Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1 | Paper Citation Record

Observation 03ea4fde-0c59-4a3d-a169-861ae803873c · inbound

Adaptive Precision CNN Accelerator Using Radix-X Parallel Connected Memristor Crossbars cites this paper.

Adaptive Precision CNN Accelerator Using Radix-X Parallel Connected Memristor Crossbars Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-05-25T18:36:07.981030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 273c704c-edfb-4a72-bb75-747e77f9399d · inbound

Improving Branch Prediction By Modeling Global History with Convolutional Neural Networks cites this paper.

Improving Branch Prediction By Modeling Global History with Convolutional Neural Networks Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-25T18:56:08.768543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 6f8ea890-1419-4227-94e6-81d9245e51c7 · inbound

New pointwise convolution in Deep Neural Networks through Extremely Fast and Non Parametric Transforms cites this paper.

New pointwise convolution in Deep Neural Networks through Extremely Fast and Non Parametric Transforms Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-25T16:56:04.257696Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 6d419b3b-5e89-48de-8916-33dff50dad5d · inbound

A Stochastic-Computing based Deep Learning Framework using Adiabatic Quantum-Flux-Parametron SuperconductingTechnology cites this paper.

A Stochastic-Computing based Deep Learning Framework using Adiabatic Quantum-Flux-Parametron SuperconductingTechnology Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-24T18:14:47.947205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 2f527e50-0cf4-43ae-b20d-584846883322 · inbound

Efficient Detection and Quantification of Timing Leaks with Neural Networks cites this paper.

Efficient Detection and Quantification of Timing Leaks with Neural Networks Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 15

Resolution: metadata mismatch; local_arxiv, observed 2026-05-24T17:09:43.435045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 90aa0f15-bece-44c9-ae84-f9a25f962e70 · inbound

Co-Evolutionary Compression for Unpaired Image Translation cites this paper.

Co-Evolutionary Compression for Unpaired Image Translation Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-24T16:49:41.819095Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 074954be-8395-451f-a706-3347707f74ef · inbound

GDRQ: Group-based Distribution Reshaping for Quantization cites this paper.

GDRQ: Group-based Distribution Reshaping for Quantization Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-14T15:17:36.215425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ac663ab-f5b5-4211-b623-6bf1f9df1253 · inbound

Exploiting Channel Similarity for Accelerating Deep Convolutional Neural Networks cites this paper.

Exploiting Channel Similarity for Accelerating Deep Convolutional Neural Networks Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-14T15:00:11.755055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b85c6ee2-032f-4168-80fb-136cde09e37b · inbound

Efficient Inference of CNNs via Channel Pruning cites this paper.

Efficient Inference of CNNs via Channel Pruning Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-14T14:25:09.944947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24040b28-b112-4a77-ae53-0e4302918ba2 · inbound

Group Pruning using a Bounded-Lp norm for Group Gating and Regularization cites this paper.

Group Pruning using a Bounded-Lp norm for Group Gating and Regularization Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-14T14:19:02.637986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f04e3bde-2da1-418a-896d-a9b414e8b735 · inbound

ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks cites this paper.

ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-14T14:01:22.822832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e351564-c915-4988-b562-3229edd1846d · inbound

Digital Biologically Plausible Implementation of Binarized Neural Networks with Differential Hafnium Oxide Resistive Memory Arrays cites this paper.

Digital Biologically Plausible Implementation of Binarized Neural Networks with Differential Hafnium Oxide Resistive Memory Arrays Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-14T13:58:37.847727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bc71f9e-192b-479c-b4a4-56cb616e722b · inbound

Implementing Binarized Neural Networks with Magnetoresistive RAM without Error Correction cites this paper.

Implementing Binarized Neural Networks with Magnetoresistive RAM without Error Correction Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-14T13:54:49.168229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1f9170a-0526-43b7-b753-83574ec08b46 · inbound

Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks cites this paper.

Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-14T13:30:12.515043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5515234a-ece0-4077-9e76-1a5752792e83 · inbound

Bayesian Optimized 1-Bit CNNs cites this paper.

Bayesian Optimized 1-Bit CNNs Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:06.045340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fc8763d-b8fe-41c0-919a-0d697d513cb5 · inbound

Detecting Gas Vapor Leaks Using Uncalibrated Sensors cites this paper.

Detecting Gas Vapor Leaks Using Uncalibrated Sensors Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-14T12:19:54.409826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28dd6e58-c423-410a-83bf-9b65ccee5a68 · inbound

RBCN: Rectified Binary Convolutional Networks for Enhancing the Performance of 1-bit DCNNs cites this paper.

RBCN: Rectified Binary Convolutional Networks for Enhancing the Performance of 1-bit DCNNs Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-14T12:12:36.992330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9920bde0-b903-4ea7-bdff-14ceadfdaa8d · inbound

Learning Filter Basis for Convolutional Neural Network Compression cites this paper.

Learning Filter Basis for Convolutional Neural Network Compression Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-14T11:31:54.895213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e433c8eb-b8f3-4938-a861-1a2f9fdb9158 · inbound

SeesawFaceNets: sparse and robust face verification model for mobile platform cites this paper.

SeesawFaceNets: sparse and robust face verification model for mobile platform Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-14T11:25:00.988736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 321d48f6-b4b0-4a5b-9816-1b189a8f8f8d · inbound

PULP-NN: Accelerating Quantized Neural Networks on Parallel Ultra-Low-Power RISC-V Processors cites this paper.

PULP-NN: Accelerating Quantized Neural Networks on Parallel Ultra-Low-Power RISC-V Processors Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-14T10:23:57.864258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 797e409c-0af9-4195-ad40-a93e77e35cd7 · inbound

A Machine Learning Accelerator In-Memory for Energy Harvesting cites this paper.

A Machine Learning Accelerator In-Memory for Energy Harvesting Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-14T10:34:11.005584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2292ced-ed1a-48f3-879f-4e8f5d4a0147 · inbound

HarDNet: A Low Memory Traffic Network cites this paper.

HarDNet: A Low Memory Traffic Network Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-14T05:36:31.921622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2f1fdcc-f656-4817-a2ff-c294d7b37229 · inbound

PSDNet and DPDNet: Efficient channel expansion, Depthwise-Pointwise-Depthwise Inverted Bottleneck Block cites this paper.

PSDNet and DPDNet: Efficient channel expansion, Depthwise-Pointwise-Depthwise Inverted Bottleneck Block Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-14T05:32:32.222616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0893c74d-738a-4519-a7b6-d1ee40eecbaa · inbound

Spiking Neural Networks for Inference and Learning: A Memristor-based Design Perspective cites this paper.

Spiking Neural Networks for Inference and Learning: A Memristor-based Design Perspective Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-14T05:16:30.524120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ab60a63-eb1b-446a-a7bf-a0094aa2a956 · inbound

Training High-Performance and Large-Scale Deep Neural Networks with Full 8-bit Integers cites this paper.

Training High-Performance and Large-Scale Deep Neural Networks with Full 8-bit Integers Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-14T04:55:40.139318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 267ccc1b-72e3-47a9-bc57-470357176411 · inbound

LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale cites this paper.

LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 125

Resolution: verified exact; arxiv_id, observed 2026-05-13T13:35:36.057909Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 8f1e0a4d-40fd-4714-8e83-b71c751d1f7e · inbound

Deep learning applied to computational mechanics: A comprehensive review, state of the art, and the classics cites this paper.

Deep learning applied to computational mechanics: A comprehensive review, state of the art, and the classics Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 297

Resolution: verified exact; local_arxiv, observed 2026-05-24T10:24:20.169666Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 7c5fb7ae-19d2-4cc0-8a33-51a33d2d1c54 · inbound

BiDM: Pushing the Limit of Quantization for Diffusion Models cites this paper.

BiDM: Pushing the Limit of Quantization for Diffusion Models Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T20:18:10.401647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0c11b9c-12b3-4e73-a0bd-488a174adca3 · inbound

Fast and Slow Gradient Approximation for Binary Neural Network Optimization cites this paper.

Fast and Slow Gradient Approximation for Binary Neural Network Optimization Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T14:42:32.854726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a755d210-5377-4d6f-8941-d2a3ff92e3bf · inbound

CBNN: 3-Party Secure Framework for Customized Binary Neural Networks Inference cites this paper.

CBNN: 3-Party Secure Framework for Customized Binary Neural Networks Inference Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T10:41:30.022000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c8d3cc7-4e2e-490b-9422-ba9fd33a05c9 · inbound

Hyperbolic Binary Neural Network cites this paper.

Hyperbolic Binary Neural Network Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-10T21:56:11.050813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cc9eda4-4e1c-4b21-beab-d0eeebca98ee · inbound

Balance Divergence for Knowledge Distillation cites this paper.

Balance Divergence for Knowledge Distillation Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-10T20:40:01.566100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d96d259f-45bd-4f30-9b75-c82e2369cd14 · inbound

BrainGuard: Privacy-Preserving Multisubject Image Reconstructions from Brain Activities cites this paper.

BrainGuard: Privacy-Preserving Multisubject Image Reconstructions from Brain Activities Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T15:19:44.189886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99945597-c8c2-404a-8623-1cb9ae615a30 · inbound

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs cites this paper.

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-10T10:42:07.728028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1dbe592b-c24d-496f-af73-f3fb1042dc95 · inbound

Partial Channel Network: Compute Fewer, Perform Better cites this paper.

Partial Channel Network: Compute Fewer, Perform Better Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-09T15:49:53.421197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ece77db1-f495-4570-9771-cecac01bba88 · inbound

An Augmented Backward-Corrected Projector Splitting Integrator for Dynamical Low-Rank Training cites this paper.

An Augmented Backward-Corrected Projector Splitting Integrator for Dynamical Low-Rank Training Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-09T10:22:03.664299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 134b50f8-5e5d-445e-aba6-c9c2e4cd65bf · inbound

Semantic Feature Division Multiple Access for Digital Semantic Broadcast Channels cites this paper.

Semantic Feature Division Multiple Access for Digital Semantic Broadcast Channels Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-09T00:13:22.479833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 537f1296-304b-43a0-9a31-8379b825e151 · inbound

ETHEREAL: Energy-efficient and High-throughput Inference using Compressed Tsetlin Machine cites this paper.

ETHEREAL: Energy-efficient and High-throughput Inference using Compressed Tsetlin Machine Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-08T18:35:03.902144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 782d0a6d-1ed7-4899-a272-4b7cb3bc47c0 · inbound

prunAdag: an adaptive pruning-aware gradient method cites this paper.

prunAdag: an adaptive pruning-aware gradient method Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-08T05:44:07.549128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe76cbb9-8e54-4408-aec7-f3b5e7ac0b56 · inbound

Low-Resolution Neural Networks cites this paper.

Low-Resolution Neural Networks Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T23:43:16.707044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88be67c0-727b-4c66-b3be-8f9c9ff9a9cc · inbound

Neuromorphic Principles for Efficient Large Language Models on Intel Loihi 2 cites this paper.

Neuromorphic Principles for Efficient Large Language Models on Intel Loihi 2 Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-08T10:59:50.569372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fffe563-642a-44d5-90b9-c2bcb9fd2f08 · inbound

Efficient FPGA Implementation of Time-Domain Popcount for Low-Complexity Machine Learning cites this paper.

Efficient FPGA Implementation of Time-Domain Popcount for Low-Complexity Machine Learning Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T01:05:20.318330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 352ca1ac-6aec-455e-a20f-4b08d8b039b9 · inbound

Efficient Continual Learning in Keyword Spotting using Binary Neural Networks cites this paper.

Efficient Continual Learning in Keyword Spotting using Binary Neural Networks Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T00:55:07.563945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6744d4d2-5a0d-4edc-a24d-6c7f66d25dbb · inbound

PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement cites this paper.

PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T20:40:48.838057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98282da1-9042-486d-9f66-2ca17ff5bb7c · inbound

Optimizing Binary and Ternary Neural Network Inference on RRAM Crossbars using CIM-Explorer cites this paper.

Optimizing Binary and Ternary Neural Network Inference on RRAM Crossbars using CIM-Explorer Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:03.354993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57b0dde0-d6a9-4d0f-87d0-8f791002e64f · inbound

A Principled Bayesian Framework for Training Binary and Spiking Neural Networks cites this paper.

A Principled Bayesian Framework for Training Binary and Spiking Neural Networks Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T14:45:11.260206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6406eee-dd6a-44da-8922-17ae5912f3aa · inbound

Beyond Discreteness: Sample Complexity Analysis of Straight-Through Estimator for 1-bit Quantization cites this paper.

Beyond Discreteness: Sample Complexity Analysis of Straight-Through Estimator for 1-bit Quantization Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:11.881764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67157648-b8a5-4448-99fd-8055fc7b4463 · inbound

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing cites this paper.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:15.952081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c3180dd-7187-4739-b876-8c735bcd2b6b · inbound

Inverse-designed nanophotonic neural network accelerators for ultra-compact optical computing cites this paper.

Inverse-designed nanophotonic neural network accelerators for ultra-compact optical computing Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T06:03:56.541008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34ebeef6-b9ec-46be-b591-08ebd593898c · inbound

Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation cites this paper.

Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T19:13:01.750947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1985138-2d8e-4ad3-bc19-e5e7c9bf15eb · inbound

A Survey on Efficiency Optimization Techniques for DNN-based Video Analytics: Process Systems, Algorithms, and Applications cites this paper.

A Survey on Efficiency Optimization Techniques for DNN-based Video Analytics: Process Systems, Algorithms, and Applications Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T15:30:19.298058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 156ff39f-d0a3-4d08-8e15-88383b96f6e3 · inbound

A Lower Bound for the Number of Linear Regions of Ternary ReLU Regression Neural Networks cites this paper.

A Lower Bound for the Number of Linear Regions of Ternary ReLU Regression Neural Networks Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-19T03:32:01.753806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 826eb67d-47d2-4620-b6fa-2ac37683b083 · inbound

Rethinking 1-bit Optimization Leveraging Pre-trained Large Language Models cites this paper.

Rethinking 1-bit Optimization Leveraging Pre-trained Large Language Models Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-21T23:44:26.573928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f6371ffb-5904-4ca7-b570-014270b17ae2 · inbound

Arbitrary Precision Printed Ternary Neural Networks with Holistic Evolutionary Approximation cites this paper.

Arbitrary Precision Printed Ternary Neural Networks with Holistic Evolutionary Approximation Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-05T15:38:49.349830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2530407c-6c81-4142-bcbf-d6fedd92c832 · inbound

Systolic Array-based Architecture for Low-Bit Integerized Vision Transformers cites this paper.

Systolic Array-based Architecture for Low-Bit Integerized Vision Transformers Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T16:55:19.747044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a436654b-1bac-45e0-9d1f-0e144ce7691d · inbound

Binary Weight Multi-Bit Activation Quantization for Compute-in-Memory CNN Accelerators cites this paper.

Binary Weight Multi-Bit Activation Quantization for Compute-in-Memory CNN Accelerators Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:31.609484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7a3e75d-4f67-4156-b75b-15e8b0c57d0e · inbound

Progressive Element-wise Gradient Estimation for Neural Network Quantization cites this paper.

Progressive Element-wise Gradient Estimation for Neural Network Quantization Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T15:16:58.394395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c3128f1-3b2d-45ac-b322-3b3a09b5b0dd · inbound

LUQ: Layerwise Ultra-Low Bit Quantization for Multimodal Large Language Models cites this paper.

LUQ: Layerwise Ultra-Low Bit Quantization for Multimodal Large Language Models Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T14:45:25.188488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aea87543-f0a2-440c-859a-12680ec31947 · inbound

Learning to Optimize by Differentiable Programming cites this paper.

Learning to Optimize by Differentiable Programming Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-03T08:39:31.794176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b50d9587-1b13-44e6-b05d-af168370a6c7 · inbound

LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation cites this paper.

LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-11T12:46:04.432031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 96c597c1-4583-4c2b-b858-4c5575a3e494 · inbound

Design and Implementation of BNN-Based Object Detection on FPGA cites this paper.

Design and Implementation of BNN-Based Object Detection on FPGA Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T10:56:29.905471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 91b215c7-fcaa-49b7-99fc-0628764febd9 · inbound

Design and Implementation of BNN-Based Object Detection on FPGA cites this paper.

Design and Implementation of BNN-Based Object Detection on FPGA Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T01:46:14.552563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 8150cf4a-f4ca-4fb4-a06d-64324051a126 · inbound

DAP: Doppler-aware Point Network for Heterogeneous mmWave Action Recognition cites this paper.

DAP: Doppler-aware Point Network for Heterogeneous mmWave Action Recognition Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T07:31:31.806905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 9cbdb982-fdcd-4d04-98f0-da147ff8290f · inbound

DAP: Doppler-aware Point Network for Heterogeneous mmWave Action Recognition cites this paper.

DAP: Doppler-aware Point Network for Heterogeneous mmWave Action Recognition Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 10

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T01:49:21.479529Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 94317dcd-77ec-4383-81f5-612ca5a9904a · inbound

SURGE: Surrogate Gradient Adaptation in Binary Neural Networks cites this paper.

SURGE: Surrogate Gradient Adaptation in Binary Neural Networks Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 22

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T06:37:26.582352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation da47ea62-4dbe-49c4-98d8-74b6662acdf6 · inbound

SURGE: Surrogate Gradient Adaptation in Binary Neural Networks cites this paper.

SURGE: Surrogate Gradient Adaptation in Binary Neural Networks Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 22

Resolution: metadata mismatch; local_arxiv, observed 2026-05-19T17:52:42.921241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

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

A Composite Activation Function for Learning Stable Binary Representations cites this paper.

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 2026-08-20T06:33:59.587034+00:00.

Observation ae2ce55c-f81d-48bb-a448-bfbcde6a93fd · inbound

FTerViT: Fully Ternary Vision Transformer cites this paper.

FTerViT: Fully Ternary Vision Transformer Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-05-21T06:03:59.464785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a5df4d6a-170b-4946-873b-06c240887488 · inbound

Signs Beat Floats: Low-Rank Double-Binary Adaptation for On-Device Fine-Tuning cites this paper.

Signs Beat Floats: Low-Rank Double-Binary Adaptation for On-Device Fine-Tuning Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-06-30T15:54:49.340326Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1633ba84-03b9-4c73-bf97-bbb7e2202632 · inbound

QuoVLA: Quotient Space for Vision-Language-Action Models cites this paper.

QuoVLA: Quotient Space for Vision-Language-Action Models Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-06-30T12:34:39.436259Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 9662aa90-cc86-48e3-b17f-9b83fdd8aa46 · inbound

Low-Energy Reduced RISC-V Instruction Subset Processor for Tsetlin Machine Inference at the Edge cites this paper.

Low-Energy Reduced RISC-V Instruction Subset Processor for Tsetlin Machine Inference at the Edge Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-07-04T03:19:30.000501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d49e7c22-9d3a-4f58-96d3-a584101cd995 · inbound

Hybrid Compression: Integrating Pruning and Quantization for Optimized Neural Networks cites this paper.

Hybrid Compression: Integrating Pruning and Quantization for Optimized Neural Networks Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 4

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T10:19:47.791156Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 05d8dc46-4d29-4003-bbb2-4d5c4bce4d7c · inbound

Spatial Partial Functionalization of Neural Networks based on Noise Fields cites this paper.

Spatial Partial Functionalization of Neural Networks based on Noise Fields Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-07-04T19:10:05.119213Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 909750c5-1408-4a28-81b6-b555895e4959 · inbound

Layerwise Progressive Freezing: A Training Scaffold for Depth-Scalable Binary Networks cites this paper.

Layerwise Progressive Freezing: A Training Scaffold for Depth-Scalable Binary Networks Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-06-29T05:13:06.512726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 87bbf8b6-7d03-4853-bd0f-629b37b4a762 · inbound

Neural Very Weak Formulations enabling Hardware-Oriented deep PDE solvers cites this paper.

Neural Very Weak Formulations enabling Hardware-Oriented deep PDE solvers Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T02:03:19.014754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cea5fbf7-5d02-4cc8-aa45-b2ac79ab7e4f · inbound

Differentiable Logic Gate Networks for Low-Latency EEG Classification on Edge Devices cites this paper.

Differentiable Logic Gate Networks for Low-Latency EEG Classification on Edge Devices Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T15:53:44.708622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2443d6a-56d3-4f78-b969-5c48ff3719e0 · inbound

HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models cites this paper.

HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T14:11:20.879253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1beff89-000f-4c2d-9f9a-5e1d8a4191b4 · inbound

AS-FedBridge: Pseudo-Spike Bridge Distillation for Heterogeneous ANN-SNN Federated Learning cites this paper.

AS-FedBridge: Pseudo-Spike Bridge Distillation for Heterogeneous ANN-SNN Federated Learning Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-05T21:03:57.567533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers