Mode Connectivity Beyond Classifiers: Evidence from Generative and Contrastive Models

• URL: http://arxiv.org/abs/2608.30366v1
• Date: Mon, 31 Aug 2026 07:24:57 GMT
• Title: Mode Connectivity Beyond Classifiers: Evidence from Generative and Contrastive Models
• Abstract summary: We propose an architecture-aware connection building algorithm for complex networks.<n>We successfully demonstrate mode connectivity between independently trained DDPM and NanoCLIP modes.
• Score: 1.1685514058765543
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The loss landscape of Deep Neural Networks (DNNs) exhibits highly complex and non-convex properties. Recent studies have revealed the phenomenon of mode connectivity, demonstrating that independently trained network modes can be connected via a continuous low-loss path. However, existing mode connectivity research is predominantly confined to classifier-based models, leaving it an open question whether similar geometric properties exist in modern complex models. In this paper, we extend the boundaries of mode connectivity to generative and contrastive domains (specifically DDPM and NanoCLIP). Addressing the unique architecture of DDPM and CLIP, we propose an architecture-aware connection building algorithm. Extensive empirical results demonstrate for the first time that we successfully discover mode connectivity between independently trained DDPM and NanoCLIP modes. Our work provides a novel perspective for understanding the geometric properties of the loss landscapes in modern generative and contrastive models.

Related papers

• POINTS-Seeker: Towards Training a Multimodal Agentic Search Model from Scratch [84.73366911912512]
  We introduce Agentic Seeding, a dedicated phase designed to weave the precursors necessary for eliciting agentic behaviors.<n>We propose V-Fold, an adaptive history-aware compression scheme that preserves recent dialogue turns in high fidelity while folding historical context into the visual space via rendering.<n>We develop POINTS-Seeker-8B, a state-of-the-art multimodal agentic search model that consistently outperforms existing models across six diverse benchmarks.
  arXiv  Detail & Related papers  (2026-04-15T16:09:37Z)
• NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching [64.10695425442164]
  We introduce NExT-OMNI, an open-source omnimodal foundation model that achieves unified modeling through discrete flow paradigms.<n>Trained on large-scale interleaved text, image, video, and audio data, NExT-OMNI delivers competitive performance on multimodal generation and understanding benchmarks.<n>To advance further research, we release training details, data protocols, and open-source both the code and model checkpoints.
  arXiv  Detail & Related papers  (2025-10-15T16:25:18Z)
• On Linear Mode Connectivity of Mixture-of-Experts Architectures [1.6747713135100666]
  We investigate the phenomenon of linear Mode Connectivity (LMC) in neural networks.<n>LMC is a notable phenomenon in the loss landscapes of neural networks, wherein independently trained models have been to be connected--up to varying symmetries of an algorithm.
  arXiv  Detail & Related papers  (2025-09-14T16:51:41Z)
• Connecting Independently Trained Modes via Layer-Wise Connectivity [0.4094848360328623]
  We propose a new empirical algorithm for connecting independently trained modes that generalizes beyond traditional architectures.<n>In addition to broader applicability, the proposed method yields more consistent connectivity paths across independently trained mode pairs.
  arXiv  Detail & Related papers  (2025-05-05T12:16:55Z)
• Unveiling Mode Connectivity in Graph Neural Networks [30.854487554682628]
  This work presents the first investigation of mode connectivity in graph neural networks (GNNs)<n>We uncover that GNNs exhibit distinct non-linear mode connectivity, diverging from patterns observed in fully-connected networks or CNNs.<n>We establish a link between mode connectivity and generalization, proposing a generalization bound based on loss barriers and revealing its utility as a diagnostic tool.
  arXiv  Detail & Related papers  (2025-02-18T07:46:10Z)
• Topological Deep Learning with State-Space Models: A Mamba Approach for Simplicial Complexes [4.787059527893628]
  We propose a novel architecture designed to operate with simplicial complexes, utilizing the Mamba state-space model as its backbone. Our approach generates sequences for the nodes based on the neighboring cells, enabling direct communication between all higher-order structures, regardless of their rank.
  arXiv  Detail & Related papers  (2024-09-18T14:49:25Z)
• Multilinear Operator Networks [60.7432588386185]
  Polynomial Networks is a class of models that does not require activation functions. We propose MONet, which relies solely on multilinear operators.
  arXiv  Detail & Related papers  (2024-01-31T16:52:19Z)
• Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis [94.64007376939735]
  We theoretically characterize the impact of connectivity patterns on the convergence of deep neural networks (DNNs) under gradient descent training. We show that by a simple filtration on "unpromising" connectivity patterns, we can trim down the number of models to evaluate.
  arXiv  Detail & Related papers  (2022-05-11T17:43:54Z)
• ModeRNN: Harnessing Spatiotemporal Mode Collapse in Unsupervised Predictive Learning [75.2748374360642]
  We propose ModeRNN, which introduces a novel method to learn hidden structured representations between recurrent states. Across the entire dataset, different modes result in different responses on the mixtures of slots, which enhances the ability of ModeRNN to build structured representations.
  arXiv  Detail & Related papers  (2021-10-08T03:47:54Z)
• Learning Bijective Feature Maps for Linear ICA [73.85904548374575]
  We show that existing probabilistic deep generative models (DGMs) which are tailor-made for image data, underperform on non-linear ICA tasks. To address this, we propose a DGM which combines bijective feature maps with a linear ICA model to learn interpretable latent structures for high-dimensional data. We create models that converge quickly, are easy to train, and achieve better unsupervised latent factor discovery than flow-based models, linear ICA, and Variational Autoencoders on images.
  arXiv  Detail & Related papers  (2020-02-18T17:58:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.