Showing 2026Show all
2 papers · 1 filter
cs.CV2026
Vertical Fusion: Condensing Internal Representations for Robust ViT Classification
Francesco Di Salvo, Shyam Nandan Rai, Hamed Damirchi +4
Despite exposing rich intermediate representations, Vision Transformers (ViTs) are almost exclusively utilized as black-box feature extractors, where only the last layer is conside…
cs.CL2026
Truth as a Trajectory: What Internal Representations Reveal About Large Language Model Reasoning
Hamed Damirchi, Ignacio Meza De la Jara, Ehsan Abbasnejad +3
Existing explainability methods for Large Language Models (LLMs) typically treat hidden states as static points in activation space, assuming that correct and incorrect inferences…