{"total":18,"items":[{"citing_arxiv_id":"2606.29105","ref_index":39,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Panel Flow Matching: A Generative Approach to Learning Distributions of Longitudinal Data","primary_cat":"stat.ME","submitted_at":"2026-06-27T23:05:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Panel Flow Matching is a generative method to estimate panel densities from longitudinal data with statistical guarantees under irregular sampling, supporting completion, synthetic data, and classification.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.26535","ref_index":22,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Recursive Flow Matching","primary_cat":"cs.LG","submitted_at":"2026-05-26T04:32:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"RecFM uses recursive self-consistency in flow matching to enable high-fidelity one- and few-step (2-4 step) generation of scientific dynamics, claiming 20x speedup over diffusion emulators and 15% lower MSE than vanilla flow matching.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21981","ref_index":2,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"RiT: Vanilla Diffusion Transformers Suffice in Representation Space","primary_cat":"cs.CV","submitted_at":"2026-05-21T04:21:43+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A vanilla Diffusion Transformer trained via x-prediction on frozen DINOv2 features reaches FID 1.14 on ImageNet 256x256 with fewer parameters and faster sampling than prior DiT variants.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.19305","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Mat\\'ern Noise for Triangulation-Agnostic Flow Matching on Meshes","primary_cat":"cs.GR","submitted_at":"2026-05-19T03:33:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Proposes discretized Matérn process noise for triangulation-agnostic flow matching on meshes with PoissonNet denoiser, tested on elastic states and humanoid poses for meshes exceeding one million triangles.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"tribution over its vertices, D ≡ N (0,Σ ), with zero mean andΣ covariance. The corresponding spectral distribution is also a normal distribution with zero mean, bD ≡ N \u0010 0,bΣ \u0011 per Equation (4), and considering thatbfis a linear transformation off, per Equation (3). Sampling discrete white noise.We define the white noise distri- bution as the normal distribution Dwhite ≜N 0,M −1\u0001 ,(6) where M is the lumped mass matrix. To verify this is indeed also aspectralwhite noise distribution, let w∼ D white be a sample, and bwits spectral coefficients. From arithmetic of the variance of Gaussians, we get that the spectral covariance matrix is bΣ white ≡Var [bw] 𝐸𝑞.(3) =Var \u0002 w⊤MΦ \u0003 𝐸𝑞.(4) =Φ ⊤MΣMΦ 𝐸𝑞.(6) =Φ ⊤MM−1MΦ=Φ ⊤MΦ 𝑜𝑟𝑡ℎ.=I. (7) ALGORITHM 1:Sampling Matérn Noise"},{"citing_arxiv_id":"2605.18472","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Flowing with Confidence","primary_cat":"stat.ML","submitted_at":"2026-05-18T14:28:17+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FMwC computes per-sample confidence scores for flow matching models via closed-form propagation of input-dependent multiplicative noise variance along the sampling ODE, supporting filtering, editing, and adaptive stepping.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.16755","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learning Unbiased Permutations via Flow Matching","primary_cat":"cs.LG","submitted_at":"2026-05-16T02:10:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"PermFlow applies conditional flow matching on the affine subspace of doubly stochastic matrices with a closed-form tangent projector and nearest-target coupling to capture multimodal permutation distributions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.06591","ref_index":32,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"BRICKS: Compositional Neural Markov Kernels for Zero-Shot Radiation-Matter Simulation","primary_cat":"cs.LG","submitted_at":"2026-05-07T17:19:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"BRICKS creates compositional neural Markov kernels via hybrid transformers and Riemannian Flow Matching on product manifolds to enable zero-shot simulation of radiation-matter interactions across arbitrary material distributions.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"target for the neural network output with loss L=E (y0,y1)∼π,t∼π(t)[(vϕ −v cond)2]. The model is trained with Schedule-Free AdamW with β= (0.95,0.999) , learning rate 5·10 −4 and weight decay 10−2. During inference, the choices of ODE solver and step-size significantly impact inference time and sample quality, which are explored in Section 6.2. 5 Datasets Standard Datasets in Particle Interaction datasets [ 32] typically only contain the overall energy depositions into the material for a large-scale geometry. In order to train a composable particle- interaction kernel a new type of dataset is required that also contains outgoing particles that emerge from the simulation of a material volume. In this work we therefore introduce the CaloBricks dataset consisting of 20M simulations of"},{"citing_arxiv_id":"2605.05736","ref_index":6,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SDFlow: Similarity-Driven Flow Matching for Time Series Generation","primary_cat":"cs.AI","submitted_at":"2026-05-07T06:28:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SDFlow learns a global transport map via similarity-driven flow matching in VQ latent space, using low-rank manifold decomposition and a categorical posterior to handle discreteness, yielding SOTA long-horizon performance and inference speedups.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Scheduled sampling for sequence prediction with recurrent neural networks.Advances in neural information processing systems, 28, 2015. [5] Huiwen Chang, Han Zhang, Lu Jiang, Ce Liu, and William T Freeman. Maskgit: Masked generative image transformer. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 11315-11325, 2022. [6] Ricky TQ Chen and Yaron Lipman. Flow matching on general geometries.arXiv preprint arXiv:2302.03660, 2023. [7] Zhicheng Chen, FENG SHIBO, Zhong Zhang, Xi Xiao, Xingyu Gao, and Peilin Zhao. Sdformer: Similarity- driven discrete transformer for time series generation.Advances in Neural Information Processing Systems, 37:132179-132207, 2024. [8] Andrea Coletta, Sriram Gopalakrishnan, Daniel Borrajo, and Svitlana Vyetrenko."},{"citing_arxiv_id":"2605.03360","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A-CODE: Fully Atomic Protein Co-Design with Unified Multimodal Diffusion","primary_cat":"q-bio.QM","submitted_at":"2026-05-05T04:41:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"A-CODE presents a fully atomic one-stage multimodal diffusion model for protein co-design that claims superior unconditional generation performance over prior one- and two-stage models plus a tenfold success-rate gain on hard binder-design tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.02222","ref_index":119,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Generative Modeling with Orbit-Space Particle Flow Matching","primary_cat":"cs.GR","submitted_at":"2026-05-04T04:51:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"OGPP is a particle flow-matching method using orbit-space canonicalization and geometric paths that achieves lower error and fewer steps than prior approaches on 3D benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.21809","ref_index":121,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Quotient-Space Diffusion Models","primary_cat":"cs.LG","submitted_at":"2026-04-23T16:04:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"Quotient-space diffusion models generate correct symmetric distributions by removing redundancy on the quotient space, simplifying learning and improving results on small molecules and proteins under SE(3) symmetry.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.11521","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Continuous Adversarial Flow Models","primary_cat":"cs.LG","submitted_at":"2026-04-13T14:23:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Continuous adversarial flow models replace MSE in flow matching with adversarial training via a discriminator, improving guidance-free FID on ImageNet from 8.26 to 3.63 for SiT and similar gains for JiT and text-to-image benchmarks.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"inducing incorrect generalization relative to the underlying data distribution. Recent work has attempted to tackle the issue from different angles. Rep- resentational autoencoders [83] convert the data space on which flow matching operates and have empirically reported improvements in generation quality, but this requires operating in a latent space instead of the original data space. Rie- mannian flow matching [7] extends flow matching to non-Euclidean geometries, but this requires manual definition of the data manifold, which is often unknown for general datasets. Other work [44] replaces Euclidean loss with perceptual dis- tances derived from frozen feature networks, motivated by the empirical finding that deep networks can serve as better perceptual metrics [81]."},{"citing_arxiv_id":"2604.07213","ref_index":18,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Diffusion Processes on Implicit Manifolds","primary_cat":"cs.LG","submitted_at":"2026-04-08T15:34:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Defines diffusion processes on implicit data manifolds via proximity-graph approximations to the infinitesimal generator and carré-du-champ operator, proves convergence in law to the continuous manifold process, and provides an Euler-Maruyama integrator validated on synthetic and MNIST manifolds.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.05303","ref_index":63,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Jeffreys Flow: Robust Boltzmann Generators for Rare Event Sampling via Parallel Tempering Distillation","primary_cat":"cs.LG","submitted_at":"2026-04-07T01:17:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Jeffreys Flow distills Parallel Tempering trajectories via Jeffreys divergence to produce robust Boltzmann generators that suppress mode collapse and correct sampling inaccuracies for rare event sampling.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2603.22564","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MIOFlow 2.0: A unified framework for inferring cellular stochastic dynamics from single cell and spatial transcriptomics data","primary_cat":"cs.LG","submitted_at":"2026-03-23T20:49:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MIOFlow 2.0 learns stochastic cellular trajectories from transcriptomics data via neural SDEs, unbalanced optimal transport for growth, and a joint latent space unifying gene expression with spatial features.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2601.23087","ref_index":7,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CoLA-Flow Policy: Temporally Coherent Imitation Learning via Continuous Latent Action Flow Matching for Robotic Manipulation","primary_cat":"cs.RO","submitted_at":"2026-01-30T15:36:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"CoLA-Flow Policy encodes action sequences into a continuous latent space and learns an explicit flow there, yielding near-single-step inference with up to 93.7% smoother trajectories and 25-point higher task success than raw-action flow baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2505.17354","ref_index":28,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CT-OT Flow: Estimating Continuous-Time Dynamics from Discrete Temporal Snapshots","primary_cat":"cs.LG","submitted_at":"2025-05-23T00:12:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CT-OT Flow estimates continuous-time dynamics from discrete temporal snapshots by using partial optimal transport to align intervals and kernel smoothing to reconstruct distributions for ODE/SDE training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2504.13618","ref_index":18,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"On the Importance of Tactile Sensing for Imitation Learning: A Case Study on Robotic Match Lighting","primary_cat":"cs.RO","submitted_at":"2025-04-18T10:48:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A multimodal visuotactile imitation learning framework using transformers and flow-based models improves robotic performance on the contact-rich task of match lighting.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}