NeuronEye: Query-Guided Visual Concept Activation for Vision-Language Reasoning
Quick summary
arXiv:2609.38098v1 Announce Type: new Abstract: Current vision-language models (VLMs) encode visual information in dense hidden states where object identity, spatial layout, and local attributes are implicitly entangled rather than explicitly disentangled, limiting their ability to isolate and modulate the specific visual evidence required by a given language query. Inspired by sparse population coding and top-down modulation in biological vision, we introduce NeuronEye, a plug-in framework that constructs a sparse, concept-level neuron vocabulary from intermediate VLM representations and sele
Key takeaways
- arXiv:2609.38098v1 Announce Type: new Abstract: Current vision-language models (VLMs) encode visual information in dense hidden states where object identity, spatial layout, and local attributes are implicitly entangled rather than explicitly disentangled, limiting their ability to isolate and modulate the specific visual evidence required by a given language query.
- Inspired by sparse population coding and top-down modulation in biological vision, we introduce NeuronEye, a plug-in framework that constructs a sparse, concept-level neuron vocabulary from intermediate VLM representations and sele
Why it matters
“NeuronEye: Query-Guided Visual Concept Activation for Vision-Language Reasoning” should be evaluated beyond branding and benchmark scores. Its practical importance will emerge in task accuracy, latency, unit cost, safety and integration with real workflows.
Member comments