All posts under category "General Research"
Watermarking large language models (LLMs) is vital for preventing their misuse, including the fabrication of fake news, plagiarism, and spam. It is especially important to watermark LLM-generated code, as it often contains intellectual property. However, we found that existing methods for watermarki
Current tool-using AI agents suffer from limited action space, context inefficiency, and probabilistic instability that makes them unsuitable for handling repetitive tasks which are otherwise reliably and efficiently tackled by agentic workflows built on platforms like n8n [12] and Zapier [8] . E
Autonomous Large Language Model (LLM) agents exhibit significant vulnerability to Indirect Prompt Injection (IPI) attacks. These attacks hijack agent behavior by polluting external information sources, exploiting fundamental trade-offs between security and functionality in existing defense mechanism
https://refkxh.github.io/BiCo_Webpage A butterfly flapping its wings softly on a vibrant yellow flower, surrounded by a vibrant Minecraft landscape featuring a dynamic volcano which erupts, spewing vibrant red lava and creating a dramatic ash cloud against a serene blue sky, with molten lava pooling
Structured Cartesian grids are a fundamental component in numerical simulations. Although these grids facilitate straightforward discretization schemes, their naïve use in sparse domains leads to excessive memory overhead and inefficient computation. Existing frameworks address are primarily optimiz
Large language models (LLMs) often solve challenging math exercises yet fail to apply the concept right when the problem requires genuine understanding. Popular Reinforcement Learning with Verifiable Rewards (RLVR) pipelines reinforce final answers but provide little fine-grained conceptual signal,
The evolution of Large Language Models (LLMs) has catalyzed a paradigm shift from superficial instruction following to rigorous long-horizon reasoning. While Group Relative Policy Optimization (GRPO) has emerged as a pivotal mechanism for eliciting such post-training reasoning capabilities due to it
Many large language models (LLMs) are trained on a massive body of knowledge present on the Internet. Darth Vecdor (DV) was designed to extract this knowledge into a structured, terminology-mapped, SQL database ('knowledge base' or 'knowledge graph'). Knowledge graphs may be useful in many domains,
We present DASH (Deception-Augmented Shared mental model for Human-machine teaming), a novel framework that enhances mission resilience by embedding proactive deception into Shared Mental Models (SMM). Designed for mission-critical applications such as surveillance and rescue, DASH introduces 'bait
Bridging the sim-to-real gap remains a fundamental challenge in robotics, as accurate dynamic parameter estimation is essential for reliable model-based control, realistic simulation, and safe deployment of manipulators. Traditional analytical approaches often fall short when faced with complex robo
Accurate and interpretable forecasting of multivariate time series is crucial for understanding the complex dynamics of cryptocurrency markets in digital asset systems. Advanced deep learning methodologies, particularly Transformer-based and MLP-based architectures, have achieved competitive predict
Generative diversity varies significantly across discrete latent generative models such as AR, MIM, and Diffusion. We propose a diagnostic framework, grounded in Information Bottleneck (IB) theory, to analyze the underlying strategies resolving this behavior. The framework models generation as a con
Currently, there exists a fundamental divide between the 'cognitive black box' (implicit intuition) of human experts and the 'computational black box' (untrustworthy decision-making) of artificial intelligence (AI). This paper proposes a new paradigm of 'human-AI collaborative cognitive enhancement,
Learning Analytics (LA) has rapidly expanded through practical and technological innovation, yet its foundational identity has remained theoretically under-specified. This paper addresses this gap by proposing the first axiomatic theory that formally defines the essential structure, scope, and limit
Large language models (LLMs) rely on self-attention for contextual understanding, demanding high-throughput inference and large-scale token parallelism (LTPP). Existing dynamic sparsity accelerators falter under LTPP scenarios due to stage-isolated optimizations. Revisiting the end-to-end sparsity a
Large Language Models (LLMs) can be backdoored to exhibit malicious behavior under specific deployment conditions while appearing safe during training a phenomenon known as 'sleeper agents.' Recent work by Hubinger et al. demonstrated that these backdoors persist through safety training, yet no prac
Botswana has not previously been surveyed with sufficient accuracy to determine the highest peak in the country. Otse Hill and Monalanong Hill have been identified as the highest peaks, but there was uncertainty on which is highest. For this study, ground surveys were conducted on each of these peak
We propose DiscoverDCP, a data-driven framework that integrates symbolic regression with the rule sets of Disciplined Convex Programming (DCP) to perform system identification. By enforcing that all discovered candidate model expressions adhere to DCP composition rules, we ensure that the output exp
The recent rapid growth of visual generative models trained on vast web-scale datasets has created significant tension with data privacy regulations and copyright laws, such as GDPR's ``Right to be Forgotten.'' This necessitates machine unlearning (MU) to remove specific concepts without the prohibi
Transformers rely on positional encoding to compensate for the inherent permutation invariance of self-attention. Traditional approaches use absolute sinusoidal embeddings or learned positional vectors, while more recent methods emphasize relative encodings to better capture translation equivariance
Large language model (LLM)-based multi-agent systems are challenging to debug because failures often arise from long, branching interaction traces. The prevailing practice is to leverage LLMs for log-based failure localization, attributing errors to a specific agent and step. However, this paradigm
Accurate segmentation of ischemic stroke lesions from diffusion magnetic resonance imaging (MRI) is essential for clinical decision-making and outcome assessment. Diffusion-Weighted Imaging (DWI) and Apparent Diffusion Coefficient (ADC) scans provide complementary information on acute and sub-acute
AI agents powered by large language models (LLMs) are being used to solve increasingly complex software engineering challenges, but struggle with hardware design tasks. Register Transfer Level (RTL) code presents a unique challenge for LLMs, as it encodes complex, dynamic, time-evolving behaviors us
This paper develops a comprehensive mathematical framework for modeling the coupled hydroelastic dynamics of sea-ice floes of arbitrary shape and non-uniform thickness under linear ocean wave forcing. We simultaneously incorporate four dominant rigid-body motions (heave, surge, roll, pitch) and the
Using a photograph of the shadow of Mont Blanc taken from Geneva at sunrise, we derive an upper limit for the Earth radius. After presenting the observational context and the model underlying assumptions, we determine the direction of the solar rays relative to the local vertical. This direction con
Echocardiography is central to contemporary cardiovascular care, but full-study interpretation remains a cognitively demanding, multi-view task that is still performed manually. While recent foundation models for echocardiography can achieve strong performance on individual perceptual subtasks such
Modern large language model (LLM) systems increasingly rely on multi-turn pipelines that are composed of multiple task-specific adapters, yet existing serving frameworks remain inefficient, incurring substantial recomputation overhead when switching between adapters. We present the first LLM serving
Conforming hexahedral (hex) meshes are favored in simulation for their superior numerical properties, yet automatically decomposing a general 3D volume into a conforming hex mesh remains a formidable challenge. Among existing approaches, methods that construct an adaptive Cartesian grid and subseque
As modern artificial intelligence (AI) systems become more advanced and capable, they can leverage a wide range of tools and models to perform complex tasks. Today, the task of orchestrating these models is often performed by Large Language Models (LLMs) that rely on qualitative descriptions of mode
The integration of the Internet of Robotic Things (IoRT) in smart greenhouses has revolutionised precision agriculture by enabling efficient and autonomous environmental control. However, existing time series forecasting models in such setups often operate as black boxes, lacking mechanisms for expl
Generative AI has begun to democratize creative work, enabling novices to produce complex artifacts such as code, images, and videos. However, in practice, existing interaction paradigms often fail to support divergent exploration: users tend to converge too quickly on early ``good enough'' results
With the rapid uptake of generative AI, investigating human perceptions of generated responses has become crucial. A major challenge is their 'aptitude' for hallucinating and generating harmful contents. Despite major efforts for implementing guardrails, human perceptions of these mitigation strateg
Diffusion Large Language Models (dLLMs) offer fast, parallel token generation, but their standalone use is plagued by an inherent efficiency-quality tradeoff. We show that, if carefully applied, the attributes of dLLMs can actually be a strength for drafters in speculative decoding with autoregressi
Recognizing whether outputs from large language models (LLMs) contain faithfulness hallucination is crucial for real-world applications, e.g., retrieval-augmented generation and summarization. In this paper, we introduce Faith-Lens, a cost-efficient and effective faithfulness hallucination detection
In todays increasing world, it is very important to have good hailing services like Ola, Uber, and Rapido as it is very essential for our daily transportation. Users often face difficulties in choosing the most appropriate and efficient ride that would lead to both cost-effective and would take us t
Coreset selection compresses large datasets into compact, representative subsets, reducing the energy and computational burden of training deep neural networks. Existing methods are either: (i) DNN-based, which are tied to model-specific parameters and introduce architectural bias; or (ii) DNN-free,
The issue of limited household budgets and nutritional demands continues to be a challenge especially in the middle-income environment where food prices fluctuate. This paper introduces a price aware agentic AI system, which combines personal finance management with diet optimization. With household
When adapting large language models (LLMs) to a specific downstream task, two primary approaches are commonly employed: (1) prompt engineering, often with in-context few-shot learning, leveraging the model's inherent generalization abilities, and (2) fine-tuning on task-specific data, directly optim
Geospatial foundation models (GeoFMs) promise broad generalisation capacity for Earth observation (EO) tasks, particularly under data-limited conditions. However, their large size poses a barrier to deployment on resource-constrained space hardware. To address this, we present compact variants of a
This study presents a comprehensive deep learning pipeline for the automated classification of 12 foraminifera species using 2D micro-CT slices derived from 3D scans. We curated a scientifically rigorous dataset comprising 97 micro-CT scanned specimens across 27 species, selecting 12 species with su
Accurate estimation of the State of Charge (SOC) is critical for ensuring the safety, reliability, and performance optimization of lithium-ion battery systems. Conventional data-driven neural network models often struggle to fully characterize the inherent complex nonlinearities and memory-dependent
Building AI systems for GUI automation task has attracted remarkable research efforts, where MLLMs are leveraged for processing user requirements and give operations. However, GUI automation includes a wide range of tasks, from document processing to online shopping, from CAD to video editing. Diver
We study the computational power of the Full-Tilt model of motion planning, where slidable polyominos are moved maximally around a board by way of a sequence of directional ``tilts.'' We focus on the deterministic scenario in which the tilts constitute a repeated clockwise rotation. We show that gen
Denoising diffusion models have emerged as a dominant paradigm in image generation. Discretizing image data into tokens is a critical step for effectively integrating images with Transformer and other architectures. Although the Denoising Diffusion Codebook Models (DDCM) pioneered the use of pre-tra
Formal, automated theorem proving has long been viewed as a challenge to artificial intelligence. We introduce here a new approach to computer theorem proving, one that employs specialized language models for Lean4 proof generation combined with recursive decomposition of difficult theorems into sim
In this work, we propose that reasoning in knowledge graph (KG) networks can be guided by surprise minimization. Entities that are close in graph distance will have lower surprise than those farther apart. This connects the Free Energy Principle (FEP) from neuroscience to KG systems, where the KG se
Large language models (LLMs) face critical safety challenges, as they can be manipulated to generate harmful content through adversarial prompts and jailbreak attacks. Many defenses are typically either black-box guardrails that filter outputs, or internals-based methods that steer hidden activation
GTAvatar broadens applications of monocular Gaussian Splatting head avatars beyond reenactment and relighting, enabling interactive editing of textures for precise control of intrinsic appearance, while preserving training efficiency, rendering speed and visual fidelity.
Deep learning models, particularly Long Short-Term Memory (LSTM) networks, are widely used in time series forecasting due to their ability to capture complex temporal dependencies. However, evaluation integrity is often compromised by data leakage, a methodological flaw in which input-output sequenc
Test-time scaling (TTS) aims to achieve better results by increasing random sampling and evaluating samples based on rules and metrics. However, in text-to-image(T2I) diffusion models, most related works focus on search strategies and reward models, yet the impact of the stochastic characteristic of
Enter keywords to search articles