Controlla: Learning Controllability via Graph-Constrained Latent Geometry

• URL: http://arxiv.org/abs/2605.16603v1
• Date: Fri, 15 May 2026 20:06:02 GMT
• Title: Controlla: Learning Controllability via Graph-Constrained Latent Geometry
• Abstract summary: We propose a modular factorized-control framework that treats controllability as a property of structured latent geometry.<n>Controlla learns identity and attribute factors from multimodal inputs and aligns them with graph priors.<n>Experiments show consistent improvements in controllability, identity preservation, and cross-modal alignment.
• Score: 3.797867929356259
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Controllable multimodal generation is commonly formulated as an inference-time conditioning problem using prompts, guidance, or auxiliary modules. While effective, such approaches do not explicitly structure how semantic attributes evolve, which can lead to identity drift and inconsistent cross-modal behavior. We propose Controlla, a modular factorized-control framework that treats controllability as a property of structured latent geometry. Controlla learns identity and attribute factors from multimodal inputs and aligns them with graph priors using graph-constrained optimal transport, encouraging attributes to follow graph-consistent trajectories while preserving reference identity. To evaluate this setting, we construct AffectHuman-43K, a leakage-aware multimodal benchmark for reference-grounded affective control, and introduce geometry-aware metrics for trajectory consistency and latent disentanglement. Experiments show consistent improvements in controllability, identity preservation, and cross-modal alignment, with additional analyses on graph sensitivity, extensibility, and robustness.

Related papers

• LargeMonitor: Monitoring Online Task-Free Continual Learning via Large Pretrained Models [5.257217773590746]
  Online task-free continual learning (TFCL) requires intelligent agents to sequentially accumulate knowledge from an unbounded, non-stationary data stream.<n>Existing online TFCL paradigms rely on parameter-efficient prompt tuning or dynamic structure expansion driven by training-coupled optimization dynamics.<n>We propose LargeMonitor, a framework that leverages large pretrained foundation models to autonomously orchestrate task-free continuous adaptation.
  arXiv  Detail & Related papers  (2026-06-08T12:41:15Z)
• Latent Space Disentanglement via Activation Steering for Interpretable Attribute Control in Symbolic Music Generation [6.897804369133787]
  This paper investigates the mechanistic interpretability of the Multitrack Music Transformer (MMT)<n>We propose a framework for deterministic attribute modulation without retraining to bridge this gap via inference-time activation steering.
  arXiv  Detail & Related papers  (2026-05-29T13:31:56Z)
• Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics [81.80010043113445]
  Local weight fine-tuning, LoRA-based adaptation, and activation-based interventions are studied in isolation.<n>We present a unified view that frames these interventions as dynamic weight updates induced by a control signal.<n>Across methods, we observe a consistent trade-off between preference and utility: stronger control increases preference while predictably reducing utility.
  arXiv  Detail & Related papers  (2026-02-02T17:04:36Z)
• From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models [77.04403907729738]
  This survey charts the evolution of uncertainty from a passive diagnostic metric to an active control signal guiding real-time model behavior.<n>We demonstrate how uncertainty is leveraged as an active control signal across three frontiers.<n>This survey argues that mastering the new trend of uncertainty is essential for building the next generation of scalable, reliable, and trustworthy AI.
  arXiv  Detail & Related papers  (2026-01-22T06:21:31Z)
• SALVE: Sparse Autoencoder-Latent Vector Editing for Mechanistic Control of Neural Networks [0.0]
  We present SALVE, a framework that bridges mechanistic interpretability and model editing.<n>We learn a sparse, model-native feature basis without supervision.<n>We validate these features with Grad-FAM, a feature-level saliency mapping method.
  arXiv  Detail & Related papers  (2025-12-17T20:06:03Z)
• Transformers Provably Learn Directed Acyclic Graphs via Kernel-Guided Mutual Information [91.66597637613263]
  transformer-based models leveraging the attention mechanism have demonstrated strong empirical success in capturing complex dependencies within graphs.<n>We introduce a novel information-theoretic metric: the kernel-guided mutual information (KG-MI) based on the $f$-divergence.<n>We prove that, given sequences generated by a $K$-parent DAG, training a single-layer, multi-head transformer via a gradient ascent converges to the global optimum time.
  arXiv  Detail & Related papers  (2025-10-29T14:07:12Z)
• Graph Neural Network and Transformer Integration for Unsupervised System Anomaly Discovery [14.982273490507986]
  This study proposes an unsupervised anomaly detection method for distributed backend service systems.<n>It addresses practical challenges such as complex structural dependencies, diverse behavioral evolution, and the absence of labeled data.<n>Results show that the proposed method outperforms existing models on several key metrics.
  arXiv  Detail & Related papers  (2025-08-13T00:35:58Z)
• Stochastic Encodings for Active Feature Acquisition [100.47043816019888]
  Active Feature Acquisition is an instance-wise, sequential decision making problem.<n>The aim is to dynamically select which feature to measure based on current observations, independently for each test instance.<n>Common approaches either use Reinforcement Learning, which experiences training difficulties, or greedily maximize the conditional mutual information of the label and unobserved features, which makes myopic.<n>We introduce a latent variable model, trained in a supervised manner. Acquisitions are made by reasoning about the features across many possible unobserved realizations in a latent space.
  arXiv  Detail & Related papers  (2025-08-03T23:48:46Z)
• Learning Action-based Representations Using Invariance [18.1941237781348]
  We introduce action-bisimulation encoding, which learns a multi-step controllability metric that discounts distant state features that are relevant for control. We demonstrate that action-bisimulation pretraining on reward-free, uniformly random data improves sample efficiency in several environments.
  arXiv  Detail & Related papers  (2024-03-25T02:17:54Z)
• Data-heterogeneity-aware Mixing for Decentralized Learning [63.83913592085953]
  We characterize the dependence of convergence on the relationship between the mixing weights of the graph and the data heterogeneity across nodes. We propose a metric that quantifies the ability of a graph to mix the current gradients. Motivated by our analysis, we propose an approach that periodically and efficiently optimize the metric.
  arXiv  Detail & Related papers  (2022-04-13T15:54:35Z)
• Is Disentanglement enough? On Latent Representations for Controllable Music Generation [78.8942067357231]
  In the absence of a strong generative decoder, disentanglement does not necessarily imply controllability. The structure of the latent space with respect to the VAE-decoder plays an important role in boosting the ability of a generative model to manipulate different attributes.
  arXiv  Detail & Related papers  (2021-08-01T18:37:43Z)

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.