Related papers: FastLane: Efficient Routed Systems for Late-Intera…

Existing Graph RAG methods aiming for insightful retrieval on corpus graphs typically rely on time-intensive processes that interleave Large Language Model (LLM) reasoning. To enable time-efficient insightful retrieval, we propose…

Modern methods mainly regard lane detection as a problem of pixel-wise segmentation, which is struggling to address the problem of challenging scenarios and speed. Inspired by human perception, the recognition of lanes under severe…

Multi-vector representations generated by late interaction models, such as ColBERT, enable superior retrieval quality compared to single-vector representations in information retrieval applications. In multi-vector retrieval systems, both…

Accurate motion forecasting is critical for safe and efficient autonomous driving, enabling vehicles to predict future trajectories and make informed decisions in complex traffic scenarios. Most of the current designs of motion prediction…

Modern deep learning models capture the semantics of complex data by transforming them into high-dimensional embedding vectors. Emerging applications, such as retrieval-augmented generation, use approximate nearest neighbor (ANN) search in…

Machine learning has emerged as a promising paradigm for enabling connected, automated vehicles to autonomously cruise the streets and react to unexpected situations. A key challenge, however, is to collect and select real-time and reliable…

The prefill stage of large language model (LLM) inference is a key computational bottleneck for long-context workloads. At short-to-moderate context lengths (1K--16K tokens), Feed-Forward Networks (FFNs) dominate this cost, accounting for…

Embedding-based vector search underpins many important applications, such as recommendation and retrieval-augmented generation (RAG). It relies on vector indices to enable efficient search. However, these indices require storing…

Neural Architecture Search (NAS) is a laborious process. Prior work on automated NAS targets mainly on improving accuracy, but lacks consideration of computational resource use. We propose the Resource-Efficient Neural Architect (RENA), an…

Deep Learning is becoming increasingly relevant in Embedded and Internet-of-things applications. However, deploying models on embedded devices poses a challenge due to their resource limitations. This can impact the model's inference…

We study the problem of approximate near neighbor (ANN) search and show the following results: - An improved framework for solving the ANN problem using locality-sensitive hashing, reducing the number of evaluations of locality-sensitive…

Minimizing computational overhead in time-series classification, particularly in deep learning models, presents a significant challenge due to the high complexity of model architectures and the large volume of sequential data that must be…

Recent progress in deep learning has continuously improved the accuracy of dialogue response selection. In particular, sophisticated neural network architectures are leveraged to capture the rich interactions between dialogue context and…

This paper presents EasyRAG, a simple, lightweight, and efficient retrieval-augmented generation framework for automated network operations. Our framework has three advantages. The first is accurate question answering. We designed a…

Approximate nearest neighbor search (ANNS) is a crucial problem in information retrieval and AI applications. Recently, there has been a surge of interest in graph-based ANNS algorithms due to their superior efficiency and accuracy.…

Trajectory classification tasks became more complex as large volumes of mobility data are being generated every day and enriched with new sources of information, such as social networks and IoT sensors. Fast classification algorithms are…

Lane detection, the process of identifying lane markings as approximated curves, is widely used for lane departure warning and adaptive cruise control in autonomous vehicles. The popular pipeline that solves it in two steps -- feature…

Approximate nearest neighbor search (ANNS) has emerged as a crucial component of database and AI infrastructure. Ever-increasing vector datasets pose significant challenges in terms of performance, cost, and accuracy for ANNS services. None…

Long-context modeling is a pivotal capability for Large Language Models, yet the quadratic complexity of attention remains a critical bottleneck, particularly during the compute-intensive prefilling phase. While various sparse attention…

Despite online learning (OL) techniques have boosted the performance of semi-supervised video object segmentation (VOS) methods, the huge time costs of OL greatly restrict their practicality. Matching based and propagation based methods run…