Related papers: Perceptually-Driven Video Coding with the Daala Vi…

CUDA and OpenCL are two different frameworks for GPU programming. OpenCL is an open standard that can be used to program CPUs, GPUs, and other devices from different vendors, while CUDA is specific to NVIDIA GPUs. Although OpenCL promises a…

While Vision-language models (VLMs) have demonstrated remarkable performance across multi-modal tasks, their choice of vision encoders presents a fundamental weakness: their low-level features lack the robust structural and spatial…

The rapid growth of deep learning (DL) has spurred interest in enhancing log-based anomaly detection. This approach aims to extract meaning from log events (log message templates) and develop advanced DL models for anomaly detection.…

Test-time adaptation (TTA) has gained increasing popularity due to its efficacy in addressing ``distribution shift'' issue while simultaneously protecting data privacy. However, most prior methods assume that a paired source domain model…

Semantic communication has been introduced into collaborative perception systems for autonomous driving, offering a promising approach to enhancing data transmission efficiency and robustness. Despite its potential, existing semantic…

This paper presents a deep learning-based video compression framework (ViSTRA3). The proposed framework intelligently adapts video format parameters of the input video before encoding, subsequently employing a CNN at the decoder to restore…

Active learning seeks to achieve strong performance with fewer training samples. It does this by iteratively asking an oracle to label new selected samples in a human-in-the-loop manner. This technique has gained increasing popularity due…

Directional cues are crucial for environmental interaction. Conventional methods rely on symbolic visual or auditory reminders that require semantic interpretation, a process that proves challenging in demanding dual-tasking scenarios. We…

The Bj{\o}ntegaard Delta (BD) method proposed in 2001 has become a popular tool for comparing video codec compression efficiency. It was initially proposed to compute bitrate and quality differences between two Rate-Distortion curves using…

Large Language Models (LLMs) exhibit high inference latency due to their autoregressive decoding nature. While the draft head in speculative decoding mitigates this issue, its full potential remains unexplored. In this paper, we introduce…

We introduce Perception Encoder (PE), a state-of-the-art vision encoder for image and video understanding trained via simple vision-language learning. Traditionally, vision encoders have relied on a variety of pretraining objectives, each…

As the parameter size of large language models (LLMs) continues to expand, the need for a large memory footprint and high communication bandwidth have become significant bottlenecks for the training and inference of LLMs. To mitigate these…

Deep Learning (DL) developers come from different backgrounds, e.g., medicine, genomics, finance, and computer science. To create a DL model, they must learn and use high-level programming languages (e.g., Python), thus needing to handle…

Code translation aims to convert code from one programming language to another automatically. It is motivated by the need for multi-language software development and legacy system migration. In recent years, neural code translation has…

This paper introduces a novel framework for end-to-end learned video coding. Image compression is generalized through conditional coding to exploit information from reference frames, allowing to process intra and inter frames with the same…

We introduce Dialz, a framework for advancing research on steering vectors for open-source LLMs, implemented in Python. Steering vectors allow users to modify activations at inference time to amplify or weaken a 'concept', e.g. honesty or…

Vision-Language-Action models (VLAs) represent a significant frontier in embodied intelligence, aiming to bridge digital knowledge with physical-world interaction. Despite their remarkable performance, foundational VLAs are hindered by the…

Understanding porous media flow is inherently a multi-scale challenge, where at the core lies the aggregation of pore-level processes to a continuum, or Darcy-scale, description. This challenge is directly mirrored in image processing,…

We examine "vibe coding": an emerging programming paradigm where developers primarily write code by interacting with code-generating large language models rather than writing code directly. We present the first empirical study of vibe…

Deep reinforcement learning (DRL) requires large samples and a long training time to operate optimally. Yet humans rarely require long periods training to perform well on novel tasks, such as computer games, once they are provided with an…