Related papers: External Hippocampus: Topological Cognitive Maps f…
Whether large language models (LLMs) construct internal spatial world models from pure-text descriptions remains contested, and whether such capabilities transfer across languages has not been systematically studied. We introduce MentalMap,…
We propose a formal foundation for cognition rooted in algebraic topology, built on a Homological Parity Principle. This posits that even-dimensional homology represents stable Structure/Context (e.g., generative models), while…
While large language models (LLMs) leverage both knowledge and reasoning during inference, the capacity to distinguish between them plays a pivotal role in model analysis, interpretability, and development. Inspired by dual-system cognitive…
Comparative reasoning is a process of comparing objects, concepts, or entities to draw conclusions, which constitutes a fundamental cognitive ability. In this paper, we propose a novel framework to pre-train language models for enhancing…
Entropy-based deep reasoning has emerged as a promising direction for improving the reasoning capabilities of Large Language Models (LLMs), but existing methods often either increase response length indiscriminately or shorten responses at…
Current Large Language Models have achieved Olympiad-level logic, yet Vision-Language Models paradoxically falter on elementary spatial tasks like block counting. This capability mismatch reveals a critical ``spatial intelligence gap,''…
Spatial awareness in mammals is based on internalized representations of the environment---cognitive maps---encoded by networks of spiking neurons. Although behavioral studies suggest that these maps can remain stable for long periods, it…
Recent reasoning Large Language Models produce a chain-of-thought (CoT) predominantly in English, even when prompted in non-English languages. Prior work suggests that forcing the CoT to remain in the input language (\emph{native…
Large Language Models (LLMs) apply uniform computation to all tokens, despite language exhibiting highly non-uniform information density. This token-uniform regime wastes capacity on locally predictable spans while under-allocating…
Visual reasoning is crucial for understanding complex multimodal data and advancing Artificial General Intelligence. Existing methods enhance the reasoning capability of Multimodal Large Language Models (MLLMs) through Reinforcement…
Systems for language understanding have become remarkably strong at overcoming linguistic imperfections in tasks involving phrase matching or simple reasoning. Yet, their accuracy drops dramatically as the number of reasoning steps…
Recent progress in latent world models (e.g., V-JEPA2) has shown promising capability in forecasting future world states from video observations. Nevertheless, dense prediction from a short observation window limits temporal context and can…
Multimodal large language models (MLLMs) have recently demonstrated strong capabilities in understanding and generating responses from diverse visual inputs, including high-resolution images and long video sequences. As these models scale…
Vision-language models (VLMs) have shown strong performance on static visual understanding, yet they still struggle with dynamic spatial reasoning that requires imagining how scenes evolve under egocentric motion. Recent efforts address…
Language models have been shown to perform remarkably well on a wide range of natural language processing tasks. In this paper, we propose LEAP, a novel system that uses language models to perform multi-step logical reasoning and…
The limited reasoning capabilities of small language models (SLMs) cast doubt on their suitability for tasks demanding deep, multi-step logical deduction. This paper introduces a framework called Small Reasons, Large Hints (SMART), which…
To make effective decisions in novel environments with long-horizon goals, it is crucial to engage in hierarchical reasoning across spatial and temporal scales. This entails planning abstract subgoal sequences, visually reasoning about the…
While large language models (LLMs) have demonstrated remarkable reasoning capabilities, they often struggle with complex tasks that require specific thinking paradigms, such as divide-and-conquer and procedural deduction, \etc Previous…
Neurons in the brain are spatially organized such that neighbors on tissue often exhibit similar response profiles. In the human language system, experimental studies have observed clusters for syntactic and semantic categories, but the…
Large language models (LLMs) encode knowledge in parametric weights, making it costly to update or extend without retraining. Retrieval-augmented generation (RAG) mitigates this limitation by appending retrieved text to the input, but…