Daily edition · Information Retrieval
TILens turns technical updates into a focused daily brief: official releases, trusted reporting, and practitioner analysis, deduplicated and organized by topic.
26 articles · 4 sources · 24 papers ·
Top topics: Information Retrieval · AI · AI Research
In this demo, Nisa Meshal (Customer Engineer, Google) introduces BM25 on AlloyDB & Cloud SQL. Key highlights include: Introducing the BM25 index's use case & comparing it with other supported indexes. A demo showcasing…
PouchDB is the reason a lot of us believed offline-first was practical at all. It landed in 2012 with a simple, powerful idea: run a database in the browser that speaks the CouchDB replication protocol, and let the two…
arXiv:2605.29271v2 Announce Type: replace-cross Abstract: Tool retrieval over large API catalogs is a core bottleneck for LLM agents: user queries arrive in colloquial, often underspecified language, while the catalog…
arXiv:2609.12754v1 Announce Type: new Abstract: Data-product discovery searches a full lake even when workloads revisit related products and regions. Repetition permits contracted search, but similarity cannot justify a…
arXiv:2609.11951v1 Announce Type: new Abstract: Long-term memory enables personalized agents, but its value depends on retrieving the right evidence at the right time. Most memory systems use static top-k retrieval:…
arXiv:2609.11970v1 Announce Type: cross Abstract: Qualitative research is widely used in the human and social sciences, characterized by a deep understanding of phenomena through the interpretation of meanings and…
arXiv:2609.11942v1 Announce Type: new Abstract: Recommender systems are usually framed as ranking systems: platforms observe users, construct candidate sets, and select items on their behalf. This framing hides a deeper…
arXiv:2609.11945v1 Announce Type: new Abstract: For two decades, recommender systems have been designed under the assumption that a human directly consumes each recommendation: receiving, interpreting, and acting upon…
arXiv:2609.12556v1 Announce Type: new Abstract: Long-sequence generative recommendation methods autoregressively model the user's interaction sequence to generate the next-item representation. Existing methods generally…
arXiv:2609.12766v1 Announce Type: new Abstract: Offline replay should estimate what a discovery system could retrieve at a historical point, yet freezing the corpus leaves interaction memory unconstrained. We formalize…
arXiv:2609.12679v1 Announce Type: new Abstract: Construction workers face workplace risks such as fatigue, heat stress, and other physically demanding conditions that can negatively affect their health and safety.…
arXiv:2609.11943v1 Announce Type: new Abstract: Recent advances in generative AI have substantially accelerated the creation of high-quality ad creatives, dramatically expanding the number of candidate variants per…
arXiv:2603.18516v2 Announce Type: replace Abstract: Deep research agents have emerged as LLM-based systems designed to perform multi-step information seeking and reasoning over large, open-domain sources to answer…
arXiv:2606.10388v3 Announce Type: replace Abstract: Agent skill libraries are becoming routable software assets: a retrieved skill can contribute instructions, scripts, resource bindings, and execution assumptions to an…
arXiv:2609.10046v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly used as interfaces for information retrieval, but they remain prone to hallucinations and faithfulness errors, in which…
arXiv:2609.12399v1 Announce Type: cross Abstract: Generative recommendation (GR) relies on large-beam decoding to generate hundreds of candidate items, creating a new scaling challenge for recurrent linear attention.…
arXiv:2609.12791v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) has empowered Large Language Models (LLMs) to tackle knowledge-intensive tasks. However, navigating global, heterogeneous knowledge…
arXiv:2609.13073v1 Announce Type: cross Abstract: Recent breakthroughs in LLM-based systems and their abilities in problem solving and coding have allowed progress in the AI for Science paradigm, potentially replacing…
arXiv:2509.11080v4 Announce Type: replace Abstract: Recommender systems (RecSys) have been widely applied to various applications, including E-commerce, finance, healthcare, social media and have become increasingly…
arXiv:2609.12268v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) can improve knowledge-intensive question answering, but the first design choice is easy to overlook: how should the source corpus be…
Showing 1 day · 26 items available
