23 papers · ranked by Valyu relevance
Lily E. Kramer, Marlene R. Cohen
Visual experience is organized in time. When riding the same bus route each day, the visual scene unfolds in a predictable order without requiring active choice. During goal-directed behavior, individuals organize actions into routines, such as repeatedly walking the same route to work even when alternatives are…
Ashena Gorgan Mohammadi, Manu Srinath Halvagal, Friedemann Zenke
Tracking prey or recognizing a lurking predator is as crucial for survival as anticipating their actions. To guide behavior, the brain must extract information about object identities and their dynamics from entangled sensory inputs. How it accomplishes this feat remains an open question. Predictive coding theories…
Antony W. N'dri, Thomas Barbier, Céline Teulière, Jochen Triesch
The ability to predict the future is of great value for biological and artificial cognitive systems alike. However, successfully predicting the future typically requires maintaining a memory of the recent past. It is currently unclear how biological or artificial spiking neural networks can learn to maintain past…
Natasa Ganea, Dominik Garber, Richard N. Aslin, David J. Lewkowicz
This study examined visual statistical learning using EEG-based steady-state visual evoked potentials (SSVEP). Fifty-one adults were exposed to image sequences organized into triplets across three conditions (n = 17 per condition) in which the alignment of category-level and exemplar-level information was manipulated.…
Mehdi Fatan Serj, C. Alejandro Parraga, Xavier Otazu
Object recognition plays a fundamental role in how biological organisms perceive and interact with their environment. While the human visual system performs this task with remarkable efficiency, reproducing similar capabil; n artificial systems remains challenging. This study investigates VisNet, a biologically…
Li-Ann Leow, Jarrad Lum, Sara Johnson, Emily Corti + 1 more
Musicians demonstrate advantages in acquiring motor sequences, showing faster learning and better explicit sequence knowledge than non-musicians. However, it is unclear whether this advantage extends beyond acquisition to the consolidation phase, which is when newly learned skills stabilize and become resistant to…
Asa Kucinkas, Chrysa Retsa, Peter B. L. Meijer, Mark T. Wallace + 2 more
Visual-to-auditory sensory substitution devices (SSDs) translate images to sounds. One SSD, The vOICe, translates a pixel’s vertical position into pitch and horizontal position into time. This mapping is primarily based on technical considerations for preserving image content in human-audible sounds without…
Maike Hille, Elisabeth Wenger, Eleftheria Papadaki, Yana Fandakova
Humans possess an astounding ability to acquire complex movement sequences with limited practice. Motor sequence learning engages a distributed network of brain regions that show distinct learning-related changes, often characterized by predominant involvement of the prefrontal cortex (PFC) early in learning and…
Mahmoud Rokaya, Dalia I. Hemdan, Mohammed A. Alzain, El-Sayed Atlam
Introduction A central limitation of existing temporal image analysis and video understanding models lies in their reliance on explicit motion cues, dense supervision, or auxiliary modalities, which constrains their ability to infer latent temporal structure, evolving semantic states, and long-range dependencies from…
Xukun Liu, Fengjuan Xie, Kai Xu, Zhenyu Liu + 3 more
Introduction Learning robust and temporally consistent manipulation policies from long-horizon visual observations remains a fundamental challenge in imitation learning. While recent Transformer-based approaches reduce compounding errors via temporally extended action chunks, most methods rely on deterministic or…
Carlos Schmidt, Simon Reiß
Visual in-context learning models are designed to adapt to new tasks by leveraging a set of example input-output pairs, enabling rapid generalization without task-specific fine-tuning. However, these models operate in a fundamentally static paradigm: while they can adapt to new tasks, they lack any mechanism to…
Li-Ann Leow, Jarrad Lum, Sara Johnson, Emily Corti + 1 more
Musicians demonstrate advantages in acquiring motor sequences, showing faster learning and better explicit sequence knowledge than non-musicians. However, it is unclear whether this advantage extends beyond acquisition to the consolidation phase, which is when newly learned skills stabilize and become resistant to…
Zhegong Shangguan, Alessandro Di Nuovo, Angelo Cangelosi
Robots are increasingly entering human-interactive scenarios that require understanding of quantity. How intelligent systems acquire abstract numerical concepts from sensorimotor experience remains a fundamental challenge in cognitive science and artificial intelligence. Here we investigate embodied numerical learning…
Michael Petrovski, Salwa Beheiry, Udichi U. Das, Simran Rooprai + 5 more
This study aims to address whether a new visual-motor-based learning paradigm with music can potentially promote neuroplasticity and create new interventional tools, building upon prior research that shows behavioral and putative neural changes following dance-based neurorehabilitation in people with Parkinson’s…
Joy Bose
The Thousand Brains Theory (TBT) and its open-source Monty framework model object recognition through sensorimotor inference -- identifying objects by actively moving a sensor across their surface and building evidence contact by contact. The current implementation encodes each contact as a dense floating-point vector.…
Mousa Karayanni, Maciej M. Jankowski, Yonatan Loewenstein, Israel Nelken
Few-shot learning reveals core mechanisms of flexible cognition and adaptive decision- making in animal behavior by showing how animals rapidly infer rules, categories, or action strategies from sparse experience. Few-shot learning often depends on abstract representations that capture task structure and generalize…
Fleming C. Peck, Hongjing Lu, Jesse Rissman
Humans readily extract statistical regularities from experience, yet natural environments require flexible adaptation when associative structures shift across changing contexts, often without warning. Across two experiments, we show that humans can incidentally learn overlapping and conflicting visual associations even…
Authors not listed
Infrared (IR) spectroscopy provides rich structural information but interpreting spectra at scale remains challenging. Here we introduce j-IR-vis, a vision-based neural model that learns chemically interpretable representations directly from IR spectra for functional-group prediction and downstream molecular…
Nikolaus Salvatore, Qiong Zhang
Past work has long recognized the important role of context in guiding how humans search their memory. While context-based memory models can explain many memory phenomena, it remains unclear why humans develop such architectures over possible alternatives in the first place. In this work, we demonstrate that…
Authors not listed
Machine olfaction—the artificial replication of the sense of smell—faces significant challenges due to the absence of large, standardized training datasets. Unlike vision, language, and audio models, which benefit from extensive corpora such as ImageNet, GLUE, and AudioSet, olfaction lacks scaled equivalents and…
Kathrin Korte, Joachim Winter Pedersen, Eleni Nisioti, Sebastian Risi
To preserve previously learned representations, continual learning systems must strike a balance between plasticity, the ability to acquire new knowledge, and stability. This stability-plasticity dilemma affects how representations can be reused across tasks: shared structure enables transfer when tasks are similar but…
Authors not listed
Inverse molecular design aims to generate novel chemical structures that satisfy multiple property constraints, yet reinforcement-learning (RL) fine-tuning can be sensitive to how objectives are converted into a scalar reward. Here, we systematically analyze how scalarization choices and stabilization mechanisms shape…
Authors not listed
Machine learning models are increasingly applied to heterogeneous materials datasets spanning different synthesis routes, measurement protocols, and structural classes. Although multi-task and representation-learning approaches are commonly used to improve predictive performance, the latent representations learned by…