Similar Items: Efficient Multivector Retrieval with Token-Aware Clustering and Hierarchical Indexing
- Taming Outlier Tokens in Diffusion Transformers
- Superintelligent Retrieval Agent: The Next Frontier of Information Retrieval
- Sharp Capacity Thresholds in Linear Associative Memory: From Winner-Take-All to Listwise Retrieval
- GRAPHLCP: Structure-Aware Localized Conformal Prediction on Graphs
- SpecKV: Adaptive Speculative Decoding with Compression-Aware Gamma Selection
- EASE: Federated Multimodal Unlearning via Entanglement-Aware Anchor Closure