3 papers
cs.AI2026
Multimodal Function Vectors for Visual Relations
Shuhao Fu, Esther Goldberg, Ying Nian Wu +1
Large Multimodal Models (LMMs) demonstrate impressive in-context learning abilities from few multimodal demonstrations, yet the internal mechanisms supporting such task learning re…
cs.CL2026
Relational Knowledge Distillation Using Fine-tuned Function Vectors
Andrea Kang, Yingnian Wu, Hongjing Lu
Representing relations between concepts is a core prerequisite for intelligent systems to make sense of the world. Recent work using causal mediation analysis has shown that a smal…
cs.AI2025
Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction
Aishni Parab, Hongjing Lu, Ying Nian Wu +1
Inductive reasoning enables humans to infer abstract rules from limited examples and apply them to novel situations. In this work, we compare an LLM-based hypothesis search framewo…