{"total":21,"rows":[{"id":"2111.12993","title":"PolyViT: Co-training Vision Transformers on Images, Videos and Audio","created":"2021-11-25","cited_by_count":58,"area":null},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2104.13424","title":"Policy Manifold Search: Exploring the Manifold Hypothesis for Diversity-based Neuroevolution","created":"2021-04-27","cited_by_count":20,"area":null},{"id":"2205.11141","title":"OPQ: Compressing Deep Neural Networks with One-shot Pruning-Quantization","created":"2022-05-23","cited_by_count":19,"area":null},{"id":"2201.08712","title":"Improved Random Features for Dot Product Kernels","created":"2022-01-21","cited_by_count":12,"area":null},{"id":"2402.08823","title":"Random Representations Outperform Online Continually Learned Representations","created":"2024-02-13","cited_by_count":11,"area":null},{"id":"2203.13556","title":"Deformable Butterfly: A Highly Structured and Sparse Linear Transform","created":"2022-03-25","cited_by_count":8,"area":null},{"id":"2403.07221","title":"LookupFFN: Making Transformers Compute-lite for CPU inference","created":"2024-03-12","cited_by_count":8,"area":null},{"id":"2510.05688","title":"vAttention: Verified Sparse Attention","created":"2025-10-07","cited_by_count":6,"area":null},{"id":"2109.11928","title":"Is the Number of Trainable Parameters All That Actually Matters?","created":"2021-09-24","cited_by_count":3,"area":null},{"id":"2206.01509","title":"Canonical convolutional neural networks","created":"2022-06-03","cited_by_count":3,"area":null},{"id":"2311.10807","title":"SENetV2: Aggregated dense layer for channelwise and global representations","created":"2023-11-17","cited_by_count":3,"area":null},{"id":"2104.02373","title":"Leverage Score Sampling for Complete Mode Coverage in Generative Adversarial Networks","created":"2021-04-06","cited_by_count":2,"area":null},{"id":"2208.00087","title":"Low-complexity Approximate Convolutional Neural Networks","created":"2022-07-29","cited_by_count":1,"area":null},{"id":"2210.13311","title":"Different Tunes Played with Equal Skill: Exploring a Unified Optimization Subspace for Delta Tuning","created":"2022-10-24","cited_by_count":1,"area":null},{"id":"2602.19134","title":"Mapping Networks","created":"2026-02-22","cited_by_count":1,"area":null},{"id":"2110.15440","title":"HD-cos Networks: Efficient Neural Architectures for Secure Multi-Party Computation","created":"2021-10-28","cited_by_count":0,"area":null},{"id":"2308.13343","title":"Squeeze aggregated excitation network","created":"2023-08-25","cited_by_count":0,"area":null},{"id":"2310.17669","title":"An Approach for Efficient Neural Architecture Search Space Definition","created":"2023-10-25","cited_by_count":0,"area":null},{"id":"2311.08125","title":"Lite it fly: An All-Deformable-Butterfly Network","created":"2023-11-14","cited_by_count":0,"area":null},{"id":"2502.00585","title":"Converting Transformers into DGNNs Form","created":"2025-02-01","cited_by_count":0,"area":null}],"next_cursor":null}