Related papers: Spineless Traversal for Layout Invalidation
Automated parsing of scanned documents into richly structured, machine-readable formats remains a critical bottleneck in Document AI, as traditional multi-stage pipelines suffer from error propagation and limited adaptability to diverse…
This paper presents a method for robust optimization for online incremental Simultaneous Localization and Mapping (SLAM). Due to the NP-Hardness of data association in the presence of perceptual aliasing, tractable (approximate) approaches…
Scalable web search systems typically employ multi-stage retrieval architectures, where an initial stage generates a set of candidate documents that are then pruned and re-ranked. Since subsequent stages typically exploit a multitude of…
In this paper, we present an advanced approach to solving the inverse rig problem in blendshape animation, using high-quality corrective blendshapes. Our algorithm introduces novel enhancements in three key areas: ensuring high data…
Noisy marginals are a common form of confidentiality protecting data release and are useful for many downstream tasks such as contingency table analysis, construction of Bayesian networks, and even synthetic data generation. Privacy…
The past few years have witnessed a growing interest in LLM-based recommender systems (RSs), although their industrial deployment remains in a preliminary stage. Most existing deployments leverage LLMs offline as feature enhancers,…
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…
Programming with replicated objects is difficult. Developers must face the fundamental trade-off between consistency and performance head on, while struggling with the complexity of distributed storage stacks. We introduce Correctables, a…
We propose a novel feature re-identification method for real-time visual-inertial SLAM. The front-end module of the state-of-the-art visual-inertial SLAM methods (e.g. visual feature extraction and matching schemes) relies on feature tracks…
An algorithm based on Artificial Neural Networks is proposed in this paper to improve the accuracy of Inertial Navigation System (INS)/ Global Navigation Satellite System (GNSS) integrated navigation during the absence of GNSS signals. The…
The inspection-planning problem calls for computing motions for a robot that allow it to inspect a set of points of interest (POIs) while considering plan quality (e.g., plan length). This problem has applications across many domains where…
Graphics rendering applications increasingly leverage neural networks in tasks such as denoising, supersampling, and frame extrapolation to improve image quality while maintaining frame rates. The temporal coherence inherent in these tasks…
Recent advances in large reasoning models have been driven by reinforcement learning and test-time scaling, accompanied by growing interest in latent rather than purely textual reasoning. However, existing latent reasoning methods lack…
As demand for Real-Time applications rises among the general public, the importance of enabling large-scale, unbound algorithms to solve conventional problems with low to no latency is critical for product viability. Timer algorithms are…
Serverless computing has grown rapidly for serving Large Language Model (LLM) inference due to its pay-as-you-go pricing, fine-grained GPU usage, and rapid scaling. However, our analysis reveals that current serverless can effectively serve…
This paper presents a generic pre-processor for expediting conventional template matching techniques. Instead of locating the best matched patch in the reference image to a query template via exhaustive search, the proposed algorithm rules…
As memory capacity has outstripped TLB coverage, large data applications suffer from frequent page table walks. We investigate two complementary techniques for addressing this cost: reducing the number of accesses required and reducing the…
Shift operation is an efficient alternative over depthwise separable convolution. However, it is still bottlenecked by its implementation manner, namely memory movement. To put this direction forward, a new and novel basic component named…
With the continuous development of neural networks for computer vision tasks, more and more network architectures have achieved outstanding success. As one of the most advanced neural network architectures, DenseNet shortcuts all feature…
We study index-based processing for connectivity queries within sliding windows on streaming graphs. These queries, which determine whether two vertices belong to the same connected component, are fundamental operations in real-time graph…