Related papers: Dala: A Simple Capability-Based Dynamic Language D…
This paper introduces Unified Language-driven Zero-shot Domain Adaptation (ULDA), a novel task setting that enables a single model to adapt to diverse target domains without explicit domain-ID knowledge. We identify the constraints in the…
Hybrid dynamical systems, which include continuous flow and discrete mode switching, can model robotics tasks like legged robot locomotion. Model-based methods usually depend on predefined gaits, while model-free approaches lack explicit…
Dense large language models(LLMs) face critical efficiency bottlenecks as they rigidly activate all parameters regardless of input complexity. While existing sparsity methods(static pruning or dynamic activation) address this partially,…
Data augmentation (DA) is crucial to mitigate model training instability and over-fitting problems in low-resource open-domain dialogue generation. However, traditional DA methods often neglect semantic data diversity, restricting the…
Nondeterminism introduced by race conditions and message reorderings makes parallel and distributed programming hard. Nevertheless, promising approaches such as LVars and CRDTs address this problem by introducing a partial order structure…
While deep learning (DL) is data-hungry and usually relies on extensive labeled data to deliver good performance, Active Learning (AL) reduces labeling costs by selecting a small proportion of samples from unlabeled data for labeling and…
Spatial dataflow architectures such as reconfigurable dataflow accelerators (RDA) can provide much higher performance and efficiency than CPUs and GPUs. In particular, vectorized reconfigurable dataflow accelerators (vRDA) in recent…
Autonomous driving systems face significant challenges in achieving human-like adaptability, robustness, and interpretability in complex, open-world environments. These challenges stem from fragmented architectures, limited generalization…
Spoken Question Answering (SQA) is to find the answer from a spoken document given a question, which is crucial for personal assistants when replying to the queries from the users. Existing SQA methods all rely on Automatic Speech…
Languages with gradual information-flow control combine static and dynamic techniques to prevent security leaks. Gradual languages should satisfy the gradual guarantee: programs that only differ in the precision of their type annotations…
The ability to express a program as a hierarchical composition of parts is an essential tool in managing the complexity of software and a key abstraction this provides is to separate the representation of data from the computation. Many…
Numerical simulations can help solve complex problems. Most of these algorithms are massively parallel and thus good candidates for FPGA acceleration thanks to spatial parallelism. Modern FPGA devices can leverage high-bandwidth memory…
Language models (LMs) have been instrumental for the rapid advance of natural language processing. This paper studies continual pre-training of LMs, in particular, continual domain-adaptive pre-training (or continual DAP-training). Existing…
When looking through the proceedings of the recent Simulation Interoperability Workshops, a lot of papers - some of them even awarded by the committee - are dealing with alternative concepts outside or beyond the High Level Architecture…
This article explores the design and experimentation of a neural network architecture capable of dynamically adjusting its internal structure based on the input data. The proposed model introduces a routing mechanism that allows each layer…
As language models continue to rapidly improve, we can expect their actions and reasoning to become difficult or impossible for weaker agents and humans to follow, undermining interpretability and oversight. With an eye on long-term…
After an apparent hiatus of roughly 30 years, we revisit a seemingly neglected subject in the theory of (one-dimensional) cellular automata: sublinear-time computation. The model considered is that of ACAs, which are language acceptors…
This work presents Drake, a dynamic executive for temporal plans with choice. Dynamic plan execution strategies allow an autonomous agent to react quickly to unfolding events, improving the robustness of the agent. Prior work developed…
Representation is a core issue in artificial intelligence. Humans use discrete language to communicate and learn from each other, while machines use continuous features (like vector, matrix, or tensor in deep neural networks) to represent…
When components of a system exchange data, they need to serialise the data so that it can be sent over the network. Then, the recipient has to deserialise the data in order to be able to process it. These steps take time and have an impact…