English
Related papers

Related papers: You Only Cache Once: Decoder-Decoder Architectures…

200 papers

We present YORO - a multi-modal transformer encoder-only architecture for the Visual Grounding (VG) task. This task involves localizing, in an image, an object referred via natural language. Unlike the recent trend in the literature of…

Computer Vision and Pattern Recognition · Computer Science 2022-11-16 Chih-Hui Ho , Srikar Appalaraju , Bhavan Jasani , R. Manmatha , Nuno Vasconcelos

The image captioning task is typically realized by an auto-regressive method that decodes the text tokens one by one. We present a diffusion-based captioning model, dubbed the name DDCap, to allow more decoding flexibility. Unlike image…

Computer Vision and Pattern Recognition · Computer Science 2022-12-12 Zixin Zhu , Yixuan Wei , Jianfeng Wang , Zhe Gan , Zheng Zhang , Le Wang , Gang Hua , Lijuan Wang , Zicheng Liu , Han Hu

Recent large language model (LLM) research has undergone an architectural shift from encoder-decoder modeling to nowadays the dominant decoder-only modeling. This rapid transition, however, comes without a rigorous comparative analysis…

Computation and Language · Computer Science 2025-10-31 Biao Zhang , Yong Cheng , Siamak Shakeri , Xinyi Wang , Min Ma , Orhan Firat

Memorization is a fundamental ability of Transformer-based Large Language Models, achieved through learning. In this paper, we propose a paradigm shift by designing an architecture to memorize text directly, bearing in mind the principle…

Neural machine translation aims at building a single large neural network that can be trained to maximize translation performance. The encoder-decoder architecture with an attention mechanism achieves a translation performance comparable to…

Computation and Language · Computer Science 2016-08-22 Shenjian Zhao , Zhihua Zhang

Conventional turbo codes (CTCs) usually employ a block-oriented interleaving so that each block is separately encoded and decoded. As interleaving and de-interleaving are performed within a block, the message-passing process associated with…

Information Theory · Computer Science 2007-07-13 Yan-Xiu Zheng , Yu T. Su

One-shot voice conversion(VC) aims to change the timbre of any source speech to match that of the target speaker with only one speech sample. Existing style transfer-based VC methods relied on speech representation disentanglement and…

Sound · Computer Science 2024-11-26 Wenhan Yao , Zedong Xing , Xiarun Chen , Jia Liu , Yongqiang He , Weiping Wen

6D object pose estimation is a crucial prerequisite for autonomous robot manipulation applications. The state-of-the-art models for pose estimation are convolutional neural network (CNN)-based. Lately, Transformers, an architecture…

Computer Vision and Pattern Recognition · Computer Science 2023-07-24 Arul Selvam Periyasamy , Arash Amini , Vladimir Tsaturyan , Sven Behnke

We present YOSO (You Only Shot Once), a single-frame phase retrieval framework for digital in-line holographic microscopy (DIHM) in which supervised deep learning is used to numerically generate an additional hologram corresponding to…

The visual projector, which bridges the vision and language modalities and facilitates cross-modal alignment, serves as a crucial component in MLLMs. However, measuring the effectiveness of projectors in vision-language alignment remains…

Computer Vision and Pattern Recognition · Computer Science 2024-06-03 Linli Yao , Lei Li , Shuhuai Ren , Lean Wang , Yuanxin Liu , Xu Sun , Lu Hou

Current state-of-the-art machine translation systems are based on encoder-decoder architectures, that first encode the input sequence, and then generate an output sequence based on the input encoding. Both are interfaced with an attention…

Computation and Language · Computer Science 2018-11-02 Maha Elbayad , Laurent Besacier , Jakob Verbeek

Cross-model retrieval has emerged as one of the most important upgrades for text-only search engines (SE). Recently, with powerful representation for pairwise text-image inputs via early interaction, the accuracy of vision-language (VL)…

Computer Vision and Pattern Recognition · Computer Science 2021-11-29 Lisai Zhang , Hongfa Wu , Qingcai Chen , Yimeng Deng , Zhonghua Li , Dejiang Kong , Zhao Cao , Joanna Siebert , Yunpeng Han

Parallel diffusion decoding can accelerate diffusion language model inference by unmasking multiple tokens per step, but aggressive parallelism often harms quality. Revocable decoding mitigates this by rechecking earlier tokens, yet we…

Computation and Language · Computer Science 2026-02-09 Yanzheng Xiang , Lan Wei , Yizhen Yao , Qinglin Zhu , Hanqi Yan , Chen Jin , Philip Alexander Teare , Dandan Zhang , Lin Gui , Amrutha Saseendran , Yulan He

Lifelong audio feature extraction involves learning new sound classes incrementally, which is essential for adapting to new data distributions over time. However, optimizing the model only on new data can lead to catastrophic forgetting of…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-08 Xilin Jiang , Yinghao Aaron Li , Nima Mesgarani

In this paper, we further explore the potential of analog in-memory computing (AiMC) and introduce an innovative artificial intelligence (AI) accelerator architecture named YOCO, featuring three key proposals: (1) YOCO proposes a novel…

Hardware Architecture · Computer Science 2025-06-12 Zihao Xuan , Yuxuan Yang , Wei Xuan , Zijia Su , Song Chen , Yi Kang

As a foundational technology for intelligent human-computer interaction, voice conversion (VC) seeks to transform speech from any source timbre into any target timbre. Traditional voice conversion methods based on Generative Adversarial…

Sound · Computer Science 2025-06-11 Wenhan Yao , Fen Xiao , Xiarun Chen , Jia Liu , YongQiang He , Weiping Wen

Recent multimodal systems often rely on separate expert modality encoders which cause linearly scaling complexity and computational overhead with added modalities. While unified Omni-models address this via Mixture-of-Expert (MoE)…

Multimedia · Computer Science 2026-03-09 Kin Wai Lau , Yasar Abbas Ur Rehman , Lai-Man Po , Pedro Porto Buarque de Gusmão

Large Language Models (LLMs) use key-value (KV) cache to reduce redundant computation in autoregressive generation. However, the KV cache size increases linearly during generation, leading to excessive memory usage, especially for long…

Computation and Language · Computer Science 2025-03-04 Jian Yuan , Ziwei He , Haoli Bai , Jingwen Leng , Bo Jiang

Decoder-only transformers have become the standard architecture for large language models (LLMs) due to their strong performance. Recent studies suggest that, in pre-trained LLMs, early, middle, and late layers may serve distinct roles:…

Computation and Language · Computer Science 2025-10-15 Xuan Luo , Weizhi Wang , Xifeng Yan

We present a new open-vocabulary detection framework. Our framework uses both image-level labels and detailed detection annotations when available. Our framework proceeds in three steps. We first train a language-conditioned object detector…

Computer Vision and Pattern Recognition · Computer Science 2023-11-30 Jang Hyun Cho , Philipp Krähenbühl