All posts under category "General Research"
Multimodal LLMs often produce fluent yet unreliable reasoning, exhibiting weak step-to-step coherence and insufficient visual grounding, largely because existing alignment approaches supervise only the final answer while ignoring the reliability of the intermediate reasoning process. We introduce SR
Catastrophic forgetting remains a fundamental challenge in continual learning for large language models. Recent work [2] revealed that performance degradation may stem from spurious forgetting caused by task alignment disruption rather than true knowledge loss. However, this foundational work left
Scaling vision-language-action (VLA) model pre-training requires large volumes of diverse, high-quality manipulation trajectories. Most current data is obtained via human teleoperation, which is expensive and difficult to scale. Reinforcement learning (RL) methods learn useful skills through autonom
Group Relative Policy Optimization (GRPO) has emerged as an effective and lightweight framework for post-training visual generative models. However, its performance is fundamentally limited by the ambiguity of textual-visual correspondence: a single prompt may validly describe diverse visual outputs
Research on promoting cooperation among autonomous, self-regarding agents has often focused on the bi-objective optimization problem: minimizing the total incentive cost while maximising the frequency of cooperation. However, the optimal value of social welfare under such constraints remains largely
Autonomous intelligence requires not only perception and reasoning, but critically, effective interaction with the existing world and its infrastructure. Everyday environments are rich in tangible control interfaces (TCIs)-e.g., light switches, appliance panels, and embedded GUIs-that demand commons
Chain-of-thought (CoT) prompting combined with few-shot in-context learning (ICL) has unlocked significant reasoning capabilities in large language models (LLMs). However, ICL with CoT examples is ineffective on novel tasks when the pre-training knowledge is insufficient. We study this problem in a
Loss of decisional capacity, coupled with the increasing absence of reliable human proxies, raises urgent questions about how individuals' values can be represented in Advance Care Planning (ACP). To probe this fraught design space of high-risk, high-subjectivity decision support, we built an experi
As computational demands continue to rise, assessing the environmental footprint of artificial intelligence (AI) requires moving beyond energy and water consumption to include the material demands of specialized hardware. This study quantifies the material footprint of AI training by linking computa
In regions of the Middle East and North Africa (MENA), there is a high demand for wastewater treatment plants (WWTPs), crucial for sustainable water management. Precise identification of WWTPs from satellite images enables environmental monitoring. Traditional methods like YOLOv8 segmentation requir
Vehicle Dispatching Systems (VDSs) are critical to the operational efficiency of Automated Container Terminals (ACTs). However, their widespread commercialization is hindered due to their low transferability across diverse terminals. This transferability challenge stems from three limitations: high
Large Language Models (LLMs) deliver exceptional performance across natural language tasks but demand substantial computational resources, limiting their deployment on resource-constrained edge devices. Existing compression techniques, such as quantization and pruning, often degrade critical linguis
Multimodal cardiovascular magnetic resonance (CMR) imaging provides comprehensive and non-invasive insights into cardiovascular disease (CVD) diagnosis and underlying mechanisms. Despite decades of advancements, its widespread clinical adoption remains constrained by prolonged scan times and heterog
Pharmaceutical three-dimensional (3D) printing is an advanced fabrication technology with the potential to enable truly personalised dosage forms. Recent studies have integrated artificial intelligence (AI) to accelerate formulation and process development, drastically transforming current approache
In the outer solar system beyond Jupiter, water ice is a dominant component of planetary bodies, and most solid objects in this region are classified as icy bodies. Icy bodies display a remarkable diversity of geological, geophysical, and atmospheric processes, which differ fundamentally from those
Cooperative multi-agent reinforcement learning (MARL) is constrained by two core design bottlenecks: dense reward engineering and curriculum design. Handcrafted rewards often misalign with global objectives, while static curricula fail to prevent agents from getting trapped in local optima. Large la
Implicit Neural Representations (INRs) have emerged as a powerful paradigm for representing signals such as images, audio, and 3D scenes. However, existing INR frameworks-including MLPs with Fourier features, SIREN, and multiresolution hash grids-implicitly assume a global and stationary spectral ba
Controller synthesis is a formal method approach for automatically generating Labeled Transition System (LTS) controllers that satisfy specified properties. The efficiency of the synthesis process, however, is critically dependent on exploration policies. These policies often rely on fixed rules or
We introduce a new tokenizer for language models that minimizes the average tokens per character, thereby reducing the number of tokens needed to represent text during training and to generate text during inference. Our method, which we refer to as the Length-MAX tokenizer, obtains its vocabulary by
We study whether a Large Language Model can learn the deterministic sequence of trees generated by the iterated prime factorization of the natural numbers. Each integer is mapped into a rooted planar tree and the resulting sequence NT defines an arithmetic text with measurable statistical structure.
Large language models (LLMs) and autonomous coding agents are increasingly used to generate software across a wide range of domains. Yet a core requirement remains unmet: ensuring that generated code is secure without compromising its functional correctness. Existing benchmarks and evaluations for s
We present M 3 -Bench, the first benchmark for evaluating multimodal tool use under the Model Context Protocol. The benchmark targets realistic, multi-hop and multi-threaded workflows that require visual grounding and textual reasoning, cross-tool dependencies, and persistence of intermediate resour
This paper argues that the traditional opposition between determinism and indeterminism in physics is representational rather than ontological. Deterministic-stochastic dualities are available in principle, and arise in a non-contrived way in many scientifically important models. When dynamical syst
Masked diffusion language models (MDLMs) offer the potential for parallel token generation, but most open-source MDLMs decode fewer than 5 tokens per model forward pass even with sophisticated sampling strategies. As a result, their sampling speeds are often comparable to AR + speculative decoding s
Offline Reinforcement Learning (RL) provides a promising avenue for training policies from pre-collected datasets when gathering additional interaction data is infeasible. However, existing offline RL methods often assume stationarity or only consider synthetic perturbations at test time, assumption
We study how generative artificial intelligence (AI) transforms the work of financial analysts. Using the 2023 launch of FactSet's AI platform as a natural experiment, we find that adoption produces markedly richer and more comprehensive reports-featuring 40% more distinct information sources, 34% b
Generative search engines based on large language models (LLMs) are replacing traditional search, fundamentally changing how information providers are compensated. To sustain this ecosystem, we need fair mechanisms to attribute and compensate content providers based on their contributions to generat
Transformers operate as horizontal token-bytoken scanners; at each generation step, attending to an ever-growing sequence of tokenlevel states. This access pattern increases prefill latency and makes long-context decoding more memory-bound, as KV-cache reads and writes dominate inference time over a
Urinary tract infection (UTI) flare-ups pose a significant health risk for older adults with chronic conditions. These infections often go unnoticed until they become severe, making early detection through innovative smart home technologies crucial. Traditional machine learning (ML) approaches relyi
Manual generation of G-code is important for learning the operation of CNC machines. Prior work in G-code verification uses Large-Language Models (LLMs), which primarily examine errors in the written programming. However, CNC machining requires extensive use and knowledge of the Human-Machine Interf
Foundation models (FMs) have opened new avenues for machine learning applications due to their ability to adapt to new and unseen tasks with minimal or no further training. Time-series foundation models (TSFMs)-FMs trained on time-series data-have shown strong performance on classification, regressi
Large Language Model (LLM)-based multi-agent systems (MAS) have become indispensable building blocks for web-scale applications (e.g., web search, social network analytics, online customer support), with cost-effectiveness becoming the primary constraint on large-scale deployment. While recent advan
Medical imaging is essential for clinical diagnosis, yet realworld data frequently suffers from corruption, noise, and potential tampering, challenging the reliability of AI-assisted interpretation. Conventional reconstruction techniques prioritize pixel-level recovery and may produce visually plaus
Enhancing low-light traffic imagery is a critical requirement for achieving reliable perception in autonomous driving, intelligent transportation, and urban surveillance systems. Traffic scenes captured under nighttime or dimly lit conditions often suffer from complex visual degradations arising fro
This paper compares Kolmogorov-Arnold Networks (KAN) and Long Short-Term Memory networks (LSTM) for forecasting non-deterministic stock price data, evaluating predictive accuracy versus interpretability trade-offs using Root Mean Square Error (RMSE). LSTM demonstrates substantial superiority across
Large language models (LLMs) demonstrate significant potential for educational applications. However, their unscrutinized deployment poses risks to educational standards, underscoring the need for rigorous evaluation. We introduce EduEval, a comprehensive hierarchical benchmark for evaluating LLMs i
This paper investigates the determination of the Qibla direction using both astronomical and geometrical approaches. The study reviews historical and classical methods employed by Muslim scholars and astronomers including the use of instruments such as the astrolabe and compass. It further explores
a person wearing decorative forehead jewelry, speaking' 'a person speaking with burning trees in the background' Source Video Edited First Frame 'a person wearing a fedora hat, speaking and moving his hand' Figure 1 . Given a source video and an edited first frame, our method propagates the visua
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 when these agents operate over sensitive user serv
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 monolithic neural networks that enforce global conti
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 hardware performance drops sharply with sequence lengt
This research full paper presents an enhancement pipeline for large language models (LLMs) in assessing homework for an undergraduate circuit analysis course, aiming to improve LLMs' capacity to provide personalized support to electrical engineering students. Existing evaluations have demonstrated t
Recent approaches employing imperceptible perturbations in input images have demonstrated promising potential to counter malicious manipulations in diffusion-based image editing systems. However, existing methods suffer from limited transferability in cross-model evaluations. To address this, we pro
Streamflow forecasting is crucial for water resource management and risk mitigation. While deep learning models have achieved strong predictive performance, they often overlook underlying physical processes, limiting interpretability and generalization. Recent causal learning approaches address thes
Optimizing CUDA kernels is a challenging and labor-intensive task, given the need for hardware-software co-design expertise and the proprietary nature of high-performance kernel libraries. While recent large language models (LLMs) combined with evolutionary algorithms show promise in automatic kerne
We develop a transparent and fully auditable LLM-based pipeline for macro-financial stress testing, combining structured prompting with optional retrieval of country fundamentals and news. The system generates machine-readable macroeconomic scenarios for the G7, which cover GDP growth, inflation, an
Embodied intelligence, a grand challenge in artificial intelligence, is fundamentally constrained by the limited spatial understanding and reasoning capabilities of current models. Prevailing efforts to address this through enhancing Vision-Language Models (VLMs) are trapped in a dilemma: template-b
Agentic AI is increasingly being explored and introduced in both manually driven and autonomous vehicles, leading to the notion of Agentic Vehicles (AgVs), with capabilities such as memory-based personalization, goal interpretation, strategic reasoning, and tool-mediated assistance. While frameworks
Heterogeneous graphs are widely present in real-world complex networks, where the diversity of node and relation types leads to complex and rich semantics. Efforts for modeling complex relation semantics in heterogeneous graphs are restricted by the limitations of predefined semantic dependencies an
Validation gating is a fundamental component of classical Kalman-based tracking systems. Only measurements whose normalized innovation squared (NIS) falls below a prescribed threshold are considered for state update. While this procedure is statistically motivated by the chi-square distribution, it
Enter keywords to search articles