Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation | Paper Citation Record

Observation d6a6a7f1-ddd0-4ec2-96fd-7cca7dc7448d · outbound

This paper cites Imagenet classification with deep convolutional neural networks.Advances in neural information processing systems, 25, 2012.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Imagenet classification with deep convolutional neural networks.Advances in neural information processing systems, 25, 2012

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:02.193202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c42e6a53-460b-482a-b99a-eaeabb3453c7 · outbound

This paper cites Deep residual learning for image recognition.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Deep residual learning for image recognition

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:02.236697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4a4a141-9822-41c8-a5ce-3ec55a0cb439 · outbound

This paper cites End-to-end object detection with transformers.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation End-to-end object detection with transformers

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:02.322985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 209beb9e-a7d5-44fd-a14e-50b45515fda4 · outbound

This paper cites Segment anything.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Segment anything

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:02.403109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a852621a-0a7a-454a-9541-f8c06abc8255 · outbound

This paper cites Do imagenet classifiers generalize to imagenet? InInternational Conference on Machine Learning (ICML), 2019.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Do imagenet classifiers generalize to imagenet? InInternational Conference on Machine Learning (ICML), 2019

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:02.490896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c9f19ba-4c99-4e10-86df-13477be6c13d · outbound

This paper cites Benchmarking neural network robustness to common corruptions and perturbations.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Benchmarking neural network robustness to common corruptions and perturbations

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:02.585471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f50c475-efeb-44e7-980b-d30940b785f6 · outbound

This paper cites Earnshaw, Imran S.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Earnshaw, Imran S

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:02.732631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed243729-0b4c-4f3c-b97f-58ce6bf47e15 · outbound

This paper cites Sequence level training with recurrent neural networks.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Sequence level training with recurrent neural networks

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:02.887784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bac78bac-91a9-4cdf-810f-b380c287c2aa · outbound

This paper cites Scheduled sampling for sequence prediction with recurrent neural networks.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Scheduled sampling for sequence prediction with recurrent neural networks

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:03.033091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 871d312d-d61a-413e-a262-584745b90fd2 · outbound

This paper cites an unresolved cited work.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:03.133187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45862ed8-d303-4514-bddf-cba526943ad5 · outbound

This paper cites Elucidating the Exposure Bias in Diffusion Models.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Elucidating the Exposure Bias in Diffusion Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:03.244967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 656272d7-642f-496e-b680-a34c7c2ebd46 · outbound

This paper cites Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:03.363097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48c42cc6-c5e4-4df1-866f-93a82c50eebc · outbound

This paper cites Denoising diffusion probabilistic models.Advances in neural information processing systems, 33:6840–6851, 2020.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Denoising diffusion probabilistic models.Advances in neural information processing systems, 33:6840–6851, 2020

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:03.482385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a60a6fab-67ab-47b9-9637-70bf95ae869f · outbound

This paper cites Consistency models, 2023.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Consistency models, 2023

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:03.590973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92c151cc-babd-474f-a470-080a8f16cb93 · outbound

This paper cites Mean flows for one-step generative modeling.Advances in Neural Information Processing Systems, 38:75460–75482, 2026.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Mean flows for one-step generative modeling.Advances in Neural Information Processing Systems, 38:75460–75482, 2026

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:03.705034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f288041e-935f-42ed-9f3d-939403f7e500 · outbound

This paper cites Training Compute-Optimal Large Language Models.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Training Compute-Optimal Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:03.813837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59749137-1800-4187-828c-3cb848770ff7 · outbound

This paper cites Diffusion policy: Visuomotor policy learning via action diffusion.The International Journal of Robotics Research, page 02783649241273668, 2023.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Diffusion policy: Visuomotor policy learning via action diffusion.The International Journal of Robotics Research, page 02783649241273668, 2023

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:03.894829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f63fa51e-8bd2-4013-8316-714d7b01eba9 · outbound

This paper cites Planning with Diffusion for Flexible Behavior Synthesis.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Planning with Diffusion for Flexible Behavior Synthesis

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:03.999870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b026885-9b5c-4024-9039-4b1de2b9206e · outbound

This paper cites Mode forcing: A unifying and predictive theory of genera- tive modeling.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Mode forcing: A unifying and predictive theory of genera- tive modeling

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:04.119962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab4df2e0-6f59-4965-b7db-a13c0a0317e0 · outbound

This paper cites Generative adversarial nets.Advances in neural information processing systems, 27, 2014.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Generative adversarial nets.Advances in neural information processing systems, 27, 2014

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:04.195580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bc664db-14c5-4b86-9d62-82b6a6c0fcab · outbound

This paper cites Training products of experts by minimizing contrastive divergence.Neural computa- tion, 14(8):1771–1800, 2002.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Training products of experts by minimizing contrastive divergence.Neural computa- tion, 14(8):1771–1800, 2002

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:04.288275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d336a95-0bed-48e6-8c9c-ea53dfd7bf5d · outbound

This paper cites Implicit generation and modeling with energy based models.Advances in neural information processing systems, 32, 2019.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Implicit generation and modeling with energy based models.Advances in neural information processing systems, 32, 2019

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:04.403511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ddb17f4-1aea-4c71-969f-1803ba307def · outbound

This paper cites Flow Matching for Generative Modeling.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Flow Matching for Generative Modeling

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:04.502848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 056f79f0-56e0-41d4-b4f9-324ab0b2fe92 · outbound

This paper cites A note on the evaluation of generative models.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation A note on the evaluation of generative models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:04.615640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98db6841-9e9e-45f7-94eb-4db49bb665a0 · outbound

This paper cites Classifier-Free Diffusion Guidance.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Classifier-Free Diffusion Guidance

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:04.726377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a50a89b0-1654-4f7b-93bf-d12762bc3040 · outbound

This paper cites Guiding a diffusion model with a bad version of itself.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Guiding a diffusion model with a bad version of itself

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:04.797716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fecf4ec4-b578-40a2-9d8a-4126edc89f39 · outbound

This paper cites Simple and Effective Masked Diffusion Language Models.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Simple and Effective Masked Diffusion Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:04.875834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97505943-2724-4971-991a-d4837d80e494 · outbound

This paper cites Murphy, and Tim Salimans.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Murphy, and Tim Salimans

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:04.954535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28e4784a-f022-4969-b643-f2a842975a24 · outbound

This paper cites Albergo, Nicholas M.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Albergo, Nicholas M

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:05.028534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63a360aa-43ed-4212-aa85-2c9987664f8e · outbound

This paper cites Jumpy generative models: Unleashing the hidden spectrum in generative modeling.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Jumpy generative models: Unleashing the hidden spectrum in generative modeling

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:05.106042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43525473-fc14-48e9-abdc-34b83d559b55 · outbound

This paper cites Gpt-4 technical report, 2023.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Gpt-4 technical report, 2023

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:05.180828Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1e2d7b5-9007-41e2-901c-568e36e1e006 · outbound

This paper cites High-resolution image synthesis with latent diffusion models.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation High-resolution image synthesis with latent diffusion models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:05.251243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ee63ce4-9132-4d9a-893d-6ebbd89be3d2 · outbound

This paper cites Stochastic multiple choice learning for training diverse deep ensembles.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Stochastic multiple choice learning for training diverse deep ensembles

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:05.341597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c648228e-36b2-467e-bc1d-d0d0c3155e9a · outbound

This paper cites Implicit Maximum Likelihood Estimation.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Implicit Maximum Likelihood Estimation

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:05.500579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27afe137-d983-4718-8d26-58238c57ac25 · outbound

This paper cites Diverse imitation learning via self-organizing generative models.IEEE Transactions on Neural Networks and Learning Systems, 36(4):7145–7157, 2024.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Diverse imitation learning via self-organizing generative models.IEEE Transactions on Neural Networks and Learning Systems, 36(4):7145–7157, 2024

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:05.576080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3348015c-e95a-4fc2-8db4-2dde7b8132bb · outbound

This paper cites Auto-Encoding Variational Bayes.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Auto-Encoding Variational Bayes

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:05.671457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 938fd98b-8ca5-44c2-93a3-b3fe0052fcc7 · outbound

This paper cites NV AE: A deep hierarchical variational autoencoder.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation NV AE: A deep hierarchical variational autoencoder

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:05.749253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7cf0faf-d03f-403c-bf84-3c6363b7cd9a · outbound

This paper cites Tackling the Generative Learning Trilemma with Denoising Diffusion GANs.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Tackling the Generative Learning Trilemma with Denoising Diffusion GANs

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:05.827379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02480333-c11d-4330-8b61-9bad12f6756e · outbound

This paper cites Improving and generalizing flow-based generative models with minibatch optimal transport.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Improving and generalizing flow-based generative models with minibatch optimal transport

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:05.922352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9dec99ac-33c9-4bd6-bdf5-5b9f5755eb7c · outbound

This paper cites Learning with minibatch Wasserstein: asymptotic and gradient properties.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Learning with minibatch Wasserstein: asymptotic and gradient properties

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:06.030448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6512728f-ad0b-4c62-bac3-15aa79e97626 · outbound

This paper cites The bitter lesson.Incomplete Ideas (blog), 13(1):38, 2019.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation The bitter lesson.Incomplete Ideas (blog), 13(1):38, 2019

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:06.137753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff5cb82f-7496-4f36-a148-425e766e1ee9 · outbound

This paper cites Deep unsupervised learning using nonequilibrium thermodynamics.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Deep unsupervised learning using nonequilibrium thermodynamics

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:06.254003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95fdf436-7b12-4c18-b026-94c9d6033fee · outbound

This paper cites Representation Fr\'echet Loss for Visual Generation.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Representation Fr\'echet Loss for Visual Generation

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:06.375333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44be4544-1aef-4a81-a48e-b79e111ff4f6 · outbound

This paper cites Improved Baselines with Representation Autoencoders.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Improved Baselines with Representation Autoencoders

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:06.501303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c981edfa-b637-4f04-888f-c15eda786170 · outbound

This paper cites Diffusion Transformers with Representation Autoencoders.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Diffusion Transformers with Representation Autoencoders

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:06.611843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b47c3290-5575-436a-ba1e-a7f2251738e0 · outbound

This paper cites Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Sampling.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Sampling

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:06.695356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b5c18fe-151b-434e-8ba0-cb426d178d57 · outbound

This paper cites Generative Frontiers: Why Evaluation Matters for Diffusion Language Models.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Generative Frontiers: Why Evaluation Matters for Diffusion Language Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:06.719845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8760b9d3-a16a-4546-9c15-874efeb6938b · outbound

This paper cites Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:06.786957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e43cacd8-259f-40f0-ad5b-4fabd1a32690 · outbound

This paper cites something something.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation something something

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:06.942897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79782013-9f20-46c6-8303-b0b40128b22f · outbound

This paper cites Diffusion beats autoregressive in data-constrained settings.Advances in Neural Information Processing Systems, 38:10581–10606, 2026.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Diffusion beats autoregressive in data-constrained settings.Advances in Neural Information Processing Systems, 38:10581–10606, 2026

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:07.087782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dad8b34d-87de-4a2e-a435-c31a3732d5f9 · outbound

This paper cites Deep double descent: Where bigger models and more data hurt.Journal of Statistical Mechanics: Theory and Experiment, 2021(12):124003, 2021.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Deep double descent: Where bigger models and more data hurt.Journal of Statistical Mechanics: Theory and Experiment, 2021(12):124003, 2021

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:07.164424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ee2a5e1-1984-4a6e-b34a-9f492ee146e2 · outbound

This paper cites Deep Learning is Not So Mysterious or Different.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Deep Learning is Not So Mysterious or Different

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:07.252186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3b248c5-9a30-46a3-b87e-05e27a5e6fe9 · outbound

This paper cites Slowrun: Language modeling with infinite compute, fixed data, 2026.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Slowrun: Language modeling with infinite compute, fixed data, 2026

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:07.311294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cffc3888-ece0-4a0e-a482-50a8eeb44672 · outbound

This paper cites Pre-training under infinite compute.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Pre-training under infinite compute

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:07.425835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dc97cd9-72cf-4963-9c20-d542b4903cac · outbound

This paper cites sd-vae-ft-mse, 2023.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation sd-vae-ft-mse, 2023

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:07.486830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17ed9dba-a2fd-4df0-a313-b9478ce0f835 · outbound

This paper cites Scalable diffusion models with transformers, 2023.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Scalable diffusion models with transformers, 2023

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:07.558635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e5ef910-2136-4c76-b44c-ef221bac426b · outbound

This paper cites Fast training of diffusion models with masked transformers, 2023.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Fast training of diffusion models with masked transformers, 2023

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:07.616961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40f64df5-1871-45ba-95ae-15ffe27885a1 · outbound

This paper cites Mdtv2: Masked diffusion transformer is a strong image synthesizer, 2023.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Mdtv2: Masked diffusion transformer is a strong image synthesizer, 2023

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:07.691086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5e26cde-d7d4-4e57-b848-aad23b684804 · outbound

This paper cites Reconstruction vs.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Reconstruction vs

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:07.759675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 401a55df-dfc9-4711-bc1c-fbd406070f0f · outbound

This paper cites Representation alignment for generation: Training diffusion transformers is easier than you think,.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Representation alignment for generation: Training diffusion transformers is easier than you think,

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:07.843944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7427359-ecae-4bf6-99d6-a646461d3523 · outbound

This paper cites Ddt: Decoupled diffusion transformer, 2025.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Ddt: Decoupled diffusion transformer, 2025

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:07.935698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 626cea65-1f64-44c9-90d1-693247fb1fee · outbound

This paper cites Repa-e: Unlocking vae for end-to-end tuning with latent diffusion transformers, 2025.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Repa-e: Unlocking vae for end-to-end tuning with latent diffusion transformers, 2025

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:08.057279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5652622-9374-4d94-9003-d7d9ee702aa5 · outbound

This paper cites Dinov2: Learning robust visual features without supervision, 2023.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Dinov2: Learning robust visual features without supervision, 2023

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:08.151041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c53297d-a12e-443d-9cba-5e58da8f55f4 · outbound

This paper cites D4RL: Datasets for Deep Data-Driven Reinforcement Learning.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation D4RL: Datasets for Deep Data-Driven Reinforcement Learning

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:08.231552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc5dff03-7473-48ca-a698-8b513b172116 · outbound

This paper cites Scaling up test-time compute with latent reasoning: A recurrent depth approach.Advances in Neural Information Processing Systems, 38:41340–41391, 2026.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Scaling up test-time compute with latent reasoning: A recurrent depth approach.Advances in Neural Information Processing Systems, 38:41340–41391, 2026

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:08.352459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7c881cb-edb4-46b4-ab36-f4c2b7922b19 · outbound

This paper cites Visualizing the loss landscape of neural nets.Advances in neural information processing systems, 31, 2018.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Visualizing the loss landscape of neural nets.Advances in neural information processing systems, 31, 2018

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:08.435300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b641e22-5a56-44b2-bdfb-245361d310a9 · outbound

This paper cites Better & faster large language models via multi-token prediction, 2024.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Better & faster large language models via multi-token prediction, 2024

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:08.491914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22f08360-23c1-412f-bb76-1a6dfd60b2de · outbound

This paper cites The free transformer, 2025.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation The free transformer, 2025

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:08.577688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 450f36dc-7179-4144-a485-09f06cb68896 · outbound

This paper cites Energy-Based Transformers are Scalable Learners and Thinkers.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Energy-Based Transformers are Scalable Learners and Thinkers

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:08.641850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c90a561-f38a-4c5f-b04f-a77a6fe52321 · outbound

This paper cites Self-supervised learning from images with a joint-embedding predictive architecture, 2023.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Self-supervised learning from images with a joint-embedding predictive architecture, 2023

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:08.703046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d75beefd-9e2d-4b9f-a765-38c2d4d3b6ec · outbound

This paper cites A path towards autonomous machine intelligence version 0.9.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation A path towards autonomous machine intelligence version 0.9

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:08.794388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c4ec1fd-cc49-4f8a-808f-da4a6df731c5 · outbound

This paper cites an unresolved cited work.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Unresolved cited work

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:08.874643Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc6647c5-0f56-417d-b2f6-b6f755e8a4b9 · outbound

This paper cites Learning iterative reasoning through energy minimization.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Learning iterative reasoning through energy minimization

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:09.019459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a807b3e-0789-4952-9386-80f0493c7cdb · outbound

This paper cites Distribution Matching in Variational Inference.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Distribution Matching in Variational Inference

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:09.098125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33482f5f-4d4c-4d4e-be1f-de56de4ac9ed · outbound

This paper cites Unified latents (ul): How to train your latents.arXiv preprint arXiv:2602.17270, 2026.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Unified latents (ul): How to train your latents.arXiv preprint arXiv:2602.17270, 2026

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:09.181252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9eecf3c-a226-48e6-830f-aabd0999d6db · outbound

This paper cites KL-regularized reinforcement learning is designed to mode collapse.arXiv preprint arXiv:2510.20817, 2025.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation KL-regularized reinforcement learning is designed to mode collapse.arXiv preprint arXiv:2510.20817, 2025

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:09.236796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3e1b247-a286-4779-8f1e-f44820c54e7c · outbound

This paper cites Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:09.320896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6952a280-a2fc-40fd-8a28-d37681c5f779 · outbound

This paper cites Inference-aware fine-tuning for best-of-n sampling in large language models.arXiv preprint arXiv:2412.15287, 2024.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Inference-aware fine-tuning for best-of-n sampling in large language models.arXiv preprint arXiv:2412.15287, 2024

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:09.384405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87c1daa1-e2a1-4dd2-8668-cced382834ab · outbound

This paper cites Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:09.464477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 066bd68e-88e9-4b5b-98f8-7b0183d3f226 · outbound

This paper cites Generalization in diffusion models arises from geometry-adaptive harmonic representations.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Generalization in diffusion models arises from geometry-adaptive harmonic representations

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:09.550212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14e0c764-3d15-4a43-89ee-fc2e38bca704 · outbound

This paper cites On Memorization in Diffusion Models.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation On Memorization in Diffusion Models

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:09.604919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0519950-19f0-49cb-a875-1b674c41079a · outbound

This paper cites Multisample Flow Matching: Straightening Flows with Minibatch Couplings.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Multisample Flow Matching: Straightening Flows with Minibatch Couplings

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:09.659189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9709a42-97de-4310-8440-6015daa5d804 · outbound

This paper cites Imagenet large scale visual recognition challenge.International journal of computer vision, 115:211–252, 2015.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Imagenet large scale visual recognition challenge.International journal of computer vision, 115:211–252, 2015

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:09.744659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55f47114-4246-4568-bcc0-385017bc6011 · outbound

This paper cites Transformer flops.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Transformer flops

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:09.798025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a2704be-9987-4841-ac93-160b7e4130d6 · outbound

This paper cites Learning from reward-free offline data: A case for planning with latent dynamics models.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Learning from reward-free offline data: A case for planning with latent dynamics models

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:09.886453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf8122ea-001f-41e2-b139-9d0221d8eeab · outbound

This paper cites Back to basics: Let denoising generative models denoise.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Back to basics: Let denoising generative models denoise

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:09.970200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 707e5643-8d0f-479e-9d43-6e613b00212a · outbound

This paper cites Elucidating the design space of diffusion-based generative models.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Elucidating the design space of diffusion-based generative models

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:10.060011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5daee6d-c7d4-42e4-bec8-96035f78f960 · outbound

This paper cites V-jepa 2: Self-supervised video models enable understanding, prediction and planning, 2025.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation V-jepa 2: Self-supervised video models enable understanding, prediction and planning, 2025

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:10.160611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9774176a-5e4d-4cc6-b821-584e6601a3e6 · outbound

This paper cites What matters in learning from offline human demonstrations for robot manipulation.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation What matters in learning from offline human demonstrations for robot manipulation

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:10.256841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 328c7fd8-aae9-4ba8-a3ec-a86fdcb2c954 · outbound

This paper cites Qwen2.5 Technical Report.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Qwen2.5 Technical Report

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:10.347628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c71cfb82-eccd-4edc-b428-33f046716863 · outbound

This paper cites Language models are unsupervised multitask learners.OpenAI blog, 1(8):9, 2019.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Language models are unsupervised multitask learners.OpenAI blog, 1(8):9, 2019

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:10.441176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34dbf4aa-1c46-4642-8c37-f4cfaa697a58 · outbound

This paper cites Diffusion models beat gans on image synthesis.Advances in neural information processing systems, 34:8780–8794, 2021.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Diffusion models beat gans on image synthesis.Advances in neural information processing systems, 34:8780–8794, 2021

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:10.556144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fde36bd1-fa4e-4257-8ebb-b66457ed94e2 · outbound

This paper cites Density estimation using real nvp.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Density estimation using real nvp

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:10.672015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37ab5b52-9979-4202-9da5-c9fb481e2bee · outbound

This paper cites Relaxing bijectivity constraints with continuously indexed normalising flows.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Relaxing bijectivity constraints with continuously indexed normalising flows

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:10.785454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffb0fc24-254a-4c70-9a08-ee8ac643e46b · outbound

This paper cites Normalizing flows are capable generative models.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Normalizing flows are capable generative models

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:10.897312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38f5d9af-4037-4f49-8cf2-b1c8b6f97589 · outbound

This paper cites Starflow-v: End-to-end video generative modeling with normalizing flows.arXiv preprint arXiv:2511.20462, 2025.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Starflow-v: End-to-end video generative modeling with normalizing flows.arXiv preprint arXiv:2511.20462, 2025

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:11.013527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6845c312-c272-45b3-9b9e-7cd93a752156 · outbound

This paper cites Minibatch optimal transport distances; analysis and applications.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Minibatch optimal transport distances; analysis and applications

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:11.129938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 890c4287-2f71-4dba-a972-401de4b86830 · outbound

This paper cites Faster inference of flow-based generative models via improved data-noise coupling.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Faster inference of flow-based generative models via improved data-noise coupling

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:11.284469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ded3803e-0e14-4fd6-b1ac-bf1c3f7acc34 · outbound

This paper cites Beyond optimal transport: Model-aligned coupling for flow matching.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Beyond optimal transport: Model-aligned coupling for flow matching

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:11.348169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f93b5490-69f8-4ef3-9187-6375cfd3c579 · outbound

This paper cites Multiple choice learning: Learning to produce multiple structured outputs.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Multiple choice learning: Learning to produce multiple structured outputs

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-01T08:41:11.486329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers