Using GPR-reconstructed angular diameter distances from DESI DR2 BAO and H0LiCOW time-delay lenses, the paper measures γ_PPN = 0.93^{+0.16}_{-0.17} and r_d = 136.36^{+5.14}_{-3.20} Mpc simultaneously without cosmological or gravity assumptions, consistent with GR within 1σ.
Learning- Based Link Anomaly Detection in Continuous-Time Dynamic Graphs
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 3
baseline 1
citation-polarity summary
verdicts
UNVERDICTED 10representative citing papers
MADreMIA amplifies membership inference signals by showing that memorized samples maintain higher coherence and slower degradation in chained regeneration trajectories than non-members.
PACE dynamically selects execution horizons for action chunks in robot policies by detecting low-speed transition points in predicted speed profiles, raising success rates from 57.8% to 64.2% on 50 simulation tasks and from 50.7% to 70.4% in real-robot tests.
GRASP detects anomalies in system provenance graphs via self-supervised executable prediction from two-hop neighborhoods, outperforming prior PIDS on DARPA datasets by identifying all documented attacks where behaviors are learnable plus additional unlabeled suspicious activity.
LTBs-KAN delivers linear-time B-spline evaluation in KANs plus parameter reduction via product-of-sums factorization, with competitive results on MNIST, Fashion-MNIST, and CIFAR-10.
Fine-grained fusion and adaptive scheduling in SSMs deliver up to 4.8x speedup and 10x lower on-chip memory, enabling a fusion-aware accelerator with 1.78x higher performance than MARCA at equal area.
For every prime p ≡ 3 mod 4, the truncated Legendre-symbol determinant evaluates to floor((p-2)/3)^2 x via reduction to Chapman's matrix inverse using Vsemirnov factorization and Schur-Pfaffian identity.
Bayesian-ARGOS is a hybrid frequentist-Bayesian method that discovers equations from limited noisy observations more efficiently than SINDy or bootstrap-ARGOS while adding uncertainty quantification.
Sequence models on EHR data from a Swedish heart failure cohort achieve AUPRCs of 0.555 to 0.854 for one-year instability and mortality predictions and support four care pathways.
PaliGemma is an open 3B VLM based on SigLIP and Gemma that achieves strong performance on nearly 40 diverse open-world tasks including benchmarks, remote-sensing, and segmentation.
citing papers explorer
-
PACE: Phase-Aware Chunk Execution for Robot Policies with Action Chunking
PACE dynamically selects execution horizons for action chunks in robot policies by detecting low-speed transition points in predicted speed profiles, raising success rates from 57.8% to 64.2% on 50 simulation tasks and from 50.7% to 70.4% in real-robot tests.