相关论文: Demand-Driven Pointer Analysis with Strong Updates…
Motivated by the need for adaptive, secure and responsive scheduling in a great range of computing applications, including human-centered and time-critical applications, this paper proposes a scheduling framework that seamlessly adds…
Distributed Stream Processing (DSP) focuses on the near real-time processing of large streams of unbounded data. To increase processing capacities, DSP systems are able to dynamically scale across a cluster of commodity nodes, ensuring a…
In recent years, interest in vision-language tasks has grown, especially those involving chart interactions. These tasks are inherently multimodal, requiring models to process chart images, accompanying text, underlying data tables, and…
Generative Recommendation (GR) has recently transitioned from atomic item-indexing to Semantic ID (SID)-based frameworks to capture intrinsic item relationships and enhance generalization. However, the adoption of high-granularity SIDs…
Vision-Language-Action (VLA) models have emerged as a unified paradigm for robotic perception and control, enabling emergent generalization and long-horizon task execution. However, their deployment in dynamic, real-world environments is…
Bounded-memory computability continues to be in the focus of those areas of AI and databases that deal with feasible computations over streams---be it feasible arithmetical calculations on low-level streams or feasible query answering for…
Attention calculation is extremely time-consuming for long-sequence inference tasks, such as text or image/video generation, in large models. To accelerate this process, we developed a low-precision, mathematically-equivalent algorithm…
Data analysts working with relational data often start with vague or underspecified questions and refine them iteratively as they explore the data. To support this iterative process, we demonstrate Pneuma-Seeker, a system that reifies a…
Diffusion- and flow-based policies deliver state-of-the-art performance on long-horizon robotic manipulation and imitation learning tasks. However, these controllers employ a fixed inference budget at every control step, regardless of task…
In the weighted flow-time problem on a single machine, we are given a set of n jobs, where each job has a processing requirement p_j, release date r_j and weight w_j. The goal is to find a preemptive schedule which minimizes the sum of…
Optical flow is a regression task where convolutional neural networks (CNNs) have led to major breakthroughs. However, this comes at major computational demands due to the use of cost-volumes and pyramidal representations. This was…
Attention mechanisms have been widely used to capture long-range dependencies among nodes in Graph Transformers. Bottlenecked by the quadratic computational cost, attention mechanisms fail to scale in large graphs. Recent improvements in…
This paper presents a parameter-efficient prompt tuning method, named PPT, to adapt a large multi-modal model for 3D point cloud understanding. Existing strategies are quite expensive in computation and storage, and depend on time-consuming…
Benefiting from the self-attention mechanism, Transformer models have attained impressive contextual comprehension capabilities for lengthy texts. The requirements of high-throughput inference arise as the large language models (LLMs)…
Histograms are widely used in medical imaging, network intrusion detection, packet analysis and other stream-based high throughput applications. However, while porting such software stacks to the GPU, the computation of the histogram is a…
Data-flow analyses like points-to analysis can vastly improve the precision of other analyses, and help perform powerful code optimizations. However, whole-program points-to analysis of large programs tend to be expensive - both in terms of…
The human brain uses selective attention to filter perceptual input so that only the components that are useful for behaviour are processed using its limited computational resources. We focus on one particular form of visual attention known…
Region proposal is critical for object detection while it usually poses a bottleneck in improving the computation efficiency on traditional control-flow architectures. We have observed region proposal tasks are potentially suitable for…
Traditional control-flow analysis (CFA) for higher-order languages, whether implemented by constraint-solving or abstract interpretation, introduces spurious connections between callers and callees. Two distinct invocations of a function…
Long-sequence state-space models (SSMs) such as Hyena and Mamba replace the quadratic complexity of self-attention with more efficient FFT and scan operations. However, modern accelerators like GPUs are poorly suited to these non-GEMM…