Related papers: From Volume to Value: Preference-Aligned Memory Co…

Current human-AI alignment and evaluation methods for large language models (LLMs) often rely on preference signals collected immediately after an interaction. This practice implicitly treats preference as static, even though many…

Large-scale deployment of generative AI tools often depends on costly API calls to a Large Language Model (LLM) to fulfil user queries. To curtail the frequency of these calls, one can employ a smaller language model -- a student -- which…

Long-horizon personalization requires dialogue assistants to retrieve user-specific facts from extended interaction histories. In practice, many relevant facts often have low semanticsimilarity to the query under dense retrieval. Standard…

LLM inference on mobile devices faces extraneous challenges due to limited memory bandwidth and computational resources. To address these issues, speculative inference and processing-in-memory (PIM) techniques have been explored at the…

Processing in memory (PIM) moves computation into memories with the goal of improving throughput and energy-efficiency compared to traditional von Neumann-based architectures. Most existing PIM architectures are either general-purpose but…

Current approaches to lifelong personalization operationalize relevance through semantic proximity, causing them to miss essential user information from topically unrelated interactions. To address this gap, we introduce LUCid, a benchmark…

Mobile edge computing (MEC) is a prominent computing paradigm which expands the application fields of wireless communication. Due to the limitation of the capacities of user equipments and MEC servers, edge caching (EC) optimization is…

Embedding-based vector search underpins many important applications, such as recommendation and retrieval-augmented generation (RAG). It relies on vector indices to enable efficient search. However, these indices require storing…

Retrieval-Augmented Generation (RAG) systems typically face constraints because of their inherent mechanism: a simple top-k semantic search [1]. The approach often leads to the incorporation of irrelevant or redundant information in the…

Various incremental learning (IL) approaches have been proposed to help deep learning models learn new tasks/classes continuously without forgetting what was learned previously (i.e., avoid catastrophic forgetting). With the growing number…

Recommendation systems are highly interested in technology companies nowadays. The businesses are constantly growing users and products, causing the number of users and items to continuously increase over time, to very large numbers.…

Modeling multi-interests has arisen as a core problem in real-world RS. Current multi-interest retrieval methods pose three major challenges: 1) Interests, typically extracted from predefined external knowledge, are invariant. Failed to…

Processing-in-Memory (PIM) architectures offer promising solutions for efficiently handling AI applications in energy-constrained edge environments. While traditional PIM designs enhance performance and energy efficiency by reducing data…

As the Web transitions from static retrieval to generative interaction, the escalating environmental footprint of Large Language Models (LLMs) presents a critical sustainability challenge. Current paradigms indiscriminately apply…

Personalization is a core capability across consumer technologies, streaming, shopping, wearables, and voice, yet it remains challenged by sparse interactions, fast content churn, and heterogeneous textual signals. We present RecMind, an…

While general-purpose computing follows Von Neumann's architecture, the data movement between memory and processor elements dictates the processor's performance. The evolving compute-in-memory (CiM) paradigm tackles this issue by…

The Mixture-of-Experts (MoE) models have emerged as the state-of-the-art paradigm for scaling up large language models (LLMs) without proportionally increased computational cost. However, its on-device deployment faces a critical challenge…

Retrieval-augmented generation (RAG) for language models significantly improves language understanding systems. The basic retrieval-then-read pipeline of response generation has evolved into a more extended process due to the integration of…

Alignment of large language models (LLMs) with human preferences typically relies on supervised reward models or external judges that demand abundant annotations. However, in fields that rely on professional knowledge, such as medicine and…

Large Language Model (LLM)-based mobile agents have made significant performance advancements. However, these agents often follow explicit user instructions while overlooking personalized needs, leading to significant limitations for real…