{"total":15,"items":[{"citing_arxiv_id":"2606.24781","ref_index":20,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Assessing Distribution Shift in Human Activity Recognition for Domain Generalization","primary_cat":"cs.AI","submitted_at":"2026-06-23T16:40:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Evaluates four distribution shifts in sensor-based HAR, finds diversity shifts dominate, and shows 28 DG methods only marginally beat ERM while releasing open benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.23758","ref_index":98,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Exploring Dualistic Meta-Learning to Enhance Domain Generalization in Open Set Scenarios","primary_cat":"cs.LG","submitted_at":"2026-06-22T08:58:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"MEDIC uses dualistic meta-learning with joint domain-class matching to balance decision boundaries in open set domain generalization.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.12930","ref_index":29,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Is Spurious Correlation Removal Always Learnable?","primary_cat":"cs.LG","submitted_at":"2026-06-11T05:49:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Conditional computational barrier exists for learning k=1 invariant subspaces in samplable multi-environment instances under sparse recovery hardness; minimax risk is Theta(k(d-k)/(n|E|)) with phase transition at n* ~ k(d-k)/(|E| gamma^2).","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.12200","ref_index":70,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Implicit Neural Representations of Individual Behavior","primary_cat":"cs.LG","submitted_at":"2026-06-10T15:19:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Behavioral INR adapts INRs to behavior by mapping states to actions with FiLM-modulated episode latents for self-supervised policy inference in unlabeled data, with new policy OOD definitions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17373","ref_index":16,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamics","primary_cat":"cs.LG","submitted_at":"2026-05-17T10:30:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"FML-Bench shows a simple greedy hill-climber nearly matches tree search on dense-opportunity tasks while an adaptive agent that broadens search on stagnation outperforms six baselines across 18 tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.14654","ref_index":147,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Beyond Instance-Level Self-Supervision in 3D Multi-Modal Medical Imaging","primary_cat":"cs.CV","submitted_at":"2026-05-14T10:10:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A self-supervised approach uses consistent spatial relationships of anatomical structures across patients to improve 3D multi-modal medical image representations, yielding modest gains on segmentation and classification tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11764","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Decomposing the Generalization Gap in PROTAC Activity Prediction: Variance Attribution and the Inter-Laboratory Ceiling","primary_cat":"cs.LG","submitted_at":"2026-05-12T08:35:02+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Inter-laboratory measurement variance dominates the generalization gap in PROTAC activity prediction, capping LOTO AUROC near 0.67 across models and architectures.","context_count":1,"top_context_role":"background","top_context_polarity":"unclear","context_text":"Saro Passaro, Gabriele Corso, Jeremy Wohlwend, Mateo Reveiz, Stephan Thaler, Vignesh Ram Somnath, Noah Getz, Tally Portnoi, Julien Roy, Hannes Stark, et al. Boltz-2: Towards accurate and efficient binding affinity prediction.BioRxiv, 2025. Judea Pearl and Elias Bareinboim. External validity: From do-calculus to transportability across populations.Statistical Science, 29(4):579-595, 2014. Xinran Qin, Yinpeng Zhang, Yajunzi Wang, Yintao Zhang, Jiachen Jing, Yuyuan Zhang, Gaoxiang Xu, Haoping Teng, Tianjun Wang, Lei Fu, et al. Tpddb: the comprehensive database of targeted protein degrader.Nucleic Acids Research, 54(D1):D1683-D1691, 2026. doi: 10.1093/nar/gkaf996. Stefano Ribes, Eva Nittinger, Christian Tyrchan, and Rocío Mercado."},{"citing_arxiv_id":"2605.07203","ref_index":21,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"From Pixels to Primitives: Scene Change Detection in 3D Gaussian Splatting","primary_cat":"cs.CV","submitted_at":"2026-05-08T03:50:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"GS-DIFF detects changes in 3D Gaussian Splatting scenes by direct primitive attribute comparison with anisotropic drift models and observability terms, outperforming render-then-compare baselines by ~17% mIoU.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 36, 2005. [20] Antoine Guédon and Vincent Lepetit. Sugar: Surface-aligned gaussian splatting for efficient 3d mesh reconstruction and high-quality mesh rendering. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 5354-5363, 2024. [21] Ishaan Gulrajani and David Lopez-Paz. In search of lost domain generalization.arXiv preprint arXiv:2007.01434, 2020. [22] Richard Hartley and Andrew Zisserman.Multiple View Geometry in Computer Vision. Cambridge University Press, New York, NY , USA, 2 edition, 2003. [23] Binbin Huang, Zehao Yu, Anpei Chen, Andreas Geiger, and Shenghua Gao. 2d gaussian splatting for"},{"citing_arxiv_id":"2605.06643","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Are We Making Progress in Multimodal Domain Generalization? A Comprehensive Benchmark Study","primary_cat":"cs.CV","submitted_at":"2026-05-07T17:51:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A large-scale benchmark finds that recent multimodal domain generalization methods give only marginal gains over a plain ERM baseline, with no method winning consistently and all degrading sharply under corruption or missing modalities.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.25817","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Magnification-Invariant Image Classification via Domain Generalization and Stable Sparse Embedding Signatures","primary_cat":"cs.CV","submitted_at":"2026-04-28T16:26:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Domain generalization via gradient reversal on the BreaKHis dataset produces magnification-invariant histopathology classifiers with three-fold smaller sparse embeddings and near-perfect cross-magnification signature reproducibility.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.23933","ref_index":26,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Robust and Clinically Reliable EEG Biomarkers: A Cross Population Framework for Generalizable Parkinson's Disease Detection","primary_cat":"cs.LG","submitted_at":"2026-04-27T01:17:43+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A cross-population framework for EEG Parkinson's detection using exhaustive 75 directional evaluations and nested validation shows asymmetric transfer and accuracy up to 94.1% when training diversity increases, supported by mixture risk theory.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.05335","ref_index":16,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Cross-Machine Anomaly Detection Leveraging Pre-trained Time-series Model","primary_cat":"cs.LG","submitted_at":"2026-04-07T02:16:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A cross-machine anomaly detection framework disentangles MOMENT embeddings using random forests to create machine-invariant condition features that improve generalization to unseen machines on industrial data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2502.05564","ref_index":202,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TabICL: A Tabular Foundation Model for In-Context Learning on Large Data","primary_cat":"cs.LG","submitted_at":"2025-02-08T13:25:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"TabICL scales in-context learning to large tabular data via column-then-row attention for row embeddings followed by a transformer, matching TabPFNv2 speed and performance while outperforming it and CatBoost on datasets over 10K samples.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2209.14742","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learning Gradient-based Mixup with Extrapolation toward Flatter Minima for Domain Generalization","primary_cat":"cs.LG","submitted_at":"2022-09-29T13:01:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FGMix learns instance weights via gradient compatibilities to perform mixup with extrapolation toward flatter minima, outperforming prior DG methods on DomainBed.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2209.03003","ref_index":20,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","primary_cat":"cs.LG","submitted_at":"2022-09-07T08:59:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"Rectified flow learns straight-path neural ODEs for distribution transport, yielding efficient generative models and domain transfers that work well even with a single simulation step.","context_count":1,"top_context_role":"dataset","top_context_polarity":"use_dataset","context_text":"on a novel domain different from the training set. Rectified flow can be applied to transfer the novel domain (π0) to the training domain (π1) to mitigate the impact of domain shift. Experiment settings We test the rectified flow for domain adaptation on a number of datasets. DomainNet [58] is a dataset of common objects in six different domain taken from DomainBed [20]. All domains from DomainNet include 345 categories (classes) of objects such as Bracelet, plane, bird and cello. Office-Home [83] is a benchmark dataset for domain adaptation which contains 4 domains where each domain consists of 65 categories. To apply our method, first we map both the training and testing data to the latent representation from final hidden layer of the pre-trained model, and construct the rectified flow on the latent representation."}],"limit":50,"offset":0}