Related papers: F-coref: Fast, Accurate and Easy to Use Coreferenc…

Performance of object detection models has been growing rapidly on two major fronts, model accuracy and efficiency. However, in order to map deep neural network (DNN) based object detection models to edge devices, one typically needs to…

In long-context large language model (LLM) inference, the prefill stage dominates computation due to self-attention over the complete input context. Sparse attention significantly reduces self-attention computation by limiting each token's…

Long-context transformers face significant efficiency challenges due to the quadratic cost of self-attention. However, many modern applications-from multi-turn dialogue to high-resolution vision-require contexts spanning tens of thousands…

Previous attempts to incorporate a mention detection step into end-to-end neural coreference resolution for English have been hampered by the lack of singleton mention span data as well as other entity information. This paper presents a…

We present a novel method for efficiently producing semi-dense matches across images. Previous detector-free matcher LoFTR has shown remarkable matching capability in handling large-viewpoint change and texture-poor scenarios but suffers…

The introduction of pretrained language models has reduced many complex task-specific NLP models to simple lightweight layers. An exception to this trend is coreference resolution, where a sophisticated task-specific model is appended to a…

Pitch estimation (PE) in monophonic audio is crucial for MIDI transcription and singing voice conversion (SVC), but existing methods suffer significant performance degradation under noise. In this paper, we propose FCPE, a fast…

Open-vocabulary 6D object pose estimation empowers robots to manipulate arbitrary unseen objects guided solely by natural language. However, a critical limitation of existing approaches is their reliance on unconstrained global matching…

Pansharpening aims to generate high-resolution multispectral (HRMS) images by fusing low-resolution multispectral (LRMS) and high-resolution panchromatic (PAN) images while preserving both spectral and spatial information. Although deep…

Fourier transforms are an often necessary component in many computational tasks, and can be computed efficiently through the fast Fourier transform (FFT) algorithm. However, many applications involve an underlying continuous signal, and a…

Digitising the 3D world into a clean, CAD model-based representation has important applications for augmented reality and robotics. Current state-of-the-art methods are computationally intensive as they individually encode each detected…

Large-scale ML accelerators rely on large numbers of PEs, imposing strict bounds on the area and energy budget of each PE. Prior work demonstrates that limited dual-issue capabilities can be efficiently integrated into a lightweight…

We propose FastMap, a new global structure from motion method focused on speed and simplicity. Previous methods like COLMAP and GLOMAP are able to estimate high-precision camera poses, but suffer from poor scalability when the number of…

Computing power has evolved into a foundational and indispensable resource in the area of deep learning, particularly in tasks such as Face Recognition (FR) model training on large-scale datasets, where multiple GPUs are often a necessity.…

Coreference resolution involves the task of identifying text spans within a discourse that pertain to the same real-world entity. While this task has been extensively explored in the English language, there has been a notable scarcity of…

Point cloud registration serves as a basis for vision and robotic applications including 3D reconstruction and mapping. Despite significant improvements on the quality of results, recent deep learning approaches are computationally…

In this work, we propose FastCoT, a model-agnostic framework based on parallel decoding without any further training of an auxiliary model or modification to the LLM itself. FastCoT uses a size-varying context window whose size changes with…

Fast 3D data analysis and steering of a tomographic experiment by changing environmental conditions or acquisition parameters require fast, close to real-time, 3D reconstruction of large data volumes. Here we present a performance-optimized…

Computational Pangenomics is an emerging field that studies genetic variation using a graph structure encompassing multiple genomes. Visualizing pangenome graphs is vital for understanding genome diversity. Yet, handling large graphs can be…

The computational challenges of Large Language Model (LLM) inference remain a significant barrier to their widespread deployment, especially as prompt lengths continue to increase. Due to the quadratic complexity of the attention…