Related papers: Conditional Attribute Estimation with Autoregressi…

We propose ContextLM, a framework that implicitly learns multi-token prediction by augmenting standard pretraining with an intrinsic next-context prediction objective. ContextLM builds a language model on top of context embeddings that span…

We present a conformal prediction method for time series using the Transformer architecture to capture long-memory and long-range dependencies. Specifically, we use the Transformer decoder as a conditional quantile estimator to predict the…

End-to-end optimization has achieved state-of-the-art performance on many specific problems, but there is no straight-forward way to combine pretrained models for new problems. Here, we explore improving modularity by learning a post-hoc…

Class-conditional generative models have emerged as accurate and robust classifiers, with diffusion models demonstrating clear advantages over other visual generative paradigms, including autoregressive (AR) models. In this work, we revisit…

Neural machine translation with millions of parameters is vulnerable to unfamiliar inputs. We propose Token Drop to improve generalization and avoid overfitting for the NMT model. Similar to word dropout, whereas we replace dropped token…

Fine-tuning a pre-trained deep neural network has become a successful paradigm in various machine learning tasks. However, such a paradigm becomes particularly challenging with tabular data when there are discrepancies between the feature…

Recent Quality Estimation (QE) models based on multilingual pre-trained representations have achieved very competitive results when predicting the overall quality of translated sentences. Predicting translation errors, i.e. detecting…

Fully test-time adaptation aims to adapt the network model based on sequential analysis of input samples during the inference stage to address the cross-domain performance degradation problem of deep neural networks. This work is based on…

Autoregressive language models like GPT aim to predict next tokens, while autoencoding models such as BERT are trained on tasks such as predicting masked tokens. We train a decoder-only architecture for predicting the second to last token…

One of the problems with automated audio captioning (AAC) is the indeterminacy in word selection corresponding to the audio event/scene. Since one acoustic event/scene can be described with several words, it results in a combinatorial…

Sequential audio event tagging can provide not only the type information of audio events, but also the order information between events and the number of events that occur in an audio clip. Most previous works on audio event sequence…

Data driven methods for time series forecasting that quantify uncertainty open new important possibilities for robot tasks with hard real time constraints, allowing the robot system to make decisions that trade off between reaction time and…

Recent multimodal deepfake detection methods designed for generalization conjecture that single-stage supervised training struggles to generalize across unseen manipulations and datasets. However, such approaches that target generalization…

We consider the problem of synthesizing multi-action human motion sequences of arbitrary lengths. Existing approaches have mastered motion sequence generation in single action scenarios, but fail to generalize to multi-action and…

Large language models benefit from training with a large amount of unlabeled text, which gives them increasingly fluent and diverse generation capabilities. However, using these models for text generation that takes into account target…

GANs have matured in recent years and are able to generate high-resolution, realistic images. However, the computational resources and the data required for the training of high-quality GANs are enormous, and the study of transfer learning…

In Neural Machine Translation (NMT), each token prediction is conditioned on the source sentence and the target prefix (what has been previously translated at a decoding step). However, previous work on interpretability in NMT has mainly…

Large language models such as GPT and Llama are trained with a next-token prediction loss. In this work, we suggest that training language models to predict multiple future tokens at once results in higher sample efficiency. More…

Token-level adaptive training approaches can alleviate the token imbalance problem and thus improve neural machine translation, through re-weighting the losses of different target tokens based on specific statistical metrics (e.g., token…

Robotics has long been a field riddled with complex systems architectures whose modules and connections, whether traditional or learning-based, require significant human expertise and prior knowledge. Inspired by large pre-trained language…