{"total":20,"items":[{"citing_arxiv_id":"2605.11394","ref_index":21,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Spatial Adapter: Structured Spatial Decomposition and Closed-Form Covariance for Frozen Predictors","primary_cat":"stat.ML","submitted_at":"2026-05-12T01:29:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"The Spatial Adapter equips frozen predictors with a spatially regularized orthonormal basis for residuals and derives a closed-form low-rank-plus-noise covariance for spatial prediction and kriging.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.10391","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Phoenix-VL 1.5 Medium Technical Report","primary_cat":"cs.CL","submitted_at":"2026-05-11T11:36:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Phoenix-VL 1.5 Medium is a 123B-parameter natively multimodal model that reaches state-of-the-art results on Singapore multimodal, legal, and policy benchmarks after localized training on 1T+ tokens while staying competitive on global benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08870","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TopoGeoScore: A Self-Supervised Source-Only Geometric Framework for OOD Checkpoint Selection","primary_cat":"cs.LG","submitted_at":"2026-05-09T10:46:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"TopoGeoScore combines a torsion-inspired Laplacian log-determinant, Ollivier-Ricci curvature, and higher-order topological summaries from source embeddings, with weights learned via self-supervised invariance to geometry-preserving views, to rank checkpoints by expected OOD robustness.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08311","ref_index":30,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Revitalizing the Beginning: Avoiding Storage Dependency for Model Merging in Continual Learning","primary_cat":"cs.LG","submitted_at":"2026-05-08T14:07:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"The paper proposes Trajectory Regularized Merging (TRM) to enable storage-free model merging in continual learning by optimizing in an augmented trajectory subspace with task alignment, prediction consistency, and gradient responsiveness objectives, claiming SOTA results.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.06903","ref_index":18,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MELD: Multi-Task Equilibrated Learning Detector for AI-Generated Text","primary_cat":"cs.CL","submitted_at":"2026-05-07T20:05:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MELD is a multi-task AI-text detector using auxiliary heads, uncertainty-weighted losses, EMA distillation, and pairwise ranking that reaches 99.9% TPR at 1% FPR on a new held-out benchmark while remaining competitive on the RAID leaderboard.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05136","ref_index":44,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CPCANet: Deep Unfolding Common Principal Component Analysis for Domain Generalization","primary_cat":"cs.CV","submitted_at":"2026-05-06T17:09:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CPCANet deep-unfolds Common PCA to learn domain-invariant subspaces, achieving state-of-the-art zero-shot domain generalization on standard benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.04326","ref_index":65,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A foundation model of vision, audition, and language for in-silico neuroscience","primary_cat":"q-bio.NC","submitted_at":"2026-05-05T22:13:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"TRIBE v2 is a multimodal AI model that predicts human brain activity more accurately than linear encoding models and recovers established neuroscientific findings through in-silico testing.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.02292","ref_index":14,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Momentum-Anchored Multi-Scale Fusion Model for Long-Tailed Chest X-Ray Classification","primary_cat":"cs.CV","submitted_at":"2026-05-04T07:28:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A new neural network stabilizes features for rare chest X-ray diseases via momentum anchoring and multi-scale fusion on EfficientNet, achieving 0.8682 AUC on ChestX-ray14.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.01632","ref_index":24,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Perturb and Correct: Post-Hoc Ensembles using Affine Redundancy","primary_cat":"cs.LG","submitted_at":"2026-05-02T22:48:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Perturb-and-Correct generates epistemically diverse predictors from a single pretrained network via hidden-layer perturbations followed by affine least-squares corrections that enforce agreement on calibration data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.20985","ref_index":33,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Differentially Private Model Merging","primary_cat":"cs.LG","submitted_at":"2026-04-22T18:13:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Post-processing via random selection or linear combination generates differentially private models for arbitrary privacy parameters from pre-trained models on the same dataset.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.20518","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Using Graph Neural Networks for hadronic clustering and to reduce beam background in the Belle~II electromagnetic calorimeter","primary_cat":"hep-ex","submitted_at":"2026-04-22T12:59:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Graph neural networks can identify and remove unwanted beam background depositions in the Belle II calorimeter to improve hadronic clustering and reduce fake photon clusters.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.22853","ref_index":27,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"FastAT Benchmark: A Comprehensive Framework for Fair Evaluation of Fast Adversarial Training Methods","primary_cat":"cs.CV","submitted_at":"2026-04-22T09:11:34+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"The FastAT Benchmark standardizes evaluation of over twenty fast adversarial training methods under unified conditions, showing that well-designed single-step approaches can match or exceed PGD-AT robustness at lower training cost on CIFAR-10, CIFAR-100, and Tiny-ImageNet.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.19740","ref_index":36,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Generalization at the Edge of Stability","primary_cat":"cs.LG","submitted_at":"2026-04-21T17:59:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Training at the edge of stability causes neural network optimizers to converge on fractal attractors whose effective dimension, measured via a new sharpness dimension from the Hessian spectrum, bounds generalization error in a way not captured by prior trace or norm measures.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.17476","ref_index":188,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Privatar: Scalable Privacy-preserving Multi-user VR via Secure Offloading","primary_cat":"cs.CR","submitted_at":"2026-04-19T15:07:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Privatar uses horizontal frequency partitioning and distribution-aware minimal perturbation to enable private offloading of VR avatar reconstruction, supporting 2.37x more users with modest overhead.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.15297","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Benchmarking Optimizers for MLPs in Tabular Deep Learning","primary_cat":"cs.LG","submitted_at":"2026-04-16T17:57:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Muon optimizer outperforms AdamW across 17 tabular datasets when training MLPs under a shared protocol.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.12018","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LLMs Struggle with Abstract Meaning Comprehension More Than Expected","primary_cat":"cs.CL","submitted_at":"2026-04-13T20:03:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"LLMs struggle with abstract meaning comprehension on SemEval-2021 Task 4 more than fine-tuned models, and a new bidirectional attention classifier yields small accuracy gains of 3-4%.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.09369","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Biologically-Grounded Multi-Encoder Architectures as Developability Oracles for Antibody Design","primary_cat":"q-bio.BM","submitted_at":"2026-04-10T14:39:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"CrossAbSense oracles using frozen PLM encoders plus self- or cross-attention decoders improve prediction accuracy by 12-20% on three of five developability assays for therapeutic IgGs, with architecture choices revealing that aggregation depends on single-chain signals while stability requires heavy","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.08358","ref_index":76,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Scalable Neural Decoders for Practical Fault-Tolerant Quantum Computation","primary_cat":"quant-ph","submitted_at":"2026-04-09T15:21:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Neural decoder for quantum LDPC codes achieves ~10^{-10} logical error at 0.1% physical error with 17x improvement and high throughput, enabling practical fault tolerance at modest code sizes.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.02719","ref_index":32,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MOMO: Mars Orbital Model Foundation Model for Mars Orbital Applications","primary_cat":"cs.CV","submitted_at":"2026-04-03T04:22:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"MOMO merges sensor-specific models from three Mars orbital instruments at matched validation loss stages to form a foundation model that outperforms ImageNet, Earth observation, sensor-specific, and supervised baselines on nine Mars-Bench tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2309.16588","ref_index":166,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Vision Transformers Need Registers","primary_cat":"cs.CV","submitted_at":"2023-09-28T16:45:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Adding register tokens to Vision Transformers eliminates high-norm background artifacts and raises state-of-the-art performance on dense visual prediction tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}