Modular TTT: Rethinking Test-Time Training as Composable Modules | Paper Citation Record

Observation 54f69f5b-e578-4fee-83be-a52e6e63d074 · outbound

This paper cites On the optimization of deep networks: Implicit acceleration by overparameterization.

Modular TTT: Rethinking Test-Time Training as Composable Modules On the optimization of deep networks: Implicit acceleration by overparameterization

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:49:01.238198Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 93169a85-7ed6-4609-a3c3-5ab3e932fdc7 · outbound

This paper cites Implicit regularization in deep matrix factorization.

Modular TTT: Rethinking Test-Time Training as Composable Modules Implicit regularization in deep matrix factorization

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:49:01.228766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6730573d-111b-4c72-aa38-f8fb94991c98 · outbound

This paper cites Hinton, Volodymyr Mnih, Joel Z.

Modular TTT: Rethinking Test-Time Training as Composable Modules Hinton, Volodymyr Mnih, Joel Z

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:49:01.218663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a421cb19-3917-4b17-b943-ef5cfe975ce5 · outbound

This paper cites Neural networks and principal component analysis: Learning from examples without local minima.Neural Networks, 2(1):53–58, 1989.

Modular TTT: Rethinking Test-Time Training as Composable Modules Neural networks and principal component analysis: Learning from examples without local minima.Neural Networks, 2(1):53–58, 1989

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-10T14:49:00.048417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb89478b-d96b-4b96-9d28-e45638da37ca · outbound

This paper cites ATLAS: Learning to Optimally Memorize the Context at Test Time.

Modular TTT: Rethinking Test-Time Training as Composable Modules ATLAS: Learning to Optimally Memorize the Context at Test Time

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-10T14:49:00.055105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62d26e52-6521-4e6c-9e27-bf5cc56bb33a · outbound

This paper cites It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization.

Modular TTT: Rethinking Test-Time Training as Composable Modules It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T14:49:00.062746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13602867-972b-4bf3-92f4-6d878d6c61ce · outbound

This paper cites Nested learning: The illusion of deep learning architectures.

Modular TTT: Rethinking Test-Time Training as Composable Modules Nested learning: The illusion of deep learning architectures

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T14:49:00.069826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1764e16b-1a82-42a3-86c2-4d6318689a62 · outbound

This paper cites Titans: Learning to Memorize at Test Time.

Modular TTT: Rethinking Test-Time Training as Composable Modules Titans: Learning to Memorize at Test Time

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T14:49:00.074916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10d57bfd-0995-4120-8206-dfe1f3fcb2c7 · outbound

This paper cites PIQA: Reasoning about physical commonsense in natural language.

Modular TTT: Rethinking Test-Time Training as Composable Modules PIQA: Reasoning about physical commonsense in natural language

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:49:01.206451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 692b1449-1447-477c-ab1f-d35945424b5b · outbound

This paper cites Rethinking attention with performers.

Modular TTT: Rethinking Test-Time Training as Composable Modules Rethinking attention with performers

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:49:01.193818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 056f0b74-97af-43f8-85b9-ad3e70e37b61 · outbound

This paper cites Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling.

Modular TTT: Rethinking Test-Time Training as Composable Modules Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T14:49:00.089876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14dbc70d-d3f5-4095-a42a-624bb6414d74 · outbound

This paper cites BoolQ: Exploring the surprising difficulty of natural yes/no questions.

Modular TTT: Rethinking Test-Time Training as Composable Modules BoolQ: Exploring the surprising difficulty of natural yes/no questions

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:49:01.182506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5d89f1bd-1978-44af-9718-01aa5db2b482 · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

Modular TTT: Rethinking Test-Time Training as Composable Modules Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T14:49:00.099403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf82f20a-7750-4732-ae3f-fe88db00a825 · outbound

This paper cites Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality.

Modular TTT: Rethinking Test-Time Training as Composable Modules Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:49:01.170651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation edbad945-5edf-4362-a22a-2a340046041e · outbound

This paper cites Franke, Arber Zela, Frank Hutter, and Massimiliano Pontil.

Modular TTT: Rethinking Test-Time Training as Composable Modules Franke, Arber Zela, Frank Hutter, and Massimiliano Pontil

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:49:01.157640Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation af3fce11-cc82-4d10-94d8-f57f00b21506 · outbound

This paper cites Mamba: Linear-time sequence modeling with selective state spaces.

Modular TTT: Rethinking Test-Time Training as Composable Modules Mamba: Linear-time sequence modeling with selective state spaces

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-10T14:49:00.109640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 325b2e00-be01-426e-ba81-4761d756fa57 · outbound

This paper cites Efficiently modeling long sequences with structured state spaces.

Modular TTT: Rethinking Test-Time Training as Composable Modules Efficiently modeling long sequences with structured state spaces

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:49:01.139876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0b6c36a8-a359-48c3-bc74-34c67ab3218a · outbound

This paper cites ViT$^3$: Unlocking Test-Time Training in Vision.

Modular TTT: Rethinking Test-Time Training as Composable Modules ViT$^3$: Unlocking Test-Time Training in Vision

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-10T14:49:00.117602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f88e6d24-502c-4c2f-8d00-9a69f73e9e10 · outbound

This paper cites From one tree to a forest: A unified solution for structured web data extraction.

Modular TTT: Rethinking Test-Time Training as Composable Modules From one tree to a forest: A unified solution for structured web data extraction

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:49:01.128261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 48aa90e4-3511-4386-bcca-b59e8de36d13 · outbound

This paper cites Long short-term memory.Neural Computation, 9(8):1735–1780, 1997.

Modular TTT: Rethinking Test-Time Training as Composable Modules Long short-term memory.Neural Computation, 9(8):1735–1780, 1997

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-10T14:49:00.126571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31df3935-0d8b-4018-9201-a2927ac71ecb · outbound

This paper cites RULER: What’s the real context size of your long-context language models? InFirst Conference on Language Modeling, 2024.

Modular TTT: Rethinking Test-Time Training as Composable Modules RULER: What’s the real context size of your long-context language models? InFirst Conference on Language Modeling, 2024

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-10T14:49:00.131180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 267b3cba-d8c3-4c2e-9a94-7fcc54ec57e0 · outbound

This paper cites Going beyond linear transformers with recurrent fast weight programmers.

Modular TTT: Rethinking Test-Time Training as Composable Modules Going beyond linear transformers with recurrent fast weight programmers

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:49:01.102273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8be17c1a-6117-4749-b5dc-38ddb220af46 · outbound

This paper cites The dual form of neural networks revisited: Connecting test time predictions to training patterns via spotlights of attention.

Modular TTT: Rethinking Test-Time Training as Composable Modules The dual form of neural networks revisited: Connecting test time predictions to training patterns via spotlights of attention

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:49:01.090105Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 70f3126e-48a4-4343-9d51-8c33a100591c · outbound

This paper cites Transformers are rnns: Fast autoregressive transformers with linear attention.

Modular TTT: Rethinking Test-Time Training as Composable Modules Transformers are rnns: Fast autoregressive transformers with linear attention

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:49:01.077490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 9262bfbf-5041-416a-a017-8510e3b1894c · outbound

This paper cites Deep learning without poor local minima.

Modular TTT: Rethinking Test-Time Training as Composable Modules Deep learning without poor local minima

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:49:01.067657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a9d1755a-4481-4555-b48d-7ad3a0ba7230 · outbound

This paper cites Dynamic evaluation of neural sequence models.

Modular TTT: Rethinking Test-Time Training as Composable Modules Dynamic evaluation of neural sequence models

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:49:01.057529Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ddad8e1c-8091-46c5-a150-e1fb20462d67 · outbound

This paper cites TNT: Improving chunkwise training for test-time memorization.arXiv preprintarXiv:2511.07343, 2025.

Modular TTT: Rethinking Test-Time Training as Composable Modules TNT: Improving chunkwise training for test-time memorization.arXiv preprintarXiv:2511.07343, 2025

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-10T14:49:00.156495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25a2d7c5-6219-43c9-8a83-3c311747eb22 · outbound

This paper cites Parallelizing linear recurrent neural nets over sequence length.

Modular TTT: Rethinking Test-Time Training as Composable Modules Parallelizing linear recurrent neural nets over sequence length

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:49:01.047102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 564325e4-01c2-47db-9436-4447cc5d660f · outbound

This paper cites Pointer sentinel mixture models.

Modular TTT: Rethinking Test-Time Training as Composable Modules Pointer sentinel mixture models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-10T14:49:00.167071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c06a6d2-d897-49be-b8fe-a49d2299f766 · outbound

This paper cites Can a suit of armor conduct electricity? A new dataset for open book question answering.

Modular TTT: Rethinking Test-Time Training as Composable Modules Can a suit of armor conduct electricity? A new dataset for open book question answering

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:49:01.030328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 710b212d-b687-4bc4-b7eb-e27242249bb8 · outbound

This paper cites Smith, Albert Gu, Anushan Fernando, Caglar Gulcehre, Razvan Pascanu, and Soham De.

Modular TTT: Rethinking Test-Time Training as Composable Modules Smith, Albert Gu, Anushan Fernando, Caglar Gulcehre, Razvan Pascanu, and Soham De

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:49:01.019664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 61c8aa02-114a-473f-b586-de04378b83ad · outbound

This paper cites The LAMBADA dataset: Word prediction requiring a broad discourse context.

Modular TTT: Rethinking Test-Time Training as Composable Modules The LAMBADA dataset: Word prediction requiring a broad discourse context

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-10T14:49:00.181836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a81b0870-2a0b-437e-914c-5f34bc76fe85 · outbound

This paper cites RWKV: Reinventing RNNs for the transformer era.

Modular TTT: Rethinking Test-Time Training as Composable Modules RWKV: Reinventing RNNs for the transformer era

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:49:01.002311Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation bf0aa4df-1a98-4374-809b-f797b99fd307 · outbound

This paper cites RWKV-7 "Goose" with Expressive Dynamic State Evolution.

Modular TTT: Rethinking Test-Time Training as Composable Modules RWKV-7 "Goose" with Expressive Dynamic State Evolution

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-10T14:49:00.197808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d6133eb-7196-4208-a829-fa7ee7af2776 · outbound

This paper cites Hierarchically gated recurrent neural network for sequence modeling.

Modular TTT: Rethinking Test-Time Training as Composable Modules Hierarchically gated recurrent neural network for sequence modeling

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:49:00.991144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 73db6233-bc09-4ed0-b9a4-415b42dfa82f · outbound

This paper cites Transnormerllm: A faster and better large language model with improved transnormer, 2024.

Modular TTT: Rethinking Test-Time Training as Composable Modules Transnormerllm: A faster and better large language model with improved transnormer, 2024

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:49:00.980209Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation af4f3e44-7159-45f7-bda9-237cc26820f2 · outbound

This paper cites HGRN2: Gated linear RNNs with state expansion.

Modular TTT: Rethinking Test-Time Training as Composable Modules HGRN2: Gated linear RNNs with state expansion

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:49:00.968910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6641f328-5cf8-4b01-b226-9c12dd49536b · outbound

This paper cites SQuAD: 100,000+ questions for machine comprehension of text.

Modular TTT: Rethinking Test-Time Training as Composable Modules SQuAD: 100,000+ questions for machine comprehension of text

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-10T14:49:00.218216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce73c9e4-ded9-486f-bc43-f6884fcdca62 · outbound

This paper cites WinoGrande: An adversarial winograd schema challenge at scale.

Modular TTT: Rethinking Test-Time Training as Composable Modules WinoGrande: An adversarial winograd schema challenge at scale

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:49:00.951506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a2a7953b-474c-4a7e-b25d-cc4613367295 · outbound

This paper cites Social IQa: Commonsense reasoning about social interactions.

Modular TTT: Rethinking Test-Time Training as Composable Modules Social IQa: Commonsense reasoning about social interactions

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-10T14:49:00.225911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03f41048-f7f9-4e32-bdc6-bcfbe2f42dc7 · outbound

This paper cites Linear transformers are secretly fast weight programmers.

Modular TTT: Rethinking Test-Time Training as Composable Modules Linear transformers are secretly fast weight programmers

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:49:00.940999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4ff1a3bf-f54e-4bc5-9820-accc5eee0f4f · outbound

This paper cites Learning to control fast-weight memories: An alternative to dynamic recurrent networks.

Modular TTT: Rethinking Test-Time Training as Composable Modules Learning to control fast-weight memories: An alternative to dynamic recurrent networks

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-10T14:49:00.233898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca97b709-115f-4030-b3c5-eaef2ff1eda0 · outbound

This paper cites GLU Variants Improve Transformer.

Modular TTT: Rethinking Test-Time Training as Composable Modules GLU Variants Improve Transformer

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-10T14:49:00.237614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e45efd3c-af20-4927-b8a6-a28cf359f19b · outbound

This paper cites Learning to (Learn at Test Time): RNNs with Expressive Hidden States.

Modular TTT: Rethinking Test-Time Training as Composable Modules Learning to (Learn at Test Time): RNNs with Expressive Hidden States

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-10T14:49:00.241580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65a79c75-62d9-4320-a00a-746f23c71e44 · outbound

This paper cites Retentive Network: A Successor to Transformer for Large Language Models.

Modular TTT: Rethinking Test-Time Training as Composable Modules Retentive Network: A Successor to Transformer for Large Language Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-10T14:49:00.245361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83684bd4-51b4-48e1-a583-5cfa26f3f7f7 · outbound

This paper cites EleutherAI/lm-evaluation-harness: v0.4.9.1, August 2025.

Modular TTT: Rethinking Test-Time Training as Composable Modules EleutherAI/lm-evaluation-harness: v0.4.9.1, August 2025

Reference 46

Resolution: verified exact; raw_fallback, observed 2026-08-10T14:49:00.677903Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7bfe8203-8b45-4575-91cd-4f0d76c38224 · outbound

This paper cites End-to-end test-time training for long context.arXiv preprint arXiv:2512.23675, 2025.

Modular TTT: Rethinking Test-Time Training as Composable Modules End-to-end test-time training for long context.arXiv preprint arXiv:2512.23675, 2025

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-10T14:49:00.253011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4935ff79-8dc5-4528-9862-470ec2672f27 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Modular TTT: Rethinking Test-Time Training as Composable Modules Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-10T14:49:00.256877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21cb32cf-e408-4111-9078-85bdf6f1ad7b · outbound

This paper cites Gomez, Lukasz Kaiser, and Illia Polosukhin.

Modular TTT: Rethinking Test-Time Training as Composable Modules Gomez, Lukasz Kaiser, and Illia Polosukhin

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-10T14:49:00.260267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82b5d303-7481-4e2c-948b-ac31f11357df · outbound

This paper cites Gated linear attention transformers with hardware-efficient training.

Modular TTT: Rethinking Test-Time Training as Composable Modules Gated linear attention transformers with hardware-efficient training

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:49:00.917146Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e5ba8a6c-2dd2-47d7-945a-11c9f8f58f44 · outbound

This paper cites Parallelizing linear transformers with the delta rule over sequence length.

Modular TTT: Rethinking Test-Time Training as Composable Modules Parallelizing linear transformers with the delta rule over sequence length

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:49:00.906742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5c7bb804-b8e1-43a0-a80f-838c4746f48a · outbound

This paper cites Gated delta networks: Improving Mamba2 with delta rule.

Modular TTT: Rethinking Test-Time Training as Composable Modules Gated delta networks: Improving Mamba2 with delta rule

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:49:00.895958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 587bd39a-dcfe-43af-88c8-205b788fbda4 · outbound

This paper cites Hellaswag: Can a machine really finish your sentence? In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019.

Modular TTT: Rethinking Test-Time Training as Composable Modules Hellaswag: Can a machine really finish your sentence? In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:49:00.886720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0d2aeadd-eed9-45f1-ad33-510559b37cde · outbound

This paper cites Test-Time Training Done Right.

Modular TTT: Rethinking Test-Time Training as Composable Modules Test-Time Training Done Right

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-10T14:49:00.283551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b99afcb-f203-48c3-a0a0-886ce4aa0881 · outbound

This paper cites Flame: Flash language modeling made easy, January 2025.

Modular TTT: Rethinking Test-Time Training as Composable Modules Flame: Flash language modeling made easy, January 2025

Reference 55

Resolution: malformed identifier; raw_fallback, observed 2026-08-10T14:49:00.503888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3c6a42e3-0169-4228-9457-d9f170eb2fd6 · outbound

This paper cites doi: 10.18653/v1/2023.findings-emnlp.936.

Modular TTT: Rethinking Test-Time Training as Composable Modules doi: 10.18653/v1/2023.findings-emnlp.936

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-10T14:49:00.192739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 385df1d3-c6f8-4acd-8e90-59fb2a6a3779 · outbound

This paper cites URL https://proceedings.neurips.cc/paper_files/paper/2024/hash/ d13a3eae72366e61dfdc7eea82eeb685-Abstract-Conference.html.

Modular TTT: Rethinking Test-Time Training as Composable Modules URL https://proceedings.neurips.cc/paper_files/paper/2024/hash/ d13a3eae72366e61dfdc7eea82eeb685-Abstract-Conference.html

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-10T14:49:00.272250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers