Home Knowledge Base Unified Latent Dynamics

Unified Latent Dynamics

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

Unifying Model-Free Efficiency and Model-Based Representations via Latent Dynamics

Announce Type: replace Abstract: We present Unified Latent Dynamics (ULD), a novel reinforcement learning algorithm that unifies the efficiency of model-free methods with the representational strengths of model-based approaches, without incurring planning overhead. By embedding state-action pairs into a latent space in which the true value function is approximately linear, our method supports a single set of hyperparameters across diverse domains -- from continuous control with...

arXiv CS 6d ago

LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestion

Announce Type: replace Abstract: Recent robot foundation models largely rely on large-scale behavior cloning, which imitates expert actions but discards transferable dynamics knowledge embedded in heterogeneous embodied data. While the Unified World Model (UWM) formulation has the potential to leverage such diverse data, existing instantiations struggle to scale to foundation-level due to coarse data usage and fragmented datasets.

arXiv CS 6d ago

EEGDancer: Dynamic Emotion Latent Space Masked Modeling with Reinforcement Learning for EEG Continuous Emotion Prediction

arXiv:2606.05855v1 Announce Type: new Abstract: Continuous electroencephalography (EEG) emotion prediction aims to model the temporal evolution of human emotional states from EEG signals. Unlike conventional discrete emotion recognition, continuous prediction requires capturing long-range temporal dependencies and coherent emotional dynamics.

arXiv CS 5d ago

ClothTransformer: Unified Latent-Space Transformers for Scalable Cloth Simulation

arXiv:2605.27852v3 Announce Type: replace Abstract: Unified and scalable Transformers have recently achieved remarkable success in modeling diverse phenomena traditionally associated with computer graphics, such as 3D visual effects, rendering processes, and motion in videos. In this work, we take a step further by investigating whether modern Transformer techniques can tackle the challenging task of cloth simulation. To this end, we present ClothTransformer, a framework that reformulates...

arXiv CS 1d ago

ClothTransformer: Unified Latent-Space Transformers for Scalable Cloth Simulation

arXiv:2605.27852v2 Announce Type: replace Abstract: Unified and scalable Transformers have recently achieved remarkable success in modeling diverse phenomena traditionally associated with computer graphics, such as 3D visual effects, rendering processes, and motion in videos. In this work, we take a step further by investigating whether modern Transformer techniques can tackle the challenging task of cloth simulation. To this end, we present ClothTransformer, a framework that reformulates...

arXiv CS 5d ago

Drift-Diffusion Matching: Embedding dynamics in latent manifolds of asymmetric neural networks

arXiv:2602.14885v2 Announce Type: replace-cross Abstract: Recurrent neural networks (RNNs) provide a theoretical framework for understanding computation in biological neural circuits, yet classical results, such as Hopfield's model of associative memory, rely on symmetric connectivity that restricts network dynamics to gradient-like flows. In contrast, biological networks support rich time-dependent behaviour facilitated by their asymmetry. Here we introduce a general framework, which we...

arXiv CS 6d ago

Circuit-Inspired High-Order Neural Networks with Unified Neural Dynamics Modeling for PDE Solving and Visual Perception

Announce Type: replace Abstract: Deep networks often rely on architectural heuristics to shape representation evolution, limiting their ability to model data governed by intrinsic dynamics. We present the Circuit-inspired High-Order Neural Network (CHONN), a modular framework that treats representation evolution as a latent potential process and increases its effective order through Kirchhoff-inspired cascade composition. A single Kirchhoff Neural Cell implements a stable first-order update,...

arXiv CS 9d ago

Reduced-order modeling of Hamiltonian dynamics based on symplectic neural networks

arXiv:2508.11911v2 Announce Type: replace Abstract: We introduce a novel data-driven symplectic induced-order modeling (ROM) framework for high-dimensional Hamiltonian systems that unifies latent-space discovery and dynamics learning within a single, end-to-end neural architecture. The encoder-decoder is built from Henon neural networks (HenonNets) and may be augmented with linear SGS-reflector layers. This yields an exact symplectic map between full and latent phase spaces.

arXiv CS 9d ago

Reduced-order modeling of Hamiltonian dynamics based on symplectic neural networks

arXiv:2508.11911v2 Announce Type: replace-cross Abstract: We introduce a novel data-driven symplectic induced-order modeling (ROM) framework for high-dimensional Hamiltonian systems that unifies latent-space discovery and dynamics learning within a single, end-to-end neural architecture. The encoder-decoder is built from Henon neural networks (HenonNets) and may be augmented with linear SGS-reflector layers. This yields an exact symplectic map between full and latent phase spaces.

arXiv Physics 9d ago

Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learning

Announce Type: new Abstract: Autonomous driving requires reasoning about how ego actions shape the evolution of the surrounding world. However, most end-to-end methods rely on direct state-to-action mappings, capturing correlations without explicitly modeling action-conditioned dynamics. Conversely, continuous-latent world models often lack compositional structure for causal reasoning across counterfactual futures.

arXiv CS 5d ago