I am a Machine Learning Engineer and Researcher with a passion for solving problems and building innovative solutions. My commitment to my work is strongest when I am engaged in projects that involve creating and realizing impactful ideas. Reflecting on my experiences, especially those at IOMAXIS, I find the most fulfillment in developing full-scale products and solutions rather than smaller, less integrated tasks.
In the near future, I am seeking opportunities that allow me to expand my skill set in both the engineering processes and the holistic development of products or ideas. My goal is to contribute to and learn from projects that have the potential to grow into something significant and lasting. I aspire to build and be proud of something that extends beyond small-scale initiatives, grounded in a vision for the future.
If you have grand ideas, let me be the developer that helps you bring them into the tangible, lasting solutions. I am eager to engage in opportunities that allow for me to contribute and scale challenging, meaningful projects.
Visit my About Me page to read about who I am.
Traditional object detection answers two questions; "what" (what the object is?) and "where" (where the object is?). "what" part of the object detection can be fine-grained further i.e. "what type", "what shape" and "what material" etc. This results in the shifting of the object detection tasks to the object description…
Despite their impressive performance on multi-modal tasks, large vision-language models (LVLMs) tend to suffer from hallucinations. An important type is object hallucination, where LVLMs generate objects that are inconsistent with the images shown to the model. Existing works typically attempt to quantify object hallucinations by detecting and measuring the fraction…
This paper presents an approach to detect out-of-context (OOC) objects in an image. Given an image with a set of objects, our goal is to determine if an object is inconsistent with the scene context and detect the OOC object with a bounding box. In this work, we consider commonly…
Open World Object Detection (OWOD) is a new and challenging computer vision task that bridges the gap between classic object detection (OD) benchmarks and object detection in the real world. In addition to detecting and classifying seen/labeled objects, OWOD algorithms are expected to detect novel/unknown objects - which can be…
Object removal refers to the process of erasing designated objects from an image while preserving the overall appearance. Existing works on object removal erase removal targets using image inpainting networks. However, image inpainting networks often generate unsatisfactory removal results. In this work, we find that the current training approach which…
Contrary to the vast literature in modeling, perceiving, and understanding agent-object (e.g., human-object, hand-object, robot-object) interaction in computer vision and robotics, very few past works have studied the task of object-object interaction, which also plays an important role in robotic manipulation and planning tasks. There is a rich space of…
Nearly thirty years ago, it was shown that $\Omega(\sqrt{n})$ registers are needed to solve obstruction-free consensus among $n$ processes. This lower bound was improved to $n$ registers in 2018, which exactly matches the best upper bound. The $\Omega(\sqrt{n})$ space complexity lower bound actually applies to a class of objects called…
Obviously, the object is the key factor of the 3D single object tracking (SOT) task. However, previous Siamese-based trackers overlook the negative effects brought by randomly dropped object points during backbone sampling which hinder trackers to predict accurate bounding boxes (BBoxes). Exploring an approach that seeks to maximize the preservation…
Appearance-based generic object recognition is a challenging problem because all possible appearances of objects cannot be registered, especially as new objects are produced every day. Function of objects, however, has a comparatively small number of prototypes. Therefore, function-based classification of new objects could be a valuable tool for generic object…
Gaze object prediction aims to predict the location and category of the object that is watched by a human. Previous gaze object prediction works use CNN-based object detectors to predict the object's location. However, we find that Transformer-based object detectors can predict more accurate object location for dense objects in…
This paper surveys the field of deep multiagent reinforcement learning. The combination of deep neural networks with reinforcement learning has gained increased traction in recent years and is slowly shifting the focus from single-agent to multiagent environments. Dealing with multiple agents is inherently more complex as (a) the future rewards…
We introduce the topic of learning in multiagent systems. We first provide a quick introduction to the field of game theory, focusing on the equilibrium concepts of iterated dominance, and Nash equilibrium. We show some of the most relevant findings in the theory of learning in games, including theorems on…
Recently, multiagent deep reinforcement learning (DRL) has received increasingly wide attention. Existing multiagent DRL algorithms are inefficient when facing with the non-stationarity due to agents update their policies simultaneously in stochastic cooperative environments. This paper extends the recently proposed weighted double estimator to the multiagent domain and propose a multiagent…
Multiagent reinforcement learning (MARL) can solve complex cooperative tasks However, the efficiency of existing MARL methods relies heavily on well-defined reward functions. Multiagent tasks with sparse reward feedback are especially challenging not only because of the credit distribution problem, but also due to the low probability of obtaining positive reward…
Real-world congestion problems (e.g. traffic congestion) are typically very complex and large-scale. Multiagent reinforcement learning (MARL) is a promising candidate for dealing with this emerging complexity by providing an autonomous and distributed solution to these problems. However, there are three limiting factors that affect the deployability of MARL approaches to…
This paper presents some basic elements regarding the domain of the collaborative systems, a domain of maximum actuality and also the multiagent systems, developed as a result of a sound study on the one-agent systems.
We introduce the "total s-energy" of a multiagent system with time-dependent links. This provides a new analytical lens on bidirectional agreement dynamics, which we use to bound the convergence rates of dynamical systems for synchronization, flocking, opinion dynamics, and social epistemology.
A traffic flow is one of the main transportation issues in nowadays industrialized agglomerations. Configuration of traffic lights is among the key aspects in traffic flow management. This paper proposes an evolutionary optimization tool that utilizes multiagent simulator in order to obtain accurate model. Even though more detailed studies are…
This paper proposes to distinguish four forms of agentive permissions in multiagent settings. The main technical results are the complexity analysis of model checking, the semantic undefinability of modalities that capture these forms of permissions through each other, and a complete logical system capturing the interplay between these modalities.
We demonstrate how multiagent systems provide useful control techniques for modular self-reconfigurable (metamorphic) robots. Such robots consist of many modules that can move relative to each other, thereby changing the overall shape of the robot to suit different tasks. Multiagent control is particularly well-suited for tasks involving uncertain and changing…