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.
38 articles · 5 sources · 37 papers ·
Top topics: Information Retrieval · AI Research · AI
Don't miss out! Join us at our next KubeCon + CloudNativeCon event in Salt Lake City, United States (Nov 9–12, 2026). Connect with our current graduated, incubating, and sandbox projects as the community gathers to…
arXiv:2610.40936v1 Announce Type: new Abstract: Recommendation systems that optimize for the average user can fail to capture the preferences of diverse demographic groups. We consider a dynamic recommendation system,…
arXiv:2610.41319v1 Announce Type: new Abstract: Map applications bridge everyday mobility with local services, creating opportunities to recommend places by uncovering users' implicit intents. However, utility-driven…
arXiv:2605.00826v2 Announce Type: replace Abstract: Text-to-video retrieval enables users to find relevant video content using natural language queries, a task that has grown increasingly important with the rapid…
arXiv:2610.41335v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) over visually rich documents must find both relevant content and the evidence that supports an answer. Screenshot retrieval preserves…
arXiv:2610.41360v1 Announce Type: new Abstract: In modern information retrieval (IR), documents are increasingly encountered as structured sequences of visually rich, paginated units, rather than as flat text. Example…
arXiv:2610.40971v1 Announce Type: cross Abstract: We present FieldGuideRAG, a training-free GraphRAG method in which a vision-language model, or VLM, recognizes fine-grained species by comparing the query with real…
arXiv:2610.36991v3 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) systems ground large language models (LLMs) by retrieving external evidence and conditioning generation on the retrieved…
arXiv:2610.40742v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) is vulnerable to knowledge poisoning, where adversaries manipulate retrieved evidence to influence model outputs. Existing defenses…
arXiv:2609.18296v2 Announce Type: replace Abstract: Traditional retrieval systems typically use multi-stage cascading architectures (MCA), where each module is optimized independently, leading to inconsistent objectives…
arXiv:2610.41172v1 Announce Type: new Abstract: Retrieval-augmented generation is becoming agentic. A search harness writes queries, reads results, reformulates, and decides when to stop. This largely solves accuracy: a…
arXiv:2610.41911v1 Announce Type: new Abstract: Location-based recommender systems shape where people go in cities and learn from the visits they steer, forming a human-AI feedback loop. This feedback loop shapes whom…
arXiv:2610.41905v1 Announce Type: new Abstract: An agent that must call several tools to fulfill a request fails when the tool retriever omits any one of them, yet tool retrievers are mostly built and evaluated on…
arXiv:2610.40658v1 Announce Type: new Abstract: Recommendation unlearning aims to remove the influence of specific historical interactions that should no longer affect future recommendations, such as noisy clicks or…
arXiv:2602.14960v2 Announce Type: replace Abstract: Neural retrieval systems are increasingly deployed in multi-domain settings, where each domain may have its own vocabulary and word distribution. A common approach is…
arXiv:2606.26439v2 Announce Type: replace Abstract: MaxSim scoring dominates the cost of multi-vector retrieval. Several groups built fused GPU kernels for it independently during 2026, and all report one measure of…
arXiv:2610.40768v1 Announce Type: new Abstract: The growing number of scientific submissions is straining the peer review process, while a large pool of relevant researchers remains unidentified and is therefore not…
arXiv:2610.41425v1 Announce Type: new Abstract: Cross-encoders are the most effective but also the least efficient models in Information Retrieval. Despite their success, the mechanisms underlying their relevance…
arXiv:2610.41521v1 Announce Type: new Abstract: Many long-term memory systems for LLM agents are built around embedding-based retrieval. Al- though effective for semantic matching, similarity ranking alone does not…
arXiv:2610.41552v1 Announce Type: cross Abstract: This study investigates the effectiveness of large pre-trained language models (LLMs) for knowledge entity relation extraction (KERE) from academic papers. Existing…
Showing 1 day · 38 items available
