相关论文: Improving Text-Audio Retrieval by Text-aware Atten…

Long-context large language models (LLMs) face constraints due to the quadratic complexity of the self-attention mechanism. The mainstream sequence parallelism (SP) method, Ring Attention, attempts to solve this by distributing the query…

Retrieval-augmented generation (RAG) ranks passages by semantic similarity to the input, implicitly assuming that semantic similarity is a reliable indication of applicability in downstream tasks. This assumption breaks down when task…

Detecting partial deepfake speech is essential due to its potential for subtle misinformation. However, existing methods depend on costly frame-level annotations during training, limiting real-world scalability. Also, they focus on…

Diffusion models achieve strong generative performance but remain slow at inference due to the need for repeated full-model denoising passes. We present Token-Adaptive Predictor (TAP), a training-free, probe-driven framework that adaptively…

Retrieval augmentation has become an effective solution to empower large language models (LLMs) with external and verified knowledge sources from the database, which overcomes the limitations and hallucinations of LLMs in handling…

Attention-based models have recently shown great performance on a range of tasks, such as speech recognition, machine translation, and image captioning due to their ability to summarize relevant information that expands through the entire…

Topic classification systems on spoken documents usually consist of two modules: an automatic speech recognition (ASR) module to convert speech into text and a text topic classification (TTC) module to predict the topic class from the…

This paper proposes a novel user-defined keyword spotting framework that accurately detects audio keywords based on text enrollment. Since audio data possesses additional acoustic information compared to text, there are discrepancies…

Image captioning has drawn considerable attention from the natural language processing and computer vision fields. Aiming to reduce the reliance on curated data, several studies have explored image captioning without any humanly-annotated…

Approximate message passing (AMP) algorithms have shown great promise in sparse signal reconstruction due to their low computational requirements and fast convergence to an exact solution. Moreover, they provide a probabilistic framework…

Recently, self-supervised pre-training has shown significant improvements in many areas of machine learning, including speech and NLP. We propose using large self-supervised pre-trained models for both audio and text modality with…

We present a novel learning framework to solve the transport-and-packing (TAP) problem in 3D. It constitutes a full solution pipeline from partial observations of input objects via RGBD sensing and recognition to final box placement, via…

Video Large Language Models (VLLMs) incur substantial prefilling cost due to the large number of visual tokens. While attention-based token pruning offers a promising acceleration strategy, applying it at shallow decoder layers often causes…

Pretrained visual-language models have made significant advancements in multimodal tasks, including image-text retrieval. However, a major challenge in image-text matching lies in language bias, where models predominantly rely on language…

Retrieval-Augmented Generation (RAG) improves factual grounding by incorporating external knowledge into language model generation. However, when retrieved context is noisy, unreliable, or inconsistent with the model's parametric knowledge,…

Text-to-image retrieval (TIR) aims to find relevant images based on a textual query, but existing approaches are primarily based on whole-image captions and lack interpretability. Meanwhile, referring expression segmentation (RES) enables…

Vision-language alignment learning for video-text retrieval arouses a lot of attention in recent years. Most of the existing methods either transfer the knowledge of image-text pretraining model to video-text retrieval task without fully…

Remote sensing (RS) image-text retrieval faces significant challenges in real-world datasets due to the presence of Pseudo-Matched Pairs (PMPs), semantically mismatched or weakly aligned image-text pairs, which hinder the learning of…

This paper presents MAST, a new model for Multimodal Abstractive Text Summarization that utilizes information from all three modalities -- text, audio and video -- in a multimodal video. Prior work on multimodal abstractive text…

Autoregressive (AR) models with diffusion heads have recently achieved strong text-to-audio performance, yet their iterative decoding and multi-step sampling process introduce high-latency issues. To address this bottleneck, we propose a…