2 citations · 2 across the 2 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.LG2026
Continual Adaptation Across Modalities: Learning and Forgetting in Unified Multimodal Models
Xinrui Wang, Zhihao Chen, Jia Tang +4
Unified multimodal models (UMMs), which can process and generate diverse modalities within a single framework, have recently emerged as a powerful paradigm. However, when these mod…
cs.CV2026
Beyond the Linear Representation Hypothesis: Non-Linear Activation Steering in Text-to-Image Models
Muhammad Atif Butt, Paweł Skierś, Joost Van De Weijer +1
Mechanistic interpretability often relies on the Linear Representation Hypothesis (LRH), which assumes that high-level concepts are encoded as linear directions in activation space…