Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond | Paper Citation Record

Observation 4be60268-c99f-4ab9-8732-a5a9ea8e3676 · outbound

This paper cites Introducing the next generation of claude., 2024.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Introducing the next generation of claude., 2024

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.511187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 279686bc-f4f6-448a-987e-81dbb735b0cf · outbound

This paper cites On exact computation with an infinitely wide neural net.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond On exact computation with an infinitely wide neural net

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.518261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1b3dbd5-b8e7-4a3d-bb6c-a0dc8be9e70b · outbound

This paper cites Llm-based interaction for content generation: A case study on the perception of employees in an it department.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Llm-based interaction for content generation: A case study on the perception of employees in an it department

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.523877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ade0c026-4d71-49d6-8974-d0266e0524f2 · outbound

This paper cites Bypass exponential time preprocessing: Fast neural network training via weight-data correlation preprocessing.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Bypass exponential time preprocessing: Fast neural network training via weight-data correlation preprocessing

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.528602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d7e539e-5db4-4c83-84cb-0c991e19df62 · outbound

This paper cites Fast attention requires bounded entries.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Fast attention requires bounded entries

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.534157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 946d25b4-c852-4266-9dc3-1c02bab19609 · outbound

This paper cites The Fine-Grained Complexity of Gradient Computation for Training Large Language Models.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond The Fine-Grained Complexity of Gradient Computation for Training Large Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.541328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94122f13-1096-4cd8-b070-b37bcc90197d · outbound

This paper cites Llm based generation of item-description for recommendation system.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Llm based generation of item-description for recommendation system

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.556757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c54e4e10-7f15-4e91-8735-c5ce0473dd69 · outbound

This paper cites Bypass exponential time preprocessing: Fast neural network training via weight-data correlation preprocessing.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Bypass exponential time preprocessing: Fast neural network training via weight-data correlation preprocessing

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.566547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e6a9525-fe91-460d-852a-2af2898b3988 · outbound

This paper cites Feature purification: How adversarial training performs robust deep learning.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Feature purification: How adversarial training performs robust deep learning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.577666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05ea6396-6df3-4a29-a3dd-14a6987877f0 · outbound

This paper cites Physics of Language Models: Part 1, Learning Hierarchical Language Structures.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Physics of Language Models: Part 1, Learning Hierarchical Language Structures

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.588988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edb75f36-af61-4fe9-a55c-b0f5cc45cccf · outbound

This paper cites Learning and generalization in overparameterized neural networks, going beyond two layers.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Learning and generalization in overparameterized neural networks, going beyond two layers

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.597787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3c83118-4231-4646-95c0-0a034bf76bce · outbound

This paper cites A convergence theory for deep learning via over-parameterization.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond A convergence theory for deep learning via over-parameterization

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.604056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d86b3676-625c-43ab-9d8a-189810c55655 · outbound

This paper cites On the convergence rate of training recurrent neural networks.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond On the convergence rate of training recurrent neural networks

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.611451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5d2edd1-b01c-4fb6-a225-c145ec4d7bf7 · outbound

This paper cites Hierarchical attention network for multivariate time series long-term forecasting.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Hierarchical attention network for multivariate time series long-term forecasting

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.617171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f300310-85ba-481c-8d22-7789f819720d · outbound

This paper cites Distribution of residual autocorrelations in autoregressive-integrated moving average time series models.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Distribution of residual autocorrelations in autoregressive-integrated moving average time series models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.622387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84517f45-5df3-446f-acd7-c8a5819e00ca · outbound

This paper cites Training (overparametrized) neural networks in near-linear time.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Training (overparametrized) neural networks in near-linear time

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.628313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d915b109-40f5-4085-abfa-35c2d5c8f6d3 · outbound

This paper cites Time series forecasting for healthcare diagnosis and prognostics with the focus on cardiovascular diseases.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Time series forecasting for healthcare diagnosis and prognostics with the focus on cardiovascular diseases

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.635056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b1b946f-992a-430b-b046-a505d3f4f377 · outbound

This paper cites Language Models are Few-Shot Learners.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Language Models are Few-Shot Learners

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.641847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20fd3485-5b1c-45d1-87f5-bc8cbb57989c · outbound

This paper cites Algorithm and Hardness for Dynamic Attention Maintenance in Large Language Models.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Algorithm and Hardness for Dynamic Attention Maintenance in Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.653536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea4cbbe5-a6c6-433a-965c-41e0e96f4aa9 · outbound

This paper cites Fast gradient computation for rope attention in almost linear time.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Fast gradient computation for rope attention in almost linear time

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.663688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc4095b5-ee5d-4a48-9f5f-520ac7c7ff1e · outbound

This paper cites Circuit Complexity Bounds for RoPE-based Transformer Architecture.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Circuit Complexity Bounds for RoPE-based Transformer Architecture

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.675235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22f0d32a-2edc-41d6-bde5-8d3630499b3f · outbound

This paper cites Bypassing the exponential dependency: Looped transformers efficiently learn in-context by multi-step gradient descent.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Bypassing the exponential dependency: Looped transformers efficiently learn in-context by multi-step gradient descent

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.684662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0ff4ddc-7495-433d-8bdd-8880486a6c82 · outbound

This paper cites The computational limits of state-space models and mamba via the lens of circuit complexity.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond The computational limits of state-space models and mamba via the lens of circuit complexity

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.694047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e68a0c98-31b4-4f95-b1d6-82a46425545f · outbound

This paper cites Universal Approximation of Visual Autoregressive Transformers.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Universal Approximation of Visual Autoregressive Transformers

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.699529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5125ce22-a7c5-4fde-900c-abedef89f749 · outbound

This paper cites Hsr-enhanced sparse attention acceleration.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Hsr-enhanced sparse attention acceleration

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.704753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2271ee52-4266-4fda-801f-b7163c685639 · outbound

This paper cites TSMixer: An All-MLP Architecture for Time Series Forecasting.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond TSMixer: An All-MLP Architecture for Time Series Forecasting

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.721211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cff61bb-db14-401a-b3e5-69459440e6e9 · outbound

This paper cites Long sequence time-series forecasting with deep learning: A survey.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Long sequence time-series forecasting with deep learning: A survey

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.730024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81cf4967-e4e5-4069-bb6a-4589df522009 · outbound

This paper cites Fine-tune Language Models to Approximate Unbiased In-context Learning.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Fine-tune Language Models to Approximate Unbiased In-context Learning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.737148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e7b7dfc-97cb-4bca-8278-fa44ed907ef8 · outbound

This paper cites How to protect copyright data in optimization of large language models? In Proceedings of the AAAI Conference on Artificial Intelligence , pages 17871--17879, 2024.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond How to protect copyright data in optimization of large language models? In Proceedings of the AAAI Conference on Artificial Intelligence , pages 17871--17879, 2024

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.747341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc23ef02-e435-4524-bd3d-c6d3b73de431 · outbound

This paper cites Long-term Forecasting with TiDE: Time-series Dense Encoder.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Long-term Forecasting with TiDE: Time-series Dense Encoder

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.759938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a4e6482-9a68-47de-aac6-88b57d054b55 · outbound

This paper cites Attention scheme inspired softmax regression, 2023.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Attention scheme inspired softmax regression, 2023

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.765636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ac29ba1-0da6-4bc4-86da-9253652e7d9d · outbound

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

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.770982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28605276-17b9-40a3-a5ff-a24e45145430 · outbound

This paper cites Tsmixer: Lightweight mlp-mixer model for multivariate time series forecasting.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Tsmixer: Lightweight mlp-mixer model for multivariate time series forecasting

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.777609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45248676-4f9b-4f23-8f3d-9ad9b33c69fc · outbound

This paper cites Mamba: Linear-Time Sequence Modeling with Selective State Spaces.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.783765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ac70c72-9f2e-4fab-994f-839965a530f1 · outbound

This paper cites Exponential smoothing: The state of the art.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Exponential smoothing: The state of the art

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.790066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4b80120-6971-43ed-a407-1be83e39932b · outbound

This paper cites How to train your hippo: State space models with generalized orthogonal basis projections, 2022.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond How to train your hippo: State space models with generalized orthogonal basis projections, 2022

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.795246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e68edea-4347-489e-b236-8a858a6b5786 · outbound

This paper cites On computational limits of flowar models: Expressivity and efficiency.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond On computational limits of flowar models: Expressivity and efficiency

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.801184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 495cb309-fe88-42e7-8137-073b791f230b · outbound

This paper cites Differential Privacy Mechanisms in Neural Tangent Kernel Regression.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Differential Privacy Mechanisms in Neural Tangent Kernel Regression

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.807219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a96ab34b-7670-40ca-a477-039c14ab2a0c · outbound

This paper cites An Over-parameterized Exponential Regression.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond An Over-parameterized Exponential Regression

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.812967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78edeb0b-25dc-4f1e-86c8-c732c9151eee · outbound

This paper cites A Fast Optimization View: Reformulating Single Layer Attention in LLM Based on Tensor and SVM Trick, and Solving It in Matrix Multiplication Time.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond A Fast Optimization View: Reformulating Single Layer Attention in LLM Based on Tensor and SVM Trick, and Solving It in Matrix Multiplication Time

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.817896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a06b5948-1f68-4e34-a8a6-cb341ac19617 · outbound

This paper cites How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.823091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 932b34b9-d478-4932-b510-99808b4b41ad · outbound

This paper cites Outlier-efficient hopfield layers for large transformer-based models.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Outlier-efficient hopfield layers for large transformer-based models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.834819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d92c60d-035f-4853-baeb-41d40292e2dc · outbound

This paper cites HyperAttention: Long-context Attention in Near-Linear Time.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond HyperAttention: Long-context Attention in Near-Linear Time

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.840028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e1e965d-e8a8-4bdc-916b-467dbd36dcd0 · outbound

This paper cites On computational limits of modern hopfield models: A fine-grained complexity analysis.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond On computational limits of modern hopfield models: A fine-grained complexity analysis

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.845921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86c974be-ef67-43d7-a0d6-87b05a7b4bcc · outbound

This paper cites Fl-ntk: A neural tangent kernel-based framework for federated learning analysis.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Fl-ntk: A neural tangent kernel-based framework for federated learning analysis

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.852057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b471655-5a91-45d5-bd7b-a6866abc898f · outbound

This paper cites Long short-term memory.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Long short-term memory

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.858339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 219df72f-c010-406f-b543-584eae2af93b · outbound

This paper cites Probability inequalities for sums of bounded random variables.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Probability inequalities for sums of bounded random variables

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.864312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64544759-e629-416e-9cfe-83880f5f65e2 · outbound

This paper cites Neural Network-Based Score Estimation in Diffusion Models: Optimization and Generalization.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Neural Network-Based Score Estimation in Diffusion Models: Optimization and Generalization

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.870994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6b16c28-37ad-4104-9068-84d1100d22a3 · outbound

This paper cites Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.877783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aee355ae-f657-496a-b880-f6910ef8bbb0 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond LoRA: Low-Rank Adaptation of Large Language Models

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.889124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 470b8d73-10b2-4f94-9fdf-7c7b426ad597 · outbound

This paper cites Training Overparametrized Neural Networks in Sublinear Time.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Training Overparametrized Neural Networks in Sublinear Time

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.897231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e727fbf-f98f-4e48-834c-6dee3f2f25f5 · outbound

This paper cites Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.901765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9f92ccc-2621-4835-a162-85017b2d15f7 · outbound

This paper cites Towards making the most of llm for translation quality estimation.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Towards making the most of llm for translation quality estimation

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.906533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 050bbf77-e3ce-49ca-839c-ba6ed4a5e321 · outbound

This paper cites Provably optimal memory capacity for modern hopfield models: Transformer-compatible dense associative memories as spherical codes.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Provably optimal memory capacity for modern hopfield models: Transformer-compatible dense associative memories as spherical codes

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.912591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9d91b4d-1ef9-474a-942b-f33da8654067 · outbound

This paper cites On Statistical Rates of Conditional Diffusion Transformers: Approximation, Estimation and Minimax Optimality.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond On Statistical Rates of Conditional Diffusion Transformers: Approximation, Estimation and Minimax Optimality

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.917505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fddc4932-9a70-4138-b433-1018f5b97042 · outbound

This paper cites On statistical rates and provably efficient criteria of latent diffusion transformers (dits).

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond On statistical rates and provably efficient criteria of latent diffusion transformers (dits)

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.923107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee20635a-29c0-4d65-b3ff-1070c32812c9 · outbound

This paper cites Bliva: A simple multimodal llm for better handling of text-rich visual questions.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Bliva: A simple multimodal llm for better handling of text-rich visual questions

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.929399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 530a4829-7699-49ab-a39f-726c35cb36ae · outbound

This paper cites On sparse modern hopfield model.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond On sparse modern hopfield model

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.935453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73d21088-e18e-4ce7-9fb9-01539f4d495d · outbound

This paper cites Neural tangent kernel: Convergence and generalization in neural networks.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Neural tangent kernel: Convergence and generalization in neural networks

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.942938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 819664b4-7710-4a21-a097-e6626c574c4d · outbound

This paper cites A Latent Space Theory for Emergent Abilities in Large Language Models.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond A Latent Space Theory for Emergent Abilities in Large Language Models

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.949524Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 282ad5c5-c343-4f29-8c6d-d92f0cb81635 · outbound

This paper cites Designing a neural network for forecasting financial and economic time series.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Designing a neural network for forecasting financial and economic time series

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.955180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e554a06d-988b-4190-beca-6570f05ab024 · outbound

This paper cites Noise Is Not the Main Factor Behind the Gap Between SGD and Adam on Transformers, but Sign Descent Might Be.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Noise Is Not the Main Factor Behind the Gap Between SGD and Adam on Transformers, but Sign Descent Might Be

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.961315Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 428b239a-0dc3-495e-8577-709978bc78b3 · outbound

This paper cites Ai in healthcare: time-series forecasting using statistical, neural, and ensemble architectures.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Ai in healthcare: time-series forecasting using statistical, neural, and ensemble architectures

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.968750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4ecfc20-1139-4b59-a44d-9de99fc4e8a1 · outbound

This paper cites On Particle Methods for Parameter Estimation in State-Space Models.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond On Particle Methods for Parameter Estimation in State-Space Models

Reference 65

Resolution: verified exact; local_arxiv, observed 2026-08-11T20:09:36.743854Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 61454908-a902-4eff-8170-ca9345e3d331 · outbound

This paper cites On Computational Limits and Provably Efficient Criteria of Visual Autoregressive Models: A Fine-Grained Complexity Analysis.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond On Computational Limits and Provably Efficient Criteria of Visual Autoregressive Models: A Fine-Grained Complexity Analysis

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.980370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1974103-8d09-4846-888f-a13d25aff3ed · outbound

This paper cites Circuit Complexity Bounds for Visual Autoregressive Model.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Circuit Complexity Bounds for Visual Autoregressive Model

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.987140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb1472a5-871d-4cc2-a392-d4fd3dafc9f3 · outbound

This paper cites On the computational complexity of self-attention.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond On the computational complexity of self-attention

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.992215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9588800-6ef8-4d86-848d-5dd8aac14cc6 · outbound

This paper cites Temporal fusion transformers for interpretable multi-horizon time series forecasting.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Temporal fusion transformers for interpretable multi-horizon time series forecasting

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:34.996940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d38d89d-b6f2-420b-8118-032682f71a5e · outbound

This paper cites Short-term traffic flow forecasting: An experimental comparison of time-series analysis and supervised learning.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Short-term traffic flow forecasting: An experimental comparison of time-series analysis and supervised learning

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.001253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 827738ef-5956-4c36-99eb-96621befef75 · outbound

This paper cites iTransformer: Inverted Transformers Are Effective for Time Series Forecasting.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond iTransformer: Inverted Transformers Are Effective for Time Series Forecasting

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.006569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adcde0ed-8b6d-4fbc-9b0b-ea015b8d0c92 · outbound

This paper cites Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.012026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7b49fd0-1f14-41ee-87a2-99a4640101d2 · outbound

This paper cites Learning overparameterized neural networks via stochastic gradient descent on structured data.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Learning overparameterized neural networks via stochastic gradient descent on structured data

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.017188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 422a822d-42e9-4753-8e82-a4ab2566e54e · outbound

This paper cites Image creation based on transformer and generative adversarial networks.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Image creation based on transformer and generative adversarial networks

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.023185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f29b44e-3530-4f03-ad75-3f2b8504d060 · outbound

This paper cites Research progress in attention mechanism in deep learning.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Research progress in attention mechanism in deep learning

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.028119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f899bf06-a821-4fa8-be75-b55a83bf2dc5 · outbound

This paper cites On the expressive power of modern hopfield networks.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond On the expressive power of modern hopfield networks

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.034010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9988b933-2a9c-433b-9a32-1d444eafd866 · outbound

This paper cites Neural algorithmic reasoning for hypergraphs with looped transformers.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Neural algorithmic reasoning for hypergraphs with looped transformers

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.039403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25b118bd-31db-4481-a68e-f7d001b1999f · outbound

This paper cites Theoretical Constraints on the Expressive Power of $\mathsf{RoPE}$-based Tensor Attention Transformers.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Theoretical Constraints on the Expressive Power of $\mathsf{RoPE}$-based Tensor Attention Transformers

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.045433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f736c0a-8ec8-46ed-92c5-0cb58966756c · outbound

This paper cites Fine-grained attention i/o complexity: Comprehensive analysis for backward passes.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Fine-grained attention i/o complexity: Comprehensive analysis for backward passes

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.051107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31154770-d751-4ef7-ad6e-53d8d44be0c9 · outbound

This paper cites Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.056576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b0d61b9-ce5e-4dc2-962b-fbcbf8621f34 · outbound

This paper cites Fourier circuits in neural networks and transformers: A case study of modular arithmetic with multiple inputs.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Fourier circuits in neural networks and transformers: A case study of modular arithmetic with multiple inputs

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.063521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96fb51ff-ae44-424a-92cf-5426d0060f35 · outbound

This paper cites On the Computational Capability of Graph Neural Networks: A Circuit Complexity Bound Perspective.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond On the Computational Capability of Graph Neural Networks: A Circuit Complexity Bound Perspective

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.075009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fee2727-9e40-455f-804d-f7c53c66d832 · outbound

This paper cites Beyond linear approximations: A novel pruning approach for attention matrix.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Beyond linear approximations: A novel pruning approach for attention matrix

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.081152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f525e9d-5c8a-4273-9690-254d07651aef · outbound

This paper cites Exploring the frontiers of softmax: Provable optimization, applications in diffusion model, and beyond.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Exploring the frontiers of softmax: Provable optimization, applications in diffusion model, and beyond

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.085975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d435474-3ef0-4d9d-9416-2d31b86247b1 · outbound

This paper cites A Tighter Complexity Analysis of SparseGPT.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond A Tighter Complexity Analysis of SparseGPT

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.093182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f726300-b392-46f4-9eec-c45fa3429d49 · outbound

This paper cites Generative time series forecasting with diffusion, denoise, and disentanglement.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Generative time series forecasting with diffusion, denoise, and disentanglement

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.102218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9f973ac-7692-4998-a884-3a2fd062e6db · outbound

This paper cites Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.108167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91c84fe1-c4fd-45ca-a201-361601bf9bad · outbound

This paper cites Looped relu mlps may be all you need as practical programmable computers.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Looped relu mlps may be all you need as practical programmable computers

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.115021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40650d1b-5f5f-4a24-bf7f-cba95f7ab9ae · outbound

This paper cites Towards Infinite-Long Prefix in Transformer.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Towards Infinite-Long Prefix in Transformer

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.120554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32b3f52e-f86c-45f2-9d7c-6380beb93b51 · outbound

This paper cites Tensor attention training: Provably efficient learning of higher-order transformers.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Tensor attention training: Provably efficient learning of higher-order transformers

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.126724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 855c0788-7175-40d2-b824-975e9327d8e7 · outbound

This paper cites Pyraformer: Low-complexity pyramidal attention for long-range time series modeling and forecasting.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Pyraformer: Low-complexity pyramidal attention for long-range time series modeling and forecasting

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.132606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84eea693-32da-47de-89da-354d110cbc23 · outbound

This paper cites Time-series forecasting with deep learning: a survey.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Time-series forecasting with deep learning: a survey

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.139281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78839df3-926b-465d-967d-4b381d6cd6e4 · outbound

This paper cites U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.149514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50531e12-03a2-4281-8856-4294ed8e9f20 · outbound

This paper cites Bounding the width of neural networks via coupled initialization a worst case analysis.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Bounding the width of neural networks via coupled initialization a worst case analysis

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.158237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50961c4e-9dc3-45ea-a890-e77eeb9d7add · outbound

This paper cites Generative Artificial Intelligence for Software Engineering -- A Research Agenda.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Generative Artificial Intelligence for Software Engineering -- A Research Agenda

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.166950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5637a151-1615-4169-acf9-7d8d33cb651f · outbound

This paper cites A Time Series is Worth 64 Words: Long-term Forecasting with Transformers.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond A Time Series is Worth 64 Words: Long-term Forecasting with Transformers

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.176976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c412c7a-5bb1-4208-9440-d0ecdd982205 · outbound

This paper cites Gpt-4 technical report, 2024.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Gpt-4 technical report, 2024

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.194947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23d8a6fa-a00a-4337-8c41-2717e31af7d3 · outbound

This paper cites An Empirical Study of the Non-determinism of ChatGPT in Code Generation.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond An Empirical Study of the Non-determinism of ChatGPT in Code Generation

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.201442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b515489-1a8d-484b-9237-153d3ac5cfce · outbound

This paper cites Toward Understanding Why Adam Converges Faster Than SGD for Transformers.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Toward Understanding Why Adam Converges Faster Than SGD for Transformers

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.207510Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec449c1e-5896-44fc-b543-d93850e9f415 · outbound

This paper cites Is Solving Graph Neural Tangent Kernel Equivalent to Training Graph Neural Network?.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Is Solving Graph Neural Tangent Kernel Equivalent to Training Graph Neural Network?

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.212872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16cf22a3-fe13-4a0f-b787-29d00310dc0d · outbound

This paper cites Feature programming for multivariate time series prediction.

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Feature programming for multivariate time series prediction

Reference 101

Resolution: unresolved; no resolver link, observed 2026-08-11T20:09:35.218633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers