Brain-inspired recurrent networks explain perceptual grouping dynamics in natural scenes
tserre · x · 2026-10-13
A preprint (arXiv:2610.05419) from Thomas Serre's Brown lab and Pieter Roelfsema's lab proposes a mechanistic framework for how the brain groups image elements into objects in natural scenes.
- Existing biological vision grouping models rely on simplified stimuli and fail on naturalistic behavior.
- Local boundary signals govern early grouping; later stages integrate top-down feedback carrying object identity, merging features across internal edges into coherent object representations.
- Instantiated as a brain-inspired recurrent neural network trained on natural images, the network propagates enhanced activity across cued objects and predicts human reaction times.
- The framework links cortical dynamics to human vision and yields testable predictions for neurophysiological and psychophysical experiments.
More from Research
- Google DeepMind hiring Summer 2027 research intern for continual learning — TheGradient · 2026-10-13
- Researcher argues reward-free imitation of verified completions inherits most of RLVR's problems — QuintinPope5 · 2026-10-13
- Proposal: replace online RL with imitation on verified successful trajectories — QuintinPope5 · 2026-10-13
- Thinking Inertia: LLMs keep reasoning even when explicitly told not to, Stanford-led study finds — StanfordUniversity · 2026-10-13
- SJTU's MAVLN: first systematic multi-agent vision-language navigation benchmark with 11,724 episodes — SJTU · 2026-10-13
- MSAR multi-stream attention residuals beat prior variants at 18B/28B MoE, 1.58x iso-loss speedup — SJTU · 2026-10-13