In this work, we present SafePlanner, a systematic testing framework for identifying safety-critical flaws in the Plan model of Automated Driving Systems (ADS)....
Differentially private federated learning (DP-FL) suffers from slow convergence under tight privacy budgets due to the overwhelming noise introduced to preserve...
We present a transaction-driven dynamic reconfiguration protocol in Modern payment systems based on Byzantine Consistent Broadcast which can achieve high perfor...
The GEneral Matrix Multiplication (GEMM) is one of the essential algorithms in scientific computing. Single-thread GEMM implementations are well-optimised with ...
Split Federated Learning (SFL) enables collaborative training between resource-constrained edge devices and a compute-rich server. Communication overhead is a c...
Invisible watermarking has become a critical mechanism for authenticating AI-generated image content, with major platforms deploying watermarking schemes at sca...
Video object segmentation methods like SAM2 achieve strong performance through memory-based architectures but struggle under large viewpoint changes due to reli...
In this work, we explore the Large Language Model (LLM) agent reviewer dynamics in an Elo-ranked review system using real-world conference paper submissions. Mu...
Despite the rapid progress of video generation models, the role of data in influencing motion is poorly understood. We present Motive (MOTIon attribution for Vi...
The evolution of recommender systems has shifted preference storage from rating matrices and dense embeddings to semantic memory in the agentic era. Yet existin...
The recent development of Large Language Models (LLMs) with strong reasoning ability has driven research in various domains such as mathematics, coding, and sci...
Large language models often solve complex reasoning tasks more effectively with Chain-of-Thought (CoT), but at the cost of long, low-bandwidth token sequences. ...
