Large Language Models (LLMs) have achieved impressive results across various tasks, yet their high computational demands pose deployment challenges, especially ...
In this paper, we describe a federated compute platform dedicated to support Artificial Intelligence in scientific workloads. Putting the effort into reproducib...
Choosing the number of topics T in Latent Dirichlet Allocation (LDA) is a key design decision that strongly affects both the statistical fit and interpretabilit...
How can neural networks evolve themselves without relying on external optimizers? We propose Self-Referential Graph HyperNetworks, systems where the very machin...
Attention is the dominant source of latency during long-context LLM inference, an increasingly popular workload with reasoning models and RAG. We propose Kascad...
Background: Compilers are fundamental to software development, translating high-level source code into executable software systems. Faults in compilers can have...
Large Language Models are increasingly deployed as judges (LaaJ) in code generation pipelines. While attractive for scalability, LaaJs tend to overlook domain s...
Spiking neurons, the fundamental information processing units of Spiking Neural Networks (SNNs), have the all-or-zero information output form that allows SNNs t...
Rank-based zeroth-order (ZO) optimization -- which relies only on the ordering of function evaluations -- offers strong robustness to noise and monotone transfo...
Disaggregated memory (DM) is a promising data center architecture that decouples CPU and memory into independent resource pools to improve resource utilization....
Apache Kafka has become a foundational platform for high throughput event streaming, enabling real time analytics, financial transaction processing, industrial ...
Disaggregated memory (DM) separates compute and memory resources, allowing flexible scaling to achieve high resource utilization. To ensure atomic and consisten...
The evolution of Large Language Model (LLM) serving towards complex, distributed architectures--specifically the P/D-separated, large-scale DP+EP paradigm--intr...
The performance of modern software systems is critically dependent on their complex configuration options. Building accurate performance models to navigate this...
Overview Most organisations don’t fail at “digital” because they can’t build software; they fail because they under‑invest in the work that delivers better dig...
As an increasing number of software systems reach unprecedented scale, relying solely on code-level abstractions is becoming impractical. While architectural ab...
Symbolic regression (SR) has emerged as a powerful method for uncovering interpretable mathematical relationships from data, offering a novel route to both scie...
Existing video generation models struggle to maintain long-term spatial and temporal consistency due to the dense, high-dimensional nature of video signals. To ...
At the most basic level, pixels are the source of the visual information through which we perceive the world. Pixels contain information at all levels, ranging ...
In recent multimodal research, the diffusion paradigm has emerged as a promising alternative to the autoregressive paradigm (AR), owing to its unique decoding a...
Interpreting the internal activations of neural networks can produce more faithful explanations of their behavior, but is difficult due to the complex structure...
We present Gaussian Pixel Codec Avatars (GPiCA), photorealistic head avatars that can be generated from multi-view images and efficiently rendered on mobile dev...
This paper proposes a dual-engine AI architectural method designed to address the complex problem of exploring potential trajectories in the evolution of art. W...
Foundation models are vital tools in various Computer Vision applications. They take as input a single RGB image and output a deep feature representation that i...
