Related papers: Seq2Seq2Seq: Lossless Data Compression via Discret…
Multimodal Large Language Models (MLLMs) encounter significant computational and memory bottlenecks from the massive number of visual tokens generated by high-resolution images or multi-image inputs. Previous token compression techniques…
Efficient audio representations in a compressed continuous latent space are critical for generative audio modeling and Music Information Retrieval (MIR) tasks. However, some existing audio autoencoders have limitations, such as multi-stage…
Multimodal Large Language Models (MLLMs) are becoming increasingly popular, while the high computational cost associated with multimodal data input, particularly from visual tokens, poses a significant challenge. Existing training-based…
This paper introduces DeCAL, a new method for tokenwise compression. DeCAL uses an encoder-decoder language model pretrained with denoising to learn to produce high-quality, general-purpose compressed representations from the encoder. DeCAL…
The emerging field semantic communication is driving the research of end-to-end data transmission. By utilizing the powerful representation ability of deep learning models, learned data transmission schemes have exhibited superior…
Recent advances in autoregressive video diffusion have enabled real-time frame streaming, yet existing solutions still suffer from temporal repetition, drift, and motion deceleration. We find that naively applying StreamingLLM-style…
The recent advances in deep neural networks (DNNs) make them attractive for embedded systems. However, it can take a long time for DNNs to make an inference on resource-constrained computing devices. Model compression techniques can address…
Accurate and efficient discrete video tokenization is essential for long video sequences processing. Yet, the inherent complexity and variable information density of videos present a significant bottleneck for current tokenizers, which…
We propose an end-to-end learned image data hiding framework that embeds and extracts secrets in the latent representations of a generic neural compressor. By leveraging a perceptual loss function in conjunction with our proposed message…
A new trend uses LLMs as dense text encoders via contrastive learning. However, since LLM embeddings predict the probability distribution of the next token, they are inherently generative and distributive, conflicting with contrastive…
Sentence compression is the task of compressing a long sentence into a short one by deleting redundant words. In sequence-to-sequence (Seq2Seq) based models, the decoder unidirectionally decides to retain or delete words. Thus, it cannot…
Missing data scenarios are very common in ML applications in general and time-series/sequence applications are no exceptions. This paper pertains to a novel Recurrent Neural Network (RNN) based solution for sequence prediction under missing…
Recently, many neural network-based image compression methods have shown promising results superior to the existing tool-based conventional codecs. However, most of them are often trained as separate models for different target bit rates,…
Deep learning models have significantly improved the visual quality and accuracy on compressive sensing recovery. In this paper, we propose an algorithm for signal reconstruction from compressed measurements with image priors captured by a…
Deep learning methods have traditionally been difficult to apply to compression of hyperspectral images onboard of spacecrafts, due to the large computational complexity needed to achieve adequate representational power, as well as the lack…
Existing Multimodal Large Language Models (MLLMs) process a large number of visual tokens, leading to significant computational costs and inefficiency. Instruction-related visual token compression demonstrates strong task relevance, which…
Natural question generation (QG) aims to generate questions from a passage and an answer. Previous works on QG either (i) ignore the rich structure information hidden in text, (ii) solely rely on cross-entropy loss that leads to issues like…
Neural compression offers a domain-agnostic approach to creating codecs for lossy or lossless compression via deep generative models. For sequence compression, however, most deep sequence models have costs that scale with the sequence…
Latent reasoning represents a new development in Transformer language models that has shown potential in compressing reasoning lengths compared to chain-of-thought reasoning. By directly passing the information-rich previous final latent…
Unsupervised style transfer aims to change the style of an input sentence while preserving its original content without using parallel training data. In current dominant approaches, owing to the lack of fine-grained control on the influence…