Related papers: PILA: Physics-Informed Low Rank Augmentation for I…
Class-Incremental Learning (CIL) aims to continually learn new categories without forgetting previously acquired knowledge. Vision-language models such as CLIP offer strong transferable representations via multi-modal supervision, making…
Representation alignment (REPA) guides generative training by distilling representations from a strong, pretrained vision encoder to intermediate diffusion features. We investigate a fundamental question: what aspect of the target…
The vibrational response of structural components carries valuable information about their underlying mechanical properties, health status and operational conditions. This underscores the need for the development of efficient physics-based…
A significant increase in renewable energy production is necessary to achieve the UN's net-zero emission targets for 2050. Using power-electronic controllers, such as Phase Locked Loops (PLLs), to keep grid-tied renewable resources in…
Exponential growth in the scale of modern foundation models has led to the widespread adoption of Low-Rank Adaptation (LoRA) as a parameter-efficient fine-tuning technique. However, standard LoRA implementations disregard the varying…
Offline Reinforcement Learning (RL) faces a fundamental challenge of extrapolation errors caused by out-of-distribution (OOD) actions. Implicit Q-Learning (IQL) employs expectile regression to achieve in-sample learning. Nevertheless, IQL…
The phase-integral method (PIM) is an asymptotic method of the geometrical optics or semi-classical type for solving approximately, but in many cases very accurately, a wide class of differential equations in physics. Unlike the related…
Accurate extraction and segmentation of the cerebral arteries from digital subtraction angiography (DSA) sequences is essential for developing reliable clinical management models of complex cerebrovascular diseases. Conventional loss…
Many Vision-Language-Action (VLA) models flatten image patches into a 1D token sequence, weakening the 2D spatial cues needed for precise manipulation. We introduce IVRA, a lightweight, training-free method that improves spatial…
Recent advances in imitative reinforcement learning (IRL) have considerably enhanced the ability of autonomous agents to assimilate expert demonstrations, leading to rapid skill acquisition in a range of demanding tasks. However, such…
We introduce a new rotationally invariant viewing angle classification method for identifying, among a large number of Cryo-EM projection images, similar views without prior knowledge of the molecule. Our rotationally invariant features are…
This work introduces reduced models based on Continuous Low Rank Adaptation (CoLoRA) that pre-train neural networks for a given partial differential equation and then continuously adapt low-rank weights in time to rapidly predict the…
Studying animal movements is essential for effective wildlife conservation and conflict mitigation. For aerial movements, operational weather radars have become an indispensable data source in this respect. However, partial measurements,…
Bimanual manipulation in cluttered scenes requires policies that remain stable under occlusions, viewpoint and scene variations. Existing vision-language-action models often fail to generalize because (i) multi-view features are fused via…
The Space Domain Awareness (SDA) community routinely tracks satellites in orbit by fitting an orbital state to observations made by the Space Surveillance Network (SSN). In order to fit such orbits, an accurate model of the forces that are…
Physics-informed machine learning (PIML), referring to the combination of prior knowledge of physics, which is the high level abstraction of natural phenomenons and human behaviours in the long history, with data-driven machine learning…
Inferring biophysical parameters and hidden state variables from partial and noisy observations is a fundamental challenge in computational neuroscience. This problem is particularly difficult for fast - slow spiking and bursting models,…
This paper introduces PINT (Physics-Informed Neural Time Series Models), a framework that integrates physical constraints into neural time series models to improve their ability to capture complex dynamics. We apply PINT to the ERA5…
While Vision-Language-Action (VLA) models hold promise in embodied intelligence, their large parameter counts lead to substantial inference latency that hinders real-time manipulation, motivating parameter sparsification. However, as the…
Reinforcement learning of real-world tasks is very data inefficient, and extensive simulation-based modelling has become the dominant approach for training systems. However, in human-robot interaction and many other real-world settings,…