Spatial question answering over egocentric video is a challenging task that requires Vision-Language Models (VLMs) to reason about 3D object positions, scene af...
Current approaches to 3D scene graph generation rely on dedicated depth sensors, such as LiDAR or RGB-D cameras, for metric 3D reconstruction. This limits deplo...
While Multi-Modal Large Language Models (MLLMs) demonstrate impressive capabilities in general reasoning, their embodied spatial intelligence remains hampered b...
Automated vulnerability detection is crucial for enhancing software security by identifying potential flaws that attackers could exploit, thereby reducing the r...
Large Language Models (LLMs) demonstrate strong potential for automated code generation, yet their ability to iteratively refine solutions using execution feedb...
Multi-agent LLM workflows -- systems composed of multiple role-specific LLM calls -- often outperform single-prompt baselines, but they remain difficult to debu...
Production log analytics in self-hosted, resource-constrained environments requires natural-language access to massive log streams without the cost of routing e...
Deploying adaptive intelligence at the edge remains challenging due to the high computational and energy cost of training neural models. Spiking Neural Networks...
Optimization problems in real-world applications across the medical and engineering domains often involve potential risks when evaluating candidate solutions. S...
Von Economo neurons (VENs) are selectively lost in behavioural-variant frontotemporal dementia (bvFTD) and reduced in autism spectrum conditions (ASC), yet thei...
This study develops and evaluates a deep reinforcement learning framework for dynamic portfolio allocation across global equity markets. The Soft Actor-Critic a...
The Manta Ray Foraging Optimization algorithm (MRFO) has proven to be a powerful heuristic strategy in the optimal solution of a large number of engineering pro...
Reconstructing coherent 3D geometry and appearance from unposed multi-view images is a fundamental yet challenging problem in computer vision. Most existing vis...
Demand for AI accelerators is rapidly increasing rack power density, with projections approaching 1MW per deployment by 2027. This poses a major challenge for d...
Distribution utilities are now expected to deliver bills that customers can actually read attach a defensible carbon number to every kWh sold and schedule load ...
Generative artificial intelligence (AI) is increasingly integrated into the online platforms where humans exchange opinions; large language models (LLMs) now po...
Billion-parameter Vision-Language-Action (VLA) policies have recently shown impressive performance in robotic manipulation, yet their size and inference cost re...
We introduce a dynamics-level approach to watermarking generative models. Rather than embedding signals into model weights or outputs, we embed the watermark di...
Probabilistic forecasting of infectious diseases is crucial for public health but relies on labor-intensive manual model curation by expert modeling teams. This...
When researchers ask whether two transformer layers are 'equivalent' for compression, they often conflate distinct tests. Replacement asks whether one layer's m...
Can LLM agents improve decision-making through self-generated memory without gradient updates? We propose FORGE (Failure-Optimized Reflective Graduation and Evo...
The accelerating convergence of smart metering, generative artificial intelligence, and quantum-inspired combinatorial optimisation is reshaping how energy util...
Magnetic order is a fundamental property of materials, governing collective behavior and enabling a broad range of functionalities. Yet magnetic structure remai...
Generative video models are increasingly used in design animation tasks, yet no standardized evaluation framework exists for this domain. Unlike natural video g...
Aphasias, selective language impairments which can arise from brain damage, reveal the functional organization of human language by providing causal links betwe...
Differential privacy changes the effective sample size governing CVaR learning. For tail mass τ, the privacy-relevant sample size is not n, but nτ; equivalently...
Deep research agents have achieved remarkable progress on complex information seeking tasks. Even long ReAct style rollouts explore only a single trajectory, wh...
Clinical decision support systems (CDSS) require scrutable, auditable pipelines that enable rigorous, reproducible validation. Yet current LLM-based CDSS remain...
Traditional scientific modeling typically begins with fixed, instance-wise effective equations and then carries out equation-specific analysis and computation, ...
Effective tutoring requires distinguishing optimal, valid but suboptimal, and incorrect student solutions, a distinction central to intelligent tutoring systems...
Deploying compound LLM agents in adversarial, partially observable sequential environments requires navigating several design dimensions: (1) what the agent see...
Second-order methods offer an attractive path toward more sample-efficient LLM training, but their practical use is often blocked by the systems cost of maintai...
Temporal random walks, which sample causality-preserving paths, are widely used to analyze time-stamped interactions in domains such as microservices, finance, ...
Agricultural landscape segmentation in the Global South is challenging as it is characterized by fragmented plots, high intra-class variance, and a scarcity of ...
Few-shot Generalist Anomaly Detection requires models to generalize to novel categories without retraining, posing significant challenges in real-world scenario...
Ransomware recovery in critical manufacturing infrastructure is not only a backup-restoration problem. Production capability depends on coupled information-tech...
Autoregressive next-token training offers a unified formulation for image generation and text understanding, but it also creates strong modality competition tha...
Vision Transformers (ViTs) are known to exhibit high-norm patch-token outliers that degrade feature map quality, a problem effectively mitigated by register tok...
Generating simulation-ready tabletop scenes from task instructions is an intriguing and promising research direction in the field of Embodied AI. However, exist...
Technical Debt (TD) refers to the long-term costs incurred when developers prioritize short-term delivery over quality-improving work. Architectural Technical D...
While multi-modal 3D semantic occupancy prediction typically enhances robustness by fusing camera and LiDAR inputs, its effectiveness is fundamentally constrain...
Diffusion-based image synthesis has made AI-generated images (AIGI) increasingly photorealistic, raising urgent concerns about authenticity in applications such...
We propose a scalable neuromorphic architecture based on spiking dynamics emerging from the autonomous time-continuous evolution of clockless (asynchronous) dig...
Federated learning (FL) is vulnerable to data poisoning attacks due to its distributed nature. Although recent GAN-based data poisoning methods have indicated t...
Unstructured-mesh ocean models are increasingly used for coastal applications due to their ability to represent complex geometries and apply local grid refineme...
In the era of big data, effectively compressing large datasets while performing complex mathematical operations is crucial. Tensor-based decomposition methods h...
Semantic code search has been widely adopted in both academia and industry. These approaches embed natural-language queries and code snippets into a shared embe...
We introduce thermodynamic networks, a general framework for autonomous, physics-based computation using non-equilibrium steady states. These networks are model...
