A Hierarchical Energy-Based Model for Multimodal Cognition

• URL: http://arxiv.org/abs/2608.12398v1
• Date: Sat, 08 Aug 2026 00:23:56 GMT
• Title: A Hierarchical Energy-Based Model for Multimodal Cognition
• Abstract summary: We propose a hierarchical, energy-based model of multimodal cognition to integrate vision and language.<n>The architecture is a hub-and-spoke hierarchy, in which predictive-coding pipelines for visual objects, scenes, and linguistic units converge on a shared amodal hub.<n>We show this architecture gives a mechanistic account of attentional phenomena such as inattentional blindness and Necker-cube bistability.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose IM-LEPP (Integrated Multimodal Latent Energy-based Predictive Processing), a hierarchical, energy-based model of multimodal cognition that extends a previously proposed single-modality model (LEPP) to integrate vision and language. Following the view that generative neural networks are effective theories of cognitive dynamics, analogous to how statistical mechanics relates to thermodynamics, IM-LEPP models cognition as latent states flowing through learned energy landscapes rather than as an account of neural circuitry. The architecture is a hub-and-spoke hierarchy, grounded in the controlled semantic cognition framework of Lambon Ralph et al., in which predictive-coding pipelines for visual objects, scenes, and linguistic units converge on a shared amodal hub modeled on the anterior temporal lobe. Each pipeline's own prediction is conditioned by, rather than overwritten by, the current hub state, preserving pipeline-specific identity while letting every prediction reflect the full multimodal context. We show this architecture gives a mechanistic account of attentional phenomena such as inattentional blindness and Necker-cube bistability, and that its structure recovers or motivates independently established findings in psycholinguistics, including surprisal theory, the N400/P600 ERP components, and garden-path reanalysis, alongside a falsifiable contrast with transformer language models on trajectory-sensitivity in next-word prediction. We also discuss data-efficient language acquisition relative to LLMs, outline a semantic/episodic memory subsystem, situate the model against predictive coding, the free-energy principle, JEPA, and Hierarchical Temporal Memory, and propose concrete experimental predictions to test its central claims Key Words: predictive processing; predictive coding; energy-based models; diffusion models; effective theory; computational neuroscience.

Related papers

• Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes [57.55143519213221]
  We provide empirical clarity through a systematic exploration of multimodal pretraining.<n>Our experiments on both synthetic and large-scale real-world datasets yield four key insights into the physics of multimodal pretraining.
  arXiv  Detail & Related papers  (2026-08-05T16:09:25Z)
• Large Vision-Language Models Get Lost in Attention [51.851592109135716]
  We propose a unified framework grounded in information theory and geometry to quantify the geometric and entropic nature of residual updates.<n>Applying this unified framework reveals a fundamental functional decoupling: Attention acts as a subspace-language operator focused on reconfiguration, whereas FFNs serve as subspace-language operators driving semantic innovation.
  arXiv  Detail & Related papers  (2026-05-07T04:45:52Z)
• OMNIFLOW: A Physics-Grounded Multimodal Agent for Generalized Scientific Reasoning [51.33849811496781]
  Large Language Models (LLMs) have demonstrated exceptional logical reasoning capabilities but frequently struggle with the continuous dynamics by Partial Differential Equations (PDEs)<n>We propose OMNIFLOW, a multimodal-symbolic architecture designed to ground frozen LLMs in fundamental physical laws without requiring domain-specific parameter updates.<n>We evaluate it on a benchmark spanning microscopic turbulence, theoretical Navier-Stokes, and macroscopic global weather forecasting.
  arXiv  Detail & Related papers  (2026-03-16T18:29:01Z)
• Beyond Language Modeling: An Exploration of Multimodal Pretraining [125.34714978184638]
  We provide empirical clarity through controlled, from-scratch pretraining experiments.<n>We adopt the Transfusion framework, using next-token prediction for language and diffusion for vision.<n>We demonstrate that the MoE architecture harmonizes this scaling asymmetry by providing the high model capacity required by language.
  arXiv  Detail & Related papers  (2026-03-03T18:58:00Z)
• Structure and Redundancy in Large Language Models: A Spectral Study via Random Matrix Theory [0.0]
  This thesis addresses two persistent and closely related challenges in modern deep learning, reliability and efficiency.<n>By analyzing the eigenvalue dynamics of hidden activations across layers and inputs, this work shows that spectral statistics provide a compact, stable, and interpretable lens on model behavior.<n>Within this framework, the first contribution, EigenTrack, introduces a real-time method for detecting hallucinations and out-of-distribution behavior in large language and vision-language models.<n>The second contribution, RMT-KD, presents a principled approach to compressing deep networks via random matrix theoretic knowledge distillation.
  arXiv  Detail & Related papers  (2026-02-25T19:11:56Z)
• 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)
• Will Pre-Training Ever End? A First Step Toward Next-Generation Foundation MLLMs via Self-Improving Systematic Cognition [89.50068130832635]
  Self-Improving cognition (SIcog) is a self-learning framework for constructing next-generation foundation MLLMs by multimodal knowledge.<n>We propose Chain-of-Description for step-by-step visual understanding and integrate structured Chain-of-Thought (CoT) reasoning to support in-depth multimodal reasoning.<n>Experiments demonstrate SIcog's effectiveness in developing MLLMs with enhanced multimodal cognition.
  arXiv  Detail & Related papers  (2025-03-16T00:25:13Z)
• Predictive Learning in Energy-based Models with Attractor Structures [5.542697199599134]
  We introduce a framework that employs an energy-based model (EBM) to capture the nuanced processes of predicting observation after action within the neural system.<n>In experimental evaluations, our model demonstrates efficacy across diverse scenarios.
  arXiv  Detail & Related papers  (2025-01-23T11:04:25Z)
• Transformers from Diffusion: A Unified Framework for Neural Message Passing [79.9193447649011]
  Message passing neural networks (MPNNs) have become a de facto class of model solutions.<n>We propose an energy-constrained diffusion model, which integrates the inductive bias of diffusion with layer-wise constraints of energy.<n>Building on these insights, we devise a new class of message passing models, dubbed Transformers (DIFFormer), whose global attention layers are derived from the principled energy-constrained diffusion framework.
  arXiv  Detail & Related papers  (2024-09-13T17:54:41Z)
• Differentiable Generalised Predictive Coding [2.868176771215219]
  This paper deals with differentiable dynamical models congruent with neural process theories that cast brain function as the hierarchical refinement of an internal generative model explaining observations. Our work extends existing implementations of gradient-based predictive coding and allows to integrate deep neural networks for non-linear state parameterization.
  arXiv  Detail & Related papers  (2021-12-02T22:02:56Z)
• On Energy-Based Models with Overparametrized Shallow Neural Networks [44.74000986284978]
  Energy-based models (EBMs) are a powerful framework for generative modeling. In this work we focus on shallow neural networks. We show that models trained in the so-called "active" regime provide a statistical advantage over their associated "lazy" or kernel regime.
  arXiv  Detail & Related papers  (2021-04-15T15:34:58Z)

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.