound

This paper cites PixArt-Sigma: Weak-to-strong training of diffusion transformer for 4k text-to-image generation.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression PixArt-Sigma: Weak-to-strong training of diffusion transformer for 4k text-to-image generation

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:16:24.117531Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a14d7039-3002-422e-b24d-f6c3e6c903e8 · outbound

This paper cites Generative pretraining from pixels.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Generative pretraining from pixels

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:12.543575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa1f79b0-8e6d-406e-8dfa-1e8a18d509a4 · outbound

This paper cites Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:12.670870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fad3e3f-9146-4a5f-beae-d73abe0a52dc · outbound

This paper cites Taming transformers for high-resolution image synthesis.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Taming transformers for high-resolution image synthesis

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:12.835884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a678a28-5f88-44c4-8487-7a8823fc6d0f · outbound

This paper cites TinyFusion: Diffusion Transformers Learned Shallow.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression TinyFusion: Diffusion Transformers Learned Shallow

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:13.014126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e6847e7-cbbb-4746-be02-7c97c4414363 · outbound

This paper cites Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:13.138387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fd9a677-964d-498e-8609-a9f486163db0 · outbound

This paper cites Not all heads matter: A head-level kv cache compression method with integrated retrieval and reasoning.arXiv preprint arXiv:2410.19258, 2024.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Not all heads matter: A head-level kv cache compression method with integrated retrieval and reasoning.arXiv preprint arXiv:2410.19258, 2024

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:13.258212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 814de7f5-fdf4-4a33-9933-76925e214302 · outbound

This paper cites Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:13.413395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc481280-ccd0-491c-af0e-50b4974a2be8 · outbound

This paper cites Geneval: An object-focused framework for evaluating text-to-image alignment.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Geneval: An object-focused framework for evaluating text-to-image alignment

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:16:23.862112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 22f15021-513d-40bb-a2ad-7b7af0fd1226 · outbound

This paper cites DART: Denoising Autoregressive Transformer for Scalable Text-to-Image Generation.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression DART: Denoising Autoregressive Transformer for Scalable Text-to-Image Generation

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:13.622854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d51690e-64bf-4e93-9317-19ab2db69ce6 · outbound

This paper cites FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:13.693484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8144f2e-57d3-4053-bc65-a0aff67de974 · outbound

This paper cites Infinity: Scaling bitwise autoregressive modeling for high-resolution image synthesis, 2024.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Infinity: Scaling bitwise autoregressive modeling for high-resolution image synthesis, 2024

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:13.770499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9cccbfa-a369-4d8f-bf85-2dddd7291d5f · outbound

This paper cites ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:13.857590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90c1a4be-0e2a-4a36-8855-c9899a98340c · outbound

This paper cites Gans trained by a two time-scale update rule converge to a local nash equilibrium.Advances in neural information processing systems, 30, 2017.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Gans trained by a two time-scale update rule converge to a local nash equilibrium.Advances in neural information processing systems, 30, 2017

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:13.948063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b128b49e-cda3-4642-9df2-5a338a5297d4 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Distilling the Knowledge in a Neural Network

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:14.033748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a26ea0ad-6364-4f16-92b9-5d354a338c16 · outbound

This paper cites ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:14.124213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4045744-1d75-4e87-b00d-b7d213d10524 · outbound

This paper cites GPT-4o System Card.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression GPT-4o System Card

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:14.194123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38eff18d-581c-469e-8f75-d9b88ac6bfaf · outbound

This paper cites GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:14.282281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1402ed7-f490-4546-badd-4fd7f608e0b5 · outbound

This paper cites Scalable autoregressive image generation with mamba.arXiv preprint arXiv:2408.12245, 2024.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Scalable autoregressive image generation with mamba.arXiv preprint arXiv:2408.12245, 2024

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:14.444559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b8bf013-ee0a-40cf-bd57-999abc287a7f · outbound

This paper cites Svdquant: Absorbing outliers by low-rank components for 4-bit diffusion models.arXiv preprint arXiv:2411.05007, 2024.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Svdquant: Absorbing outliers by low-rank components for 4-bit diffusion models.arXiv preprint arXiv:2411.05007, 2024

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:14.611793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06423f51-cfd0-4ae9-88ef-0b4c16487a02 · outbound

This paper cites Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:14.731278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb8defb5-873d-46e9-9eb1-3f9540d81714 · outbound

This paper cites Autoregressive Image Generation without Vector Quantization.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Autoregressive Image Generation without Vector Quantization

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:14.884901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62903964-d2cc-40eb-8e34-f2ca28e166b2 · outbound

This paper cites ControlVAR: Exploring Controllable Visual Autoregressive Modeling.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression ControlVAR: Exploring Controllable Visual Autoregressive Modeling

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:15.022702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4026be12-2d5f-44b1-a227-95b768acf7cd · outbound

This paper cites Q-diffusion: Quantizing diffusion models.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Q-diffusion: Quantizing diffusion models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:15.125418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29d6db59-5830-46f1-a198-ef87d091c6e3 · outbound

This paper cites Snapfusion: Text-to-image diffusion model on mobile devices within two seconds.Advances in Neural Information Processing Systems, 36, 2024.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Snapfusion: Text-to-image diffusion model on mobile devices within two seconds.Advances in Neural Information Processing Systems, 36, 2024

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:16:23.563170Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8e0543e4-440f-4b44-b65f-4a42fa18ac23 · outbound

This paper cites SnapKV: LLM Knows What You are Looking for Before Generation.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression SnapKV: LLM Knows What You are Looking for Before Generation

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:15.378042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fd371e8-a244-47b5-b834-3ef570d38900 · outbound

This paper cites ControlAR: Controllable Image Generation with Autoregressive Models.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression ControlAR: Controllable Image Generation with Autoregressive Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:15.523883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a495cb52-b5cc-4ba3-9c05-bbf931b8765b · outbound

This paper cites Microsoft coco: Common objects in context.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Microsoft coco: Common objects in context

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:15.657471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46aec037-8f7c-40db-bf10-3ec3a2194891 · outbound

This paper cites MiniCache: KV Cache Compression in Depth Dimension for Large Language Models.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression MiniCache: KV Cache Compression in Depth Dimension for Large Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:15.805734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1adb9af2-121c-41eb-81d2-c622f8fed257 · outbound

This paper cites Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:15.891755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bebf9bab-5a0c-4ab4-b687-370c985bcc0a · outbound

This paper cites Scissorhands: Exploiting the persistence of importance hypothesis for llm kv cache compression at test time.Advances in Neural Information Processing Systems, 36, 2024.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Scissorhands: Exploiting the persistence of importance hypothesis for llm kv cache compression at test time.Advances in Neural Information Processing Systems, 36, 2024

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:16.016184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c237317-f6f2-4a3b-8185-92f5aef59083 · outbound

This paper cites KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:16.195264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0675899-2855-42d8-8823-4a6794e46234 · outbound

This paper cites Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:16.358206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5edde25-459b-4fdb-8432-9e94b657d3a9 · outbound

This paper cites Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:16.536400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6133ddb2-fc52-429d-8bbf-4dcf6ebadf01 · outbound

This paper cites Accelerating Diffusion Models via Early Stop of the Diffusion Process.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Accelerating Diffusion Models via Early Stop of the Diffusion Process

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:16.665647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4eb1f813-b788-4468-b191-0668b04482d3 · outbound

This paper cites STAR: Scale-wise Text-conditioned AutoRegressive image generation.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression STAR: Scale-wise Text-conditioned AutoRegressive image generation

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:16.780411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2eec77e1-4b91-470e-85ac-3b668055466b · outbound

This paper cites DeepCache: Accelerating Diffusion Models for Free.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression DeepCache: Accelerating Diffusion Models for Free

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:16.890592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c33b358f-77c5-4223-bb69-6eaff1831127 · outbound

This paper cites Transformers are Multi-State RNNs.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Transformers are Multi-State RNNs

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:17.009571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c17afa5-d337-45c2-9e6c-6c4729a30143 · outbound

This paper cites SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:17.118171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba685361-ef66-4fa7-89e4-8b276a81e4f1 · outbound

This paper cites Head-aware kv cache compression for efficient visual autoregressive modeling.arXiv preprint arXiv:2504.09261, 2025.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Head-aware kv cache compression for efficient visual autoregressive modeling.arXiv preprint arXiv:2504.09261, 2025

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:17.201417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9c6dae5-05e4-4040-a6e6-e81f9537114c · outbound

This paper cites Efficient Autoregressive Audio Modeling via Next-Scale Prediction.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Efficient Autoregressive Audio Modeling via Next-Scale Prediction

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:17.266768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c21181a6-5cea-470f-a97a-05134b04e7ca · outbound

This paper cites On the Efficacy of Eviction Policy for Key-Value Constrained Generative Language Model Inference.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression On the Efficacy of Eviction Policy for Key-Value Constrained Generative Language Model Inference

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:17.384573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a14f778-46c6-4d1f-a4ec-dcbf3ab8e720 · outbound

This paper cites Progressive Distillation for Fast Sampling of Diffusion Models.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Progressive Distillation for Fast Sampling of Diffusion Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:17.490839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa9df552-5935-49c0-8aa1-7d1032654f6d · outbound

This paper cites Adversarial Diffusion Distillation.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Adversarial Diffusion Distillation

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:17.578156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d0a08cb-ef61-469a-b213-c19bf6a9ab4c · outbound

This paper cites Post-training quantization on diffusion models.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Post-training quantization on diffusion models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:17.679607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8693224-84aa-45a6-b7c3-dfc107049171 · outbound

This paper cites FRDiff : Feature Reuse for Universal Training-free Acceleration of Diffusion Models.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression FRDiff : Feature Reuse for Universal Training-free Acceleration of Diffusion Models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:17.772212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 353a2226-eed9-4e36-903e-a49527443e35 · outbound

This paper cites Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:18.009369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8d75859-c32a-486a-af2c-e1c44e89e10f · outbound

This paper cites HART: Efficient Visual Generation with Hybrid Autoregressive Transformer.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression HART: Efficient Visual Generation with Hybrid Autoregressive Transformer

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:18.127539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4080b004-8286-4e92-9045-62ccd4f9bc2c · outbound

This paper cites Visual autoregressive modeling: Scalable image generation via next-scale prediction.Advances in neural information processing systems, 37:84839–84865, 2024.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Visual autoregressive modeling: Scalable image generation via next-scale prediction.Advances in neural information processing systems, 37:84839–84865, 2024

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:18.201368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 456bd8c8-8727-471a-935e-d761f58b42f2 · outbound

This paper cites Conditional image generation with pixelcnn decoders.Advances in neural information processing systems, 29, 2016.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Conditional image generation with pixelcnn decoders.Advances in neural information processing systems, 29, 2016

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:18.298675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cb61cd6-bea0-49cc-9630-78d1767074d0 · outbound

This paper cites Neural discrete representation learning.Advances in neural information processing systems, 30, 2017.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Neural discrete representation learning.Advances in neural information processing systems, 30, 2017

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:18.412301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 735fab92-1f44-4700-825d-a90d83fc65a6 · outbound

This paper cites D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:18.517957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cabc8b2-404d-4115-8940-3fe58a98ed21 · outbound

This paper cites LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:18.606283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa87dea9-225f-47b8-8879-38d93ae314cb · outbound

This paper cites Emu3: Next-Token Prediction is All You Need.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Emu3: Next-Token Prediction is All You Need

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:18.699512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 975c5e03-be46-46c4-8191-fea0a7ff031d · outbound

This paper cites Cache Me if You Can: Accelerating Diffusion Models through Block Caching.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Cache Me if You Can: Accelerating Diffusion Models through Block Caching

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:18.760250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9eb3f00-e6d4-4429-849e-e68f1db1311f · outbound

This paper cites Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:18.842698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 545bebb5-615d-4ecf-b2f1-754fcf5878c5 · outbound

This paper cites VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:18.961783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bacfe7e9-9139-4137-abab-317b6f2257e6 · outbound

This paper cites Efficient streaming language models with attention sinks.arXiv, 2023.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Efficient streaming language models with attention sinks.arXiv, 2023

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:19.047855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8655804e-2349-42e9-9902-0e4d05f68341 · outbound

This paper cites Show-o: One Single Transformer to Unify Multimodal Understanding and Generation.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Show-o: One Single Transformer to Unify Multimodal Understanding and Generation

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:19.134844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f56e95aa-f6be-4e5f-994b-a7f82c45c05c · outbound

This paper cites LiteVAR: Compressing Visual Autoregressive Modelling with Efficient Attention and Quantization.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression LiteVAR: Compressing Visual Autoregressive Modelling with Efficient Attention and Quantization

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:19.250138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 827a1ae8-2935-4ac9-96d7-895870c2b1be · outbound

This paper cites PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:19.360068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d6893d3-7a1a-463f-9bef-f80db39d814d · outbound

This paper cites Hash3D: Training-free Acceleration for 3D Generation.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Hash3D: Training-free Acceleration for 3D Generation

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:19.475008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7a8c97c-e8de-47ce-bb5a-d8e082b59bd0 · outbound

This paper cites Diffusion probabilistic model made slim.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Diffusion probabilistic model made slim

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:16:23.209684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f523d14b-49a3-43af-9877-e8c9330bc139 · outbound

This paper cites CAR: Controllable Autoregressive Modeling for Visual Generation.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression CAR: Controllable Autoregressive Modeling for Visual Generation

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:19.608040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f4c3011-d88a-411d-8bb5-7ed536fb36b2 · outbound

This paper cites One-step Diffusion with Distribution Matching Distillation.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression One-step Diffusion with Distribution Matching Distillation

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:19.701607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e775c07-916f-4896-ae0c-6090247f3f33 · outbound

This paper cites WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:19.784103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3557f87b-5aab-4826-a750-14232c37e679 · outbound

This paper cites Resshift: Efficient diffusion model for image super-resolution by residual shifting.Advances in Neural Information Processing Systems, 36, 2024.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Resshift: Efficient diffusion model for image super-resolution by residual shifting.Advances in Neural Information Processing Systems, 36, 2024

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:16:22.897167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation affe042c-ddf2-4a81-9f3d-0a82e5985e68 · outbound

This paper cites LAPTOP-Diff: Layer Pruning and Normalized Distillation for Compressing Diffusion Models.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression LAPTOP-Diff: Layer Pruning and Normalized Distillation for Compressing Diffusion Models

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:20.004397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aaa1b858-7fb0-4d7a-8413-b7a35de4a838 · outbound

This paper cites G3PT: Unleash the power of Autoregressive Modeling in 3D Generation via Cross-scale Querying Transformer.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression G3PT: Unleash the power of Autoregressive Modeling in 3D Generation via Cross-scale Querying Transformer

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:20.116154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91b9fa70-7ee9-4c17-b71a-2ec91cd63095 · outbound

This paper cites VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:20.208413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e2adf34-da4a-445f-a409-4db203c50c08 · outbound

This paper cites The unreasonable effectiveness of deep features as a perceptual metric.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression The unreasonable effectiveness of deep features as a perceptual metric

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:20.320593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b14eb1c8-94d5-4847-9600-356c9fdc9949 · outbound

This paper cites Faster Diffusion via Temporal Attention Decomposition.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Faster Diffusion via Temporal Attention Decomposition

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:20.398774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55a8508a-c4ac-4be5-804e-d2fb45026751 · outbound

This paper cites Cam: Cache merging for memory-efficient llms inference.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Cam: Cache merging for memory-efficient llms inference

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:16:22.625939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c37d9c57-6909-4482-b493-26005cd2d039 · outbound

This paper cites H2o: Heavy-hitter oracle for efficient generative inference of large language models.Advances in Neural Information Processing Systems, 36:34661–34710, 2023.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression H2o: Heavy-hitter oracle for efficient generative inference of large language models.Advances in Neural Information Processing Systems, 36:34661–34710, 2023

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:20.627739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30e5a746-e8e1-4266-af0e-8df43ff5936d · outbound

This paper cites Real-Time Video Generation with Pyramid Attention Broadcast.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Real-Time Video Generation with Pyramid Attention Broadcast

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:20.706471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76094485-c0db-45ea-b5ce-5a4b36647ba1 · outbound

This paper cites MobileDiffusion: Instant Text-to-Image Generation on Mobile Devices.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression MobileDiffusion: Instant Text-to-Image Generation on Mobile Devices

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:20.821528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f972b876-9b38-4a37-98c5-2063619a429b · outbound

This paper cites Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:20.927090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 1a3ca253-3931-42c1-bdfb-79ffa010f511 · inbound

Visual Implicit Autoregressive Modeling cites this paper.

Visual Implicit Autoregressive Modeling Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression

Reference 29

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T16:41:18.325747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 348b6ba1-7a44-4b8c-91ef-076c5be59bb4 · inbound

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond cites this paper.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:58:07.596260Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 14f8186d-8235-4945-ba0f-c792e5ebda9f · inbound

Token Radius Attention for Efficient Video Generation cites this paper.

Token Radius Attention for Efficient Video Generation Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T06:03:03.062322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.