{"total":12,"items":[{"citing_arxiv_id":"2606.24985","ref_index":170,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Retrieval-Augmented Personalization with Foundation Models for Wearable Stress Detection","primary_cat":"cs.LG","submitted_at":"2026-06-23T14:24:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Retrieval from out-of-domain foundation models enables personalization of a lightweight transformer for stress detection, yielding +3.92% accuracy and +4.76% F1 gains on WESAD without user labels.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.22182","ref_index":34,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Dual-Stream EEG Decoding for 3D Visual Perception","primary_cat":"cs.CV","submitted_at":"2026-06-20T18:25:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Dual-stream EEG decoder separates identity and orientation to support 3D reconstruction from neural signals via circular regression and conditioned diffusion.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.10237","ref_index":107,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Minimalist Genetic Programming","primary_cat":"cs.AI","submitted_at":"2026-06-08T22:51:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MGP uses a MERGE-based Markovian process from linguistic minimalism to discover and combine atomic building blocks into exact symbolic regression models, avoiding bloat when a suitable lexicon is provided.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.10075","ref_index":29,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"An algorithm for dynamical quantum optimal transport with applications to quantum chemistry","primary_cat":"math.OC","submitted_at":"2026-06-08T18:49:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"An interior-point method is introduced to compute dynamical quantum optimal transport geodesics on density matrices, shown to approximate some quantum chemistry problems after parameter tuning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13520","ref_index":40,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Beyond Explained Variance: A Cautionary Tale of PCA","primary_cat":"cond-mat.stat-mech","submitted_at":"2026-05-13T13:37:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"PCA scatterplots misleadingly indicate clusters in Kuehneotherium teeth data, whereas t-SNE and persistent homology detect a ring-like one-dimensional manifold, backed by a generative model of uniform sampling from a unit circle whose cosine distances follow an arcsine distribution.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"distance [19] and the Wasserstein distances [38, 39]. The typical topological features considered areH 0,H 1, andH 2, corresponding to the number of connected com- ponents, loops (or holes), and voids, respectively. In what follows, persistent homology diagrams, along with their equivalent persistent barcodes, and the bottleneck dis- tance are computed using the giotto-tda toolbox [40]. D. Cosine Distance This works crucially depends on the choice of the ap- propriate distance. In fact, it is found that replacing the Euclidean distance by the cosine distancedcos,t-SNE and persistent homology yield reasonable consistent results. That being said, the cosine distance reads [41] dcos (xi,x j) = 1− xi·x j ∥xi∥2∥xj∥2 .(2) Note that Eq."},{"citing_arxiv_id":"2605.08485","ref_index":32,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Sinkhorn Treatment Effects: A Causal Optimal Transport Measure","primary_cat":"stat.ML","submitted_at":"2026-05-08T21:03:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"The Sinkhorn treatment effect is a new entropic optimal transport measure of divergence between counterfactual distributions that admits first- and second-order pathwise differentiability, debiased estimators, and asymptotically valid tests for distributional treatment effects.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"48) yields the stated Hadamard derivative S′′ ε [µ, µ](γ1, γ2) = (γ1 −γ 2)K µ (γ1 −γ 2). D. Pathwise Differentiability of STE In this appendix, we prove the main results stated in Sec. 3. We begin by introducing notation that will be used throughout the proofs. For any score functions∈ ˙PP , define sX(x) :=E P [s(X, A, Y)|X=x]ands Y|A,X (y|a, x) :=s(x, a, y)−E P [s(X, A, Y)|A=a, X=x].(32) For notational convenience, we also introduce evaluation operators: for functions f:Z →R , g:{0,1} × X →R,andh: X →R, we use the operator notationE zf=f(z),E a,xg=g(a, x), andE xh=h(x). We recall the expectation operators PY|A,X , PA|X ,andP X introduced in (7). For f:Z →R , a∈ {0,1} , x∈ X , and z′ ∈ Z ′, we define the shorthand notation (PY|a,X f)(z ′) := (PY|A,X f)(x ′, a, y′)"},{"citing_arxiv_id":"2605.05907","ref_index":40,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"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":"2605.05652","ref_index":19,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Information-Preserving Domain Transfer with Unlabeled Data in Misspecified Simulation-Based Inference","primary_cat":"cs.LG","submitted_at":"2026-05-07T04:06:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SPIN performs bidirectional domain transfer in SBI to retain parameter mutual information from unlabeled real observations, improving real-world posterior inference under increasing misspecification.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"real-world data setting to an inductive and amortized setting using OT-based alignment over unpaired observations. Without such a calibration set, recent work has used unlabeled real-world observations during training. NPE with self-consistency (NPE+SC) [13] augments the simulation-based posterior loss with a self- consistency loss evaluated on unlabeled observations. This loss exploits the Bayesian self-consistency relation [19, 20] that the likelihood-prior to posterior ratio is constant across parameter values under exact inference. However, evaluating this constraint requires likelihood evaluations or an auxiliary likelihood estimator. Other methods using unlabeled real-world data include domain alignment methods such as NPE with robust statistics (NPE-RS) [12], NPE-MMD [21], and NPE-DANN [21]."},{"citing_arxiv_id":"2604.27398","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Why Mean Pooling Works: Quantifying Second-Order Collapse in Text Embeddings","primary_cat":"cs.CL","submitted_at":"2026-04-30T04:09:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Modern text encoders resist second-order collapse under mean pooling because token embeddings concentrate tightly within texts, and this resistance correlates with stronger downstream performance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2502.10600","ref_index":74,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Weighted quantization using MMD: From mean field to mean shift via gradient flows","primary_cat":"stat.ML","submitted_at":"2025-02-14T23:13:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Derives MSIP algorithm from MMD gradient flows for weighted quantization, extending mean shift and relating to preconditioned gradient descent and Lloyd's clustering.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1907.01729","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Implementation of batched Sinkhorn iterations for entropy-regularized Wasserstein loss","primary_cat":"stat.ML","submitted_at":"2019-07-01T15:25:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":1.0,"formal_verification":"none","one_line_summary":"Documents a practical PyTorch implementation of batched Sinkhorn iterations for the entropy-regularized Wasserstein loss introduced by Cuturi.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1907.00257","ref_index":37,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Hausdorff and Wasserstein metrics on graphs and other structured data","primary_cat":"math.OC","submitted_at":"2019-06-29T18:56:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Defines Hausdorff-style and Wasserstein-style metrics on C-sets, proving the latter are convex relaxations of the former and computable as linear programs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}