WM
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
WALL-WM: Carving World Action Modeling at the Event Joints
arXiv:2606.01955v1 Announce Type: new Abstract: WALL-WM is a World Action Model that shifts video-action learning from chunk-centric optimization to event-grounded Vision-Language-Action pretraining, using semantically coherent action events as the atomic unit of learning. Existing WAMs commonly initialize from multimodal or video foundation models and then optimize fixed-length action chunks conditioned directly on the current observation and instruction. Although convenient, this...
STRIPS-WM: Learning Grounded Propositional STRIPS-style World Models from Images
arXiv:2606.06832v1 Announce Type: new Abstract: Robots performing long-horizon visual manipulation observe high-dimensional images, but successful plans depend on action-relevant facts: what can be done now and what changes afterward. A useful planning representation should discard irrelevant visual details while preserving action applicability and effects.
World2Act: Latent Action Post-Training from World Model Dynamics
arXiv:2603.10422v2 Announce Type: replace Abstract: World Models (WMs) offer a promising mechanism for post-training Vision-Language-Action (VLA) policies by providing dynamics priors that improve generalization under task and scene variation. However, most WM-based post-training methods rely on pixel-space supervision, making policies sensitive to visual artifacts introduced by imperfect WM rollouts. We present World2Act, a latent-space post-training framework that transfers WM dynamics to...
Relative Hemodynamic Timing in Human White Matter
Hemodynamic lag in white matter (WM) remains poorly understood despite its relevance to neurovascular health. We developed Local Propagation Mapping to quantify the spatiotemporal architecture of relative hemodynamic timing within WM. In young adults, WM lag architecture was reliable, aligned with venous anatomy, and reconfigured during working-memory task engagement; the magnitude of macroscopic lag modulation was associated with cognitive performance.
Orientation Dependence of R2' in White Matter: Digital Characterization, Modelling and Implications for Studying Brain Physiology
Introduction R2* is the transverse relaxation rate of tissue, influenced by local magnetic field inhomogeneities arising from susceptibility differences. It decomposes into R2 and R2', where R2' is the reversible component most sensitive to blood oxygenation and forms the basis of the BOLD fMRI signal. Although orientation dependence of R2 and R2* in white matter (WM) has been attributed primarily to myelin, the vascular contribution to R2' has not been systematically characterized.
Policy and World Modeling Co-Training for Language Agents
Announce Type: new Abstract: Reinforcement learning (RL) improves large language model (LLM) agents by teaching them which actions lead to high rewards, but provides little supervision on what those actions do to the environment. World modeling (WM) can fill this gap, yet existing approaches often require separate simulators, extra training stages, or additional inference-time computation. We observe that on-policy RL rollouts already contain the needed signal: each transition pairs an...
Agentic World Modeling for 6G: Near-Real-Time Generative State-Space Reasoning
Announce Type: replace Abstract: We argue that sixth-generation (6G) intelligence is not fluent token prediction but the capacity to imagine and choose -- to simulate future scenarios, weigh trade-offs, and act with calibrated uncertainty. We reframe open radio access network (O-RAN) near-real-time (Near-RT) control via counterfactual dynamics and a world modeling (WM) paradigm that learns an action-conditioned generative state space. This enables quantitative "what-if" forecasting beyond...
Connectional neuroanatomy of U-fibers in the rhesus monkey brain
The superficial white matter (SWM), the region of white matter immediately beneath the gray matter-white matter (GM-WM) border, contains short cortico-cortical association fibers that interconnect neighboring cortical regions. The SWM is estimated to comprise the majority of axons in the cerebral white matter and is thus thought to play a major role in cortical information processing. Despite this prominence, and growing attention in the diffusion MRI field, the connectional organization of...
Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators
Announce Type: new Abstract: While Vision-Language Models (VLMs) have shown strong visual reasoning capabilities, their spatial reasoning abilities remain largely constrained to the observed images and text-oriented chain-of-thought. They often struggle to infer unobserved layouts, maintain cross-view consistency, and reason from alternative viewpoints when only limited egocentric observations are available. In this work, we study this problem as thinking with imagination, where a VLM...
Giant magneto-optical rotation in a Rydberg atomic gas via symmetry-breaking wave mixing
arXiv:2606.01030v1 Announce Type: cross Abstract: The nonlinear magneto-optical rotation effect is central to precision measurements of weak magnetic fields and optical quantum information processing. In conventional single-beam excitation systems, the propagation of the nonlinear signal is restricted by an energy-symmetry-induced propagation blockade. This blockade originates from the symmetrical evolution of the orthogonal circularly polarized components of the probe field, which prevents...