{"total":22,"items":[{"citing_arxiv_id":"2605.13614","ref_index":89,"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":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11098","ref_index":68,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"AffectCodec: Emotion-Preserving Neural Speech Codec for Expressive Speech Modeling","primary_cat":"cs.SD","submitted_at":"2026-05-11T18:04:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"AffectCodec is an emotion-guided neural speech codec that preserves emotional cues during quantization while maintaining semantic fidelity and prosodic naturalness.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.10577","ref_index":61,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Training continuously-coupled reconfigurable photonic chips with quantum machine learning","primary_cat":"quant-ph","submitted_at":"2026-05-11T13:49:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A black-box machine learning technique trains continuously-coupled photonic waveguide arrays to implement target unitaries using limited single- and two-photon measurements without requiring detailed internal models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09408","ref_index":23,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"GravityGraphSAGE: Link Prediction in Directed Attributed Graphs","primary_cat":"cs.LG","submitted_at":"2026-05-10T08:19:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"GravityGraphSAGE adapts GraphSAGE with a gravity-inspired decoder to outperform prior graph deep learning methods on directed link prediction across citation networks and 16 real-world graphs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.06593","ref_index":46,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"ReActor: Reinforcement Learning for Physics-Aware Motion Retargeting","primary_cat":"cs.RO","submitted_at":"2026-05-07T17:20:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"ReActor jointly optimizes motion retargeting and RL policy training with an approximate gradient to generate physically consistent robot motions from human references using only sparse body correspondences.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08183","ref_index":39,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Sparsity Hurts: Simple Linear Adapter Can Boost Generalized Category Discovery","primary_cat":"cs.CV","submitted_at":"2026-05-05T10:14:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"LAGCD inserts residual linear adapters into each ViT block plus a distribution alignment loss to improve generalized category discovery by increasing model flexibility while reducing bias between seen and novel classes.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.02591","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Universal Smoothness via Bernstein Polynomials: A Constructive Approximation Approach for Activation Functions","primary_cat":"cs.AI","submitted_at":"2026-05-04T13:38:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"BerLU constructs a C1-differentiable activation with Lipschitz constant 1 via Bernstein polynomial approximation, showing better performance and efficiency than baselines on image classification with ViTs and CNNs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.01990","ref_index":25,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Constraints on the baryon density from fast radio bursts using a non-parametric reconstruction of the Hubble parameter","primary_cat":"astro-ph.CO","submitted_at":"2026-05-03T17:48:16+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"FRB dispersion measures combined with non-parametric H(z) reconstruction yield Ω_b h² = 0.02236 ± 0.00090, agreeing with BBN and Planck CMB to within 0.05%.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.01702","ref_index":36,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Floating-Point Networks with Automatic Differentiation Can Represent Almost All Floating-Point Functions and Their Gradients","primary_cat":"cs.LG","submitted_at":"2026-05-03T04:06:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"Floating-point neural networks with automatic differentiation can represent arbitrary floating-point functions and their gradients under mild conditions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.24050","ref_index":34,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A sound-horizon-free measurement of the Hubble constant from DESI DR2 baryon acoustic oscillations using artificial neural networks","primary_cat":"astro-ph.CO","submitted_at":"2026-04-27T05:12:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Neural network reconstruction of DESI DR2 BAO, SNe Ia, and cosmic chronometer data gives H0 = 71.5 ± 2.2 km s^{-1} Mpc^{-1} without sound horizon input.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.22372","ref_index":64,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Testing $\\Lambda$CDM with ANN-Reconstructed Expansion History from Cosmic Chronometers","primary_cat":"astro-ph.CO","submitted_at":"2026-04-24T09:06:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"The ANN-reconstructed Hubble parameter H(z) from cosmic chronometers aligns with Lambda CDM predictions within uncertainties.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.21677","ref_index":3,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Geometric Monomial (GEM): a family of rational 2N-differentiable activation functions","primary_cat":"cs.LG","submitted_at":"2026-04-23T13:42:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"GEM is a new family of C^{2N}-smooth rational activation functions with variants that achieve performance on par with or exceeding GELU on ResNet, GPT-2, and BERT benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.19344","ref_index":34,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Quadruped Parkour Learning: Sparsely Gated Mixture of Experts with Visual Input","primary_cat":"cs.RO","submitted_at":"2026-04-21T11:27:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Sparsely gated MoE policies double the success rate of a real Unitree Go2 quadruped on large-obstacle parkour versus matched-active-parameter MLP baselines while cutting inference time compared with a scaled-up MLP.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.16232","ref_index":43,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Neuro-Symbolic ODE Discovery with Latent Grammar Flow","primary_cat":"cs.LG","submitted_at":"2026-04-17T16:46:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Latent Grammar Flow discovers ODEs by placing grammar-based equation representations in a discrete latent space, using a behavioral loss to cluster similar equations, and sampling via a discrete flow model guided by data fit and constraints.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.14270","ref_index":92,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Fast neural network surrogate for multimodal effective-one-body gravitational waveforms from generically precessing compact binaries","primary_cat":"gr-qc","submitted_at":"2026-04-15T18:00:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Neural network surrogate approximates precessing compact binary gravitational waveforms up to 1000x faster than the base EOB model with validated accuracy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2310.16828","ref_index":177,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","primary_cat":"cs.LG","submitted_at":"2023-10-25T17:57:07+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"TD-MPC2 scales an implicit world-model RL method to a 317M-parameter agent that masters 80 tasks across four domains with a single hyperparameter configuration.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2210.13438","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"High Fidelity Neural Audio Compression","primary_cat":"eess.AS","submitted_at":"2022-10-24T17:52:02+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":7.0,"formal_verification":"none","one_line_summary":"EnCodec is an end-to-end trained streaming neural audio codec that uses a single multiscale spectrogram discriminator and a gradient-normalizing loss balancer to achieve higher fidelity than prior methods at the same bitrates for 24 kHz mono and 48 kHz stereo audio.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2209.15571","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Building Normalizing Flows with Stochastic Interpolants","primary_cat":"cs.LG","submitted_at":"2022-09-30T16:30:31+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":8.0,"formal_verification":"none","one_line_summary":"Normalizing flows are constructed by learning the velocity of a stochastic interpolant via a quadratic loss derived from its probability current, yielding an efficient ODE-based alternative to diffusion models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2009.14794","ref_index":118,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Rethinking Attention with Performers","primary_cat":"cs.LG","submitted_at":"2020-09-30T17:09:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Performers approximate full-rank softmax attention in Transformers via FAVOR+ random features for linear complexity, with theoretical guarantees of unbiased estimation and competitive results on pixel, text, and protein tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1912.01603","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Dream to Control: Learning Behaviors by Latent Imagination","primary_cat":"cs.LG","submitted_at":"2019-12-03T18:57:16+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Dreamer learns to control from images by imagining and optimizing behaviors in a learned latent world model, outperforming prior methods on 20 visual tasks in data efficiency and final performance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1710.05941","ref_index":3,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Searching for Activation Functions","primary_cat":"cs.NE","submitted_at":"2017-10-16T18:05:45+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Automated search discovers Swish activation f(x) = x * sigmoid(βx) that improves top-1 ImageNet accuracy over ReLU by 0.9% on Mobile NASNet-A and 0.6% on Inception-ResNet-v2.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1605.07146","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Wide Residual Networks","primary_cat":"cs.CV","submitted_at":"2016-05-23T19:27:13+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Wide residual networks achieve higher accuracy and faster training than very deep thin residual networks by increasing width and decreasing depth, setting new state-of-the-art results on CIFAR, SVHN, and ImageNet.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}