Pixels over Symbols: Sensory Realism Improves Behavioral Alignment in Models of Cognition
q-bio.NC, cs.AI
Submitted: 2026-11-07
Updated: 2026-11-07
Code: https://github.com/BashivanLab/pixels-over-symbols
Project page: https://rdh1115.github.io/abs_nat_psychopy_mturk
Terminology
Sources
- Scaling and context steer LLMs along the same computational path as the human brain
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Going Deeper with Convolutions
- Layer Normalization
- Gaussian Error Linear Units (GELUs)
- Decoupled Weight Decay Regularization
- Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas
- Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models
- What's "up" with vision-language models? Investigating their struggle with spatial reasoning
- An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models
- DINOv3
- Large Language Models as General Pattern Machines
- Understanding intermediate layers using linear classifier probes
- EVA-CLIP: Improved Training Techniques for CLIP at Scale
- Qwen3 Technical Report
Related papers
- Self-Supervised Learning of Local Predictive Directions as a Neural Computation
- Synchronized Hearts, Desynchronized Brains: A Nonlinear Dynamics Perspective for Function and Failure
- Message interaction dynamics covary with brain volume across mammalian connectomes
- Planning as Dynamics Relaxation: Hippocampal Recurrent Network Realizes Optimal Goal-Directed Navigation
- The Platonic brain bridge hypothesis: brain networks as architectural priors for multimodal large language models
- BrainPFN: Amortized Brain-Behaviour Prediction via Prior-Data Fitted Networks