相关论文: Masked Trajectory Models for Prediction, Represent…

Knowledge of the symmetries of reinforcement learning (RL) systems can be used to create compressed and semantically meaningful representations of a low-level state space. We present a method of automatically detecting RL symmetries…

Despite their prevalence in deep-learning communities, over-parameterized models convey high demands of computational costs for proper training. This work studies the fine-grained, modular-level learning dynamics of over-parameterized…

Unsupervised cross-lingual pretraining has achieved strong results in neural machine translation (NMT), by drastically reducing the need for large parallel data. Most approaches adapt masked-language modeling (MLM) to sequence-to-sequence…

Context plays a significant role in the generation of motion for dynamic agents in interactive environments. This work proposes a modular method that utilises a learned model of the environment for motion prediction. This modularity…

World models derived from large-scale video generative pre-training have emerged as a promising paradigm for generalist robot policy learning. However, standard approaches often focus on high-fidelity RGB video prediction, this can result…

Accurate prediction of human behavior is crucial for AI systems to effectively support real-world applications, such as autonomous robots anticipating and assisting with human tasks. Real-world scenarios frequently present challenges such…

We introduce a representation learning framework for spatial trajectories. We represent partial observations of trajectories as probability distributions in a learned latent space, which characterize the uncertainty about unobserved parts…

Trajectory representation learning on a network enhances our understanding of vehicular traffic patterns and benefits numerous downstream applications. Existing approaches using classic machine learning or deep learning embed trajectories…

Masked diffusion models (MDMs) for text offer a compelling alternative to traditional autoregressive language models. Parallel generation makes them efficient, but their computational capabilities and the limitations inherent in their…

Vision-based trajectory prediction is an important task that supports safe and intelligent behaviours in autonomous systems. Many advanced approaches have been proposed over the years with improved spatial and temporal feature extraction.…

Masked language modeling (MLM) is a widely used self-supervised pretraining objective, where a model needs to predict an original token that is replaced with a mask given contexts. Although simpler and computationally efficient pretraining…

We propose a unified framework for adaptive routing in multitask, multimodal prediction settings where data heterogeneity and task interactions vary across samples. Motivated by applications in psychotherapy where structured assessments and…

Multi-modal large language models (MLLMs) have enabled numerous advances in understanding and reasoning in domains like vision, but we have not yet seen this broad success for time-series. Although prior works on time-series MLLMs have…

Tensor network (TN) techniques - often used in the context of quantum many-body physics - have shown promise as a tool for tackling machine learning (ML) problems. The application of TNs to ML, however, has mostly focused on supervised and…

We generalise the problem of reward modelling (RM) for reinforcement learning (RL) to handle non-Markovian rewards. Existing work assumes that human evaluators observe each step in a trajectory independently when providing feedback on agent…

When Masked Diffusion Models (MDMs) generate sequences through iterative refinement, the rich internal computation over masked positions is discarded, forcing every subsequent refinement step to recompute the valuable internal information…

The current Air Traffic Management (ATM) system worldwide has reached its limits in terms of predictability, efficiency and cost effectiveness. Different initiatives worldwide propose trajectory-oriented transformations that require high…

Large-scale pre-trained Vision-Language Models (VLMs) have significantly advanced transfer learning across diverse tasks. However, adapting these models with limited few-shot data often leads to overfitting, undermining their ability to…

Prompt tuning and adapter tuning have shown great potential in transferring pre-trained vision-language models (VLMs) to various downstream tasks. In this work, we design a new type of tuning method, termed as regularized mask tuning, which…

The ability to adapt to changing environments and settings is essential for robots acting in dynamic and unstructured environments or working alongside humans with varied abilities or preferences. This work introduces an extremely simple…