Related papers: The Phantom of PCIe: Constraining Generative Artif…
Efficient parallelism is necessary for achieving low-latency, high-throughput inference with large language models (LLMs). Tensor parallelism (TP) is the state-of-the-art method for reducing LLM response latency, however GPU communications…
Co-expression network is a critical technique for the identification of inter-gene interactions, which usually relies on all-pairs correlation (or similar measure) computation between gene expression profiles across multiple samples.…
Generating high-quality images without prompt engineering expertise remains a challenge for text-to-image (T2I) models, which often misinterpret poorly structured prompts, leading to distortions and misalignments. While humans easily…
Large language models (LLMs) have transformed artificial intelligence, but their computational requirements remain prohibitive for most users. Standard inference demands expensive datacenter GPUs or cloud API access, leaving over one…
In modern computer architectures, the performance of many memory-bound workloads (e.g., machine learning, graph processing, databases) is limited by the data movement bottleneck that emerges when transferring large amounts of data between…
Discovering novel high-level concepts is one of the most important steps needed for human-level AI. In inductive logic programming (ILP), discovering novel high-level concepts is known as predicate invention (PI). Although seen as crucial…
In collaborative systems with complex tasks relying on distributed resources, trust evaluation of potential collaborators has emerged as an effective mechanism for task completion. However, due to the network dynamics and varying…
Although large language models (LLMs) excel in complex reasoning tasks, they suffer from severe causal hallucination in event causality identification (ECI), particularly in smaller models ($\leq$1.5B parameters). A promising approach to…
We present the Lightweight Parallel Foundations (LPF), an interoperable and model-compliant communication layer adhering to a strict performance model of parallel computations. LPF consists of twelve primitives, each with strict performance…
Diffusion models have exhibited exciting capabilities in generating images and are also very promising for video creation. However, the inference speed of diffusion models is limited by the slow sampling process, restricting its use cases.…
Modern LLM serving is no longer homogeneous or monolithic. Production systems now combine disaggregated execution, complex parallelism, runtime optimizations, and stateful workloads such as reasoning, agents, and RL rollouts. Simulation is…
Hardware peripherals such as GPUs and FPGAs are commonly available in server-grade computing to accelerate specific compute tasks, from database queries to machine learning. CSPs have integrated these accelerators into their infrastructure…
How humans and machines make sense of current inputs for relation reasoning and question-answering while putting the perceived information into context of our past memories, has been a challenging conundrum in cognitive science and…
We study Transformers on the task \emph{program trace generation} (PTG), where models produce step-by-step execution traces for synthetic programs. Unlike existing algorithmic problems, PTG externalizes reasoning through long traces where…
Artificial intelligence (AI) research today is largely driven by ever-larger neural network models trained on graphics processing units (GPUs). This paradigm has yielded remarkable progress, but it also risks entrenching a hardware lottery…
The widespread 'deeper is better' philosophy has driven the creation of architectures like ResNet and Transformer, which achieve high performance by stacking numerous layers. However, increasing model depth comes with challenges such as…
The growing demand for efficient, high-performance processing in machine learning (ML) and image processing has made hardware accelerators, such as GPUs and Data Streaming Accelerators (DSAs), increasingly essential. These accelerators…
This research introduces Procedural Artificial Narrative using Generative AI (PANGeA), a structured approach for leveraging large language models (LLMs), guided by a game designer's high-level criteria, to generate narrative content for…
Modern text-to-image (T2I) generation systems (e.g., DALL$\cdot$E 3) exploit the memory mechanism, which captures key information in multi-turn interactions for faithful generation. Despite its practicality, the security analyses of this…
The growing realism of AI-generated images produced by recent GAN and diffusion models has intensified concerns over the reliability of visual media. Yet, despite notable progress in deepfake detection, current forensic systems degrade…