{"total":158,"items":[{"citing_arxiv_id":"2606.27634","ref_index":8,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Continual Learning for Sequential Personalization of Small Language Models: A Stability Monitoring Analysis","primary_cat":"cs.LG","submitted_at":"2026-06-26T01:16:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Checkpoint monitoring during sequential LoRA adaptation of SLMs reveals instability patterns via reference set diagnostics that standard task metrics can miss.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.26334","ref_index":29,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Debiasing the Observed Fast Radio Burst Population with the CHIME/FRB Selection Function","primary_cat":"astro-ph.HE","submitted_at":"2026-06-24T19:21:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Analysis of CHIME/FRB Catalog 2 with synthetic injections and a multidimensional selection function yields evidence for a slight downturn in the intrinsic scattering timescale distribution, though flat or rising distributions remain possible.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.25045","ref_index":60,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"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":"2606.24807","ref_index":34,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"The Impact of Host Galaxy Properties on Supernova Classification with Hierarchical Labels","primary_cat":"astro-ph.IM","submitted_at":"2026-06-23T16:55:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Host galaxy properties enable >90% pure Type Ia samples from photometry alone and improve classification accuracy when redshift is unavailable, via a new hierarchical cross-entropy objective.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.23478","ref_index":45,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"ffortissimo: A Freeform Forward-Modeling Pipeline for High-Contrast Images of Circumstellar Disks Based on Automatic Differentiation","primary_cat":"astro-ph.IM","submitted_at":"2026-06-22T15:25:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"ffortissimo is a JAX-based freeform forward-modeling pipeline that fits complex dust distributions and infers scattering properties in KLIP-reduced images of circumstellar disks such as HR 4796A.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.23458","ref_index":27,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"A matrix-free, differentiable PyTorch solver for phase-field fracture: Formulation, benchmarks, and inverse analysis","primary_cat":"cs.CE","submitted_at":"2026-06-22T15:06:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A matrix-free, GPU-compatible PyTorch implementation of phase-field fracture with explicit dynamics, custom differentiable implicit damage solve, benchmarks on dynamic and quasi-static cases, and inverse recovery of fracture energy G_c via L-BFGS.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.11870","ref_index":22,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Modelling magnetic material properties with uncertainty-aware neural networks","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-06-10T09:47:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Uncertainty-aware neural networks using Gaussian negative log-likelihood and dropout are applied to predict intrinsic magnetic properties and coercivity via graph neural networks in permanent magnet research.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.06174","ref_index":60,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Learning to model pediatric asthma exacerbation from multiple risk factors: a case study in coastal Virginia","primary_cat":"cs.LG","submitted_at":"2026-06-04T13:47:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A case study develops a sparse dictionary learning approach to model pediatric asthma exacerbations from multiple risk factors and reports consensus on relative risks across statistical and machine learning models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.05103","ref_index":23,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Identifying Gems from Roman RAPIDly","primary_cat":"cs.LG","submitted_at":"2026-06-03T17:06:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Machine learning models RuBR_comb, RuBR_loc, and RuBR_DA for real-bogus classification of transients using combined simulated data and domain adaptation for the Roman RAPID pipeline.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.03077","ref_index":37,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Libra: Efficient Resource Management for Agentic RL Post-Training","primary_cat":"cs.LG","submitted_at":"2026-06-02T03:09:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Libra optimizes GPU allocation across rollout and training in agentic RL via an elastic hybrid pool and C-MLFQ scheduler based on tool-return causal signals, claiming up to 3.0x throughput and 2.5x faster reward convergence on 48 A800 GPUs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.00219","ref_index":176,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"21cmEMUv3: a hybrid diffusion-LSTM emulator of 21cmFAST summary observables","primary_cat":"astro-ph.CO","submitted_at":"2026-05-29T18:00:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"21cmEMUv3 emulates the cylindrical 21cm power spectrum via score-based diffusion and six other 21cmFAST observables via LSTM networks at sub-percent accuracy, then uses the emulator to infer a lower limit on soft-band X-ray luminosity from HERA data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.30429","ref_index":86,"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":"2605.29911","ref_index":23,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Reducing Experimental Testing in Space Propulsion Film Cooling Analyses by Pixelwise Generative Image Interpolation","primary_cat":"cs.LG","submitted_at":"2026-05-28T13:29:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A feed-forward neural network with positional encoding generates film cooling images from 30% fewer experimental measurements while achieving RMSE below 8% and SSIM above 93%.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29798","ref_index":8,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Low-Magnification SEM May Suffice: Interpretable Deep Learning for Multi-Scale Fracture-Cause Classification in Zirconia-Toughened Alumina","primary_cat":"cs.CV","submitted_at":"2026-05-28T11:47:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A fine-tuned ViT on 8493 SEM images classifies fracture causes in zirconia-toughened alumina at 0.907 accuracy and 0.888 macro-F1, with comparable performance at 50x versus higher magnifications.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29505","ref_index":22,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"ESAM++: Efficient Online 3D Perception on the Edge","primary_cat":"cs.CV","submitted_at":"2026-05-28T07:29:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"ESAM++ introduces a 3D Sparse Feature Pyramid Network for efficient online 3D scene perception on edge devices, claiming competitive accuracy with up to 3x faster inference and 2x smaller model size than ESAM on four benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29109","ref_index":28,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"First steps towards gauge-independent vortex identification through machine learning","primary_cat":"hep-lat","submitted_at":"2026-05-27T21:17:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A neural network trained on 2D SU(2) lattices with inserted thin Z2 vortices, after random gauge transformations, noise, and cooling, can locate center vortices at moderate visibility levels and scales via tiling.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29039","ref_index":17,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Kolmogorov--Arnold Networks as Implicit Regularizers: Noise Robustness and Interpretability for Stellar Classification","primary_cat":"astro-ph.IM","submitted_at":"2026-05-27T19:38:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"KAN noise robustness in star/galaxy/quasar classification arises from implicit C2-spline regularization rather than architecture, as weight-decay-tuned MLPs match performance on SDSS and DESI data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.27231","ref_index":54,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"A Fast Method to Compute Scalar Induced Gravitational Waves on a Lattice with Primordial Non-Gaussianities","primary_cat":"astro-ph.CO","submitted_at":"2026-05-26T16:11:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A new lattice method recasts SIGW integrals as FFT convolutions to compute fully non-Gaussian spectra in seconds with ~10% error on a radiation-dominated background.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.23538","ref_index":39,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Scalable Dark Siren Cosmology with gwcosmo: GPU Acceleration, Validation and Systematics","primary_cat":"astro-ph.CO","submitted_at":"2026-05-22T12:00:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"GPU-accelerated gwcosmo enables 1000x faster dark-siren cosmological analyses for large GW catalogs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.22199","ref_index":49,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Equation of State at High Baryon Densities from a Thermodynamically Informed Neural Network","primary_cat":"hep-ph","submitted_at":"2026-05-21T09:03:18+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":"2605.21606","ref_index":27,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning","primary_cat":"cs.LG","submitted_at":"2026-05-20T18:14:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Position-Weighted On-Policy Self-Distillation (PW-OPSD) weights later tokens more heavily after a diagnostic shows position predicts teacher reliability better than entropy, yielding +1.0 and +1.1 Avg@12 gains on AIME 2024/2025.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.19589","ref_index":45,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"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":"2605.19520","ref_index":89,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"A Value-added Physical Properties Catalog for Low-redshift Galaxies from DESI Legacy Imaging Surveys DR10","primary_cat":"astro-ph.GA","submitted_at":"2026-05-19T08:21:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A multimodal neural network trained on MPA-JHU references produces SFR, stellar mass, and metallicity estimates for 547 million low-redshift galaxies in DESI LS DR10.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18658","ref_index":58,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Universal Jaynes-Cummings Control of an Oscillator","primary_cat":"quant-ph","submitted_at":"2026-05-18T17:04:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Experimental demonstration of universal qudit control on a cavity oscillator via compiled Jaynes-Cummings gates with a transmon ancilla, reaching 96% mean post-selected process fidelity for qutrit gates.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17133","ref_index":34,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"CAM-VFD: Cross-Attention Multimodal Video Forgery Detection","primary_cat":"cs.CV","submitted_at":"2026-05-16T19:46:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CAM-VFD detects video forgeries by using cross-attention to identify contradictions between CLIP appearance, VideoMAE motion, and MiDaS depth features.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.16468","ref_index":63,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Mechanistically Interpretable Neural Encoding Reveals Fine-Grained Functional Selectivity in Human Visual Cortex","primary_cat":"cs.CV","submitted_at":"2026-05-15T11:28:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MINE uses mechanistic interpretability on language-aligned image representations to generate per-voxel feature descriptions, validated via image generation and counterfactual edits that causally shift brain activation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.15752","ref_index":51,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Forecasting megaelectron-volt electron flux in the Earth's outer radiation belt using supervised machine learning algorithms and a timeseries foundation model","primary_cat":"astro-ph.IM","submitted_at":"2026-05-15T09:13:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Hybrid TimesFM plus ridge regression on covariates forecasts 1-MeV electron flux with average R² of 0.9 on out-of-sample 2024 data, outperforming linear regression, CNN, LSTM and Transformer models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.15558","ref_index":6,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Text-RSIR: A Text-Guided Framework for Efficient Remote Sensing Image Transmission and Reconstruction","primary_cat":"eess.IV","submitted_at":"2026-05-15T02:54:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A text-guided framework for remote sensing image transmission uses low-res images and compact text to reduce data volume to 2%, with text-conditioned reconstruction achieving PSNRs of 16.36-27.41 dB on tested datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.16454","ref_index":23,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"QuChaTeR: A Hybrid Quantum-Chaotic Temporal Framework for Earthquake Prediction","primary_cat":"cs.LG","submitted_at":"2026-05-14T13:40:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"QuChaTeR hybridizes chaotic maps and variational quantum circuits with recurrent networks and wavelets to achieve faster convergence and better performance than classical and quantum-inspired baselines on real seismic datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.14308","ref_index":95,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Reconstructing the Stripping History of the Sagittarius Stream with Neural Networks","primary_cat":"astro-ph.GA","submitted_at":"2026-05-14T03:21:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A neural network trained on simulations infers stripping times for Sagittarius stream stars from phase-space data, measuring a 0.3 dex/Gyr metallicity gradient and estimating ages for globular clusters such as Pal 12 and NGC 2419.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13614","ref_index":88,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Search for pair production of additional neutral scalars within the Inert Doublet Model in a final state with two electrons or two muons in proton-proton collisions at $\\sqrt{s}$ = 13 TeV and 13.6 TeV","primary_cat":"hep-ex","submitted_at":"2026-05-13T14:45:01+00:00","verdict":"ACCEPT","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"No significant excess found; new exclusion limits reach m_H = 108 GeV for m_H - m_A = 78 GeV in the Inert Doublet Model.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"The signal samples are also reweighted such that the sum of weights for each sam- ple is equal. During training, the signal samples are passed through the pNN with the IDM parameters(m H,m A)at which they were simulated. The background samples are randomly assigned(m H,m A)values from the set of signal(m H,m A)values used in the training. The pNN is implemented using PYTORCH[88], and consists of a feedforward network with six layers, each layer containing 60 hidden units and an ELU activation function [89], where the architecture was determined over a grid search of different hyperparameters. The model is trained using the Adam optimiser [90] with a learning rate of 10 −4 to minimise the weighted binary cross-entropy loss function [91]."},{"citing_arxiv_id":"2605.13131","ref_index":44,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"ERPPO: Entropy Regularization-based Proximal Policy Optimization","primary_cat":"cs.LG","submitted_at":"2026-05-13T08:01:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"ERPPO adds a DSA-based ambiguity estimator to MAPPO and switches between L1 and L2 entropy regularization to improve exploration and stability in non-stationary multi-dimensional observations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12503","ref_index":59,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Unveiling Hidden Lyman Alpha Emitters in the DESI DR1 Data","primary_cat":"astro-ph.GA","submitted_at":"2026-05-12T17:59:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A CNN detects 19,685 LAEs at z=2-3.5 in DESI DR1 spectra with 95% purity and completeness.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12388","ref_index":53,"ref_count":2,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Events as Triggers for Behavioral Diversity in Multi-Agent Reinforcement Learning","primary_cat":"cs.MA","submitted_at":"2026-05-12T16:51:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Events trigger on-the-fly LoRA module generation via hypernetworks over a shared team policy in MARL, paired with a Neural Manifold Diversity metric, enabling sequential role reassignment while preserving reward maximization.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13899","ref_index":33,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Frequency-Space Mechanics: A Sequence and Coordinate-Free Representation for Protein Function Prediction","primary_cat":"q-bio.BM","submitted_at":"2026-05-12T14:29:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Vibrational mode graphs from molecular dynamics enable sequence-free protein function prediction via graph neural networks, with entrainment improving signals for collective dynamics.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18807","ref_index":15,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Block-Based Double Decoders","primary_cat":"cs.LG","submitted_at":"2026-05-11T22:41:03+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":"2605.11274","ref_index":35,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"End-to-End Population Inference from Gravitational-Wave Strain using Transformers","primary_cat":"gr-qc","submitted_at":"2026-05-11T21:54:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Dingo-Pop uses a transformer to perform amortized, end-to-end population inference from GW strain data in seconds, bypassing per-event Monte Carlo sampling.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"and B. Sch¨ olkopf, Real-Time Gravitational Wave Science with Neural Posterior Estimation, Phys. Rev. Lett.127, 241103 (2021), arXiv:2106.12594 [gr-qc]. [34] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, Attention Is All You Need, arXiv e-prints , arXiv:1706.03762 (2017), arXiv:1706.03762 [cs.CL]. [35] A. Paszkeet al., PyTorch: An Imperative Style, High-Performance Deep Learning Library, (2019), arXiv:1912.01703 [cs.LG]. [36] M. Gloeckler, M. Deistler, C. Weilbach, F. Wood, and 7 J. H. Macke, All-in-one simulation-based inference, arXiv preprint arXiv:2404.09636 (2024). [37] J.-Q. Jiang, H.-L. Huang, J. He, Y.-T. Wang, and Y.-S. Piao, A fast deep-learning approach to probing primor-"},{"citing_arxiv_id":"2605.08975","ref_index":29,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Latency Analysis and Optimization of Alpamayo 1 via Efficient Trajectory Generation","primary_cat":"cs.AI","submitted_at":"2026-05-09T14:34:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Redesigning Alpamayo 1 to single-reasoning and optimizing diffusion action generation cuts inference latency by 69.23% while preserving trajectory diversity and prediction quality.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"linear projection head derived from the Qwen3-VL language model. The token sampler then selects the next token from the probability distribution derived from the logits produced by the language decoder. While the official release [7] refers to the language decoder as the Cosmos-Reason 1 [28] backbone, the two may not share identical weights, as Cosmos-Reason 1 is built on Qwen2.5-VL [29] whereas the open-source release of Alpamayo is built on Qwen3-VL. The language decoder operates in two distinct phases: prefillanddecode. In the prefill phase, all input embeddings are processed in parallel through the36transformer blocks, building an initial understanding of the full input context. In the decode phase, CoT reasoning tokens are generated autore-"},{"citing_arxiv_id":"2605.08808","ref_index":38,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Curvature-Aware Captioning:Leveraging Geodesic Attention for 3D Scene Understanding","primary_cat":"cs.CV","submitted_at":"2026-05-09T08:54:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A new framework combines self-attention on the Oblique manifold with bidirectional geodesic cross-attention on the Lorentz hyperboloid to improve both localization accuracy and descriptive coherence in 3D dense captioning.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"720 epochs of joint training on ScanRefer and Nr3D apply cross-entropy loss with a batch size of 8, with fixed10 −6 detector learning rate while decaying the caption head from 10−4 to10 −6. The final stage refines the caption head via SCST [42] for 180 epochs at fixed10 −6 learning rate and batch size 2, freezing detector parameters. Implemented in PyTorch [38], our framework exhibits distinct performance characteristics across its three training phases. Table 2 summarizes the basic configurations for different training phases. During the pre-training stage, the average iteration time is 0.878s with a statistical sample size of 16,635 and memory consumption of approximately 18GB, achieving a per-sample computational complexity of 10."},{"citing_arxiv_id":"2605.07775","ref_index":92,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"POETS: Uncertainty-Aware LLM Optimization via Compute-Efficient Policy Ensembles","primary_cat":"cs.LG","submitted_at":"2026-05-08T14:16:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"POETS uses compute-efficient LLM policy ensembles to implicitly perform KL-regularized Thompson sampling, delivering O(sqrt(T gamma_T)) regret bounds and state-of-the-art sample efficiency in scientific discovery tasks such as protein search and quantum circuit design.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.07611","ref_index":9,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Compositional Quantum Heuristics for Max-Clique Detection","primary_cat":"quant-ph","submitted_at":"2026-05-08T11:38:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Compositional quantum circuits with symmetry-induced invariant losses produce trainable equivariant quantum GNNs that generalize on max-clique problems and improve hybrid recursive search accuracy and scalability.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08289","ref_index":102,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"What If We Let Forecasting Forget? A Sparse Bottleneck for Cross-Variable Dependencies","primary_cat":"cs.LG","submitted_at":"2026-05-08T08:16:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MS-FLOW uses a capacity-limited sparse routing mechanism to model only critical inter-variable dependencies in time series data, achieving state-of-the-art accuracy on 12 benchmarks with fewer but more reliable connections.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.06992","ref_index":87,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Why Does Agentic Safety Fail to Generalize Across Tasks?","primary_cat":"cs.LG","submitted_at":"2026-05-07T22:16:03+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Agentic safety fails to generalize across tasks because the task-to-safe-controller mapping has a higher Lipschitz constant than the task-to-controller mapping alone, as proven in linear-quadratic control and demonstrated in quadcopter and LLM experiments.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"arXiv preprint arXiv:1810.12282, 2018. [86] Jacopo Panerati, Hehui Zheng, SiQi Zhou, James Xu, Amanda Prorok, and Angela P Schoellig. Learning to fly-a gym environment with pybullet physics for reinforcement learning of multi-agent quadcopter control. In2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 7512-7519. IEEE, 2021. [87] Adam Paszke. Pytorch: An imperative style, high-performance deep learning library.arXiv preprint arXiv:1912.01703, 2019. 14 [88] Michel Plancherel. Contribution à l'étude de la représentation d'une fonction arbitraire par des intégrales définies.Rendiconti del Circolo Matematico di Palermo, 30:289-335, 1910. [89] Tomaso Poggio, Kenji Kawaguchi, Qianli Liao, Brando Miranda, Lorenzo Rosasco, Xavier Boix, Jack"},{"citing_arxiv_id":"2605.05907","ref_index":69,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Decoding Alignment without Encoding Alignment: A critique of similarity analysis in neuroscience","primary_cat":"q-bio.NC","submitted_at":"2026-05-07T09:17:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Decoding alignment metrics can remain high and unchanged even when encoding manifold topology is causally altered, so they do not imply similar function or computation across neural populations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.03660","ref_index":42,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Stage Light is Sequence$^2$: Multi-Light Control via Imitation Learning","primary_cat":"cs.MM","submitted_at":"2026-05-05T11:41:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SeqLight maps music to multi-light HSV control via SkipBART for global color prediction followed by hybrid imitation learning in a goal-conditioned MDP to decompose colors across lights.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.04115","ref_index":55,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Learning reveals invisible structure in low-rank RNNs","primary_cat":"cs.LG","submitted_at":"2026-05-05T07:41:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Learning in low-rank RNNs reduces to an exact low-dimensional ODE system in overlap space, where loss-invisible overlaps encode training history without affecting function.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.02723","ref_index":242,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Euclid preparation. CosmoPostProcess: A simulation calibrated framework for weak lensing selection bias in richness-selected galaxy clusters","primary_cat":"astro-ph.CO","submitted_at":"2026-05-04T15:22:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CosmoPostProcess delivers simulation-calibrated radial corrections for projection-induced selection bias (20-40% amplitude near 1 h^{-1} Mpc) and baryonic effects in Euclid richness-selected cluster weak lensing profiles.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.02614","ref_index":36,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Validation of an AI-based end-to-end model for prostate pathology using long-term archived routine samples","primary_cat":"cs.CV","submitted_at":"2026-05-04T14:02:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"GleasonAI achieves quadratic-weighted kappa of 0.86 on ISUP grading of 10,366 long-term archived prostate biopsy cores, with performance stable over 17 years and a clear prognostic gradient for cancer-specific mortality.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.01209","ref_index":45,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"ClarifySTL: An Interactive LLM Agent Framework for STL Transformation through Requirements Clarification","primary_cat":"cs.SE","submitted_at":"2026-05-02T02:55:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ClarifySTL uses LLM agents to interactively detect and resolve vagueness and ambiguity in natural language requirements via clarification queries before generating STL formulas, with evaluations on existing and new benchmarks showing effectiveness.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00650","ref_index":22,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"AdaMeZO: Adam-style Zeroth-Order Optimizer for LLM Fine-tuning Without Maintaining the Moments","primary_cat":"cs.LG","submitted_at":"2026-05-01T13:31:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"AdaMeZO adapts Adam moment estimates to zeroth-order LLM fine-tuning without extra memory storage, outperforming MeZO with up to 70% fewer forward passes.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}