Related papers: PRISE: LLM-Style Sequence Compression for Learning…

Despite it being the cornerstone of BPE, the most common tokenization algorithm, the importance of compression in the tokenization process is still unclear. In this paper, we argue for the theoretical importance of compression, that can be…

In the literature, the research on abstract meaning representation (AMR) parsing is much restricted by the size of human-curated dataset which is critical to build an AMR parser with good performance. To alleviate such data size…

Large Language Models (LLMs) have demonstrated impressive capabilities in a wide range of natural language processing tasks when leveraging in-context learning. To mitigate the additional computational and financial costs associated with…

Sequential decision making techniques hold great promise to improve the performance of many real-world systems, but computational complexity hampers their principled application. Influence-based abstraction aims to gain leverage by modeling…

Linear Time Invariant (LTI) systems are ubiquitous in control applications. Unbounded-time reachability analysis that can cope with industrial-scale models with thousands of variables is needed. To tackle this problem, we use abstract…

Context-aware compression techniques have gained increasing attention as model sizes continue to grow, introducing computational bottlenecks that hinder efficient deployment. A structured encoding approach was proposed to selectively…

Video Large Language Models (Video LLMs) have achieved significant success by adopting the paradigm of large-scale pre-training followed by supervised fine-tuning (SFT). However, existing approaches struggle with temporal reasoning due to…

Social goods, such as healthcare, smart city, and information networks, often produce ordered event data in continuous time. The generative processes of these event data can be very complex, requiring flexible models to capture their…

Exploration in sparse-reward reinforcement learning is difficult due to the requirement of long, coordinated sequences of actions in order to achieve any reward. Moreover, in continuous action spaces there are an infinite number of possible…

Large Language Models (LLMs) have pushed the frontier of artificial intelligence but are comprised of hundreds of billions of parameters and operations. For faster inference latency, LLMs are deployed on multiple hardware accelerators…

Learning from demonstrations is a common way for users to teach robots, but it is prone to spurious feature correlations. Recent work constructs state abstractions, i.e. visual representations containing task-relevant features, from…

Abstraction plays an important role in the generalisation of knowledge and skills and is key to sample efficient learning. In this work, we study joint temporal and state abstraction in reinforcement learning, where temporally-extended…

Recurrent neural networks have a strong inductive bias towards learning temporally compressed representations, as the entire history of a sequence is represented by a single vector. By contrast, Transformers have little inductive bias…

Early action prediction deals with inferring the ongoing action from partially-observed videos, typically at the outset of the video. We propose a bottleneck-based attention model that captures the evolution of the action, through…

A major challenge in modern reinforcement learning (RL) is efficient control of dynamical systems from high-dimensional sensory observations. Learning controllable embedding (LCE) is a promising approach that addresses this challenge by…

Robotic imitation learning typically requires models that capture multimodal action distributions while operating at real-time control rates and accommodating multiple sensing modalities. Although recent generative approaches such as…

The past few years have witnessed increasing interests in applying deep learning to video compression. However, the existing approaches compress a video frame with only a few number of reference frames, which limits their ability to fully…

Extractive summarization can produce faithful summaries but often requires additional constraints such as a desired summary length. Traditional sentence compression models do not typically consider the constraints because of their…

In this paper, we propose Precision-Informed Semantic Modeling (PRISM), a structured topic modeling framework combining the benefits of rich representations captured by LLMs with the low cost and interpretability of latent semantic…

In reinforcement learning, temporal abstraction in the action space, exemplified by action repetition, is a technique to facilitate policy learning through extended actions. However, a primary limitation in previous studies of action…