Related papers: Designing and Implementing a Generator Framework f…
Real world collection of Activities of Daily Living data is challenging due to privacy concerns, costly deployment and labeling, and the inherent sparsity and imbalance of human behavior. We present ADLGen, a generative framework…
Contextual sparsity is one of the approaches used to reduce computational complexity in the inference process of large language models (LLMs). Existing techniques for efficient LLM inference acceleration based on contextual sparsity with…
We propose a language and compiler to productively build high-performance {\it software systolic arrays} that run on GPUs. Based on a rigorous mathematical foundation (uniform recurrence equations and space-time transform), our language has…
Multimodal Large Language Models (MLLMs) have achieved remarkable advances by integrating text, image, and audio understanding within a unified architecture. However, existing distributed training frameworks remain fundamentally data-blind:…
Visual Simultaneous Localization and Mapping (VSLAM) research faces significant challenges due to fragmented toolchains, complex system configurations, and inconsistent evaluation methodologies. To address these issues, we present…
In today's production machine learning (ML) systems, models are continuously trained, improved, and deployed. ML design and training are becoming a continuous workflow of various tasks that have dynamic resource demands. Serverless…
Recently, large language models (LLMs) have achieved huge success in the natural language processing (NLP) field, driving a growing demand to extend their deployment from the cloud to edge devices. However, deploying LLMs on…
The growing demand for deploying Small Language Models (SLMs) on edge devices, including laptops, smartphones, and embedded platforms, has exposed fundamental inefficiencies in existing accelerators. While GPUs handle prefill workloads…
Stochastic Gradient Descent (SGD) is a popular algorithm that can achieve state-of-the-art performance on a variety of machine learning tasks. Several researchers have recently proposed schemes to parallelize SGD, but all require…
How to generate testing scenario libraries for connected and automated vehicles (CAVs) is a major challenge faced by the industry. In previous studies, to evaluate maneuver challenge of a scenario, surrogate models (SMs) are often used…
The SIMT execution model is commonly used for general GPU development. CUDA and OpenCL developers write scalar code that is implicitly parallelized by compiler and hardware. On Intel GPUs, however, this abstraction has profound performance…
Skill libraries have become a practical way for LLM agents to reuse procedural experience across tasks. However, existing systems typically treat skills as flat, single-resolution prompt blocks. This creates a tension between relevance and…
To overcome the well-known memory bottleneck of AI chips, 3D stacked architectures that employ advanced packaging technology with high-density through-silicon vias (TSVs) pins have proven to be a promising solution. The 3D-stacked AI chip…
The ever-increasing size and computational complexity of today's machine-learning algorithms pose an increasing strain on the underlying hardware. In this light, novel and dedicated architectural solutions are required to optimize energy…
Hybrid parallelism underpins large-scale LLM training across tens of thousands of GPUs. At such scale, hardware failures on individual devices lead to performance skew across devices, diminishing overall training efficiency. Existing…
High-level synthesis (HLS) allows hardware designers to create hardware designs with high-level programming languages like C/C++/OpenCL, which greatly improves hardware design productivity. However, existing HLS flows require programmers'…
An abstraction can be used to relate two structural causal models representing the same system at different levels of resolution. Learning abstractions which guarantee consistency with respect to interventional distributions would allow one…
Stylized abstraction synthesizes visually exaggerated yet semantically faithful representations of subjects, balancing recognizability with perceptual distortion. Unlike image-to-image translation, which prioritizes structural fidelity,…
Vision-Language Models (VLMs) excel at understanding single images, aided by high-quality instruction datasets. However, multi-image reasoning remains underexplored in the open-source community due to two key challenges: (1) scaling…
The growing demands of distributed learning on resource constrained edge devices underscore the importance of efficient on device model compression. Tensor Train Decomposition (TTD) offers high compression ratios with minimal accuracy loss,…