{"total":36,"items":[{"citing_arxiv_id":"2607.00275","ref_index":15,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Entropy-Regularized Probabilistic Gates for Sparse Model Discovery in Scarce-Data Federated Learning","primary_cat":"cs.LG","submitted_at":"2026-06-30T23:51:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Entropy regularization of probabilistic gates improves test performance and sparsity recovery in scarce-data federated learning over Fed-IHT and FedAvg pruning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.32016","ref_index":186,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning","primary_cat":"cs.LG","submitted_at":"2026-06-30T17:47:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FedLAB organizes multimodal graph knowledge into typed hierarchical codebooks for modality evidence, node semantics, and topology context via federated semantic barycenter pre-training, improving performance by up to 7.53% on benchmarks while enabling semantic traceability.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.31282","ref_index":106,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Revisiting the Volume Hypothesis","primary_cat":"cs.LG","submitted_at":"2026-06-30T07:58:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"The generalization advantage of SGD over random sampling diminishes with growing training set size in binary networks, as measured by joint density of states over train and test accuracy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.00031","ref_index":29,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Joint Discovery of Object and Action Symbols through Effect Prediction for Robotic Manipulation Planning","primary_cat":"cs.RO","submitted_at":"2026-06-22T11:58:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A binary-bottleneck model discovers object and action symbols from multi-modal effect predictions on random interactions, then uses discrete planning on predicted trajectories for tabletop repositioning and stacking with few-shot generalization to novel objects.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.18535","ref_index":194,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Shrinkage priors for Bayesian Substitute Confounders","primary_cat":"stat.ME","submitted_at":"2026-06-16T23:03:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Bayesian shrinkage priors on factor models produce sparse substitute confounders that support consistent regression-adjusted causal estimates under latent variable identification assumptions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.06867","ref_index":70,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Multi-FRuGaL: Multimodal Flexible Redundancy-aware Decomposed Gated Learning for Cancer Diagnosis and Prognosis","primary_cat":"cs.CV","submitted_at":"2026-06-05T03:33:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Multi-FRuGaL is a decomposition-aware gated fusion framework for multimodal cancer data that maintains performance under missing modalities and reports AUC gains on two head-and-neck cancer cohorts.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.06288","ref_index":68,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Discrete Causal Representations from Heterogeneous Domains: A Bayesian Approach with Social Survey Applications","primary_cat":"stat.ML","submitted_at":"2026-06-04T15:25:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A Bayesian approach with SMC inference learns discrete causal representations from heterogeneous domains, demonstrated on social survey data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.05756","ref_index":31,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Beyond Soft Masks: Hard-Perturbation Mixup Explainer for Robust GNN Explainability","primary_cat":"cs.LG","submitted_at":"2026-06-04T06:32:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"HPME proposes hard-perturbation mixup explainer grounded in generalized Graph Information Bottleneck to extract discrete subgraphs and generate in-distribution explanations that outperform soft-mask approaches on synthetic and real datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.05437","ref_index":58,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Uncertainty-Aware Adaptive Sensor Fusion for Autonomous Navigation","primary_cat":"cs.RO","submitted_at":"2026-06-03T20:59:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Hybrid ViT-MCNN model with UKF and uncertainty-aware loss claims superior ATE/RPE on KITTI for VIO at 155 FPS.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.30429","ref_index":58,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Attention-based optimizer for symmetry finding","primary_cat":"quant-ph","submitted_at":"2026-05-28T18:00:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A Set-Transformer architecture with self-attention encodes Pauli-string correlations, optimizes via commutation objective, and finds symmetries with near-deterministic success on physical models like Ising and Toric code.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.25551","ref_index":15,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Learning Permutation from Structure Without Supervision","primary_cat":"cs.LG","submitted_at":"2026-05-25T08:08:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Entropy-adaptive Gumbel-Sinkhorn formulation for unsupervised permutation learning that modulates temperature per assignment to address non-uniform uncertainty.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.00078","ref_index":33,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Flow-Based Generative Modeling for Optimizing Sampling Policies in Compressed Sensing Applications","primary_cat":"cs.CV","submitted_at":"2026-05-22T12:35:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A task-aware flow-based generative framework optimizes subsampling masks in compressed sensing, reporting SOTA PSNR of 25.17 dB at 5% rate on CelebA and 29.24 dB for 8x MRI on fastMRI.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.20088","ref_index":27,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"INSHAPE: Instance-Level Shapelets for Interpretable Time-Series Classification","primary_cat":"cs.LG","submitted_at":"2026-05-19T16:43:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"INSHAPE discovers instance-specific non-overlapping shapelets, models their temporal dependencies, and aggregates them bottom-up into population-level prototypes for improved accuracy and interpretability in time-series classification.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18204","ref_index":7,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Forward-Learned Discrete Diffusion: Learning how to noise to denoise faster","primary_cat":"stat.ML","submitted_at":"2026-05-18T10:43:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"FLDD learns non-Markovian marginal and posterior distributions for the forward process so a factorized reverse process can match the target better and produce higher-quality samples in fewer steps.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17568","ref_index":59,"ref_count":2,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Structured Neural Marked Point Processes for Interpretable Event Interaction Modeling","primary_cat":"cs.LG","submitted_at":"2026-05-17T17:56:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SNMPP builds a product-form neural influence kernel from a signed interaction network over event classes and a delay-aware monotonic temporal network to enable explicit discovery of inter-event relationships alongside strong prediction.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.14297","ref_index":95,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Policy Optimization in Hybrid Discrete-Continuous Action Spaces via Mixed Gradients","primary_cat":"cs.LG","submitted_at":"2026-05-14T02:59:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"HPO enables unbiased policy optimization in hybrid action spaces by mixing differentiable simulation gradients with score-function estimates, outperforming PPO as continuous dimensions increase.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.10292","ref_index":113,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LeapTS: Rethinking Time Series Forecasting as Adaptive Multi-Horizon Scheduling","primary_cat":"cs.LG","submitted_at":"2026-05-11T09:54:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"LeapTS reformulates forecasting as adaptive multi-horizon scheduling via hierarchical control and NCDEs, delivering at least 7.4% better performance and 2.6-5.3x faster inference than Transformer baselines while adapting to non-stationary dynamics.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.07837","ref_index":71,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Approximation-Free Differentiable Oblique Decision Trees","primary_cat":"cs.LG","submitted_at":"2026-05-08T15:04:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"DTSemNet gives an exact, invertible neural-network encoding of hard oblique decision trees that supports direct gradient training for both classification and regression without probabilistic softening or quantized estimators.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05769","ref_index":28,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Adaptive Selection of LoRA Components in Privacy-Preserving Federated Learning","primary_cat":"cs.LG","submitted_at":"2026-05-07T07:01:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"AS-LoRA adaptively chooses which LoRA factor to update per layer and round using a curvature-aware second-order score, eliminating reconstruction error floors and improving performance in DP federated learning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05096","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CapsID: Soft-Routed Variable-Length Semantic IDs for Generative Recommendation","primary_cat":"cs.IR","submitted_at":"2026-05-06T16:33:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CapsID uses probabilistic capsule routing and confidence-based termination to generate variable-length semantic IDs, improving recall by 9.6% over strong baselines with half the latency of dual-representation systems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.01226","ref_index":45,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Arbitrarily Conditioned Hierarchical Flows for Spatiotemporal Events","primary_cat":"cs.LG","submitted_at":"2026-05-02T03:50:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"ARCH is a hierarchical flow-based generative model that enables tractable conditional intensity computation and arbitrary conditioning for spatiotemporal event distributions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00670","ref_index":26,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Robust Multimodal Recommendation via Graph Retrieval-Enhanced Modality Completion","primary_cat":"cs.IR","submitted_at":"2026-05-01T13:50:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"GRE-MC retrieves relevant subgraphs and uses a graph transformer plus sparse codebook to complete missing modalities, outperforming prior methods on recommendation benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00445","ref_index":31,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"The Power of Order: Fooling LLMs with Adversarial Table Permutations","primary_cat":"cs.LG","submitted_at":"2026-05-01T06:25:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Semantically invariant row and column permutations in tables can cause LLMs to output incorrect answers, and a gradient-based attack called ATP efficiently finds such permutations that degrade performance across many models.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"Rethinking tabular data understanding with large language models. InProceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), NAACL 2024, Mexico City, Mexico, June 16-21, 2024, pages 450-482. Association for Computational Linguistics, 2024. [31] Chris J Maddison, Andriy Mnih, and Yee Whye Teh. The concrete distribution: A continuous relaxation of discrete random variables.arXiv preprint arXiv:1611.00712, 2016. [32] Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. Towards deep learning models resistant to adversarial attacks.arXiv preprint arXiv:1706."},{"citing_arxiv_id":"2604.26181","ref_index":20,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SWAN: World-Aware Adaptive Multimodal Networks for Runtime Variations","primary_cat":"cs.LG","submitted_at":"2026-04-28T23:56:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SWAN is the first adaptive multimodal network that meets variable compute budgets, optimizes layer use by sample complexity, and drops irrelevant features, cutting FLOPs up to 49% in 3D object detection with minimal accuracy loss.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.18556","ref_index":24,"ref_count":2,"confidence":0.98,"is_internal_anchor":true,"paper_title":"GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling","primary_cat":"cs.CL","submitted_at":"2026-04-20T17:45:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"GSQ uses Gumbel-Softmax to optimize scalar quantization grids for LLMs, closing most of the accuracy gap to vector methods like QTIP at 2-3 bits per parameter while using symmetric scalar grids compatible with existing kernels.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.10994","ref_index":32,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LumiMotion: Improving Gaussian Relighting with Scene Dynamics","primary_cat":"cs.CV","submitted_at":"2026-04-13T04:50:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"LumiMotion improves albedo estimation and scene relighting in dynamic scenes by leveraging motion to separate lighting effects from surface appearance in a dynamic 2D Gaussian Splatting representation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.09955","ref_index":18,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learnable Motion-Focused Tokenization for Effective and Efficient Video Unsupervised Domain Adaptation","primary_cat":"cs.CV","submitted_at":"2026-04-10T23:30:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"LMFT enables state-of-the-art performance in video unsupervised domain adaptation by focusing on motion-rich tokens and reducing computational overhead.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2603.15250","ref_index":20,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"In-Context Symbolic Regression for Robustness-Improved Kolmogorov-Arnold Networks","primary_cat":"cs.LG","submitted_at":"2026-03-16T13:21:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"In-context symbolic regression methods improve robustness of symbolic formula recovery from KANs, cutting median OFAT test MSE by up to 99.8 percent across hyperparameter sweeps.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2603.10225","ref_index":40,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Rethinking the Harmonic Loss via Non-Euclidean Distance Layers","primary_cat":"cs.LG","submitted_at":"2026-03-10T20:51:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Non-Euclidean distance variants of harmonic loss improve accuracy, gradient stability, and energy efficiency over cross-entropy and Euclidean harmonic loss in vision backbones and large language models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.15451","ref_index":27,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Molecular Design beyond Training Data with Novel Extended Objective Functionals of Generative AI Models Driven by Quantum Annealing Computer","primary_cat":"q-bio.QM","submitted_at":"2026-02-17T09:38:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Quantum annealing combined with a Neural Hash Function lets generative models create molecules that are more drug-like than classical versions or the training set itself.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.08880","ref_index":21,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Differentiable Logical Programming for Quantum Circuit Discovery and Optimization","primary_cat":"quant-ph","submitted_at":"2026-02-09T16:40:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A differentiable logic programming approach optimizes continuous gate switches to discover and adapt quantum circuits while satisfying user-defined logical axioms.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.12340","ref_index":20,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"LILogic Net: Compact Logic Gate Networks with Learnable Connectivity for Efficient Hardware Deployment","primary_cat":"cs.LG","submitted_at":"2025-11-15T19:44:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LILogicNet trains compact logic-gate networks with learnable sparse connectivity via Top-K selection, reaching 98.45% MNIST accuracy with 8k gates and 60.98% CIFAR-10 accuracy with 256k gates while using far fewer gates than prior logic models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2406.09250","ref_index":59,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"MirrorCheck: Efficient Adversarial Defense for Vision-Language Models","primary_cat":"cs.CV","submitted_at":"2024-06-13T15:55:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"MirrorCheck detects adversarial attacks on VLMs via T2I regeneration for semantic consistency checks, using stochastic model selection and one-time perturbations for robustness against adaptive attacks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2006.12024","ref_index":97,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Bayesian Neural Networks: An Introduction and Survey","primary_cat":"stat.ML","submitted_at":"2020-06-22T06:30:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":1.0,"formal_verification":"none","one_line_summary":"A survey introducing Bayesian Neural Networks and comparing approximate inference methods to enable uncertainty quantification in neural network predictions.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"by examples and intuitive figures to illustrate this property. This property of under-estimated variance is present within much of the current research in BNNs [39]. Recent work has aimed to address these issues through the use of noise contrastive priors [94] and through use of calibration data sets [95]. The authors in [96] employ the use of the concrete distribution [97] to ap- proximate the Bernoulli parameter in the MC Dropout method [85], allowing for it to be optimised, resulting in posterior variances that are better cali- brated. Despite these efforts, the task of formulating reliable and calibrated uncertainty estimates within a VI framework for BNNs remains unsolved. It is reasonable to consider that perhaps the limitations of the current VI"},{"citing_arxiv_id":"1907.00664","ref_index":62,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Learning World Graphs to Accelerate Hierarchical Reinforcement Learning","primary_cat":"cs.LG","submitted_at":"2019-07-01T11:22:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A two-stage framework learns a world graph of pivotal states task-agnostically via joint training of a latent model and curiosity-driven policy, then uses the graph to accelerate hierarchical RL on maze tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1906.12087","ref_index":22,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"ARMIN: Towards a More Efficient and Light-weight Recurrent Memory Network","primary_cat":"cs.LG","submitted_at":"2019-06-28T08:21:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"ARMIN introduces auto-addressing via hidden states and a novel RNN cell to produce a lighter recurrent memory network with lower overhead than existing MANNs or vanilla LSTMs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}