相关论文: An Efficient Implementation of the Head-Corner Par…

In this paper, we propose an autonomous information seeking visual question answering framework, AVIS. Our method leverages a Large Language Model (LLM) to dynamically strategize the utilization of external tools and to investigate their…

Unsupervised Learning based monocular visual odometry (VO) has lately drawn significant attention for its potential in label-free leaning ability and robustness to camera parameters and environmental variations. However, partially due to…

Recently, conformer-based end-to-end automatic speech recognition, which outperforms recurrent neural network based ones, has received much attention. Although the parallel computing of conformer is more efficient than recurrent neural…

Benefiting from the inductive biases learned from large-scale datasets, open-vocabulary semantic segmentation (OVSS) leverages the power of vision-language models, such as CLIP, to achieve remarkable progress without requiring task-specific…

As large-scale models evolve, language instructions are increasingly utilized in multi-modal tasks. Due to human language habits, these instructions often contain ambiguities in real-world scenarios, necessitating the integration of visual…

In this paper, a communication-efficient multi-processor compressed sensing framework based on the approximate message passing algorithm is proposed. We perform lossy compression on the data being communicated between processors, resulting…

Open-vocabulary semantic segmentation (OVSS) entails assigning semantic labels to each pixel in an image using textual descriptions, typically leveraging world models such as CLIP. To enhance out-of-domain generalization, we propose Cost…

In this paper, we propose a novel design for AI-native goal-oriented communications, exploiting transformer neural networks under dynamic inference constraints on bandwidth and computation. Transformers have become the standard architecture…

The growing demand for efficient semantic communication systems capable of managing diverse tasks and adapting to fluctuating channel conditions has driven the development of robust, resource-efficient frameworks. This article introduces a…

Long-horizon agentic reasoning necessitates effectively compressing growing interaction histories into a limited context window. Most existing memory systems serialize history as text, where token-level cost is uniform and scales linearly…

Intelligent reflecting surfaces (IRSs) are a promising technology for enhancing coverage and spectral efficiency, both in the sub-6 GHz and the millimeter wave (mmWave) bands. Existing approaches to leverage the benefits of IRS involve the…

Event cameras, known for low-latency operation and superior performance in challenging lighting conditions, are suitable for sensitive computer vision tasks such as semantic segmentation in autonomous driving. However, challenges arise due…

This paper describes our submission to ICASSP 2022 Multi-channel Multi-party Meeting Transcription (M2MeT) Challenge. For Track 1, we propose several approaches to empower the clustering-based speaker diarization system to handle overlapped…

The skip-thought model has been proven to be effective at learning sentence representations and capturing sentence semantics. In this paper, we propose a suite of techniques to trim and improve it. First, we validate a hypothesis that,…

Syllabification describes the task of dividing words into syllables. Due to many rules and exceptions, training an algorithm to perform syllabification with high accuracy remains a challenge. Throughout the last decades, different…

In the framework of learned image compression, the context model plays a pivotal role in capturing the dependencies among latent representations. To reduce the decoding time resulting from the serial autoregressive context model, the…

Large language models often expose their brittleness in reasoning tasks, especially while executing long chains of reasoning over context. We propose MemReasoner, a new and simple memory-augmented LLM architecture, in which the memory…

Attention-based encoder-decoder architectures such as Listen, Attend, and Spell (LAS), subsume the acoustic, pronunciation and language model components of a traditional automatic speech recognition (ASR) system into a single neural…

In this paper, a semantic-aware joint communication and computation resource allocation framework is proposed for mobile edge computing (MEC) systems. In the considered system, each terminal device (TD) has a computation task, which needs…

Open-vocabulary semantic segmentation (OVSS) employs pixel-level vision-language alignment to associate category-related prompts with corresponding pixels. A key challenge is enhancing the multimodal dense prediction capability,…