5 papers
Fractional Decay KV-Cache: Ownership-Aware Memory Management for Improved Inference Relevancy in Dialog Systems
Sukanta Ganguly
Key-value (KV) caching is essential for efficient autoregressive inference in transformer based dialog systems, yet existing strategies treat all cached entries uniformly or apply…
PLACEMEM: Toward a Compute-Aware Memory Plane for Lifelong Agents
Sukanta Ganguly
Lifelong agents need more than larger context windows and better retrieval. They need memories that can persist, evolve, and be corrected without forcing the serving stack to recom…
HypRAG: Hyperbolic Dense Retrieval for Retrieval Augmented Generation
Hiren Madhu, Ngoc Bui, Ali Maatouk +6
Embedding geometry plays a fundamental role in retrieval quality, yet dense retrievers for retrieval-augmented generation (RAG) remain largely confined to Euclidean space. However,…
Your Embedding Model is SMARTer Than You Think
Jianrui Zhang, Hyun Jung Lee, Sukanta Ganguly +3
Multimodal retrieval relies heavily on single-vector retrievers, which compress rich, sequential token sequences into one single global representation. While efficient, they discar…
Reasoning-Augmented Representations for Multimodal Retrieval
Jianrui Zhang, Anirudh Sundara Rajan, Brandon Han +3
Universal Multimodal Retrieval (UMR) seeks any-to-any search across text and vision, yet modern embedding models remain brittle when queries require latent reasoning (e.g., resolvi…