Related papers: DVM: A Bytecode Virtual Machine Approach for Dynam…
Efficient transformer variants with linear time complexity have been developed to mitigate the quadratic computational overhead of the vanilla transformer. Among them are low-rank projection methods such as Linformer and kernel-based…
Existing iterative compilation and machine-learning-based optimization techniques have been proven very successful in achieving better optimizations than the standard optimization levels of a compiler. However, they were not engineered to…
We consider the problem of coded distributed computing where a large linear computational job, such as a matrix multiplication, is divided into $k$ smaller tasks, encoded using an $(n,k)$ linear code, and performed over $n$ distributed…
In the era of big data, effectively compressing large datasets while performing complex mathematical operations is crucial. Tensor-based decomposition methods have shown superior compression capabilities with minimal loss of accuracy…
In this paper, we introduce LightVLM, a simple but effective method that can be seamlessly deployed upon existing Vision-Language Models (VLMs) to greatly accelerate the inference process in a training-free manner. We divide the inference…
Semantic segmentation remains a computationally intensive algorithm for embedded deployment even with the rapid growth of computation power. Thus efficient network design is a critical aspect especially for applications like automated…
Quantum computation is a promising emerging technology which, compared to conventional computation, allows for substantial speed-ups e.g. for integer factorization or database search. However, since physical realizations of quantum…
We present ShapeFlow, a dynamic abstract interpreter for TensorFlow which quickly catches tensor shape incompatibility errors, one of the most common bugs in deep learning code. ShapeFlow shares the same APIs as TensorFlow but only captures…
Long-form video question answering (VQA) overwhelms current vision-language models (VLMs) because attention and key-value (KV) caches grow with runtime, forcing either expensive inference or near-sighted sliding windows. We introduce…
Many recent machine learning models rely on fine-grained dynamic control flow for training and inference. In particular, models based on recurrent neural networks and on reinforcement learning depend on recurrence relations, data-dependent…
The run time of many scientific computation applications for numerical methods is heavily dependent on just a few multi-dimensional loop nests. Since these applications are often limited by memory bandwidth rather than computational…
Dynamic Vision Sensor (DVS) event camera models are important tools for predicting camera response, optimizing biases, and generating realistic simulated datasets. Existing DVS models have been useful, but have not demonstrated high realism…
This letter presents a method to reduce the computational demands of including second-order dynamics sensitivity information into the Differential Dynamic Programming (DDP) trajectory optimization algorithm. An approach to DDP is developed…
As large language models engage in extended reasoning tasks, they accumulate significant state -- architectural mappings, trade-off decisions, codebase conventions -- within the context window. This understanding is lost when sessions reach…
Scaling the input image resolution is essential for enhancing the performance of Vision Language Models (VLMs), particularly in text-rich image understanding tasks. However, popular visual encoders such as ViTs become inefficient at high…
Electronic structure calculations of molecular systems are among the most promising applications for fault-tolerant quantum computing (FTQC) in quantum chemistry and drug design. However, while recent algorithmic advancements such as…
Semantic segmentation assigns labels to pixels in images, a critical yet challenging task in computer vision. Convolutional methods, although capturing local dependencies well, struggle with long-range relationships. Vision Transformers…
Conventional pedestrian simulators are inevitable tools in the design process of a building, as they enable project engineers to prevent overcrowding situations and plan escape routes for evacuation. However, simulation runtime and the…
Vision Transformers (ViTs) have achieved state-of-the-art performance on various vision tasks. However, ViTs' self-attention module is still arguably a major bottleneck, limiting their achievable hardware efficiency. Meanwhile, existing…
Modern GPUs increasingly rely on specialized and asynchronous hardware units to deliver high performance. Yet these units are often underutilized because today's GPU software stacks still organize programming and execution around a…