Heatmap-based non-autoregressive solvers for large-scale Travelling Salesman Problems output dense edge-probability scores, yet final performance largely hinges...
Raga identification in Indian Art Music (IAM) remains challenging due to the presence of numerous rarely performed Ragas that are not represented in available t...
The reliability of Large Language Models (LLMs) in high-stakes domains such as healthcare, law, and scientific discovery is often compromised by hallucinations....
The automatic generation of pull requests (PRs) using AI agents has become increasingly common. Although AI-generated PRs are fast and easy to create, their mer...
Talking Head Generation aims at synthesizing natural-looking talking videos from speech and a single portrait image. Previous 3D talking head generation methods...
The global optimization of atomic clusters represents a fundamental challenge in computational chemistry and materials science due to the exponential growth of ...
Machine Learning (ML) Operations (MLOps) frameworks have been conceived to support developers and AI engineers in managing the lifecycle of their ML models. Whi...
To address the 'novelty-vicious cycle' and the 'replicability crisis' of the field (both discussed in the survey) we propose abolishing the 'ICSE paper' as we k...
Evolutionary algorithms (EAs) are increasingly implemented on graphics processing units (GPUs) to leverage parallel processing capabilities for enhanced efficie...
With the advent of blockchain technology, the number of proposals has boomed. The network traffic imposed by these blockchain proposals increases the cost of ho...
In recent years, Spiking Neural Networks (SNNs) have achieved remarkable progress, with Spiking Transformers emerging as a promising architecture for energy-eff...
Ransomware variants increasingly combine privilege escalation with sophisticated evasion strategies such as intermittent encryption, low-entropy encryption, and...
Verilog's design cycle is inherently labor-intensive and necessitates extensive domain expertise. Although Large Language Models (LLMs) offer a promising pathwa...
We introduce Resonant Sparse Geometry Networks (RSGN), a brain-inspired architecture with self-organizing sparse hierarchical input-dependent connectivity. Unli...
Auditability and reproducibility still are critical challenges for real-time data streams pipelines. Streaming engines are highly dependent on runtime schedulin...
Despite recent progress, medical foundation models still struggle to unify visual understanding and generation, as these tasks have inherently conflicting goals...
Frontier LLMs are increasingly utilised across academia, society and industry. A commonly used unit for comparing models, their inputs and outputs, and estimati...
Large reasoning models (LRMs) produce a textual chain of thought (CoT) in the process of solving a problem, which serves as a potentially powerful tool to under...
Frontier language model capabilities are improving rapidly. We thus need stronger mitigations against bad actors misusing increasingly powerful systems. Prior w...
Recent advances in 3D shape generation have achieved impressive results, but most existing methods rely on clean, unoccluded, and well-segmented inputs. Such co...
While using formal methods offers advantages over unit testing, their steep learning curve can be daunting to developers and can be a major impediment to widesp...
Indoor environments evolve as objects move, appear, or disappear. Capturing these dynamics requires maintaining temporally consistent instance identities across...
Progress in Type 1 Diabetes (T1D) algorithm development is limited by the fragmentation and lack of standardization across existing T1D management datasets. Cur...
Smart grid infrastructures have revolutionized energy distribution, but their day-to-day operations require robust anomaly detection methods to counter risks as...
