TILens turns technical updates into a focused daily brief: official releases,
trusted reporting, and practitioner analysis, deduplicated and organized by topic.
Written by Tara Khani, CEO & Co-Founder, Moorcheh.ai Can a $399 single-board computer index millions of technical documents, search video frames and audio logs in milliseconds, and run an 8B-class local LLM, all while…
Microsoft says its Bing search engine now has one billion monthly users. The company says those are humans — not The post Microsoft says Bing serves 1B people. Its next search engine isn’t for them. appeared first on…
arXiv:2611.10357v3 Announce Type: replace-cross Abstract: A generative recommender names each candidate with a short token sequence, a Semantic ID, and recommends by generating those tokens. Some generative…
arXiv:2611.18179v2 Announce Type: replace-cross Abstract: Medical AI systems that answer users' queries rely on retrieving medical knowledge from large document collections. In this context, finetuning general models on…
arXiv:2611.22503v1 Announce Type: new Abstract: Agentic search demands that a search engine move beyond per document relevance ranking to assemble document sets optimized for downstream LLM reasoning. Prior work…
arXiv:2611.18244v2 Announce Type: replace Abstract: Efficient sequential recommendation has emerged as a promising paradigm for providing real-time personalized service. To deploy models under resource-constrained…
arXiv:2611.22353v1 Announce Type: new Abstract: Dense retrieval is central to modern search, question answering, and retrieval-augmented generation, where high similarity is often treated as evidence of semantic…
arXiv:2611.22270v1 Announce Type: new Abstract: Patent prior-art searchers issue Boolean queries line by line, broadening to find relevant documents and narrowing until candidates can be screened. We distill 38,397…
arXiv:2607.29241v2 Announce Type: replace Abstract: Optimizing recommender models remains heavily reliant on manual iteration over architectures, objectives, and training strategies. While LLM-based agents can automate…
arXiv:2611.22079v1 Announce Type: new Abstract: Multi-vector retrieval models such as ColBERT achieve state-of-the-art effectiveness by representing documents as sets of token-level vectors and scoring via MaxSim, but…
arXiv:2611.21625v1 Announce Type: cross Abstract: Incident diagnosis requires retrieving source-linked operational evidence from large codebases. We evaluate graph-augmented retrieval for Apache Kafka using an…
arXiv:2611.22382v1 Announce Type: cross Abstract: Large language models (LLMs) have renewed interest in Page Stream Segmentation (PSS), splitting a multi-page file into its constituent documents. Yet published LLM…
arXiv:2611.22509v1 Announce Type: new Abstract: Real-world e-commerce queries often express user intent without naming a target product, and a single intent may be fulfilled by products from multiple categories.…
arXiv:2611.21974v1 Announce Type: new Abstract: Low-bit LLM quantization is useful only if a model preserves service-relevant accuracy, executes through supported GPU kernels, and meets measured memory and latency…
arXiv:2611.22274v1 Announce Type: new Abstract: In traditional recommender systems (RSs), textual information typically serves as auxiliary signals for representation learning. In contrast, in LLM-based RSs, textual…
arXiv:2508.21572v2 Announce Type: replace Abstract: Reproducing and comparing results in neural news recommendation research remains difficult due to fragmented codebases, inconsistent preprocessing pipelines, and tight…
arXiv:2611.21941v1 Announce Type: cross Abstract: We show that efficient and high-precision quantum associative retrieval is possible with an exponential complexity advantage with respect to the classical brute force…
arXiv:2611.22392v1 Announce Type: new Abstract: Listwise LLM rerankers cannot reliably rank hundreds of documents in a single call, and rely on schedules to orchestrate their calls. Parallel schedules split candidates…