All posts under category "Research"
Tool calling agents are an emerging paradigm in LLM deployment, with major platforms such as ChatGPT, Claude, and Gemini adding connectors and autonomous capabilities. However, the inherent unreliability of LLMs introduces fundamental security risks
Considering that Turing's original test was co-opted by Weizenbaum and that six of the most common criticisms of the Turing test are unfair to both Turing's argument and the historical development of AI.
Representation learning is fundamental to modern machine learning, powering applications such as text retrieval and multimodal understanding. However, learning robust and generalizable representations remains challenging. While prior work has demonst
Signed graphs with positive and negative edges can model complex relationships in social networks. Leveraging on balance theory that deduces edge signs from multi-hop node pairs, signed graph learning can generate node embeddings that preserve both s
Domain adaptive retrieval aims to transfer knowledge from a labeled source domain to an unlabeled target domain, enabling effective retrieval while mitigating domain discrepancies. However, existing methods encounter several fundamental limitations:
Despite significant advancements in deep learning-based sparse-view computed tomography (SVCT) reconstruction algorithms, these methods still encounter two primary limitations: (i) It is challenging to explicitly prove that the prior networks of deep
Model-based planning in robotic domains is fundamentally challenged by the hybrid nature of physical dynamics, where continuous motion is punctuated by discrete events such as contacts and impacts. Conventional latent world models typically employ mo
Accurate structural relaxation is critical for advanced materials design. Traditional approaches built on physics-derived first-principles calculations are computationally expensive, motivating the creation of machine-learning interatomic potentials
Aggressively quantized large language models (LLMs), such as BitNet-style 1.58-bit Transformers with ternary weights, make it feasible to deploy generative AI on low-power edge FPGAs. However, as prompts grow to tens of thousands of tokens, edge hard
Neural networks have shown remarkable success in supervised learning when trained on a single task using a fixed dataset. However, when neural networks are trained on a reinforcement learning task, their ability to continue learning from new experien
Latent inpainting in diffusion models still relies almost universally on linearly interpolating VAE latents under a downsampled mask. We propose a key principle for compositing image latents: Pixel-Equivalent Latent Compositing (PELC). An equivalent
This work presents a review of attack methodologies targeting Pix, the instant payment system launched by the Central Bank of Brazil in 2020. The study aims to identify and classify the main types of fraud affecting users and financial institutions,
As artificial intelligence (AI) becomes increasingly integrated into education, understanding how students perceive its risks is essential for supporting responsible and effective adoption. This research aimed to examine the relationships between per
Differences in perception, information asymmetries, and bounded rationality lead game-theoretic players to derive a private, subjective view of the game that may diverge from the underlying 'ground-truth' scenario and may be misaligned with other pla
Foreign Object Debris (FOD) within aircraft fuel tanks presents critical safety hazards including fuel contamination, system malfunctions, and increased maintenance costs. Despite the severity of these risks, there is a notable lack of dedicated data
We seek to clarify the concept of active inference by disentangling it from the Free Energy Principle. We show how the optimizations that need to be carried out in order to implement active inference in discrete state spaces can be formulated as cons
A multigraph G = (V, E) is (k, ell) -sparse if every subset X subseteq V induces at most max{k X - ell, 0} edges. Finding a maximum-size (k, ell) -sparse subgraph is a classical problem in rigidity theory and combinatorial optimization, with
Conventional AI-driven AMS design automation algorithms remain constrained by their reliance on high-quality datasets to capture underlying circuit behavior, coupled with poor transferability across architectures, and a lack of adaptive mechanisms. T
Given just a few glimpses of a scene, can you imagine the movie playing out as the camera glides through it? That's the lens we take on emph{sparse-input novel view synthesis}, not only as filling spatial gaps between widely spaced views, but also as
The main objective of this paper is to develop the two different ways in which round robin architecture is modified and made suitable to be implemented in real time and embedded systems. The scheduling algorithm plays a significant role in the design
We present new Chandra X-ray and Giant Meterwave Radio Telescope (GMRT) radio observations of the nearby merging galaxy cluster Abell 754. Our X-ray data confirm the presence of a shock front by obtaining the first direct measurement of a gas tempera
We present a simple numerical model of the plasma flow within the open field line tube in the pulsar magnetosphere. We study how the plasma screens the rotationally induced electric field and maintains the electric current demanded by the global stru
Efficiency and simplicity of random algorithms have made them a lucrative alternative for solving complex problems in the domain of communication networks. This paper presents a random algorithm for handling the routing problem in Mobile Ad hoc Netwo
An integrated software-based solution for a modular and self-independent networked robot is introduced. The wirelessly operatable robot has been developed mainly for autonomous monitoring works with full control over web. The integrated software solu
Graph coloring, also known as vertex coloring, considers the problem of assigning colors to the nodes of a graph such that adjacent nodes do not share the same color. The optimization version of the problem concerns the minimization of the number of
Although software managers are generally good at new project estimation, their experience of scheduling rework tends to be poor. Inconsistent or incorrect effort estimation can increase the risk that the completion time for a project will be problema
Weighted automata are nondeterministic automata with numerical weights on transitions. They can define quantitative languages L that assign to each word w a real number L(w) . In the case of infinite words, the value of a run is naturally comput
This paper presents Fast load balancing technique inspired by Bioinformatics is a special case to assign a particular patient with a specialist physician cluster at real time. The work is considered soft presentation of the Gaussian mixture model bas
Community identification is a long-standing challenge in the modern network science, especially for very large scale networks containing millions of nodes. In this paper, we propose a new metric to quantify the structural similarity between subgraphs
We present a fully relativistic computation of the torques due to Lindblad resonances from perturbers on circular, equatorial orbits on discs around Schwarzschild and Kerr black holes. The computation proceeds by establishing a relation between the L
Complex, non-additive genetic interactions are common and can be critical in determining phenotypes. Genome-wide association studies (GWAS) and similar statistical studies of linkage data, however, assume additive models of gene interactions in looki
The emission mechanisms in extragalactic jets include synchrotron and various inverse-Compton processes. At low (radio through infrared) energies, it is widely agreed that synchrotron emission dominates in both low-power (FR I) and high-power (FR II
Sharing musical files via the Internet was the essential motivation of early P2P systems. Despite of the great success of the P2P file sharing systems, these systems support only 'simple' queries. The focus in such systems is how to carry out an effi
Let a, b and n be nonnegative integers (b geq a, b > 0, n geq 1) , mathcal{G}_n(a,b) be a multigraph on n vertices in which any pair of vertices is connected with at least a and at most b edges and textbf{v =} (v_1, v_2, ..., v_n) be
Dependently typed lambda calculi such as the Logical Framework (LF) are capable of representing relationships between terms through types. By exploiting the 'formulas-as-types' notion, such calculi can also encode the correspondence between formulas
Traumatic brain injury [TBI] has become a signature injury of current military conflicts, with debilitating, costly, and long-lasting effects. Although mechanisms by which head impacts cause TBI have been well-researched, the mechanisms by which blas
The miniaturization process of various sensing devices has become a reality by enormous research and advancements accomplished in Micro Electro-Mechanical Systems (MEMS) and Very Large Scale Integration (VLSI) lithography. Regardless of such extensiv
We construct the model of a long lived plasma structure based on spherically symmetric oscillations of electrons in plasma. Oscillations of electrons are studied in frames of both classical and quantum approaches. We obtain the density profile of ele
In recent times there have been several attacks against critical infrastructure such as the 2021 Oldsmar Water Treatment System breach and the 2023 Denmark Energy Sector compromise. These breaches clearly show the need for security improvements withi
A game-theoretic framework is used to study the effect of constellation size on the energy efficiency of wireless networks for M-QAM modulation. A non-cooperative game is proposed in which each user seeks to choose its transmit power (and possibly tr
Enter keywords to search articles