Related papers: Combining Constrained and Unconstrained Decoding v…

Image-based single-modality compression learning approaches have demonstrated exceptionally powerful encoding and decoding capabilities in the past few years , but suffer from blur and severe semantics loss at extremely low bitrates. To…

Syndrome-based neural decoding (SBND) has emerged as a promising deep learning approach for soft-decision decoding of high-rate, short-length codes. However, this approach still has substantial room for improvement. In this paper, we show…

Recent advancements in deep learning-based image compression are notable. However, prevalent schemes that employ a serial context-adaptive entropy model to enhance rate-distortion (R-D) performance are markedly slow. Furthermore, the…

Existing captioning models often adopt the encoder-decoder architecture, where the decoder uses autoregressive decoding to generate captions, such that each token is generated sequentially given the preceding generated tokens. However,…

Dense retrieval requires high-quality text sequence embeddings to support effective search in the representation space. Autoencoder-based language models are appealing in dense retrieval as they train the encoder to output high-quality…

We propose a novel approach for using unsupervised boosting to create an ensemble of generative models, where models are trained in sequence to correct earlier mistakes. Our meta-algorithmic framework can leverage any existing base learner…

This paper proposes a structure-aware decoding method based on large language models to address the difficulty of traditional approaches in maintaining both semantic integrity and structural consistency in nested and overlapping entity…

Gradient boosted decision trees are a popular machine learning technique, in part because of their ability to give good accuracy with small models. We describe two extensions to the standard tree boosting algorithm designed to increase this…

Speculative decoding accelerates large language model (LLM) inference by using a lightweight draft model to propose tokens that are later verified by a stronger target model. While effective in centralized systems, its behavior in…

Ensuring truthfulness in large language models (LLMs) remains a critical challenge for reliable text generation. While supervised fine-tuning and reinforcement learning with human feedback have shown promise, they require a substantial…

We present a novel deep neural model for text detection in document images. For robust text detection in noisy scanned documents, the advantages of multi-task learning are adopted by adding an auxiliary task of text enhancement. Namely, our…

Generally, the decoder-only large language models (LLMs) are adapted to context-aware neural machine translation (NMT) in a concatenating way, where LLMs take the concatenation of the source sentence (i.e., intra-sentence context) and the…

Recent advances in conditional recurrent language modelling have mainly focused on network architectures (e.g., attention mechanism), learning algorithms (e.g., scheduled sampling and sequence-level training) and novel applications (e.g.,…

Discrete diffusion models generate sequences by iteratively denoising samples corrupted by categorical noise, offering an appealing alternative to autoregressive decoding for structured and symbolic generation. However, standard training…

In this work, we dive deep into the impact of additive noise in pre-training deep networks. While various methods have attempted to use additive noise inspired by the success of latent denoising diffusion models, when used in combination…

Despite pre-training's progress in many important NLP tasks, it remains to explore effective pre-training strategies for dense retrieval. In this paper, we propose RetroMAE, a new retrieval oriented pre-training paradigm based on Masked…

Language models (LMs) can perform complex reasoning either end-to-end, with hidden latent state, or compositionally, with transparent intermediate state. Composition offers benefits for interpretability and safety, but may need workflow…

Bandwidth extension, the task of reconstructing the high-frequency components of an audio signal from its low-pass counterpart, is a long-standing problem in audio processing. While traditional approaches have evolved alongside the broader…

We present CoDa (Constrained Generation based Data Augmentation), a controllable, effective, and training-free data augmentation technique for low-resource (data-scarce) NLP. Our approach is based on prompting off-the-shelf…

Multimodal pre-training for audio-and-text has recently been proved to be effective and has significantly improved the performance of many downstream speech understanding tasks. However, these state-of-the-art pre-training audio-text models…