Related papers: Working Paper: Towards Schema-based Learning from …

This paper proposes a formal cognitive framework for problem solving based on category theory. We introduce cognitive categories, which are categories with exactly one morphism between any two objects. Objects in these categories are…

A new model of symbol grounding is presented, in which the structures of natural language, logical semantics, perception and action are represented categorically, and symbol grounding is modeled via the composition of morphisms between the…

Signal Temporal Logic (STL) has emerged as an expressive language for reasoning intricate planning objectives. However, existing STL-based methods often assume full observation and known dynamics, which imposes constraints on real-world…

This paper describes implementation details for a 3-level cognitive model, described in the paper series. The whole architecture is now modular, with different levels using different types of information. The ensemble-hierarchy relationship…

Large Language Models (LLMs) have demonstrated significant potential as autonomous software engineering (SWE) agents. Recent work has further explored augmenting these agents with memory mechanisms to support long-horizon reasoning.…

Exploring sparse reward multi-agent reinforcement learning (MARL) environments with traps in a collaborative manner is a complex task. Agents typically fail to reach the goal state and fall into traps, which affects the overall performance…

Span-level skill extraction from job advertisements underpins candidate-job matching and labor-market analytics, yet generative large language models (LLMs) often yield malformed spans, boundary drift, and hallucinations, especially with…

Deep reinforcement learning (RL) agents rely on shortcut learning, preventing them from generalizing to slightly different environments. To address this problem, symbolic method, that use object-centric states, have been developed. However,…

This work proposes a decentralized architecture, where individual agents aim at solving a classification problem while observing streaming features of different dimensions and arising from possibly different distributions. In the context of…

Semantic data and knowledge infrastructures must reconcile two fundamentally different forms of representation: natural language, in which most knowledge is created and communicated, and formal semantic models, which enable…

General purpose agents will require large repertoires of skills. Empowerment -- the maximum mutual information between skills and states -- provides a pathway for learning large collections of distinct skills, but mutual information is…

Approaches to Natural language processing (NLP) may be classified along a double dichotomy open/opaque - strict/adaptive. The former axis relates to the possibility of inspecting the underlying processing rules, the latter to the use of…

The scene graph generation (SGG) task involves detecting objects within an image and predicting predicates that represent the relationships between the objects. However, in SGG benchmark datasets, each subject-object pair is annotated with…

The integration of knowledge extracted from different models described by domain experts or from models generated by machine learning algorithms is strongly conditioned by the lack of an appropriated framework to specify and integrate…

Expertise is often built by learning from examples. This process, known as schema induction, helps us identify patterns from examples. Despite its importance, schema induction remains a challenging cognitive task. Recent advances in…

Malignant brain tumors have become an aggressive and dangerous disease that leads to death worldwide.Multi-modal MRI data is crucial for accurate brain tumor segmentation, but missing modalities common in clinical practice can severely…

While imitation learning has shown impressive results in single-task robot manipulation, scaling it to multi-task settings remains a fundamental challenge due to issues such as suboptimal demonstrations, trajectory noise, and behavioral…

Circuit schematics play a crucial role in analog integrated circuit design, serving as the primary medium for human understanding and verification of circuit functionality. While recent large language model (LLM)-based approaches have shown…

Representation learning on large-scale unstructured volumetric and surface meshes poses significant challenges in neuroimaging, especially when models must incorporate diverse vertex-level morphometric descriptors, such as cortical…

Spatial reasoning in large language models (LLMs) has gained increasing attention due to applications in navigation and planning. Despite strong general language capabilities, LLMs still struggle with spatial transformations and multi-step…