Related papers: An Optimised Flow for Futures: From Theory to Prac…
Learning-based approaches often outperform hand-coded algorithmic solutions for many problems in robotics. However, learning long-horizon tasks on real robot hardware can be intractable, and transferring a learned policy from simulation to…
This paper considers the problem of designing a continuous-time dynamical system that solves a constrained nonlinear optimization problem and makes the feasible set forward invariant and asymptotically stable. The invariance of the feasible…
Pre-trained language models based on general text enable huge success in the NLP scenario. But the intrinsical difference of linguistic patterns between general text and task-oriented dialogues makes existing pre-trained language models…
This study addresses a task designed to predict the future success or failure of open-vocabulary object manipulation. In this task, the model is required to make predictions based on natural language instructions, egocentric view images…
Generative modeling has recently shown remarkable promise for visuomotor policy learning, enabling flexible and expressive control across diverse embodied AI tasks. However, existing generative policies often struggle with data…
Transformers have been successfully applied to sequential, auto-regressive tasks despite being feedforward networks. Unlike recurrent neural networks, Transformers use attention to capture temporal relations while processing input tokens in…
Learning is a process which can update decision rules, based on past experience, such that future performance improves. Traditionally, machine learning is often evaluated under the assumption that the future will be identical to the past in…
We present a unified method, based on convex optimization, for managing the power produced and consumed by a network of devices over time. We start with the simple setting of optimizing power flows in a static network, and then proceed to…
Though remarkable successes have been achieved by Neural Machine Translation (NMT) in recent years, it still suffers from the inadequate-translation problem. Previous studies show that explicitly modeling the Past and Future contents of the…
Language evolves over time in many ways relevant to natural language processing tasks. For example, recent occurrences of tokens 'BERT' and 'ELMO' in publications refer to neural network architectures rather than persons. This type of…
Future sequence represents the outcome after executing the action into the environment (i.e. the trajectory onwards). When driven by the information-theoretic concept of mutual information, it seeks maximally informative consequences.…
The conventional designs of mobile computation offloading fetch user-specific data to the cloud prior to computing, called offline prefetching. However, this approach can potentially result in excessive fetching of large volumes of data and…
Computation is commonly defined as the execution of abstract algorithms over symbolic representations, with physical systems treated as substrates that realise predefined operations. While effective for engineered machines, this separation…
Massively parallel Fourier transforms are widely used in computational sciences, and specifically in computational fluid dynamics which involves unbounded Poisson problems. In practice the latter is usually the most time-consuming operation…
General vision-language models increasingly support unified spatiotemporal reasoning over long video streams, yet deploying such capabilities on robots remains constrained by the prohibitive latency of processing long-horizon histories and…
Optimizing resource allocation with predicted information has shown promising gain in boosting network performance and improving user experience. Earlier research efforts focus on optimizing proactive policies under the assumption of…
Prolog's very useful expressive power is not captured by traditional logic programming semantics, due mainly to the cut and goal and clause order. Several alternative semantics have been put forward, exposing operational details of the…
Although the cloud has reached a state of robustness, the burden of using its resources falls on the shoulders of programmers who struggle to keep up with ever-growing cloud infrastructure services and abstractions. As a result, state…
Transformers replace recurrence with a memory that grows with sequence length and self-attention that enables ad-hoc lookups over past tokens. Consequently, they lack an inherent incentive to compress history into compact latent states with…
Previous studies have shown that neural machine translation (NMT) models can benefit from explicitly modeling translated (Past) and untranslated (Future) to groups of translated and untranslated contents through parts-to-wholes assignment.…