2 citations · 3 across the 8 of their papers we have counts for
11 papers
Event-SAMA: Language-Grounded Video Object Segmentation on Neuromorphic Event Streams
Sergei Fedorchenko, Max Zehnder, Nikola Zubić +2
Event cameras offer microsecond temporal resolution, high dynamic range and no motion blur, but referring video object segmentation (RVOS) lacks event-stream datasets and models. W…
When Does Tool Use Increase the Expressive Power of Finite-Precision Recurrent Models?
Nikola Zubić, Qian Li, Yuyi Wang +1
Modern sequence models are increasingly deployed as agents that interleave token generation with calls to external tools. We study when such tool access increases computational exp…
On the Expressive Power and Limitations of Multi-Layer SSMs
Nikola Zubić, Qian Li, Yuyi Wang +1
We study how depth, finite precision, state dimension, and chain-of-thought (CoT) affect the expressive power of multi-layer state-space models (SSMs). For the explicit-table -f…
Low-Latency Event-Based Object Detection with Spatially-Sparse Linear Attention
Haiqing Hao, Zhipeng Sui, Rong Zou +4
Event cameras provide sequential visual data with spatial sparsity and high temporal resolution, making them attractive for low-latency object detection. Existing asynchronous even…
Regularity and Stability Properties of Selective SSMs with Discontinuous Gating
Nikola Zubić, Davide Scaramuzza
Selective State-Space Models (SSMs) such as Mamba have become central to long-sequence modeling. Still, their stability is poorly understood: their state-space coefficients are mod…
Maximizing Asynchronicity in Event-based Neural Networks
Haiqing Hao, Nikola Zubić, Weihua He +3
Event cameras deliver visual data with high temporal resolution, low latency, and minimal redundancy, yet their asynchronous, sparse sequential nature challenges standard tensor-ba…
Perturbed State Space Feature Encoders for Optical Flow with Event Cameras
Gokul Raju Govinda Raju, Nikola Zubić, Marco Cannici +1
With their motion-responsive nature, event-based cameras offer significant advantages over traditional cameras for optical flow estimation. While deep learning has improved upon tr…
GG-SSMs: Graph-Generating State Space Models
Nikola Zubić, Davide Scaramuzza
State Space Models (SSMs) are powerful tools for modeling sequential data in computer vision and time series analysis domains. However, traditional SSMs are limited by fixed, one-d…
S7: Selective and Simplified State Space Layers for Sequence Modeling
Taylan Soydan, Nikola Zubić, Nico Messikommer +2
A central challenge in sequence modeling is efficiently handling tasks with extended contexts. While recent state-space models (SSMs) have made significant progress in this area, t…
Limits of Deep Learning: Sequence Modeling through the Lens of Complexity Theory
Nikola Zubić, Federico Soldá, Aurelio Sulser +1
Despite their successes, deep learning models struggle with tasks requiring complex reasoning and function composition. We present a theoretical and empirical investigation into th…
An Effective Loss Function for Generating 3D Models from Single 2D Image without Rendering
Nikola Zubić, Pietro Liò
Differentiable rendering is a very successful technique that applies to a Single-View 3D Reconstruction. Current renderers use losses based on pixels between a rendered image of so…