Related papers: Emergent Semantic Representations in World Models …
Emerging generative world models and vision-language-action (VLA) systems are rapidly reshaping automated driving by enabling scalable simulation, long-horizon forecasting, and capability-rich decision making. Across these directions,…
Recent studies show that auto-encoder based approaches successfully perform language generation, smooth sentence interpolation, and style transfer over unseen attributes using unlabelled datasets in a zero-shot manner. The latent space…
Learning structured task representations from human demonstrations is essential for understanding long-horizon manipulation behaviors, particularly in bimanual settings where action ordering, object involvement, and interaction geometry can…
Effective collaboration between embodied agents requires more than acting in a shared environment; it demands communication grounded in each agent's evolving understanding of the world. When agents can only partially observe their…
Embodied cognition argues that intelligence arises from sensorimotor interaction rather than passive observation. It raises an intriguing question: do modern vision-language models (VLMs), trained largely in a disembodied manner, exhibit…
Natural language offers an intuitive and flexible means for humans to communicate with the robots that we will increasingly work alongside in our homes and workplaces. Recent advancements have given rise to robots that are able to interpret…
Visual-spatial understanding, the ability to infer object relationships and layouts from visual input, is fundamental to downstream tasks such as robotic navigation and embodied interaction. However, existing methods face spatial…
Geospatial analysis lacks methods like the word vector representations and pre-trained networks that significantly boost performance across a wide range of natural language and computer vision tasks. To fill this gap, we introduce Tile2Vec,…
Human physical reasoning relies on internal "body" representations - coarse, volumetric approximations that capture an object's extent and support intuitive predictions about motion and physics. While psychophysical evidence suggests humans…
Molecular generative models often assume meaningful latent geometry, but apparent property predictability can reflect sequence-level shortcuts rather than chemical organization. We study this issue in an unsupervised autoregressive…
In recent years, more and more attention has been paid to the learning of 3D human representation. However, the complexity of lots of hand-defined human body constraints and the absence of supervision data limit that the existing works…
Much of model-based reinforcement learning involves learning a model of an agent's world, and training an agent to leverage this model to perform a task more efficiently. While these models are demonstrably useful for agents, every…
A world model is an internal model that simulates how the world evolves. Given past observations and actions, it predicts the future physical state of both the embodied agent and its environment. Accurate world models are essential for…
World models enable agents to predict future dynamics conditioned on actions, making the choice of latent representation central to planning and control. Such representations are often either learned directly from pixels with limited…
Vision-language models encode continuous geometry that their text pathway fails to express: a 6,000-parameter linear probe extracts hand joint angles at 6.1 degrees MAE from frozen features, while the best text output achieves only 20.0…
Recent findings in neuroscience suggest that the human brain represents information in a geometric structure (for instance, through conceptual spaces). In order to communicate, we flatten the complex representation of entities and their…
Understanding the latent space geometry of large language models (LLMs) is key to interpreting their behavior and improving alignment. Yet it remains unclear to what extent LLMs linearly organize representations related to semantic…
Representation learning seeks to expose certain aspects of observed data in a learned representation that's amenable to downstream tasks like classification. For instance, a good representation for 2D images might be one that describes only…
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…
How large language models (LLMs) align with the neural representation and computation of human language is a central question in cognitive science. Using representational geometry as a mechanistic lens, we addressed this by tracking…