相关论文: Operational Latent Spaces

Large and diverse datasets have been the cornerstones of many impressive advancements in artificial intelligence. Intelligent creatures, however, learn by interacting with the environment, which changes the input sensory signals and the…

Meaning can be generated when information is related at a systemic level. Such a system can be an observer, but also a discourse, for example, operationalized as a set of documents. The measurement of semantics as similarity in patterns…

R1-style LLMs have attracted growing attention for their capacity for self-reflection, yet the internal mechanisms underlying such behavior remain unclear. To bridge this gap, we anchor on the onset of reflection behavior and trace its…

We develop a machine learning method for mapping data originating from both Standard Model processes and various theories beyond the Standard Model into a unified representation (latent) space while conserving information about the…

In this paper, we propose a new self-supervised learning (SSL) method for representations that enable logic operations. Representation learning has been applied to various tasks, such as image generation and retrieval. The logical…

Semantic parsing aims at translating natural language (NL) utterances onto machine-interpretable programs, which can be executed against a real-world environment. The expensive annotation of utterance-program pairs has long been…

Even though large language models (LLMs) have demonstrated remarkable capability in solving various natural language tasks, the capability of an LLM to follow human instructions is still a concern. Recent works have shown great improvements…

What sorts of structure might enable a learner to discover classes from unlabeled data? Traditional approaches rely on feature-space similarity and heroic assumptions on the data. In this paper, we introduce unsupervised learning under…

As language models (LMs) deliver increasing performance on a range of NLP tasks, probing classifiers have become an indispensable technique in the effort to better understand their inner workings. A typical setup involves (1) defining an…

In this paper, we propose a novel active learning approach integrated with an improved semi-supervised learning framework to reduce the cost of manual annotation and enhance model performance. Our proposed approach effectively leverages…

Executing complex manipulation in cluttered environments requires satisfying coupled geometric and temporal constraints. Although Spatio-Temporal Logic (SpaTiaL) offers a principled specification framework, its use in gradient-based…

Intrinsically motivated goal exploration algorithms enable machines to discover repertoires of policies that produce a diversity of effects in complex environments. These exploration algorithms have been shown to allow real world robots to…

Self-supervised learning (SSL) is a powerful tool in machine learning, but understanding the learned representations and their underlying mechanisms remains a challenge. This paper presents an in-depth empirical analysis of SSL-trained…

Interpreting camera data is key for autonomously acting systems, such as autonomous vehicles. Vision systems that operate in real-world environments must be able to understand their surroundings and need the ability to deal with novel…

A fundamental challenge in embodied AI is verifying if agents build internal models of spatial structure or merely learn to mimic task-specific expert trajectories. This is critical as foundational approaches rooted in action-centric tasks…

Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but controlling their behavior reliably remains challenging, especially in open-ended generation settings. This paper…

Motivated by the recent developments of pseudo-Hermitian quantum mechanics, we analyze the structure generated by unbounded metric operators in a Hilbert space. To that effect, we consider the notions of similarity and quasi-similarity…

The ability to decompose complex multi-object scenes into meaningful abstractions like objects is fundamental to achieve higher-level cognition. Previous approaches for unsupervised object-oriented scene representation learning are either…

When large language models (LLMs) use in-context learning (ICL) to solve a new task, they must infer latent concepts from demonstration examples. This raises the question of whether and how transformers represent latent structures as part…

Human languages have evolved to be structured through repeated language learning and use. These processes introduce biases that operate during language acquisition and shape linguistic systems toward communicative efficiency. In this paper,…