Related papers: Causal Physics Steering in Video World Models via …
Vortex-induced vibration (VIV) is a typical nonlinear fluid-structure interaction phenomenon, which widely exists in practical engineering (the flexible riser, the bridge and the aircraft wing, etc). The conventional finite element model…
Robotic imitation learning has advanced from solving static tasks to addressing dynamic interaction scenarios, but testing and evaluation remain costly and challenging due to the need for real-time interaction with dynamic environments. We…
Variational inference (VI) is a computationally efficient and scalable methodology for approximate Bayesian inference. It strikes a balance between accuracy of uncertainty quantification and practical tractability. It excels at generative…
Concept-based interpretations of black-box models are often more intuitive for humans to understand. The most widely adopted approach for concept-based interpretation is Concept Activation Vector (CAV). CAV relies on learning a linear…
Material parameters such as thermal diffusivity govern how microstructural fields evolve during processing, but difficult to measure directly. The Stability-Aware Frozen Euler Physics-Informed Tracking for Continuum Mechanics (SAFE-PIT-CM),…
We predict future video frames from complex dynamic scenes, using an invertible neural network as the encoder of a nonlinear dynamic system with latent linear state evolution. Our invertible linear embedding (ILE) demonstrates successful…
Current approaches in video forecasting attempt to generate videos directly in pixel space using Generative Adversarial Networks (GANs) or Variational Autoencoders (VAEs). However, since these approaches try to model all the structure and…
Recent work in computer vision and cognitive reasoning has given rise to an increasing adoption of the Violation-of-Expectation (VoE) paradigm in synthetic datasets. Inspired by infant psychology, researchers are now evaluating a model's…
Transfer learning has become crucial in computer vision tasks due to the vast availability of pre-trained deep learning models. However, selecting the optimal pre-trained model from a diverse pool for a specific downstream task remains a…
Steering methods influence Large Language Model behavior by identifying semantic directions in hidden representations, but are typically realized through inference-time activation interventions that apply a fixed, global modification to the…
Video diffusion models have rich world priors, but their use in spatial tasks is limited by poor control, spatial-temporal inconsistent results, and entangled scene-camera dynamics. Current approaches, such as per-task fine-tuning or…
Physics Informed Neural Networks offer a mesh free framework for solving PDEs but are highly sensitive to loss weight selection. We propose two dimensional analysis based weighting schemes, one based on quantifiable terms, and another also…
Deep generative models are reported to be useful in broad applications including image generation. Repeated inference between data space and latent space in these models can denoise cluttered images and improve the quality of inferred…
Adhesion-independent migration is a prominent mode of cell motility in confined environments, yet the physical principles that guide such movement remain incompletely understood. We present a phase-field model for simulating the motility of…
Vision-Language-Action (VLA) models leverage powerful perceptual priors from web-scale Vision-Language Model (VLM) pre-training, yet they remain surprisingly brittle in practice, frequently failing at simple robotic tasks. To mitigate this,…
A physical simulation engine (PSE) is a software system that simulates physical environments and objects. Modern PSEs feature both forward and backward simulations, where the forward phase predicts the behavior of a simulated system, and…
Inverse kinematics is a fundamental technique for motion and positioning control in robotics, typically applied to end-effectors. In this paper, we extend the concept of inverse kinematics to guiding vector fields for path following in…
Modeling complex spatiotemporal dynamics, particularly in far-from-equilibrium systems, remains a grand challenge in science. The governing partial differential equations (PDEs) for these systems are often intractable to derive from first…
Despite rapid progress in video diffusion transformers, how their internal model signals can be leveraged with minimal overhead to enhance video generation quality remains underexplored. In this work, we study the role of Massive…
Despite the recent success of instruction-tuned language models and their ubiquitous usage, very little is known of how models process instructions internally. In this work, we address this gap from a mechanistic point of view by…