Related papers: Why Any-Order Autoregressive Models Need Two-Strea…

Aligning multimodal generative models with human preferences demands reward signals that respect the compositional, multi-dimensional structure of human judgment. Prevailing RLHF approaches reduce this structure to scalar or pairwise…

Existing sentence ordering approaches generally employ encoder-decoder frameworks with the pointer net to recover the coherence by recurrently predicting each sentence step-by-step. Such an autoregressive manner only leverages unilateral…

Inspired by the remarkable success of autoregressive models in language modeling, this paradigm has been widely adopted in visual generation. However, the sequential token-by-token decoding mechanism inherent in traditional autoregressive…

Simultaneous or streaming machine translation generates translation while reading the input stream. These systems face a quality/latency trade-off, aiming to achieve high translation quality similar to non-streaming models with minimal…

Online Contention Resolution Schemes (OCRS's) represent a modern tool for selecting a subset of elements, subject to resource constraints, when the elements are presented to the algorithm sequentially. OCRS's have led to some of the…

End-to-end (E2E) automatic speech recognition (ASR) with sequence-to-sequence models has gained attention because of its simple model training compared with conventional hidden Markov model based ASR. Recently, several studies report the…

Multiple-Input Multiple-Output (MIMO) systems are essential for wireless communications. Sinceclassical algorithms for symbol detection in MIMO setups require large computational resourcesor provide poor results, data-driven algorithms are…

Explanations obtained from transformer-based architectures in the form of raw attention, can be seen as a class-agnostic saliency map. Additionally, attention-based pooling serves as a form of masking the in feature space. Motivated by this…

Inspired by human-like behaviors for navigation: first searching to explore unknown areas before discovering the target, and then the pathfinding of moving towards the discovered target, recent studies design parallel submodules to achieve…

Masked Diffusion Language Models (DLMs) have recently emerged as a promising alternative to traditional Autoregressive Models (ARMs). DLMs employ transformer encoders with bidirectional attention, enabling parallel token generation while…

Recently, a deep reinforcement learning method is proposed to solve multiobjective optimization problem. In this method, the multiobjective optimization problem is decomposed to a number of single-objective optimization subproblems and all…

We propose a unified data-driven reduced order model (ROM) that bridges the performance gap between linear and nonlinear manifold approaches. Deep learning ROM (DL-ROM) using deep-convolutional autoencoders (DC-AE) has been shown to capture…

While linear attention architectures offer efficient inference, compressing unbounded history into a fixed-size memory inherently limits expressivity and causes information loss. To address this limitation, we introduce Random Access Memory…

Heretofore, neural networks with external memory are restricted to single memory with lossy representations of memory interactions. A rich representation of relationships between memory pieces urges a high-order and segregated relational…

The field of learning-augmented algorithms has gained significant attention in recent years. These algorithms, using potentially inaccurate predictions, must exhibit three key properties: consistency, robustness, and smoothness. In…

Multi-modality image fusion, particularly infrared and visible, plays a crucial role in integrating diverse modalities to enhance scene understanding. Although early research prioritized visual quality, preserving fine details and adapting…

Transformer-based models have emerged as a leading architecture for natural language processing, natural language generation, and image generation tasks. A fundamental element of the transformer architecture is self-attention, which allows…

There has been a lot of recent interest in designing neural network models to estimate a distribution from a set of examples. We introduce a simple modification for autoencoder neural networks that yields powerful generative models. Our…

Attention-based mechanisms are widely used in machine learning, most prominently in transformers. However, hyperparameters such as the rank of the attention matrices and the number of heads are scaled nearly the same way in all realizations…

Data stream classification is an important problem in the field of machine learning. Due to the non-stationary nature of the data where the underlying distribution changes over time (concept drift), the model needs to continuously adapt to…