Pith. sign in

Paper Citation Record · LEDGER

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation

As of 8 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 0 inbound Pith citation observations for arXiv:2607.24025.

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

pith.paper-citation-record.v1
2607.24025 v2

Coverage vector

measured 58 of 58 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T04:02:20.100422Z

measured 58 of 58 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+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

58 of 58 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved58
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 52c41f62-5afd-4372-aacc-1cfacd4e50fc · outbound

This paper cites Attention is all you need,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Attention is all you need,

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:19.960405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:19.960405Z digest=sha256:b70e3d708029b15410c5c21e45f1775e58d2932075dbfd48ee9176a680e4d8a4

Observation 91f9edbc-29b6-4796-8f2e-e500dfad1679 · outbound

This paper cites Bert: Pre-training of deep bidirectional transformers for language understanding,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Bert: Pre-training of deep bidirectional transformers for language understanding,

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:19.963790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:19.963790Z digest=sha256:a0a637a0d9ae56a56c41f5780f202887bc93482aad6d2d478e502f514a472d16

Observation 384cd131-0909-400a-8ad5-b9cb6fd9f62c · outbound

This paper cites Language mod- els are few-shot learners,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Language mod- els are few-shot learners,

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:19.966382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:19.966382Z digest=sha256:9d0958ad36370e3e9f9af1ee47f5183aa97fca3fe54597653d1f7d292c23d6f3

Observation 1ce6bcf7-c016-42d1-ab67-3ca3047d2713 · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:19.969134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:19.969134Z digest=sha256:99107d2e2df7c01c49704c71aff6b6d40dd7bf6488dd1d33fa5c9ad2bce56f55

Observation c8eab13c-3c24-4c58-a377-814070a4b550 · outbound

This paper cites Swin transformer: Hierarchical vision transformer using shifted windows,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Swin transformer: Hierarchical vision transformer using shifted windows,

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:19.971982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:19.971982Z digest=sha256:76ca969e9329c98a1572feb2b805eef09735b1e81ad516560ba11313826c915a

Observation 9c2d7e0e-81e6-4a0e-a6bb-8cac7bb86199 · outbound

This paper cites Onetrans: Unified feature interaction and sequence modeling with one transformer in industrial recommender,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Onetrans: Unified feature interaction and sequence modeling with one transformer in industrial recommender,

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:19.974519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:19.974519Z digest=sha256:ff1628ad23c6aa24fedae5d1098d8000e40a6384fa4d7daa5efe150cacdef892

Observation 6bbc5731-5b2c-41cd-9c9d-f662d4c0a876 · outbound

This paper cites Final: Factorized interaction layer for ctr prediction,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Final: Factorized interaction layer for ctr prediction,

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:19.977241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:19.977241Z digest=sha256:8c8c550de478858a56cf0ca33d3d56d1ebd390f52bde8575704e5cf8386b6518

Observation e953d0fd-1f69-483a-93c9-bfd4ff8be727 · outbound

This paper cites Bert4rec: Sequential recommendation with bidirectional encoder representations from transformer,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Bert4rec: Sequential recommendation with bidirectional encoder representations from transformer,

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:19.979553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:19.979553Z digest=sha256:911ea2012b1a751bc2e977e173b933b01bbe5abd8e402cd5bc6cd2efc505ff4b

Observation a18bfaa1-0571-40bb-b75a-154c9b86acb2 · outbound

This paper cites Self-attentive sequential recommenda- tion,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Self-attentive sequential recommenda- tion,

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:19.981858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:19.981858Z digest=sha256:93b82aa7ac2a9cabfe40f7ac69aa4432bce875659fa6dab64cd5bd8b1d111554

Observation 7d514556-5654-4900-bcf9-8463741a11a0 · outbound

This paper cites Autoint: Automatic feature interaction learning via self-attentive neural networks,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Autoint: Automatic feature interaction learning via self-attentive neural networks,

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:19.984153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:19.984153Z digest=sha256:6f6be1a8854dc9fd3b51e47ca7b8626adf208d770f67c86b944f86e2698c3eb4

Observation d97a5720-a68d-4612-be71-28f533e621bf · outbound

This paper cites Rankmixer: Scaling up ranking models in industrial recommenders,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Rankmixer: Scaling up ranking models in industrial recommenders,

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:19.986716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:19.986716Z digest=sha256:87a0a6f2c1f9de7682afcae0c9829ecbf054e97d4b88b3c32eb2cc21836d06e7

Observation abe69cc7-9f9a-4e37-9307-cd421d9735aa · outbound

This paper cites Qwen3 Technical Report.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Qwen3 Technical Report

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:19.988997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:19.988997Z digest=sha256:134eee65edec07b2a7a2fc8804aad252c69ec8521ebc1ef10dc522bd4255c681

Observation 9a47b7bd-b8ea-42bc-8f53-f55cdbcfe8ff · outbound

This paper cites How do recommendation models amplify popularity bias? an analysis from the spectral perspective,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation How do recommendation models amplify popularity bias? an analysis from the spectral perspective,

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:19.991523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:19.991523Z digest=sha256:3e3c71a967bb50744b227de60f88999408fc561bf3d60c892f7fbb2a53615025

Observation 92c97666-b6ef-44cb-9686-f635ce9e7d61 · outbound

This paper cites On the Embedding Collapse when Scaling up Recommendation Models.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation On the Embedding Collapse when Scaling up Recommendation Models

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:19.993952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:19.993952Z digest=sha256:ab5620ea570d795afed29d295a233984d9fca9118719819a82d4b563e7af2714

Observation 181fa77c-ed5c-44a0-8a3f-c13ba2ba369f · outbound

This paper cites RankUp: Towards High-rank Representations for Large Scale Advertising Recommender Systems.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation RankUp: Towards High-rank Representations for Large Scale Advertising Recommender Systems

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:19.996551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:19.996551Z digest=sha256:6e2e202fb7387a488f8bf7278c71fc03fdb7da10a642b6d0407c71d2beb91777

Observation c1bdb5d4-2ab3-4e36-a8fc-17c26ddd9485 · outbound

This paper cites From Scaling to Structured Expressivity: Rethinking Transformers for CTR Prediction.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation From Scaling to Structured Expressivity: Rethinking Transformers for CTR Prediction

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:19.999061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:19.999061Z digest=sha256:8438bd21e361a5683ea1fe16ed69da63d4a928ef5fb7e4458a5037778d3d1819

Observation f33a9bb1-3150-4441-8928-7d3ace94b19d · outbound

This paper cites Are id embeddings nec- essary? whitening pre-trained text embeddings for effective sequential recommendation,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Are id embeddings nec- essary? whitening pre-trained text embeddings for effective sequential recommendation,

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.001615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.001615Z digest=sha256:c3fab4745597da50ae150d827769d5b255084fbb56498adea1e675ed2f210122

Observation b91b1fb0-0e57-4c2b-b514-2abe31619e3e · outbound

This paper cites FEDIN: Frequency-Enhanced Deep Interest Network for Click-Through Rate Prediction.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation FEDIN: Frequency-Enhanced Deep Interest Network for Click-Through Rate Prediction

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.003934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.003934Z digest=sha256:bd0f6c601f0043fe3d47aaa411bba985f99666dd9593df0e65a3b37889bf8710

Observation 3564dc0b-73df-459d-a076-aaaf78e81d79 · outbound

This paper cites A convolutional click prediction model,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation A convolutional click prediction model,

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.006723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.006723Z digest=sha256:4da0518b9b4d46e9c4447f69de74dbfd6972112df74dab91f674dc518db3998f

Observation 05fa382f-a435-452d-a4aa-5efd6854225e · outbound

This paper cites Fibinet: combining feature impor- tance and bilinear feature interaction for click-through rate prediction,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Fibinet: combining feature impor- tance and bilinear feature interaction for click-through rate prediction,

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.009070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.009070Z digest=sha256:77926de53dd2cdf8780d9f20ab13022de05a7a7b911e3251c0ebb10430198cd0

Observation 561a33df-e673-4491-a9bc-39b57ed471d2 · outbound

This paper cites Field-weighted factorization machines for click-through rate prediction in display advertising,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Field-weighted factorization machines for click-through rate prediction in display advertising,

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.011439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.011439Z digest=sha256:180b079f1731a1127a426d0e0fe14eb5e02b8bc6d71256e2e7a4acd9846b06ff

Observation 185d5887-22ba-4ab3-a1f0-75a6eeb50660 · outbound

This paper cites Fm2: Field-matrixed factor- ization machines for recommender systems,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Fm2: Field-matrixed factor- ization machines for recommender systems,

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.014068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.014068Z digest=sha256:df901381e60d7e55ce7c0687607cf81da8d8578ac5aade0dd637a24172eb0123

Observation 016fcee9-a7fb-46d8-bf86-39e88c92c481 · outbound

This paper cites DeepFM: A Factorization-Machine based Neural Network for CTR Prediction.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation DeepFM: A Factorization-Machine based Neural Network for CTR Prediction

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.016540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.016540Z digest=sha256:6f124c64e838aae12d598447757b350f801af624e786208c1e8fed1efa2f1b1a

Observation 8f749684-312e-4c61-b8bd-30672b6c6df2 · outbound

This paper cites Fibinet++: Reducing model size by low rank feature interaction layer for ctr prediction,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Fibinet++: Reducing model size by low rank feature interaction layer for ctr prediction,

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.019143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.019143Z digest=sha256:348485786eaaf5d1aeb81b08eb5ebd41d87dc4c72e9a82ecac5a978a39b824b0

Observation 260a4727-6feb-4845-a7f0-857380a5a8cd · outbound

This paper cites Factorization machines,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Factorization machines,

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.021422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.021422Z digest=sha256:08cb803246cb1d4ae9bd856b6fb2886c6efe59bcac67b6be0238ae373c759a63

Observation b38a2f74-7bbd-46da-abc2-30a9ccabe70c · outbound

This paper cites Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.023774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.023774Z digest=sha256:80abb0f375a617764c09b9743ec98bc9e712fefd0d82d9c426762ba44403a1ba

Observation 143abf4d-4933-4a35-bc17-f7adf55cfc02 · outbound

This paper cites Wide & deep learning for recommender systems,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Wide & deep learning for recommender systems,

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.026323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.026323Z digest=sha256:10ad386f184069c8acb39648bf88c6fceb935a7f1d42b61b8006566417b3171a

Observation ac60bb36-fc01-44a4-ba1e-b3a171e124fa · outbound

This paper cites Hiformer: Heterogeneous Feature Interactions Learning with Transformers for Recommender Systems.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Hiformer: Heterogeneous Feature Interactions Learning with Transformers for Recommender Systems

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.028664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.028664Z digest=sha256:96812630a7960f96be3b05498ac59ab916271e83a819420f386aae5647b0dbda

Observation 759ffbee-6216-445e-8f63-bbfd49cd90f1 · outbound

This paper cites Layer Normalization.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Layer Normalization

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.031196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.031196Z digest=sha256:4ce4fe35e3414772836dcb3842ace567b0c4a9559a9682e4b3dfd1ecf9c2eb89

Observation a73648fd-1cfb-4f57-866f-118272bc662d · outbound

This paper cites Svd approach to data unfolding,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Svd approach to data unfolding,

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.033736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.033736Z digest=sha256:ce527e02c5172c0100dbea54843fd7419e38319f16ba94923c2f3a3d54383ca7

Observation 39ddc59a-647b-4aa5-8734-293e0dd21733 · outbound

This paper cites Towards mitigat- ing dimensional collapse of representations in collaborative filtering,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Towards mitigat- ing dimensional collapse of representations in collaborative filtering,

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.036063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.036063Z digest=sha256:ee031d0fd6fbd02aa4ccbc341fb3adea45cafd5b42d3f747c2800da1983376b7

Observation 1e995d6b-6e38-48e3-9e3b-f5fd0cc7df36 · outbound

This paper cites SpecTran: Spectral-Aware Transformer-based Adapter for LLM-Enhanced Sequential Recommendation.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation SpecTran: Spectral-Aware Transformer-based Adapter for LLM-Enhanced Sequential Recommendation

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.038398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.038398Z digest=sha256:f196404ff2bea364c1c73d3fa7acf14f4be228b38cf6167dbf5996caef2eda0a

Observation 49f6ff1a-5eb1-4690-82ea-4c89752b79c0 · outbound

This paper cites The effective rank: A measure of effective dimensionality,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation The effective rank: A measure of effective dimensionality,

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.040853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.040853Z digest=sha256:d24d84a04d0a3671d105942a92234424bc344d7312de312c017c43b1abb07214

Observation 56517dd1-8613-4009-9d39-9282bc6c0bb5 · outbound

This paper cites A mathematical theory of communication,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation A mathematical theory of communication,

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.043106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.043106Z digest=sha256:0372637a9cae5f961ce2c80f560c40aa9edd0cf9c80e8595156731b2471d805a

Observation e7d60c81-f44d-42a9-a40f-5ba4953ffb15 · outbound

This paper cites Signal propagation in transformers: Theoretical perspectives and the role of rank collapse,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Signal propagation in transformers: Theoretical perspectives and the role of rank collapse,

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.045555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.045555Z digest=sha256:84a6f49be1449f94df41ed6839963fe131fdeb9de2d4d5866abea5cc335747dd

Observation 64b498cf-548b-4a2b-b254-4c79dfb899c8 · outbound

This paper cites Diff-erank: A novel rank- based metric for evaluating large language models,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Diff-erank: A novel rank- based metric for evaluating large language models,

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.047931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.047931Z digest=sha256:4a2d1f8685dbb6c92b2b552d6e05c5c47abc2e9c2a4387d7c3f31192c066229e

Observation 7accd237-d786-457e-a665-412bed5a7a71 · outbound

This paper cites Dcn v2: Improved deep & cross network and practical lessons for web- scale learning to rank systems,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Dcn v2: Improved deep & cross network and practical lessons for web- scale learning to rank systems,

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.050183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.050183Z digest=sha256:ee2b006ac8beb2c85acf8a23497b6a6272b1fdd988f1b18ce4b8d17b21fcf9b1

Observation 8fbdc09e-88bd-4432-8af7-cf4905b25626 · outbound

This paper cites Attention is not all you need: Pure attention loses rank doubly exponentially with depth,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Attention is not all you need: Pure attention loses rank doubly exponentially with depth,

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.052525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.052525Z digest=sha256:a882cff2425ef8f1d3c6b423d77f32c78ba96cecc3331deb1d99589879438475

Observation 6330d395-4451-4d42-9695-266afb97123c · outbound

This paper cites On the Properties of the Softmax Function with Application in Game Theory and Reinforcement Learning.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation On the Properties of the Softmax Function with Application in Game Theory and Reinforcement Learning

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.054877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.054877Z digest=sha256:4ae0c3e30f1493651fa0b8496cfeda64095c14e8dc4c179ada5d3edec16c3758

Observation 955f5317-bd76-468d-9548-63aafb2763fe · outbound

This paper cites MaskNet: Introducing Feature-Wise Multiplication to CTR Ranking Models by Instance-Guided Mask.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation MaskNet: Introducing Feature-Wise Multiplication to CTR Ranking Models by Instance-Guided Mask

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.057452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.057452Z digest=sha256:5124c12a55bdb922c34fee59cbcc6c39c9afbcbb6dd78b03850a2b3ba36df7e0

Observation 781c8584-75f2-4c02-9ef7-2db3852518e5 · outbound

This paper cites Towards deeper, lighter and interpretable cross network for ctr prediction,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Towards deeper, lighter and interpretable cross network for ctr prediction,

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.059892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.059892Z digest=sha256:bc4020a66d7799e43b00bf5096e8237a30b4ec70b8bd9eaf91c5d7e720688808

Observation 0e915f7e-a94e-4b12-97d3-24294b331b76 · outbound

This paper cites Deep interest network for click-through rate prediction,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Deep interest network for click-through rate prediction,

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.062160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.062160Z digest=sha256:c94bc849c684ffe916a72b78daa06790d8618890153d6e7cea5264bf721a4976

Observation 480b09c5-130d-4699-9376-8a13588b37ad · outbound

This paper cites Adaptive subgradient methods for online learning and stochastic optimization.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Adaptive subgradient methods for online learning and stochastic optimization

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.064577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.064577Z digest=sha256:605254f5c5843c6249937eadb9710ae8cbb84d00e3ec7e401087f5a218280328

Observation ae74afbf-ec8b-426d-b515-9ab197fc63cd · outbound

This paper cites A generic learning framework for sequential recommendation with distribution shifts,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation A generic learning framework for sequential recommendation with distribution shifts,

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.066855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.066855Z digest=sha256:65f85bad56d956eccb834e58c36789a5e548bef6857fab60c44827301d8ae067

Observation 80bbae74-82dc-4ca7-8541-d8e99f52701b · outbound

This paper cites Search-based user interest modeling with lifelong sequential behavior data for click-through rate prediction,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Search-based user interest modeling with lifelong sequential behavior data for click-through rate prediction,

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.069168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.069168Z digest=sha256:55afc22f8f4bb138ee9fb1a41877d94040e933b94861a6476702cfbb9c43375b

Observation 28157985-1608-458b-b396-8633d633f2db · outbound

This paper cites Tallrec: An effective and efficient tuning framework to align large language model with recommendation,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Tallrec: An effective and efficient tuning framework to align large language model with recommendation,

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.071461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.071461Z digest=sha256:e4b3098384311d5504a091710a7eb012c1f215ab745faf21b257b2d20a7c6ea2

Observation b3314d9f-8a23-47b4-a4d6-d66d9aa987f9 · outbound

This paper cites HLLM: Enhancing Sequential Recommendations via Hierarchical Large Language Models for Item and User Modeling.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation HLLM: Enhancing Sequential Recommendations via Hierarchical Large Language Models for Item and User Modeling

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.073864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.073864Z digest=sha256:ae2d92aa1e715782c692d6b1c9660376905f929eda26c1c4bd2242f4efe7adab

Observation 2e5e6948-3a76-48f0-a3d5-eeff0890bd34 · outbound

This paper cites Rella: Retrieval-enhanced large language models for lifelong sequential behavior comprehension in recommendation,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Rella: Retrieval-enhanced large language models for lifelong sequential behavior comprehension in recommendation,

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.076422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.076422Z digest=sha256:3344da39a26316f6930f5caa25d76749bf33ea0287d9578ad5dbd19e7590919b

Observation 49ca7f9a-aa19-4113-b840-df9b8b1abf71 · outbound

This paper cites Breaking the length barrier: Llm-enhanced ctr prediction in long textual user behaviors,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Breaking the length barrier: Llm-enhanced ctr prediction in long textual user behaviors,

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.078804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.078804Z digest=sha256:8e8028ee76d50d8aa57daef986de52b66872440fa7f299e8194c75f6d326ba52

Observation 3d162885-8bd2-4fef-a7f0-1b1efa28c76b · outbound

This paper cites Ctrl: Connect collaborative and language model for ctr prediction,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Ctrl: Connect collaborative and language model for ctr prediction,

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.081076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.081076Z digest=sha256:036068680991e0cecd60165a6b2705307fdd35fe18423c0887f136fca6d9e0f2

Observation 6d547ed6-fba1-46ec-9f93-f11fa5efaaa1 · outbound

This paper cites Towards open-world recommendation with knowledge augmentation from large language models,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Towards open-world recommendation with knowledge augmentation from large language models,

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.083485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.083485Z digest=sha256:04b6adfee2c527477204f3978224a43d94d291b3bed52eec9fe96b05aeaa12e7

Observation dea0b752-4bf9-4b3e-8622-a0b9a9789ade · outbound

This paper cites Large language models enhanced collaborative filtering,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Large language models enhanced collaborative filtering,

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.085807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.085807Z digest=sha256:067523f94b40f2aa95e17a333113fecf18a4473d4421603912c5a192a0b7fc4e

Observation e4566b20-1fde-4292-a03e-b9ad89e66865 · outbound

This paper cites Field matters: A lightweight llm-enhanced method for ctr prediction,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Field matters: A lightweight llm-enhanced method for ctr prediction,

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.088087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.088087Z digest=sha256:30d8315d8110e93ca73bd83a0e4546e13fef631a43f34e228b5f9ec8567046ff

Observation 85186d44-c892-490e-b2da-4ea130d879d7 · outbound

This paper cites Representation Degeneration Problem in Training Natural Language Generation Models.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Representation Degeneration Problem in Training Natural Language Generation Models

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.090483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.090483Z digest=sha256:7cda3139882e33e55135426798b0c47dd487df0d6a10bba9d056d7bbca8f5a16

Observation 464d843e-6527-472c-b714-98f1cf04fc90 · outbound

This paper cites Understanding Dimensional Collapse in Contrastive Self-supervised Learning.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Understanding Dimensional Collapse in Contrastive Self-supervised Learning

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.093063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.093063Z digest=sha256:0576560d20bd02e1222b06437528cf2cc3685a4f817f0c68a063b2ed727b5103

Observation 13fce91e-549f-4611-8dc1-dae510479f10 · outbound

This paper cites On feature decorrelation in self-supervised learning,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation On feature decorrelation in self-supervised learning,

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.095616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.095616Z digest=sha256:0230aabb1c8d44a05b638e28914f339c881bc3f629d0db1cb9eeef19dbd6bc5a

Observation 18193bd7-b05b-41f4-be8e-31a7ce04bc03 · outbound

This paper cites Alphafuse: Learn id embeddings for sequential recommendation in null space of language embeddings,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Alphafuse: Learn id embeddings for sequential recommendation in null space of language embeddings,

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.098088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.098088Z digest=sha256:f30d138a17c25b08bfd3e2495f5ad51d73a26a445e72ecd8290c8b3830d4ec5b

Observation 8d7d4436-565a-4a14-8330-6401f786bbef · outbound

This paper cites Low-rank bottleneck in multi-head attention models,.

SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation Low-rank bottleneck in multi-head attention models,

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-04T04:02:20.100422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T04:02:20.100422Z digest=sha256:c95fb08b2c8ebee2519ce32b11233b1a4602e4ed64ca5dff8cb3ee5a49074ad6

Pith citing papers

No inbound Pith citation observations are available.