{"total":19,"items":[{"citing_arxiv_id":"2606.01670","ref_index":33,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Time-Aware Diffusion based on Preference Disentanglement for Generative Recommendation","primary_cat":"cs.IR","submitted_at":"2026-06-01T04:27:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"TDPM is a diffusion-based generative recommender that disentangles user preferences into period and point components to enable time-aware diffusion on semantic indices, reporting up to 29% gains on HR@20 and NDCG@20 over baselines on three datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.00776","ref_index":102,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Latent Diffusion Pretraining for Crystal Property Prediction","primary_cat":"cs.LG","submitted_at":"2026-05-30T15:44:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CrysLDNet combines VAE and latent diffusion pretraining on unlabeled crystals to improve graph encoder performance on property prediction by about 4-5% on JARVIS and MP datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.24578","ref_index":80,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"World Models as Group Actions","primary_cat":"cs.CV","submitted_at":"2026-05-23T13:42:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Formalizes video world models as group actions on states and uses latent regularization with synthesized supervision to enforce consistency, introducing GAC and GAR metrics that improve structural correctness in SOTA models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.14276","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Training-Free Generative Sampling via Moment-Matched Score Smoothing","primary_cat":"stat.ML","submitted_at":"2026-05-14T02:20:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"MM-SOLD is a training-free particle sampler whose large-particle limit converges to a moment-matched Gibbs distribution obtained by exponentially tilting a score-smoothed target.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13448","ref_index":46,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"On the Limits of Latent Reuse in Diffusion Models","primary_cat":"stat.ML","submitted_at":"2026-05-13T12:42:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Reusing source latent spaces in diffusion models under distribution shift produces target score error set by principal-angle misalignment and diffusion-time-amplified ambient noise.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09275","ref_index":61,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"DiffATS: Diffusion in Aligned Tensor Space","primary_cat":"cs.LG","submitted_at":"2026-05-10T02:53:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DiffATS trains diffusion models directly on aligned Tucker tensor primitives that are proven to be homeomorphisms, delivering efficient unconditional and conditional generation across images, videos, and PDE data with high compression.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[59] Unterthiner, T., Van Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., and Gelly, S. (2018). Towards accurate generative models of video: A new metric & challenges.arXiv preprint arXiv:1812.01717. [60] Van Den Oord, A., Vinyals, O., et al. (2017). Neural discrete representation learning.Advances in neural information processing systems, 30. [61] Xu, M., Yu, L., Song, Y ., Shi, C., Ermon, S., and Tang, J. (2022). Geodiff: A geometric diffusion model for molecular conformation generation.arXiv preprint arXiv:2203.02923. [62] Xu, Y ., Wang, Y ., Luo, S., Gao, K., He, T., He, D., and Liu, C. (2026). Quotient-space diffusion models. InThe Fourteenth International Conference on Learning Representations."},{"citing_arxiv_id":"2605.08767","ref_index":8,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"From Holo Pockets to Electron Density: GPT-style Drug Design with Density","primary_cat":"cs.AI","submitted_at":"2026-05-09T07:51:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"EDMolGPT generates molecules from low-resolution electron density for de novo structure-based drug design, claiming better performance than pocket-based methods on 101 targets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.07693","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Toward Better Geometric Representations for Molecule Generative Models","primary_cat":"cs.LG","submitted_at":"2026-05-08T13:02:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LENSEs improves representation-conditioned molecule generation by jointly training a multi-level representation head, perceptual loss, and REPA alignment on pretrained encoders, yielding 97.28% validity and 98.51% stability on GEOM-DRUG.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[6] Austin H Cheng, Andy Cai, Santiago Miret, Gustavo Malkomes, Mariano Phielipp, and Alán Aspuru-Guzik. Group selfies: a robust fragment-based molecular string representation.Digital Discovery, 2(3):748-758, 2023. [7] Emiel Hoogeboom, Víctor Garcia Satorras, Clement Vignac, and Max Welling. Equivariant diffusion for molecule generation in 3d.International Conference on Machine Learning, pages 9087-9102, 2022. [8] Minkai Xu, Lantao Yu, Yang Song, Chence Shi, Stefano Ermon, and Jian Tang. Geodiff: A geo- metric diffusion model for molecular conformation generation.arXiv preprint arXiv:2203.02923, 2022. [9] Deepan Adak, Yogesh Singh Rawat, and Shruti Vyas. Molvision: Molecular property prediction with vision language models.arXiv preprint arXiv:2507.03283, 2025."},{"citing_arxiv_id":"2605.07319","ref_index":64,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Generative Modeling with Flux Matching","primary_cat":"cs.LG","submitted_at":"2026-05-08T06:28:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"Flux Matching generalizes score-based generative modeling by using a weaker objective that admits infinitely many non-conservative vector fields with the data as stationary distribution, enabling new design choices beyond traditional score matching.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"A connection between score matching and denoising autoencoders.Neural compu- tation, 23(7):1661-1674, 2011. [63] J. L. Watson, D. Juergens, N. R. Bennett, B. L. Trippe, J. Yim, H. E. Eisenach, W. Ahern, A. J. Borst, R. J. Ragotte, L. F. Milles, et al. De novo design of protein structure and function with rfdiffusion.Nature, 620(7976):1089-1100, 2023. [64] M. Xu, L. Yu, Y . Song, C. Shi, S. Ermon, and J. Tang. Geodiff: A geometric diffusion model for molecular conformation generation.arXiv preprint arXiv:2203.02923, 2022. [65] Y . Xu, S. Tong, and T. Jaakkola. Stable target field for reduced variance score estimation in diffusion models.arXiv preprint arXiv:2302.00670, 2023. [66] Y . Zhang and M. Levin."},{"citing_arxiv_id":"2605.07020","ref_index":44,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"FlashMol: High-Quality Molecule Generation in as Few as Four Steps","primary_cat":"cs.LG","submitted_at":"2026-05-07T23:04:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FlashMol produces chemically valid 3D molecules in 4 steps via distribution matching distillation with respaced timesteps and Jensen-Shannon regularization, matching or exceeding 1000-step teacher performance on QM9 and GEOM-DRUG.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[42] Lemeng Wu, Chengyue Gong, Xingchao Liu, Mao Ye, and Qiang Liu. Diffusion-based molecule generation with informative prior bridges.Advances in Neural Information Processing Systems, 2022. [43] Minkai Xu, Alexander Powers, Ron Dror, Stefano Ermon, and Jure Leskovec. Geometric latent diffusion models for 3d molecule generation.Proceedings of the 40th International Conference on Machine Learning, 2023. [44] Minkai Xu, Lantao Yu, Yang Song, Chence Shi, Stefano Ermon, and Jian Tang. Geodiff: A geo- metric diffusion model for molecular conformation generation.arXiv preprint arXiv:2203.02923, 2022. [45] Yilun Xu, Weili Nie, and Arash Vahdat. One-step diffusion models with f-divergence distribu- tion matching.arXiv preprint arXiv:2502.15681, 2025. [46] Zehra Yildirim, Kyle Swanson, Xuekun Wu, James Zou, and Joseph Wu."},{"citing_arxiv_id":"2605.06140","ref_index":30,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SymDrift: One-Shot Generative Modeling under Symmetries","primary_cat":"cs.LG","submitted_at":"2026-05-07T12:38:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SymDrift makes drifting models produce symmetry-invariant samples in one step via symmetrized coordinate drifts or G-invariant embeddings, outperforming prior one-shot baselines on molecular benchmarks and cutting compute by up to 40x.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05165","ref_index":58,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Interests Burn-down Diffusion Process for Personalized Collaborative Filtering","primary_cat":"cs.IR","submitted_at":"2026-05-06T17:33:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A new interests burn-down diffusion process models decaying user interests for personalized collaborative filtering and outperforms prior generative methods in the StageCF implementation.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"There are two main paradigms in diffusion models, namely denoising diffusion probabilistic model[2, 11] and score based generative model[1, 44]. Some researchers have achieved great success in using diffusion models to generate images [11, 15, 39, 40], and it is also widely used in other areas, such as audio synthesis [17], text generation [22], and molecular conformation generation [58]. CODIGEM ACM Trans. Inf. Syst., Vol. 1, No. 1, Article . Publication date: May 2026. Interests Burn-down Diffusion Process for Personalized Collaborative Filtering 5 Table 1. Summary of key notations. Notation Description UThe User set. IThe Item set. 𝑅The binary interaction matrix. ˜𝑅The normalized interaction matrix. ˜𝐺𝐼 The item Gram matrix. 𝑇Diffusion time range."},{"citing_arxiv_id":"2605.03548","ref_index":34,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"PerFlow: Physics-Embedded Rectified Flow for Efficient Reconstruction and Uncertainty Quantification of Spatiotemporal Dynamics","primary_cat":"cs.LG","submitted_at":"2026-05-05T09:19:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"PerFlow decouples observation conditioning from physics enforcement in rectified flows using constraint-preserving projections and invariance guarantees for fast, physics-consistent reconstruction of spatiotemporal dynamics.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.23134","ref_index":26,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"h-MINT: Modeling Pocket-Ligand Binding with Hierarchical Molecular Interaction Network","primary_cat":"cs.LG","submitted_at":"2026-04-25T04:25:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"h-MINT improves ligand-protein binding affinity prediction by 2-4% and virtual screening metrics by 1-3% via overlapping fragment tokenization and hierarchical modeling.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.18031","ref_index":40,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"How Creative Are Large Language Models in Generating Molecules?","primary_cat":"cs.CL","submitted_at":"2026-04-20T09:57:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Large language models exhibit distinct creative patterns in molecule generation, including higher constraint satisfaction when more constraints are added, and this is the first work to reframe molecule generation abilities as creativity.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.13520","ref_index":16,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LEGO-MOF: Equivariant Latent Manipulation for Editable, Generative, and Optimizable MOF Design","primary_cat":"cs.LG","submitted_at":"2026-04-15T06:06:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LEGO-MOF maps MOF linkers to an equivariant latent space for continuous editing and uses test-time optimization to achieve a 147.5% average boost in pure CO2 uptake while preserving structural validity.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":", Cohen, S.M.: Isoreticular expansion of polymofs achieves high surface area materials. Chemical Communications53(77), 23 10684-10687 (2017) https://doi.org/10.1039/C7CC04222A [15] Hoogeboom, E., Satorras, V.G., Vignac, C., Welling, M.: Equivariant diffusion for molecule generation in 3d. In: Proc. Int. Conf. Mach. Learn., vol. 162, pp. 8867-8887 (2022) [16] Xu, M., Yu, L., Song, Y., Shi, C., Ermon, S., Tang, J.: Geodiff: A geo- metric diffusion model for molecular conformation generation. arXiv preprint arXiv:2203.02923 (2022) [17] Igashov, I., St¨ ark, H., Vignac, C., Schneuing, A., Satorras, V.G., Frossard, P., Welling, M., Bronstein, M., Correia, B.: Equivariant 3d-conditional diffu- sion model for molecular linker design."},{"citing_arxiv_id":"2604.04403","ref_index":19,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MolDA: Molecular Understanding and Generation via Large Language Diffusion Model","primary_cat":"cs.AI","submitted_at":"2026-04-06T04:04:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MolDA is a multimodal molecular model that uses a discrete large language diffusion backbone plus a hybrid graph encoder to achieve better global coherence and validity than autoregressive approaches.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2512.22597","ref_index":26,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Energy-Guided Generative Modeling for Low-Energy Molecular Structure Discovery","primary_cat":"cs.LG","submitted_at":"2025-12-27T14:00:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"EnFlow integrates flow-based conformer generation with energy landscape modeling to enable joint ensemble generation and ground-state identification using only 1-2 ODE steps.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2211.01095","ref_index":16,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models","primary_cat":"cs.LG","submitted_at":"2022-11-02T13:14:30+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DPM-Solver++ enables high-quality guided sampling of diffusion models in 15-20 steps via data-prediction ODE solving and multistep stabilization.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}