Similar Items: Sharp Capacity Thresholds in Linear Associative Memory: From Winner-Take-All to Listwise Retrieval
- Superintelligent Retrieval Agent: The Next Frontier of Information Retrieval
- It Just Takes Two: Scaling Amortized Inference to Large Sets
- Efficient Multivector Retrieval with Token-Aware Clustering and Hierarchical Indexing
- Memory-Efficient Continual Learning with CLIP Models
- Continual Knowledge Updating in LLM Systems: Learning Through Multi-Timescale Memory Dynamics
- Tool Calling is Linearly Readable and Steerable in Language Models