arXiv:2606. 06664v1 Announce Type: cross Abstract: Despite high accuracy, Vision Transformer (ViT) predictions can be driven by spurious cues, raising the need to understand their inner workings before safe deployment.
arXiv:2608. 14922v1 Announce Type: cross Abstract: Mechanistic interpretability has recently expanded to Vision Transformers (ViTs), with Sparse Autoencoders (SAEs) increasingly used as post-hoc tools to decompose internal representations into sparse and more interpretable features.
arXiv:2605.22902v2 Announce Type: replace-cross Abstract: Generative Vision-Language Models (VLMs) perform well on multimodal reasoning, but how visual inputs are transformed to text remains poorly u...
arXiv:2607. 07316v1 Announce Type: new Abstract: This article offers a comprehensive overview of mechanistic interpretability, an emerging field that seeks to reverse-engineer the internal algorithms of modern neural networks.
arXiv:2607. 08605v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have emerged as a promising technique for mechanistic interpretability by learning a set of sparse latent features in large models, each of which encodes a distinct concept.
arXiv:2606. 16193v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-language tasks, yet their internal visual representations remain difficult to interpret.
arXiv:2607. 00089v1 Announce Type: new Abstract: Mechanistic interpretability has produced a rich inventory of component-level analyses that characterise what neural-network components encode and how they interact.
NeuronEye is a plug‑in framework that builds a sparse, concept‑level neuron vocabulary from intermediate vision‑language model (VLM) representations and selectively activates query‑relevant visual concepts during inference. It decomposes vision‑token states into an overcomplete sparse basis organized by concept clusters, uses the language query to activate relevant clusters, localizes the corresponding image patches, and injects the focused evidence back into the vision tokens, while a suppression mechanism attenuates dominant perceptual directions. Experiments on Qwen2.5‑VL‑7B and LLaVA‑1.6‑7B show that NeuronEye improves CV‑Bench overall accuracy by +3.1, boosts Distance by +9.5, and raises BLINK Multi‑view by +8.3, indicating that sparse neuron vocabularies can act as active interfaces for concept‑level visual reasoning.
arXiv:2511. 19418v3 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) excel at reasoning in linguistic space but struggle with perceptual understanding that requires dense visual perception, e.
arXiv:2606. 24716v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are increasingly used to extract interpretable concepts from vision and vision language models, yet existing evaluation methods largely rely on proxy metrics or qualitative inspection rather than measuring semantic correspondence.
arXiv:2607. 04593v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated impressive capabilities across different tasks, but their computational cost is dominated by the large number of visual tokens fed to the language model.
arXiv:2609.13198v1 Announce Type: new Abstract: One of the pivotal recent challenges in neural network interpretability is polysemanticity, where a single neuron is activated by multiple, often unrel...
arXiv:2603. 23867v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) have been applied to a wide range of reasoning tasks, yet it remains unclear whether they can reason robustly under distribution shifts.