{"total":21,"items":[{"citing_arxiv_id":"2606.11251","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Mechanical Field Networks: Structured Neural Dynamics for Multivariate Systems","primary_cat":"cs.LG","submitted_at":"2026-06-08T15:23:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MF-Net learns a shared field state and mechanical transition rule from trajectories to deliver competitive forecasting and recoverable relation matrices on Lorenz-96 and real systems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.30592","ref_index":1,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learning Transferable Predictability Representations","primary_cat":"cs.LG","submitted_at":"2026-05-28T21:38:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"GON uses 2-jet features and an anchor-and-variance objective to fix gauge freedom in ordinal predictability scoring, enabling pretrained initialization to outperform scratch training on held-out dynamical systems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.00133","ref_index":191,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"World Models: A Comprehensive Survey of Architectures, Methodologies, Reasoning Paradigms, and Applications","primary_cat":"cs.LG","submitted_at":"2026-05-28T21:23:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"The paper delivers a multi-axis taxonomy for world models that maps architectures, training families, reasoning strategies, and domains from early cognitive foundations through systems such as Dreamer, MuZero, and Sora while noting evaluation gaps.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.30542","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Physically Viable World Models: A Case for Query-Conditioned Embodied AI","primary_cat":"cs.AI","submitted_at":"2026-05-28T20:18:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Embodied AI requires query-conditioned world models that select the simplest physical abstraction sufficient to answer intervention queries.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.30429","ref_index":28,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"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":"2605.30347","ref_index":23,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"NeuROK: Generative 4D Neural Object Kinematics","primary_cat":"cs.CV","submitted_at":"2026-05-28T17:59:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"NeuROK learns a data-driven latent kinematic parameterization on a large 4D dataset to generate realistic object deformations by simulating dynamics only in low-dimensional latent space via Lagrangian mechanics.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.23510","ref_index":36,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learning partially observed systems with neural Hamiltonian ordinary differential equations","primary_cat":"cs.LG","submitted_at":"2026-05-22T11:18:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"NHODE framework learns partially observed dynamical systems by combining Hamiltonian neural networks with neural ODEs, enforcing energy conservation and improving long-horizon stability over data-driven baselines on mass-spring and three-body problems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.22820","ref_index":68,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Integrable Elasticity via Neural Demand Potentials","primary_cat":"cs.LG","submitted_at":"2026-05-21T17:59:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ICDN is a neural network that models log-demand from log-prices so elasticities can be derived exactly by differentiation, showing better out-of-sample performance than log-log benchmarks on beer sales data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21160","ref_index":20,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learning First Integrals via Backward-Generated Data and Guided Reinforcement Learning","primary_cat":"cs.LG","submitted_at":"2026-05-20T13:27:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"FISolver trains a compact LLM on backward-generated (differential equation, first integral) pairs and uses guided reinforcement learning to outperform larger models and Mathematica on first-integral benchmarks at lower cost.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.20299","ref_index":14,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Mechanisms of Misgeneralization in Physical Sequence Modeling","primary_cat":"cs.LG","submitted_at":"2026-05-19T12:34:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Generative sequence models for physical tasks exhibit physical misgeneralization where local prediction errors propagate through physical measurements to distort aggregate distributions over quantities like distance or energy; a data deviation kernel explains and predicts the shifts and supports a内核","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"which is piecewise linear and has slope magnitude r at every differentiable state xt ̸= 1/2. Solving the Lyapunov exponent yields λH(r) = logr (proof in Appx. D.2.2), meaning that sequences are non-chaotic for r≤1 , while sensitivity of the measurement increases logarithmically asr approaches 2. Finally, we use the logistic map, xt+1 =rx t(1−x t), r∈[0,4],(14) as a sanity check. This is a classical nonlinear population dynamics model in which r controls the growth rate. The logistic map is challenging to predict because its Lyapunov exponent depends on realized orbits (proof in Appx. D.2.3); we include it here to test whether our mechanism generalizes beyond the tent map. For these iterated maps, we discretize intermediate states to 1024 bins and use"},{"citing_arxiv_id":"2605.19589","ref_index":80,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"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":1,"top_context_role":"background","top_context_polarity":"background","context_text":"The improvement ofELGINover M0 in MDE and Rg-err therefore reflects primarily superiorspatialtrajectory fidelity from the RANS coupling, not kinetic-energy conservation per se. D. Clinical metric: Breathing Zone Exposure The Breathing Zone Exposure (BZE) fraction is the share of the simultaneously active parcels that lie inside the dentist's breathing-zone rectanglex∈[1.30,1.80]m,y∈[1.525,1.675]m at timet. WithN(t)the alive parcel count in the evaluator subgraph andN BZ(t)the subset inside that rectan- 16 0.0 0.5 1.0 1.5 2.0 2.5 3.0 3.5 4.0 0.0 0.5 1.0 1.5 2.0 2.5 3.0 y (m) ELGIN (prediction) (t = 5.00 s) Dentist Patient Air Inlet Outlet Nozzle 0.0 0.5 1.0 1.5 2.0 2.5 3.0 3.5 4.0 0.0 0.5 1.0 1.5 2.0 2.5 3.0 OpenFOAM (ground truth) (t = 5."},{"citing_arxiv_id":"2605.16398","ref_index":27,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Support-Safe Variational Hybrid Filtering for Contact-Mode and Sparse-Law Recovery","primary_cat":"cs.RO","submitted_at":"2026-05-12T18:13:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"VHYDRO is a support-safe variational hybrid filter that jointly recovers continuous latent states, discrete contact modes, and sparse port-Hamiltonian laws per regime while preventing loss of feasible transitions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08279","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LaWM: Least Action World Models for Long-Horizon Physical Consistency from Visual Observations","primary_cat":"cs.LG","submitted_at":"2026-05-08T07:03:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LaWM induces latent transitions from a learned discrete variational principle rather than an unconstrained neural predictor, yielding improved physical consistency on synthetic dynamics and robot benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.04405","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Detecting Deepfakes via Hamiltonian Dynamics","primary_cat":"cs.CV","submitted_at":"2026-05-06T01:55:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"HAAD detects deepfakes by modeling latent manifolds as potential energy surfaces and quantifying instability via Hamiltonian trajectory statistics such as action and energy dissipation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00412","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Physically Native World Models: A Hamiltonian Perspective on Generative World Modeling","primary_cat":"cs.AI","submitted_at":"2026-05-01T05:09:32+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":"2605.00394","ref_index":24,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Mesh Field Theory: Port-Hamiltonian Formulation of Mesh-Based Physics","primary_cat":"cs.LG","submitted_at":"2026-05-01T04:35:21+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":"2604.18277","ref_index":29,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Dissipative Latent Residual Physics-Informed Neural Networks for Modeling and Identification of Electromechanical Systems","primary_cat":"cs.LG","submitted_at":"2026-04-20T13:52:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DiLaR-PINN learns dissipative effects in electromechanical systems via a skew-dissipative latent residual PINN that guarantees non-increasing energy and uses recurrent curriculum training for partial observations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.12103","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Parametric Interpolation of Dynamic Mode Decomposition for Predicting Nonlinear Systems","primary_cat":"eess.SY","submitted_at":"2026-04-13T22:23:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"piDMD learns a single parameter-affine Koopman surrogate ROM from training samples at multiple parameters to predict dynamics at unseen parameters with improved robustness over interpolation baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2510.17193","ref_index":29,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Optimal transport by a Lagrangian dynamics of population distribution","primary_cat":"cond-mat.dis-nn","submitted_at":"2025-10-20T06:13:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A quadratic Lagrangian incorporating dissipation models human mobility from population distributions and fits both synthetic and empirical data, showing comparable inertia and dissipation effects.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2409.18272","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SLIDE: A machine-learning based method for forced dynamic response estimation of multibody systems","primary_cat":"cs.LG","submitted_at":"2024-09-26T20:34:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SLIDE is a deep learning estimator that truncates initial effects via complex eigenvalues of linearized equations to predict output sequences of damped multibody systems, reporting speedups up to several million times.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2104.13478","ref_index":20,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","primary_cat":"cs.LG","submitted_at":"2021-04-27T21:09:51+00:00","verdict":"ACCEPT","verdict_confidence":"HIGH","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Geometric deep learning provides a unified mathematical framework based on grids, groups, graphs, geodesics, and gauges to explain and extend neural network architectures by incorporating physical regularities.","context_count":1,"top_context_role":"background","top_context_polarity":"unclear","context_text":"structure that comes with differentiable manifolds, where such maps are calleddiffeomorphisms and denoted byDiff(Ω). Additional examples of struc- tures we will encounter includedistancesormetrics(maps preserving them are calledisometries) ororientation(to the best of our knowledge, orientation- preserving maps do not have a common Greek name). A metric or distance is a functiond : Ω× Ω→ [0,∞) satisfying for all u, v, w∈ Ω: Identity of indiscernibles:d(u, v) = 0 iff u = v. Symmetry: d(u, v) = d(v, u). Triangle inequality:d(u, v)≤ d(u, w) + d(w, v). A space equipped with a metric(Ω, d) is called ametric space. Therightlevelofstructuretoconsiderdependsontheproblem. Forexample, when segmenting histopathology slide images, we may wish to consider flipped versions of an image as equivalent (as the sample can be flipped when put under the microscope), but if we are trying to classify road signs, we would only want to consider orientation-preserving transformations as symmetries (since reflections could change the meaning of the sign). As we add levels of structure to be preserved, the symmetry group will get smaller. Indeed,addingstructureisequivalenttoselectinga subgroup,which is a subset of the larger group that satisfies the axioms of a group by itself: Let (G,◦) be a group andH⊆ G a subset.H is said to be asubgroupof G if (H,◦) constitutes a group with the same operation. For instance, the group of Euclidean isometriesE(2) is a subgroup of the groupofplanardiffeomorphisms Diff(2),andinturnthegroupoforientation- preserving isometriesSE(2) is a subgroup ofE(2). This hierarchy of struc- ture follows the Erlangen Programme philosophy outlined in the Preface: in Klein's construction, the Projective, Affine, and Euclidean geometries 3. GEOMETRIC PRIORS 19 have increasingly more invariants and correspond to progressively smaller groups. Isomorphisms and Automorphisms We have described symmetries as structure preserving and invertible mapsfrom an object to itself. Such maps are"}],"limit":50,"offset":0}