{"total":126,"items":[{"citing_arxiv_id":"2606.28225","ref_index":92,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Estimation--Prediction Tradeoff in Causal Probabilistic Temporal Graphs","primary_cat":"cs.LG","submitted_at":"2026-06-26T16:13:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Characterizes an estimation-prediction tradeoff in binary logistic models for causal probabilistic temporal graphs and proposes a framework to jointly evaluate temporal link prediction with causal parameter recovery via Cramér-Rao bounds.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.28145","ref_index":18,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Autoencoder Architectures for Athlete Performance Scoring from Wearable Telemetry","primary_cat":"cs.LG","submitted_at":"2026-06-26T14:41:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Deep autoencoders outperform PCA and VAE variants on a composite of reconstruction MSE and interpretability metrics when reducing runner wearable data to a single latent performance score.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.27348","ref_index":44,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Bridging Performance and Generalization in Reinforcement Learning for Agile Flight","primary_cat":"cs.RO","submitted_at":"2026-06-25T17:54:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"RL framework for agile drone racing combines task-aware switching and physically informed procedural track generation to achieve 7.4x better zero-shot generalization to unseen tracks while maintaining competitive speeds.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.26406","ref_index":16,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Beyond Feedforward Networks: Reentry Neural Systems as the Fundamental Basis of Subjecthood and Intrinsic Safety of Next-Generation AGI","primary_cat":"cs.LG","submitted_at":"2026-06-24T21:54:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A cycle-based reentry architecture is proposed to guarantee self-model emergence, self-preservation, and prompt-injection immunity in AGI via a D-I loop and a new S-measure of integrated information.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.25519","ref_index":170,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Quantization Inflates Reasoning: Token Inflation as a Hidden Cost of Low-Bit Reasoning Models","primary_cat":"cs.AI","submitted_at":"2026-06-24T07:54:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Low-bit post-training quantization of reasoning LLMs increases reasoning token counts while preserving accuracy, introducing a hidden test-time compute cost.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.25342","ref_index":21,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Lifelong In-Context Learning with Transformers Requires Parametric Forms of Attention","primary_cat":"cs.LG","submitted_at":"2026-06-24T03:14:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Argues that parametric attention forms are necessary for lifelong in-context learning in transformers to maintain constant memory footprint over arbitrary sequence lengths.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.25045","ref_index":79,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Machine Learning Approaches for Improved Scalability of Metallic Magnetic Calorimeters","primary_cat":"physics.ins-det","submitted_at":"2026-06-23T18:02:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Machine learning methods are explored for pulse classification, artifact rejection, and shape analysis in metallic magnetic calorimeters to improve scalability over traditional signal processing.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.24062","ref_index":16,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"RAVEN: A Regime-Aware Variable-context Expert Network for Financial Time Series Forecasting","primary_cat":"cs.LG","submitted_at":"2026-06-23T02:11:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"RAVEN proposes a regime-aware MoE architecture with cumulative importance thresholding and correlation-aware weighting to adaptively select temporal context for non-stationary financial forecasting.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.23940","ref_index":20,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Prediction of Viscoelastic Droplet Impact Dynamics Using a Vision Transformer-Based Approach","primary_cat":"physics.flu-dyn","submitted_at":"2026-06-22T21:03:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ViViT model predicts full viscoelastic droplet impact dynamics from initial 10-20% of VOF simulation data, reducing cost by 80-90% while capturing spreading and bouncing regimes.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.23425","ref_index":32,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Interpretable Kolmogorov-Arnold Network with Feature-Isolated Temporal Attention Mechanism for Electricity Load Forecasting","primary_cat":"cs.LG","submitted_at":"2026-06-22T14:46:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"LoadKAN combines feature-isolated temporal attention with KAN to produce competitive load forecasts on three U.S. markets and enables quantitative analysis of non-linear mobility-load relationships via learned activation functions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.24932","ref_index":21,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Recursive QLSTM with Dynamic Variational Quantum Circuit Adaptation","primary_cat":"quant-ph","submitted_at":"2026-06-22T10:10:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"The paper introduces Recursive QLSTM via metacore recursion, numerically tests variants on sequence lengths, and offers theoretical arguments for better temporal propagation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.22969","ref_index":27,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Topological Out-of-Domain Generalization in Dynamical Systems Reconstruction","primary_cat":"cs.LG","submitted_at":"2026-06-22T07:51:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Proposes feature splitting and a closed-form bound on extrapolation range to enable zero-shot topological out-of-domain generalization in dynamical systems reconstruction across tipping points.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.21188","ref_index":14,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Remember what you did?: Learning Behavioral Memories for Partially Observable Object Manipulation","primary_cat":"cs.RO","submitted_at":"2026-06-19T07:56:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CAMP learns a compressed behavioral memory from action history to enable success in long-horizon partially observable object manipulation without extra supervision, showing gains over baselines in real-robot and simulation tests.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.20562","ref_index":42,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"MemoryWAM: Efficient World Action Modeling with Persistent Memory","primary_cat":"cs.RO","submitted_at":"2026-06-18T17:59:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"MemoryWAM is a world action model with a hybrid memory design using recent frames, anchor frames, and gist tokens for efficient long-horizon robotic manipulation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.20561","ref_index":267,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"TimeProVe: Propose, then Verify for Efficient Long Video Temporal Reasoning in Activities of Daily Living","primary_cat":"cs.CV","submitted_at":"2026-06-18T17:59:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"TimeProVe proposes a propose-then-verify framework using lightweight action-based candidate evidence generation followed by targeted VLM verification for efficient long video temporal reasoning, achieving 7.3% improvement on OTB with 75% fewer VLM calls.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.19560","ref_index":50,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Understanding Key Features of Time Series Foundation Models from Epidemic Forecasting","primary_cat":"cs.LG","submitted_at":"2026-06-17T20:01:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"UNKNOWN","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Mixture-of-experts fusing multiple pretrained forecasters achieves strongest performance on influenza time series, with pretraining gains largest at longer horizons when domain-aligned and LLM methods underperforming.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.19026","ref_index":12,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"A Hybrid LSTM--Vision Transformer Architecture for Predicting HRRR Forecast Errors","primary_cat":"cs.LG","submitted_at":"2026-06-17T12:51:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Hybrid LSTM-ViT model using mesonet surface data and profiler vertical profiles improves HRRR forecast error prediction for precipitation, wind speed, and temperature, with roughly twofold skill gain for precipitation over baseline LSTM.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.18049","ref_index":11,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"ConTex: Reformulating Counterfactual Generation For Time Series Forecasting","primary_cat":"cs.LG","submitted_at":"2026-06-16T15:25:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"ConTex learns a global intervention strategy via a decomposed temporal-conditional encoder architecture to generate consistent, sparse counterfactuals for time series models in a single forward pass.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.17555","ref_index":1,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"An AI Security Agent for Banking: Multi-Vector Fraud and AML Detection Across Retail and Corporate Accounts","primary_cat":"cs.CR","submitted_at":"2026-06-16T05:58:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"A three-component fusion architecture of LSTM, statistical, and graph modules detects fraud and AML on synthetic banking data with F1 scores of 0.787 (transactions) and 0.867 (sessions), outperforming rule-based and LSTM-only baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.15948","ref_index":31,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Artificial Intelligence for Power-Converter-Rich Electrical Systems: A Review","primary_cat":"eess.SY","submitted_at":"2026-06-14T18:09:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":2.0,"formal_verification":"none","one_line_summary":"Review of AI applications in power-converter-rich systems across design, control, operations, and governance, highlighting deployment gaps.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.12364","ref_index":7,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"On Subquadratic Architectures: From Applications to Principles","primary_cat":"cs.LG","submitted_at":"2026-06-10T17:33:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"xLSTM outperforms Mamba-2 and Gated DeltaNet on tasks with complex dependencies because its gating scheme enables more flexible and stable state tracking and memory accumulation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.10278","ref_index":20,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Towards Robust Arabic Speech Emotion Recognition with Deep Learning","primary_cat":"cs.SD","submitted_at":"2026-06-09T00:59:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"CNN-Transformer hybrid reaches 98.1% accuracy on Arabic SER using EYASE and BAVED datasets, outperforming CNN-LSTM and fine-tuned wav2vec 2.0.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.10088","ref_index":17,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Interpretable Temporal Facial-Region Motion Analysis for In-the-Wild Parkinson's Disease Video Classification","primary_cat":"cs.CV","submitted_at":"2026-06-08T19:15:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Normalized velocity descriptors from facial keypoints with Random Forest yield 0.826 balanced accuracy and 0.855 AUROC on YouTubePD video classification, stable across 10 seeds with region ablation and permutation importance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.09822","ref_index":72,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Causally Evaluating the Learnability of Formal Language Tasks","primary_cat":"cs.CL","submitted_at":"2026-06-08T17:58:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Introduces the binning semiring and causal graphical models to show that correlational evaluation of learnability in formal language tasks leads to incorrect conclusions from confounders.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.08930","ref_index":18,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"RankGLU: Residual Gated Score Formation for Cross-Sectional Stock Prediction","primary_cat":"cs.CE","submitted_at":"2026-06-08T02:14:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"RankGLU improves mean information coefficient on CSI300 from 0.0654 to 0.0727 by using a residual bottleneck gated linear unit for cross-sectional stock score formation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.08498","ref_index":103,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Tests for Independence of High-Dimensional Nonstationary Time Series","primary_cat":"math.ST","submitted_at":"2026-06-07T07:54:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A new test statistic and bootstrap for independence testing of high-dimensional nonstationary time series that avoids whitening by removing temporal dependence bias under the null.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.08303","ref_index":25,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"GeoGNN: Time Series Geo-Localization using Two-Tower Graph Neural Networks","primary_cat":"cs.LG","submitted_at":"2026-06-06T19:10:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"GeoGNN is a two-tower GNN that learns geographic cell embeddings from adjacency graphs and matches them to temporal representations via dot-product similarity plus classification, improving geolocalization accuracy by ~27% on electricity datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.05078","ref_index":68,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Attention-Augmented LSTMs for Automatic Homophonic Ciphertext Decipherment","primary_cat":"cs.CR","submitted_at":"2026-06-03T16:35:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Attention-augmented LSTMs achieve near-perfect character-level decryption of homophonic ciphers from 1500-1899 English and Swedish texts when all ciphertexts share a known code pool.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.04576","ref_index":28,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"ReSGA: A Large Tail Risk Model for Learning Value-at-Risk and Expected Shortfall","primary_cat":"stat.ML","submitted_at":"2026-06-03T08:11:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ReSGA, a large autoencoder, outperforms prior methods on joint VaR-ES forecasting for US equities and converts the edge into economic gains via a size-enhanced momentum strategy, with gains attributed to data complexity.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.04574","ref_index":20,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Dynamic Multi-Pair Trading Strategy in Cryptocurrency Markets with Deep Reinforcement Learning","primary_cat":"cs.LG","submitted_at":"2026-06-03T08:10:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A hybrid DRL system for multi-pair crypto trading with deterministic risk shielding outperforms a heuristic baseline at 10% significance on Binance futures data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.03321","ref_index":37,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Validation-Gated Multi-Agent Governance for Online Adaptation of Thermal-Hydraulic Surrogate Models under Operating-Regime Shift","primary_cat":"cs.LG","submitted_at":"2026-06-02T08:31:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A validation-gated multi-agent framework enables online adaptation of thermal-hydraulic surrogates and reduces forecast error by 19% under regime shifts on experimental loop data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.02852","ref_index":28,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"RESCAST-100K: A Comprehensive Dataset for Cross-Domain Residential Load and Indoor Temperature Forecasting","primary_cat":"cs.LG","submitted_at":"2026-06-01T20:17:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"RESCAST-100K is a large-scale benchmark dataset of simulated and real residential energy data for cross-domain load and temperature forecasting.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.01972","ref_index":59,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"AI-Based KPI Prediction Methods in Future 6G Networks: A Survey","primary_cat":"eess.SY","submitted_at":"2026-06-01T09:34:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A systematic literature survey that classifies data-driven KPI prediction methods for 6G networks across KPI type, data source, protocol stack layer, horizon, model family, and objective.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.07597","ref_index":30,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Repetition Mismatch: Why Data Mixture Experiments Don't Scale and How to Fix Them","primary_cat":"cs.LG","submitted_at":"2026-05-29T06:08:57+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Repetition rate mismatch between small-scale proxies and target budgets is the main reason data mixture experiments do not scale; a subsampling procedure that equalizes repetition rates recovers optimal mixtures from 1/16-scale experiments.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.30213","ref_index":1,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Faithful Embeddings of Irregular and Asynchronous Data for Online Log-NCDEs","primary_cat":"cs.LG","submitted_at":"2026-05-28T16:46:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Introduces a continuous injective embedding for Log-NCDEs that builds log-signatures from data increments without interpolation or imputation while preserving compact-set universality.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29467","ref_index":8,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Composing Non-Conjugate Factor Graphs with Closed-Form Variational Inference","primary_cat":"cs.LG","submitted_at":"2026-05-28T06:59:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Models composed from bilinear factor, exponential link, Gamma prior, Gaussian likelihood, and equality node admit closed-form variational message passing under mean-field factorization.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.22162","ref_index":12,"ref_count":2,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Spectra as Language: Large Language Models for Scalable Stellar Parameter and Abundance Inference","primary_cat":"astro-ph.IM","submitted_at":"2026-05-21T08:33:47+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.19589","ref_index":39,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Physics-Informed Graph Neural Network Surrogates for Turbulent Nanoparticle Dispersion in Dental Clinical Environments","primary_cat":"cs.LG","submitted_at":"2026-05-19T09:31:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"ELGIN is a graph-based physics-informed surrogate model that predicts carrier flow and polydisperse particle motion in dental aerosol scenarios, achieving lower tracking errors and 37x speedup versus full OpenFOAM CFD in a preliminary single-case test.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18865","ref_index":11,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"From Sparsity to Simplicity: Enabling Simpler Sequential Replacements via Sparse Attention Distillation","primary_cat":"cs.LG","submitted_at":"2026-05-15T07:47:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Sparsity-guided distillation enables replacing attention layers in ViTs with simpler sequential modules, with sparser layers showing smaller performance drops.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13924","ref_index":10,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Dual-axis attribution of zebrafish tectal microcircuits for energy-efficient and robust neurocomputing","primary_cat":"cs.NE","submitted_at":"2026-05-13T15:05:43+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Zebrafish tectal subcircuits are dissociated into spike-efficient information gating and feedback-like robustness stabilization, then transferred to improve ResNet efficiency and noise tolerance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12230","ref_index":10,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Neural Network-Based Virtual Wheel-Speed Sensor for Enhanced Low-Velocity State Estimation","primary_cat":"eess.SY","submitted_at":"2026-05-12T15:05:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A neural network fuses wheel and motor speed signals to cut wheel-speed estimation error by up to 85% versus the production sensor on real Volkswagen ID.7 data.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":", Lv, C., Wang, H., and Yang, S. (2018). Vehicle dynamic state estimation: state of the art schemes and perspectives.IEEE/CAA Journal of Automatica Sinica, 5(2), 418-431. doi: 10.1109/JAS.2017.7510811. Heidfeld, H., Sch¨ unemann, M., and Kasper, R. (2020). Ukf- based state and tire slip estimation for a 4wd electric vehicle.Vehicle System Dynamics, 58(10), 1479-1496. doi:10.1080/00423114.2019.1648836. Hermansdorfer, L., Trauth, R., Betz, J., and Lienkamp, M. (2020). End-to-end neural network for vehicle dynamics modeling. In2020 6th IEEE Congress on Information Science and Technology (CiSt), 407-412. doi:10.1109/CiSt49399.2021.9357196. Hochreiter, S. and Schmidhuber, J. (1997). Long short- term memory."},{"citing_arxiv_id":"2605.15216","ref_index":27,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Hardware-Software Co-Design of Scalable, Energy-Efficient Analog Recurrent Computations","primary_cat":"cs.AR","submitted_at":"2026-05-12T09:44:32+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11537","ref_index":7,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Fast MoE Inference via Predictive Prefetching and Expert Replication","primary_cat":"cs.LG","submitted_at":"2026-05-12T05:03:53+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Dynamic replication of predicted overloaded experts in MoE models achieves near-100% GPU utilization and up to 3x faster inference while retaining 90-95% of baseline performance.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"13:(Physical replicas added within cap) 14:end if 15:end for Make sure to move all experts in𝐸 𝑖 to CPU 16:end for 17:𝑀 MoE-MPMC ←𝑀 18:output =𝑀 MoE-MPMC (X𝑖 ) 19:end for which experts would be activated. The detailed algorithm with its flow is given in the algorithm 2. Our approach advances the hash building process by replacing the conventional LSTM [ 7] with a Simple Recurring Unit (SRU) [11] to predict expert activations. SRUs, compared to LSTMs, offer Algorithm 2Fast MoE Daemon Hash building using MoE-MPMC (Hash Building Thread), same as SiDA-MoE 1:foreach batchX 𝑖 do 2:foreach MoE layer𝑙do 3:foreach token𝑠do 4:Expert𝑘←ℎ 𝑙 (X𝑖 [𝑠]) 5:H 𝑖 [𝑙] [𝑠] ←Expert𝑘 6:end for 7:end for 8:EnqueueH 𝑖 9:end for"},{"citing_arxiv_id":"2605.11314","ref_index":43,"ref_count":2,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Quantifying Rodda and Graham Gait Classification from 3D Markerless Kinematics derived from a Single-view Video in a Heterogeneous Pediatric Clinical Cohort","primary_cat":"cs.CV","submitted_at":"2026-05-11T23:04:08+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"joint and limb interactions based on human skeletal structure, suffices for z-score regression. DCL [27] does away with the graph structure entirely and treats the input as a single-channel pseudo image of shape (T=90, F) and processes it through four stacked 2D convolutional layers (64 filters each, kernel size (5,1)) followed by a two-layer LSTM [43], testing whether temporal dynamics alone carry sufficient predictive signal without explicit joint relationship modeling. DCL is a widely adopted baseline for deep learning-based human activity recognition from sensor and motion-capture streams [27,44], including kinematic gait analysis in neurological conditions [39], which sets this model as a baseline model for this work."},{"citing_arxiv_id":"2605.11247","ref_index":31,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"A Proof-of-Concept Simulation-Driven Digital Twin Framework for Decision-Aware Diabetes Modeling","primary_cat":"cs.LG","submitted_at":"2026-05-11T21:10:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"A simulation-driven digital twin framework is shown to generate interpretable diabetes trajectories for decision-aware analysis by combining benchmark data with controlled synthetic scenarios.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"ically useful system must capture the evolving disease state, infer latent physiological structure, and estimate the effects of candidate interventions. Prior work has demonstrated that time-series models, including recurrent, transformer-based, and hybrid deep learning approaches, can improve short-term glucose prediction [9], [10], [23], [24], [25], [30], [31], [32]. However, predictive accuracy alone is not sufficient to meet clinical needs. The key question is not only what will happen next, but which action is most likely to lead to a safer and more desirable outcome. 2.2. Digital Twins in Healthcare Medical digital twins are commonly defined as patient- specific computational models that integrate physiological"},{"citing_arxiv_id":"2605.10341","ref_index":76,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents","primary_cat":"cs.AI","submitted_at":"2026-05-11T10:43:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"PaperFit uses rendered page images in a closed loop to diagnose and repair typesetting defects in LaTeX documents, outperforming baselines on a new benchmark of 200 papers.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"in the document automation pipeline and highlight the decisive role of structured visual closed-loop control in producing publication-ready documents. 2 Related Work 2.1 Document Layout Analysis and Automated Formatting Recent research in document automation primarily emphasizes structural formatting. Early foun- dational work in sequence modeling [ 76] and automatic evaluation [ 154] established the building 2 PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents From Code-Level Formatting to Visual Closed-Loop Typesetting Optimization Rule-based tools LaTeX source \\LaTeX{\\malfetx{vcont}beginz{consitiveresolution{mase-lonfigure{\\scompile{ \\\\sails{consmes-resolution{mansiorizations{endi}fondelle\\LaTeX}"},{"citing_arxiv_id":"2605.09905","ref_index":90,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Rethinking Random Transformers as Adaptive Sequence Smoothers for Sleep Staging","primary_cat":"cs.LG","submitted_at":"2026-05-11T02:48:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Randomly initialized Transformers act as adaptive sequence smoothers for sleep staging via a Random Attention Prior Kernel, with gains mainly from inductive bias rather than training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09795","ref_index":13,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"cantnlp@DravidianLangTech 2026: organic domain adaptation improves multi-class hope speech detection in Tulu","primary_cat":"cs.CL","submitted_at":"2026-05-10T22:32:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":2.0,"formal_verification":"none","one_line_summary":"Organic domain adaptation of XLM-RoBERTa on Tulu social media text improves multi-class hope speech detection in code-mixed Tulu on the development set.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09523","ref_index":45,"ref_count":2,"confidence":0.88,"is_internal_anchor":false,"paper_title":"HS-FNO: History-Space Fourier Neural Operator for Non-Markovian Partial Differential Equations","primary_cat":"cs.LG","submitted_at":"2026-05-10T13:14:59+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":8.0,"formal_verification":"none","one_line_summary":"HS-FNO lifts the state to include history and decomposes updates into a learned future-slice predictor plus an exact shift-append transport, yielding lower rollout errors than standard or lag-stack FNO baselines on five non-Markovian PDE families.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08696","ref_index":50,"ref_count":2,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Structured Recurrent Mixers for Massively Parallelized Sequence Generation","primary_cat":"cs.CL","submitted_at":"2026-05-09T05:07:55+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}