Paper Citation Record · LEDGER

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload

As of 5 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 0 inbound Pith citation observations for arXiv:2605.20179.

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

pith.paper-citation-record.v1
2605.20179 v1

Coverage vector

measured 27 of 27 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-20T05:08:07.318040Z

measured 27 of 27 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

27 of 27 outbound references displayed

verified exact17
verified fuzzy3
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch7

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0f9b5235-1bde-4ee7-b7ec-2389628b6e1f · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload OPT: Open Pre-trained Transformer Language Models

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-20T05:13:03.731050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 113e6e4b-1039-4dd0-aa8a-15d076ecfb09 · outbound

This paper cites DeepSeek-V3 Technical Report.

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload DeepSeek-V3 Technical Report

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T05:13:03.752058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d4d7dabb-125b-4680-95e9-b135c9382e38 · outbound

This paper cites Mixtral of Experts.

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload Mixtral of Experts

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-20T05:13:03.757977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7bb4c9cd-a4e7-4a86-93dc-a577b0d4497a · outbound

This paper cites Large Language Diffusion Models.

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload Large Language Diffusion Models

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T05:13:03.733901Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation caffc47f-c238-4bb0-a6e1-db6383da6e8b · outbound

This paper cites Dream 7B: Diffusion Large Language Models.

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload Dream 7B: Diffusion Large Language Models

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-20T05:13:03.719093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 00bcf1f7-fbe1-44f3-adc6-934c17a35432 · outbound

This paper cites LLaDA2.0: Scaling Up Diffusion Language Models to 100B.

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload LLaDA2.0: Scaling Up Diffusion Language Models to 100B

Reference 7

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T05:13:03.722203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 55e81f24-ade2-442f-918f-5f08c67fda51 · outbound

This paper cites Scaling Diffusion Language Models via Adaptation from Autoregressive Models.

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload Scaling Diffusion Language Models via Adaptation from Autoregressive Models

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:59:37.219442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0f0044f2-cd4c-4b3c-96b8-aab802e1b118 · outbound

This paper cites Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity.

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-20T05:13:03.713281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 45ff2155-b4bf-45d5-93ea-97901e71d8b9 · outbound

This paper cites Jiakun Fan, Yanglin Zhang, Xiangchen Li, and Dimitrios S.

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload Jiakun Fan, Yanglin Zhang, Xiangchen Li, and Dimitrios S

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-20T05:13:03.716225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9338576d-07b3-400e-a5f0-267a21c1bbab · outbound

This paper cites FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU.

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-20T05:13:03.728349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d6e6d716-bb7c-44dc-9b1b-860c560dc3a5 · outbound

This paper cites ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Caching.

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Caching

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-20T05:13:03.755282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bf5801a3-2f0a-49de-8c30-6ff1c7e08711 · outbound

This paper cites Quant- dllm: Post-training extreme low-bit quantization for diffusion large language models.

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload Quant- dllm: Post-training extreme low-bit quantization for diffusion large language models

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T05:13:03.760772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6bb5c8fc-a2bc-4180-8bb0-5ba106576c76 · outbound

This paper cites dKV-Cache: The Cache for Diffusion Language Models.

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload dKV-Cache: The Cache for Diffusion Language Models

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-20T05:13:03.704690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 83b15ddb-21a6-43cf-a67d-2c5854c9bf0d · outbound

This paper cites Diffusion Language Models Know the Answer Before Decoding.

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload Diffusion Language Models Know the Answer Before Decoding

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-05-20T05:13:03.698590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4322819a-bd0e-4967-a810-1c4b771e50c1 · outbound

This paper cites Post-training quantization on diffusion models.2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 1972–1981.

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload Post-training quantization on diffusion models.2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 1972–1981

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T05:13:21.926676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3ba97499-6cd2-48b3-922a-bb25b555c152 · outbound

This paper cites PTQD: Accurate Post-Training Quantization for Diffusion Models.

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload PTQD: Accurate Post-Training Quantization for Diffusion Models

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-20T05:13:03.701766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 27eaf72f-a32c-4b38-86b6-2340c878028f · outbound

This paper cites Fast Inference of Mixture-of-Experts Language Models with Offloading.

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload Fast Inference of Mixture-of-Experts Language Models with Offloading

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-20T05:13:03.710574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b4175d1d-845f-4f1c-b391-4bfa1a17e30f · outbound

This paper cites MoE-Infinity: Efficient MoE Inference on Personal Machines with Sparsity-Aware Expert Cache.

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload MoE-Infinity: Efficient MoE Inference on Personal Machines with Sparsity-Aware Expert Cache

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-20T05:13:03.693206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1087921c-6810-437f-8404-1439cc18a27b · outbound

This paper cites Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models.

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models

Reference 20

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T05:13:03.696021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 32ea3cec-a299-4346-adaa-988a4b61ef13 · outbound

This paper cites Denoising Diffusion Probabilistic Models.

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload Denoising Diffusion Probabilistic Models

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-20T05:13:03.686922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c8430cca-59cd-4e44-b0b3-004cb7a03812 · outbound

This paper cites Blattmann, Dominik Lorenz, Patrick Esser, and Björn Ommer.

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload Blattmann, Dominik Lorenz, Patrick Esser, and Björn Ommer

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T05:13:21.924691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 65361a2d-8d96-4de8-b9c6-17d23ec44c8a · outbound

This paper cites Peebles and Saining Xie.

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload Peebles and Saining Xie

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T05:13:21.922737Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ea46ffab-6b91-458b-afc5-6c615999db4d · outbound

This paper cites PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis.

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

Reference 24

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T05:13:03.684257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9a57b365-99be-4e39-92bd-606b847d5be0 · outbound

This paper cites Open-Sora: Democratizing Efficient Video Production for All.

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload Open-Sora: Democratizing Efficient Video Production for All

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-05-20T05:13:03.690121Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9e642b10-4d14-4661-9f30-87781363a849 · outbound

This paper cites DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale.

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale

Reference 26

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T05:13:03.707662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a5390296-79ae-412d-9ec3-3f59d777ff3b · outbound

This paper cites Code available athttps://github.com/EleutherAI/lm-evaluation-harness.

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload Code available athttps://github.com/EleutherAI/lm-evaluation-harness

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-20T05:13:03.677996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b6041338-c31f-4bd1-a05b-bb137fe18b2e · outbound

This paper cites dinfer: An efficient inference framework for diffusion language models.

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload dinfer: An efficient inference framework for diffusion language models

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-20T05:13:03.681182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Pith citing papers

No inbound Pith citation observations are available.