AI.info

Zeynep Akata

Explore Zeynep Akata on AI.info.

• Are Reasoning LLMs Robust to Interventions on Their Chain-of-Thought?
• Dissecting Multimodal In-Context Learning: Modality Asymmetries and Circuit Dynamics in modern Transformers
• TimeSAE: Causal Sparse Decoding for Faithful Explanations of Black-Box Time Series Models
• A Systematic Study of In-the-Wild Model Merging for Large Language Models
• Sparse Autoencoders are Topic Models