A Composite Activation Function for Learning Stable Binary Representations | Paper Citation Record

Observation 920fd037-be4f-47af-aa17-c5bf3412561f · outbound

This paper cites kaggle.

A Composite Activation Function for Learning Stable Binary Representations kaggle

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.770176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation dd872592-e52b-4fe2-a2cb-70c435d43af3 · outbound

This paper cites FICO Explainable Learning Challenge.

A Composite Activation Function for Learning Stable Binary Representations FICO Explainable Learning Challenge

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.699877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 05d75af4-b7c8-461c-80ac-2fd8bb723991 · outbound

This paper cites Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation.

A Composite Activation Function for Learning Stable Binary Representations Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-13T02:07:07.894885Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 70a33501-e09a-4f02-9753-b4686100c076 · outbound

This paper cites Efficient activation function optimization through surrogate modeling.Advances in Neural Information Processing Systems, 36:6634–6661.

A Composite Activation Function for Learning Stable Binary Representations Efficient activation function optimization through surrogate modeling.Advances in Neural Information Processing Systems, 36:6634–6661

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.691443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation af16e840-a523-43a7-bc85-884614282217 · outbound

This paper cites Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901.

A Composite Activation Function for Learning Stable Binary Representations Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.695894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 294142f4-d4d7-4c5d-9acb-8406bad0791a · outbound

This paper cites Spiking deep convolutional neural networks for energy-efficient object recognition.International Journal of Computer Vision, 113(1):54–66.

A Composite Activation Function for Learning Stable Binary Representations Spiking deep convolutional neural networks for energy-efficient object recognition.International Journal of Computer Vision, 113(1):54–66

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.681364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3b1a5df7-43fc-4e5d-84d8-2a8d02571025 · outbound

This paper cites Hashnet: Deep learning to hash by continuation.

A Composite Activation Function for Learning Stable Binary Representations Hashnet: Deep learning to hash by continuation

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.718505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1cc46c00-e4e8-4f46-b66a-3f3b0fc9c564 · outbound

This paper cites Training for stable explanation for free.Advances in Neural Information Processing Systems, 37:3421–3457.

A Composite Activation Function for Learning Stable Binary Representations Training for stable explanation for free.Advances in Neural Information Processing Systems, 37:3421–3457

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.676901Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation feccdc70-1488-4aaf-ae82-a0e113797821 · outbound

This paper cites Neural characteristic activation analysis and geometric parameteri- zation for relu networks.Advances in Neural Information Processing Systems, 37:97562–97586.

A Composite Activation Function for Learning Stable Binary Representations Neural characteristic activation analysis and geometric parameteri- zation for relu networks.Advances in Neural Information Processing Systems, 37:97562–97586

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.570674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 127cf276-a6f2-4aa9-ba73-4169a54591ef · outbound

This paper cites Cerdeira, F.

A Composite Activation Function for Learning Stable Binary Representations Cerdeira, F

Reference 10

Resolution: verified exact; doi, observed 2026-05-13T02:07:07.283530Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 88780506-129a-42ec-847c-21206f3e2120 · outbound

This paper cites Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1.

A Composite Activation Function for Learning Stable Binary Representations Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-13T02:07:07.875986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c4e7e324-822e-4dd3-a101-ebaf1d469e66 · outbound

This paper cites Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing.

A Composite Activation Function for Learning Stable Binary Representations Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.579613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e40a1f05-1a46-4684-90dc-968bb1d1cd04 · outbound

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

A Composite Activation Function for Learning Stable Binary Representations An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-13T02:07:07.988104Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 39068377-a22e-4d05-b16b-c135627799bd · outbound

This paper cites Globally Optimal Training of Neural Networks with Threshold Activation Functions.

A Composite Activation Function for Learning Stable Binary Representations Globally Optimal Training of Neural Networks with Threshold Activation Functions

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-13T02:07:07.939635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation fd6264d6-3a38-42cb-b340-a6018e85a20d · outbound

This paper cites Spikingjelly: An open-source machine learning infrastructure platform for spike-based intelligence.Science Advances, 9(40):eadi1480.

A Composite Activation Function for Learning Stable Binary Representations Spikingjelly: An open-source machine learning infrastructure platform for spike-based intelligence.Science Advances, 9(40):eadi1480

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.639146Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation eb7ccfed-9ae4-4053-95b2-d4839d794248 · outbound

This paper cites Deep residual learning in spiking neural networks.Advances in neural information processing systems, 34:21056–21069.

A Composite Activation Function for Learning Stable Binary Representations Deep residual learning in spiking neural networks.Advances in neural information processing systems, 34:21056–21069

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.566074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 754ec247-3bcd-4f65-bdcf-de945123fba2 · outbound

This paper cites Craft: Concept recursive activation factorization for ex- plainability.

A Composite Activation Function for Learning Stable Binary Representations Craft: Concept recursive activation factorization for ex- plainability

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.602039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f0e3bf70-3ad1-470b-b0b8-d6df10aaaf34 · outbound

This paper cites Towards automatic concept- based explanations.Advances in neural information processing systems, 32.

A Composite Activation Function for Learning Stable Binary Representations Towards automatic concept- based explanations.Advances in neural information processing systems, 32

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.820969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c8587054-2966-4223-b9ab-67ec4ddfcf3c · outbound

This paper cites Understanding the difficulty of training deep feedfor- ward neural networks.

A Composite Activation Function for Learning Stable Binary Representations Understanding the difficulty of training deep feedfor- ward neural networks

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.783414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a4351cab-21d5-45f2-94ae-b01969b27eda · outbound

This paper cites Deep sparse rectifier neural networks.

A Composite Activation Function for Learning Stable Binary Representations Deep sparse rectifier neural networks

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.787336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 92fd2883-5775-431f-8efc-4aa37edace9a · outbound

This paper cites On the impact of the activation function on deep neural networks training.

A Composite Activation Function for Learning Stable Binary Representations On the impact of the activation function on deep neural networks training

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.791642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7f30b2cf-4ba7-4ae7-a834-4898438f89da · outbound

This paper cites Deep residual learning for image recognition.

A Composite Activation Function for Learning Stable Binary Representations Deep residual learning for image recognition

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.774800Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 88bec5a6-36b2-46b0-a1b7-25eedd3f3862 · outbound

This paper cites AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty.

A Composite Activation Function for Learning Stable Binary Representations AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty

Reference 23

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T02:07:08.017690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f3c7e6e3-1c91-451e-b9de-03923da49cd2 · outbound

This paper cites Lora: Low-rank adaptation of large language models.Iclr, 1(2):3.

A Composite Activation Function for Learning Stable Binary Representations Lora: Low-rank adaptation of large language models.Iclr, 1(2):3

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.795022Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 198e1cda-1994-40b0-8805-c112939a89ed · outbound

This paper cites BiLLM: Pushing the Limit of Post-Training Quantization for LLMs.

A Composite Activation Function for Learning Stable Binary Representations BiLLM: Pushing the Limit of Post-Training Quantization for LLMs

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-13T02:07:07.889038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1edf4ccb-3bc7-438e-ae37-e1f102e97950 · outbound

This paper cites Quan- tized neural networks: Training neural networks with low precision weights and activations.

A Composite Activation Function for Learning Stable Binary Representations Quan- tized neural networks: Training neural networks with low precision weights and activations

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.779435Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7549d417-461b-4727-824c-48ed91382ad4 · outbound

This paper cites On the universal representation property of spiking neural networks.

A Composite Activation Function for Learning Stable Binary Representations On the universal representation property of spiking neural networks

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-13T02:07:07.907720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4ea037db-f837-49ee-a3a0-9fa2ac9defe8 · outbound

This paper cites On the approximation of the step function by some sigmoid functions.Mathematics and Computers in Simulation, 133:223–234.

A Composite Activation Function for Learning Stable Binary Representations On the approximation of the step function by some sigmoid functions.Mathematics and Computers in Simulation, 133:223–234

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.807279Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d68b8590-7fc7-46c4-ad74-c55a0e6f9716 · outbound

This paper cites Deep nonparametric regression on approximate manifolds: Nonasymptotic error bounds with polynomial prefactors.The Annals of Statistics, 51(2):691–716.

A Composite Activation Function for Learning Stable Binary Representations Deep nonparametric regression on approximate manifolds: Nonasymptotic error bounds with polynomial prefactors.The Annals of Statistics, 51(2):691–716

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.742182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3da3ff81-8577-476f-85d6-c7afaa6ffb51 · outbound

This paper cites Enhancing concept localization in clip-based concept bottleneck models.arXiv preprint arXiv:2510.07115.

A Composite Activation Function for Learning Stable Binary Representations Enhancing concept localization in clip-based concept bottleneck models.arXiv preprint arXiv:2510.07115

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-13T02:07:07.964785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 580a73db-b991-4ff8-a072-81e3c4ab5969 · outbound

This paper cites Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav).

A Composite Activation Function for Learning Stable Binary Representations Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav)

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.588624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 34a9338c-03ac-4182-9807-fba9d9f83ca6 · outbound

This paper cites Concept bottleneck models.

A Composite Activation Function for Learning Stable Binary Representations Concept bottleneck models

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.561855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation bad49bdd-26d8-43b5-ab16-b683599ea67c · outbound

This paper cites On the rate of convergence of fully connected deep neural network regression estimates.The Annals of Statistics, 49(4):2231 – 2249.

A Composite Activation Function for Learning Stable Binary Representations On the rate of convergence of fully connected deep neural network regression estimates.The Annals of Statistics, 49(4):2231 – 2249

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.733306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1c2d7f87-7ae9-4c69-87d0-40ad5d896a79 · outbound

This paper cites On the expressivity of deep Heaviside networks.

A Composite Activation Function for Learning Stable Binary Representations On the expressivity of deep Heaviside networks

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-08-11T01:24:25.830181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 48cf3d6b-e6a8-4c52-98b2-f195f6faf9f4 · outbound

This paper cites Posterior concentrations of fully-connected bayesian neural networks with general priors on the weights.Journal of Machine Learning Research, 26(94):1– 60.

A Composite Activation Function for Learning Stable Binary Representations Posterior concentrations of fully-connected bayesian neural networks with general priors on the weights.Journal of Machine Learning Research, 26(94):1– 60

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.652645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6e70f95a-cfdf-426c-8195-126bfa32e875 · outbound

This paper cites Learning multiple layers of features from tiny images.

A Composite Activation Function for Learning Stable Binary Representations Learning multiple layers of features from tiny images

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.728501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0cc01f46-caea-4ebc-9b8e-3e43989adc1d · outbound

This paper cites Interpretable generative models through post-hoc concept bottlenecks.

A Composite Activation Function for Learning Stable Binary Representations Interpretable generative models through post-hoc concept bottlenecks

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.825290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e2e69532-e173-406e-9e10-d41d675c63a2 · outbound

This paper cites Self-Binarizing Networks.

A Composite Activation Function for Learning Stable Binary Representations Self-Binarizing Networks

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-13T02:07:07.971253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f70b766f-006a-4867-80cf-5e8f7c8f0348 · outbound

This paper cites Tiny imagenet visual recognition challenge.CS 231N, 7(7):3.

A Composite Activation Function for Learning Stable Binary Representations Tiny imagenet visual recognition challenge.CS 231N, 7(7):3

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.756725Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d7b4fb6b-d4e1-4487-85d0-b8670993626f · outbound

This paper cites Seeking interpretability and explainability in binary activated neural networks.

A Composite Activation Function for Learning Stable Binary Representations Seeking interpretability and explainability in binary activated neural networks

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.812084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4e45ce3d-d395-423c-89cd-5fd765de4722 · outbound

This paper cites Differ- entiable spike: Rethinking gradient-descent for training spiking neural networks.Advances in neural information processing systems, 34:23426–23439.

A Composite Activation Function for Learning Stable Binary Representations Differ- entiable spike: Rethinking gradient-descent for training spiking neural networks.Advances in neural information processing systems, 34:23426–23439

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.708847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 08021222-0a29-4cdc-86aa-0a64b4868ba2 · outbound

This paper cites Bi-real net: Enhancing the performance of 1-bit cnns with improved representational capability and advanced training algorithm.

A Composite Activation Function for Learning Stable Binary Representations Bi-real net: Enhancing the performance of 1-bit cnns with improved representational capability and advanced training algorithm

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.685837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 122642f9-b15b-424e-96cc-594cf5a18640 · outbound

This paper cites Deep network approximation for smooth functions.SIAM Journal on Mathematical Analysis, 53(5):5465–5506.

A Composite Activation Function for Learning Stable Binary Representations Deep network approximation for smooth functions.SIAM Journal on Mathematical Analysis, 53(5):5465–5506

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.704190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6e03f6e3-717a-445a-902d-722081bb3e85 · outbound

This paper cites The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits.

A Composite Activation Function for Learning Stable Binary Representations The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-05-17T20:11:43.638959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 733df3cc-c9fc-49b1-a5b8-872f38fedec2 · outbound

This paper cites Networks of spiking neurons: the third generation of neural network models.

A Composite Activation Function for Learning Stable Binary Representations Networks of spiking neurons: the third generation of neural network models

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.575257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c1117672-1de4-4a9d-b94b-03526818e6c6 · outbound

This paper cites Torchvision: Pytorch’s computer vision library.

A Composite Activation Function for Learning Stable Binary Representations Torchvision: Pytorch’s computer vision library

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.761002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e3274d6e-05b9-4a2c-b7fd-45aaafc4687b · outbound

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

A Composite Activation Function for Learning Stable Binary Representations Can a suit of armor conduct electricity? a new dataset for open book question answering

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.722922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b4bc9f80-1e6d-4709-8abf-ceb9371b23f5 · outbound

This paper cites Surrogate gradient learning in spiking neural networks.IEEE Signal Processing Magazine, 36(6):51–63.

A Composite Activation Function for Learning Stable Binary Representations Surrogate gradient learning in spiking neural networks.IEEE Signal Processing Magazine, 36(6):51–63

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.714038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1456e553-30ef-4c6e-bd92-79e2739dd88e · outbound

This paper cites Smooth function approximation by deep neural networks with general activation functions.Entropy, 21(7):627.

A Composite Activation Function for Learning Stable Binary Representations Smooth function approximation by deep neural networks with general activation functions.Entropy, 21(7):627

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.634330Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 96246e06-4808-443c-9768-52d70089e6ef · outbound

This paper cites Label-Free Concept Bottleneck Models.

A Composite Activation Function for Learning Stable Binary Representations Label-Free Concept Bottleneck Models

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-13T02:07:07.927970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation dcb915c6-af1b-4222-a029-ba4edcc3dd72 · outbound

This paper cites Optimal approximation of piecewise smooth functions using deep ReLU neural networks.Neural Networks, 108:296–330.

A Composite Activation Function for Learning Stable Binary Representations Optimal approximation of piecewise smooth functions using deep ReLU neural networks.Neural Networks, 108:296–330

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.620871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3ac6f198-fd9b-404e-8ea2-285bd13656a4 · outbound

This paper cites Binary neural networks: A survey.Pattern Recognition, 105:107281.

A Composite Activation Function for Learning Stable Binary Representations Binary neural networks: A survey.Pattern Recognition, 105:107281

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.658798Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c454fc5b-04ea-45b8-9b8d-51743f6730fb · outbound

This paper cites Qwen3.5: Towards native multimodal agents, February 2026.

A Composite Activation Function for Learning Stable Binary Representations Qwen3.5: Towards native multimodal agents, February 2026

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.766093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3c7566cf-b74d-4ecc-b0f6-8fe3fdcf0d0a · outbound

This paper cites Learning transferable visual models from natural language supervision.

A Composite Activation Function for Learning Stable Binary Representations Learning transferable visual models from natural language supervision

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.751949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b8233e75-fbf3-4ee4-b2d8-008cd2548625 · outbound

This paper cites Xnor-net: Imagenet classification using binary convolutional neural networks.

A Composite Activation Function for Learning Stable Binary Representations Xnor-net: Imagenet classification using binary convolutional neural networks

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.816447Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8c8c5733-290b-4cf3-b834-1c0f126e30c0 · outbound

This paper cites The perceptron: a probabilistic model for information storage and organization in the brain.Psychological review, 65(6):386.

A Composite Activation Function for Learning Stable Binary Representations The perceptron: a probabilistic model for information storage and organization in the brain.Psychological review, 65(6):386

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.737902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f953e760-a396-487f-b4a8-42b4472e34fb · outbound

This paper cites Conversion of continuous-valued deep networks to efficient event-driven networks for image classification.Frontiers in neuroscience, 11:682.

A Composite Activation Function for Learning Stable Binary Representations Conversion of continuous-valued deep networks to efficient event-driven networks for image classification.Frontiers in neuroscience, 11:682

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.664543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2c73ecd5-7368-4750-bcf8-1659d33dcf63 · outbound

This paper cites Learning representations by back-propagating errors.nature, 323(6088):533–536.

A Composite Activation Function for Learning Stable Binary Representations Learning representations by back-propagating errors.nature, 323(6088):533–536

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.798973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c940d5fd-e200-4d30-8a34-c66ab9b991c1 · outbound

This paper cites Winogrande: An adversarial winograd schema challenge at scale.Communications of the ACM, 64(9):99–106.

A Composite Activation Function for Learning Stable Binary Representations Winogrande: An adversarial winograd schema challenge at scale.Communications of the ACM, 64(9):99–106

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.625852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4b20b56c-8174-46a5-98e9-f511c38c33f1 · outbound

This paper cites Deep ReLU network approximation of functions on a manifold.

A Composite Activation Function for Learning Stable Binary Representations Deep ReLU network approximation of functions on a manifold

Reference 60

Resolution: verified exact; arxiv_id, observed 2026-05-13T02:07:08.000306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 97a59e67-3e05-4131-942f-949bebcf89b9 · outbound

This paper cites Nonparametric regression using deep neural networks with ReLU activation function.The Annals of Statistics, 48(4):1875 – 1897.

A Composite Activation Function for Learning Stable Binary Representations Nonparametric regression using deep neural networks with ReLU activation function.The Annals of Statistics, 48(4):1875 – 1897

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.593068Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8283b32e-af10-45de-9822-5403f9241471 · outbound

This paper cites Going deeper in spiking neural networks: Vgg and residual architectures.Frontiers in neuroscience, 13:95.

A Composite Activation Function for Learning Stable Binary Representations Going deeper in spiking neural networks: Vgg and residual architectures.Frontiers in neuroscience, 13:95

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.802917Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ebe3a1f6-db0f-423d-9a77-8c62780caed3 · outbound

This paper cites GLU Variants Improve Transformer.

A Composite Activation Function for Learning Stable Binary Representations GLU Variants Improve Transformer

Reference 63

Resolution: verified exact; local_arxiv, observed 2026-05-13T02:07:08.022000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7c35b50a-c6da-47ce-8e94-002943a02c22 · outbound

This paper cites OpenAI GPT-5 System Card.

A Composite Activation Function for Learning Stable Binary Representations OpenAI GPT-5 System Card

Reference 64

Resolution: verified exact; local_arxiv, observed 2026-05-13T02:07:07.976497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8f971808-a027-43eb-bd43-e8db25f8fa99 · outbound

This paper cites Low curvature activations reduce overfitting in adversarial training.

A Composite Activation Function for Learning Stable Binary Representations Low curvature activations reduce overfitting in adversarial training

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.606524Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation efd38078-e91d-4d3e-ab3d-f41b621c48f4 · outbound

This paper cites Deep learning in spiking neural networks.Neural networks, 111:47–63.

A Composite Activation Function for Learning Stable Binary Representations Deep learning in spiking neural networks.Neural networks, 111:47–63

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.671704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cc080a8a-9723-4f21-afa4-728d508206cf · outbound

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

A Composite Activation Function for Learning Stable Binary Representations Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 67

Resolution: verified exact; local_arxiv, observed 2026-05-13T02:07:07.945698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9f21a6ae-3c61-4565-be54-5b246532b214 · outbound

This paper cites Stochastic concept bottleneck models.Advances in Neural Information Processing Systems, 37:51787–51810.

A Composite Activation Function for Learning Stable Binary Representations Stochastic concept bottleneck models.Advances in Neural Information Processing Systems, 37:51787–51810

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.597675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3c236e00-a969-485c-8dd4-8b5cb97d02af · outbound

This paper cites an unresolved cited work.

A Composite Activation Function for Learning Stable Binary Representations Unresolved cited work

Reference 69

Resolution: unresolved; raw_fallback, observed 2026-05-13T13:52:51.616490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e706d0d4-37fd-4cc7-a7a2-e61f43a52145 · outbound

This paper cites BitNet: Scaling 1-bit Transformers for Large Language Models.

A Composite Activation Function for Learning Stable Binary Representations BitNet: Scaling 1-bit Transformers for Large Language Models

Reference 70

Resolution: verified exact; arxiv_id, observed 2026-05-13T02:07:07.901449Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c7256990-480f-46e4-a193-d94bf6241877 · outbound

This paper cites Exponential Convergence of the Deep Neural Network Approximation for Analytic Functions.

A Composite Activation Function for Learning Stable Binary Representations Exponential Convergence of the Deep Neural Network Approximation for Analytic Functions

Reference 71

Resolution: verified exact; arxiv_id, observed 2026-07-04T22:52:49.458199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7c89109b-cd45-49d3-b3e0-152f4e9a567e · outbound

This paper cites Warwick Nash, Tracy Sellers, Simon Talbot, Andrew Cawthorn, and Wes Ford.

A Composite Activation Function for Learning Stable Binary Representations Warwick Nash, Tracy Sellers, Simon Talbot, Andrew Cawthorn, and Wes Ford

Reference 72

Resolution: verified exact; doi, observed 2026-05-13T02:07:07.279976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7f3ce70c-22cc-4bc5-84e0-6d76e9e13bfc · outbound

This paper cites Adjustable Bounded Rectifiers: Towards Deep Binary Representations.

A Composite Activation Function for Learning Stable Binary Representations Adjustable Bounded Rectifiers: Towards Deep Binary Representations

Reference 73

Resolution: verified exact; arxiv_id, observed 2026-07-04T20:41:08.077766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5f7d27c0-5fc7-4d29-9214-aba618109788 · outbound

This paper cites Smooth Adversarial Training.

A Composite Activation Function for Learning Stable Binary Representations Smooth Adversarial Training

Reference 74

Resolution: verified exact; arxiv_id, observed 2026-05-13T02:07:07.882428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cce9c5aa-dc19-4364-a6a8-000457ab6b68 · outbound

This paper cites Optimal rates of approximation by shallow ReLUk neural networks and applications to nonparametric regression.Constructive Approximation, pages 1–32.

A Composite Activation Function for Learning Stable Binary Representations Optimal rates of approximation by shallow ReLUk neural networks and applications to nonparametric regression.Constructive Approximation, pages 1–32

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.643639Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 705487da-dc30-4aa9-ab11-cb2fa7156b45 · outbound

This paper cites Error bounds for approximations with deep ReLU networks.Neural Networks, 94:103–114.

A Composite Activation Function for Learning Stable Binary Representations Error bounds for approximations with deep ReLU networks.Neural Networks, 94:103–114

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.583779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2a54ecb4-049a-4e40-957a-a760461bc804 · outbound

This paper cites Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets.

A Composite Activation Function for Learning Stable Binary Representations Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets

Reference 77

Resolution: verified exact; arxiv_id, observed 2026-05-13T02:07:07.920946Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 56015d91-db34-48aa-b16f-13c683275b36 · outbound

This paper cites Torchcv: A pytorch-based framework for deep learning in computer vision.https://github.com/donnyyou/torchcv.

A Composite Activation Function for Learning Stable Binary Representations Torchcv: A pytorch-based framework for deep learning in computer vision.https://github.com/donnyyou/torchcv

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.746915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 91c71328-3c29-4fc1-a25f-61734a0d5b65 · outbound

This paper cites Learning interpretable differentiable logic networks.IEEE Transactions on Circuits and Systems for Artificial Intelligence.

A Composite Activation Function for Learning Stable Binary Representations Learning interpretable differentiable logic networks.IEEE Transactions on Circuits and Systems for Artificial Intelligence

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.630291Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 29fa1dec-d6fb-4b8e-a0f3-2a0850ee0988 · outbound

This paper cites When and why vision-language models behave like bags-of-words, and what to do about it?.

A Composite Activation Function for Learning Stable Binary Representations When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 80

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T02:07:07.934212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 39712e7f-ecb7-4cc9-a1eb-38be191750a5 · outbound

This paper cites Post-hoc Concept Bottleneck Models.

A Composite Activation Function for Learning Stable Binary Representations Post-hoc Concept Bottleneck Models

Reference 81

Resolution: verified exact; arxiv_id, observed 2026-05-13T02:07:08.006383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 721da4f0-c912-4678-90ff-ed877d3fc919 · outbound

This paper cites Wide Residual Networks.

A Composite Activation Function for Learning Stable Binary Representations Wide Residual Networks

Reference 82

Resolution: verified exact; local_arxiv, observed 2026-05-13T02:07:08.011670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4fd1393b-8a85-49ac-a8c7-6bb2eb39e088 · outbound

This paper cites Superspike: Supervised learning in multilayer spiking neural networks.Neural computation, 30(6):1514–1541.

A Composite Activation Function for Learning Stable Binary Representations Superspike: Supervised learning in multilayer spiking neural networks.Neural computation, 30(6):1514–1541

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T13:52:51.611965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6a07faae-4aea-418d-8007-1ef98c181e24 · outbound

This paper cites light-duty.

A Composite Activation Function for Learning Stable Binary Representations light-duty

Reference 84

Resolution: malformed identifier; raw_fallback, observed 2026-05-13T13:52:51.647772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers