The field of cognitive computing and AI is rapidly advancing, with a focus on developing more sophisticated and human-like intelligence. Recent research has explored the alignment between popular CNN architectures and human brain processing, with findings suggesting that CNNs struggle to go beyond simple visual processing. Meanwhile, the development of multimodal large language models (MLLMs) has enabled more accurate emotion recognition and reasoning, with applications in areas such as virtual reality and human-computer interaction. Noteworthy papers in this area include 'Bridging the behavior-neural gap: A multimodal AI reveals the brain's geometry of emotion more accurately than human self-reports', which demonstrates the ability of MLLMs to develop rich, neurally-aligned affective representations, and 'The Dragon Hatchling: The Missing Link between the Transformer and Models of the Brain', which introduces a new large language model architecture based on a scale-free biologically inspired network. These advances have significant implications for the development of more intelligent and human-like AI systems, and highlight the importance of interdisciplinary research in cognitive computing and AI.
Advances in Cognitive Computing and AI
Sources
Assessing the Alignment of Popular CNNs to the Brain for Valence Appraisal
AI for Sustainable Future Foods
Bacterial Gene Regulatory Neural Network as a Biocomputing Library of Mathematical Solvers
Incorporating Scene Context and Semantic Labels for Enhanced Group-level Emotion Recognition
Customizing Visual Emotion Evaluation for MLLMs: An Open-vocabulary, Multifaceted, and Scalable Approach
Understanding Cognitive States from Head & Hand Motion Data
Bridging the behavior-neural gap: A multimodal AI reveals the brain's geometry of emotion more accurately than human self-reports
Exploring Similarity between Neural and LLM Trajectories in Language Processing
Multimodal Large Language Models Meet Multimodal Emotion Recognition and Reasoning: A Survey
Enabling Physical AI through Biological Principles
Inducing Dyslexia in Vision Language Models
Neural network embeddings recover value dimensions from psychometric survey items on par with human data
Information Transmission in Quorum Sensing for Gut Microbiome
Plug-and-Play Emotion Graphs for Compositional Prompting in Zero-Shot Speech Emotion Recognition
Anticipatory Structure in the Propagation of Signal
The Dragon Hatchling: The Missing Link between the Transformer and Models of the Brain
Identifying Information-Transfer Nodes in a Recurrent Neural Network Reveals Dynamic Representations