collaborators

6 papers

math.PR2026

DisCo Algebra: Why Disintegration and Combination Are Not Inverses

Xuexing Lu

We present DisCo algebra---a compositional framework for joint probability built from a symmetric cooperad (disintegration) and a magma-operad (non-associative partial combination,…

cs.LG2026

Collapsed Effective Operators for Higher-order Structures

Maximilian Krahn, Lennart Bastian, Vikas Garg +2

Higher-order structures are powerful relational modeling tools, yet existing spectral operators decompose the topology into separate ranks, leaving practitioners to fuse the inform…

cs.LG2026

Flexible Flows for Biological Sequence Design

Yogesh Verma, Dani Korpela, Harri Lähdesmäki +1

Designing functional biological sequences requires navigating vast discrete spaces under strict evolutionary and biophysical constraints. Discrete Flow Matching (DFM) offers a gene…

cs.CV2026

Divide-and-Denoise: A Game-Theoretic Method for Fairly Composing Diffusion Models

Abhi Gupta, Polina Barabanshchikova, Vikas Garg +2

The abundance of pre-trained diffusion models provides an opportunity for composition. Combining several models, however, runs the risk of one model dominating or models disagreein…

cs.LG2026

Margin-calibrated Classifier Guidance for Property-driven Synthesis Planning

Najwa Laabid, Vikas Garg

Synthesis planning seeks an efficient sequence of chemical reactions that produce a target molecule. Typically, a pretrained single-step (autoregressive) retrosynthesis model is re…

cs.LG2025

Heterophily-informed Message Passing

Haishan Wang, Arno Solin, Vikas Garg

Graph neural networks (GNNs) are known to be vulnerable to oversmoothing due to their implicit homophily assumption. We mitigate this problem with a novel scheme that regulates the…