Related papers: HALMA: Humanlike Abstraction Learning Meets Afford…

Human cognition excels at symbolic reasoning, deducing abstract rules from limited samples. This has been explained using symbolic and connectionist approaches, inspiring the development of a neuro-symbolic architecture that combines both…

The need for modelling causal knowledge at different levels of granularity arises in several settings. Causal Abstraction provides a framework for formalizing this problem by relating two Structural Causal Models at different levels of…

The seemingly infinite diversity of the natural world arises from a relatively small set of coherent rules, such as the laws of physics or chemistry. We conjecture that these rules give rise to regularities that can be discovered through…

Combining reinforcement learning with language grounding is challenging as the agent needs to explore the environment while simultaneously learning multiple language-conditioned tasks. To address this, we introduce a novel method: the…

LLM-based automated scoring approaches near-human performance, but scaling to new tasks remains bottlenecked by the per-item human configuration of upstream stages such as rubric construction. Human experts bypass this bottleneck through…

Meta learning is a promising solution to few-shot learning problems. However, existing meta learning methods are restricted to the scenarios where training and application tasks share the same out-put structure. To obtain a meta model…

Large Language Models (LLMs) have demonstrated impressive capabilities, yet their deployment in high-stakes domains is hindered by inherent limitations in trustworthiness, including hallucinations, instability, and a lack of transparency.…

Humans can ground natural language commands to tasks at both abstract and fine-grained levels of specificity. For instance, a human forklift operator can be instructed to perform a high-level action, like "grab a pallet" or a low-level…

Multi-Task Reinforcement Learning aims at developing agents that are able to continually evolve and adapt to new scenarios. However, this goal is challenging to achieve due to the phenomenon of catastrophic forgetting and the high demand of…

In the face of difficult exploration problems in reinforcement learning, we study whether giving an agent an object-centric mapping (describing a set of items and their attributes) allow for more efficient learning. We found this problem is…

Natural language is generated by people, yet traditional language modeling views words or documents as if generated independently. Here, we propose human language modeling (HuLM), a hierarchical extension to the language modeling problem…

Reinforcement learning agents deployed in the real world often have to cope with partially observable environments. Therefore, most agents employ memory mechanisms to approximate the state of the environment. Recently, there have been…

The compositional structure of language enables humans to decompose complex phrases and map them to novel visual concepts, showcasing flexible intelligence. While several algorithms exhibit compositionality, they fail to elucidate how…

Large language models (LLMs) have shown impressive capabilities across tasks such as mathematics, coding, and reasoning, yet their learning ability, which is crucial for adapting to dynamic environments and acquiring new knowledge, remains…

Analogical reasoning is a fundamental capacity of human cognition that allows us to reason abstractly about novel situations by relating them to past experiences. While it is thought to be essential for robust reasoning in AI systems,…

Multimodal Large Language Models (MLLMs) have become a powerful tool for integrating visual and textual information. Despite their exceptional performance on visual understanding benchmarks, measuring their ability to reason abstractly…

Despite the remarkable progress in neural models, their ability to generalize, a cornerstone for applications such as logical reasoning, remains a critical challenge. We delineate two fundamental aspects of this ability: compositionality,…

Abstraction is an important aspect of intelligence which enables agents to construct robust representations for effective decision making. In the last decade, deep networks are proven to be effective due to their ability to form…

Humans exhibit incredibly high levels of multi-modal understanding - combining visual cues with read, or heard knowledge comes easy to us and allows for very accurate interaction with the surrounding environment. Various simulation…

Achieving generalizable manipulation in unconstrained environments requires the robot to proactively resolve information uncertainty, i.e., the capability of active perception. However, existing methods are often confined in limited types…