{"total":12,"items":[{"citing_arxiv_id":"2605.30019","ref_index":18,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"elasticAI.explorer: Towards a Unified End-to-End Framework for Hardware-Aware Neural Architecture Search","primary_cat":"cs.AR","submitted_at":"2026-05-28T14:41:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"elasticAI.explorer is an extensible framework for hardware-aware NAS supporting multiple search space types with YAML specs, code generation, cross-compilation, and on-device benchmarking.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.15551","ref_index":54,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Characterizing Learning in Deep Neural Networks using Tractable Algorithmic Complexity Analysis","primary_cat":"cs.LG","submitted_at":"2026-05-15T02:44:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"QuBD extends algorithmic complexity estimation to quantized DNN weights, revealing that complexity decreases during learning, increases with overfitting, follows grokking patterns, and correlates with generalization.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"pirical frequency of a blocku∈S π, similar to Eq. (19). We writez q,r =ϕ(W (q))to denote the exposure ofWwithq-bit quantization and representationr. Partitionz q,r into blocks by Ππ(zq,r) = (w1, . . . ,wm), wherem=|z q,r|/π. For each supported blocku∈S π, define cπ(u;z q,r) :=|{i≤m: w i =u}|, Aπ(zq,r) :={u∈S π :c π(u;z q,r)>0}, aπ(zq,r) :=|A π(zq,r)|. (54) Herec π(u;z q,r)counts how oftenuis exposed underz q,r, whilea π(zq,r)is the number of supported blocks that appear. The KCS estimate of Eq. (2) can then be expressed as CBDM(zq,r) = X u∈Aπ(zq,r) −log 2 f(u) | {z } new blocks + X u∈Aπ(zq,r) log2 cπ(u;z q,r) | {z } multiplicity .(55) Importantly, after most supported blocks have appeared, the first term changes little, and the estimate"},{"citing_arxiv_id":"2310.02540","ref_index":63,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Auto-FP: An Experimental Study of Automated Feature Preprocessing for Tabular Data","primary_cat":"cs.LG","submitted_at":"2023-10-04T02:46:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Experimental comparison of 15 HPO and NAS algorithms for automated feature preprocessing on 45 tabular datasets finds evolution-based methods and random search as top performers.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1907.11587","ref_index":12,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Self-Adaptive 2D-3D Ensemble of Fully Convolutional Networks for Medical Image Segmentation","primary_cat":"eess.IV","submitted_at":"2019-07-26T14:14:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Self-adaptive 2D-3D FCN ensemble optimized by multiobjective evolution for prostate segmentation on PROMISE12 achieves top-10 ranking with smaller size than prior auto-designed models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1907.10473","ref_index":14,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Switchable Normalization for Learning-to-Normalize Deep Representation","primary_cat":"cs.CV","submitted_at":"2019-07-22T17:50:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Switchable Normalization learns per-layer weights to combine channel, layer, and minibatch normalizers, claiming robustness to batch size and better results than fixed normalizers on ImageNet, COCO, CityScapes, ADE20K, MegaFace, and Kinetics.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1907.07160","ref_index":35,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"EnforceNet: Monocular Camera Localization in Large Scale Indoor Sparse LiDAR Point Cloud","primary_cat":"cs.CV","submitted_at":"2019-07-16T17:35:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"EnforceNet achieves centimeter-level monocular camera localization in sparse LiDAR maps of indoor parking garages via a novel resistor module that improves generalization, accuracy, and training speed.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1907.04632","ref_index":18,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Video Action Recognition Via Neural Architecture Searching","primary_cat":"cs.CV","submitted_at":"2019-07-10T11:44:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Uses differentiable NAS with temporal segments and pseudo-3D operators to discover a video action recognition network that outperforms hand-designed models on UCF101 with ~1% of the parameters when trained from scratch.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1907.04648","ref_index":34,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"EPNAS: Efficient Progressive Neural Architecture Search","primary_cat":"cs.LG","submitted_at":"2019-07-07T03:50:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"EPNAS uses a progressive search policy with REINFORCE performance prediction to search neural architectures in parallel, supporting multiple resource constraints and outperforming ENAS and PNAS on CIFAR-10 and ImageNet in speed and accuracy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1907.02871","ref_index":6,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Genetic Network Architecture Search","primary_cat":"cs.NE","submitted_at":"2019-07-05T14:50:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Genetic algorithm searches convolution cell architectures with weight sharing via SGD, reporting 96% accuracy on CIFAR10 and 80.1% on CIFAR100.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1906.12348","ref_index":16,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"MLFriend: Interactive Prediction Task Recommendation for Event-Driven Time-Series Data","primary_cat":"cs.LG","submitted_at":"2019-06-28T17:59:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"MLFriend enumerates prediction tasks for event-driven time-series data and interactively recommends useful ones, with evaluation on three datasets yielding 2885 tasks of which 722 were deemed useful by experts.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1906.11080","ref_index":25,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"AGAN: Towards Automated Design of Generative Adversarial Networks","primary_cat":"cs.LG","submitted_at":"2019-06-25T10:12:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"AGAN is the first neural architecture search method for GANs that discovers architectures outperforming state-of-the-art on CIFAR-10 unsupervised image generation and competitive on supervised tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1906.08879","ref_index":16,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Placeto: Learning Generalizable Device Placement Algorithms for Distributed Machine Learning","primary_cat":"cs.LG","submitted_at":"2019-06-20T22:08:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Placeto learns generalizable RL policies for device placement via iterative improvements and graph embeddings, needing up to 6.1x fewer steps than prior methods and applying to unseen graphs without retraining.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}