Related papers: Modeling Dynamic Computations in the Primate Ventr…
The local viscoelastic (VE) environment governs the motion of an embedded microsphere and consequently, pertinent dynamical phenomena. However, studying such phenomena with varying VE properties remains challenging for various reasons,…
Optical flow is a crucial component of the feature space for early visual processing of dynamic scenes especially in new applications such as self-driving vehicles, drones and autonomous robots. The dynamic vision sensors are well suited…
The extensive adoption of Deep Neural Networks has led to their increased utilization in challenging scientific visualization tasks. Recent advancements in building compressed data models using implicit neural representations have shown…
Humans have a strong intuitive understanding of the 3D environment around us. The mental model of the physics in our brain applies to objects of different materials and enables us to perform a wide range of manipulation tasks that are far…
Manipulating dynamic objects remains an open challenge for Vision-Language-Action (VLA) models, which, despite strong generalization in static manipulation, struggle in dynamic scenarios requiring rapid perception, temporal anticipation,…
Vision Transformers (ViTs) have demonstrated remarkable capabilities in learning representations, but their performance is compromised when applied to unseen domains. Previous methods either engage in prompt learning during the training…
In the primate primary visual area (V1), the ocular dominance pattern consists of alternating monocular stripes. Stripe orientation follows systematic trends preserved across several species. I propose that these trends result from…
Handling static images that lack inherent temporal dynamics remains a fundamental challenge for spiking neural networks (SNNs). In directly trained SNNs, static inputs are typically repeated across time steps, causing the temporal dimension…
While vision-language models (VLMs) have exhibited multi-turn visual reasoning capabilities, their reasoning trajectories remain relatively shallow and are dominated by a text-centric paradigm, limiting their applicability to complex visual…
Mathematical modelling and numerical simulations of interaction populations are crucial topics in systems biology. The interactions of ecological models may occur among individuals of the same species or individuals of different species.…
As artificial intelligence models have exploded in scale and capability, understanding of their internal mechanisms remains a critical challenge. Inspired by the success of dynamical systems approaches in neuroscience, here we propose a…
We introduce Neuro-Vesicles, a framework that augments conventional neural networks with a missing computational layer: a dynamical population of mobile, discrete vesicles that live alongside the network rather than inside its tensors. Each…
Autonomous systems, such as self-driving cars, rely on reliable semantic environment perception for decision making. Despite great advances in video semantic segmentation, existing approaches ignore important inductive biases and lack…
Model visualization (ModelVis) has emerged as a major research direction, yet existing taxonomies are largely organized by data or tasks, making it difficult to treat models as first-class analysis objects. We present a model-centric…
Modern techniques for physical simulations rely on numerical schemes and mesh-refinement methods to address trade-offs between precision and complexity, but these handcrafted solutions are tedious and require high computational power.…
Mathematical modeling has broad applications in neuroscience whether modeling the dynamics of a single synapse or an entire network of neurons. In Part I, we model vesicle replenishment and release at the photoreceptor synapse to better…
Streaming vision-language models (VLMs) continuously generate responses given an instruction prompt and an online stream of input frames. This is a core mechanism for real-time visual assistants. Existing VLM frameworks predominantly assess…
A critical visual computation is to construct global scene properties from activities of early visual cortical neurons which have small receptive fields. Such a computation is enabled by contextual influences, through which a neuron's…
Dynamic Vision Sensor (DVS)-based solutions have recently garnered significant interest across various computer vision tasks, offering notable benefits in terms of dynamic range, temporal resolution, and inference speed. However, as a…
In robotics, Vision-Language-Action (VLA) models that integrate diverse multimodal signals from multi-view inputs have emerged as an effective approach. However, most prior work adopts static fusion that processes all visual inputs…