Related papers: Reinforced Fast Weights with Next-Sequence Predict…

Reasoning over long sequences of observations and actions is essential for many robotic tasks. Yet, learning effective long-context policies from demonstrations remains challenging. As context length increases, training becomes increasingly…

The attention module, which is a crucial component in Transformer, cannot scale efficiently to long sequences due to its quadratic complexity. Many works focus on approximating the dot-then-exponentiate softmax function in the original…

Parameter-Efficient finetuning (PEFT) enhances model performance on downstream tasks by updating a minimal subset of parameters. Representation finetuning (ReFT) methods further improve efficiency by freezing model weights and optimizing…

Many efforts have been devoted to training generative latent variable models with autoregressive decoders, such as recurrent neural networks (RNN). Stochastic recurrent models have been successful in capturing the variability observed in…

Token representation strategies within large-scale neural architectures often rely on contextually refined embeddings, yet conventional approaches seldom encode structured relationships explicitly within token interactions. Self-attention…

Semantic-rich features from Vision Foundation Models (VFMs) have been leveraged to enhance Latent Diffusion Models (LDMs). However, raw VFM features are typically high-dimensional and redundant, increasing the difficulty of learning and…

Recent years have seen the ever-increasing importance of pre-trained models and their downstream training in deep learning research and applications. At the same time, the defense for adversarial examples has been mainly investigated in the…

In this work, we propose the Residual-Weighted Physics-Informed Neural Network (RW-PINN), a new method designed to enhance the accuracy of Physics-Informed Neural Network (PINN) based algorithms. We construct a deep learning framework with…

Transformer-based models primarily rely on Next Token Prediction (NTP), which predicts the next token in a sequence based on the preceding context. However, NTP's focus on single-token prediction often limits a model's ability to plan ahead…

The mainstream machine learning paradigms for NLP often work with two underlying presumptions. First, the target task is predefined and static; a system merely needs to learn to solve it exclusively. Second, the supervision of a task mainly…

A generic and scalable Reinforcement Learning scheme for Artificial Neural Networks is presented, providing a general purpose learning machine. By reference to a node threshold three features are described 1) A mechanism for Primary…

Efficient fine-tuning of pre-trained Text-to-Image (T2I) models involves adjusting the model to suit a particular task or dataset while minimizing computational resources and limiting the number of trainable parameters. However, it often…

Transformers have achieved extraordinary success in modern machine learning due to their excellent ability to handle sequential data, especially in next-token prediction (NTP) tasks. However, the theoretical understanding of their…

In this work, we propose Reinforced Functional Token Tuning (RFTT), a novel reinforced fine-tuning framework that empowers Large Language Models (LLMs) with self-play learn-to-reason capabilities. Unlike prior prompt-driven reasoning…

Standardized DNN models that have been proved to perform well on machine learning tasks are widely used and often adopted as-is to solve downstream tasks, forming the transfer learning paradigm. However, when serving multiple instances of…

Dynamical systems describe how a physical system evolves over time. Physical processes can evolve faster or slower in different environmental conditions. We use time-warping as rescaling the time in a model of a physical system. This thesis…

Memory efficiency is crucial in training deep learning networks on resource-restricted devices. During backpropagation, forward tensors are used to calculate gradients. Despite the option of keeping those dependencies in memory until they…

Text reranking models are a crucial component in modern systems like Retrieval-Augmented Generation, tasked with selecting the most relevant documents prior to generation. However, current Large Language Models (LLMs) powered rerankers…

We compare the fast training and decoding speed of RETURNN of attention models for translation, due to fast CUDA LSTM kernels, and a fast pure TensorFlow beam search decoder. We show that a layer-wise pretraining scheme for recurrent…

Fixed-point optimization of deep neural networks plays an important role in hardware based design and low-power implementations. Many deep neural networks show fairly good performance even with 2- or 3-bit precision when quantized weights…