Topic - Edition
arXiv:2610.11451v1 Announce Type: cross Abstract: We introduce SAIL, an open model with 35B total and 3B active parameters for literature research, scientific coding, and multi-step research workflows. SAIL is developed…
arXiv:2610.10955v1 Announce Type: new Abstract: Conversational Query Rewriting (CQR) turns a context dependent user turn into a standalone query for a retriever, and most methods do this in a single step from the…
arXiv:2609.30717v2 Announce Type: replace Abstract: Recent advances in agentic recommender systems are shifting recommender systems from passive filtering engines to instruction-following agents that use external tools…
arXiv:2607.28397v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) over knowledge graphs requires retrievers that can effectively capture both graph structure and semantic information. Recent…
arXiv:2610.11816v1 Announce Type: new Abstract: Dense retrievers have made significant progress on text and image corpora, but whether these capabilities extend reliably to mixed corpora containing text, image, and…
arXiv:2605.28510v3 Announce Type: replace-cross Abstract: Large language models (LLMs) for code completion and generation are increasingly used in software development, yet they may reproduce training examples verbatim…
arXiv:2610.11277v1 Announce Type: new Abstract: Point-of-Interest (POI) reranking in local search must model query-conditioned tradeoffs among lexical semantics, geospatial proximity, and numerical quality signals such…
arXiv:2605.28888v2 Announce Type: replace Abstract: Real-world user behavior rarely consists of isolated actions; instead, it often forms intent flows governed by spatiotemporal dependencies. To provide integrated…
arXiv:2610.11489v1 Announce Type: cross Abstract: Visual instance retrieval often fails when the same object appears at different apparent sizes in the query and gallery. We show that the dominant cause is usually not…
arXiv:2610.12300v1 Announce Type: new Abstract: This paper investigates how to substantially reduce the memory footprint of learned sparse retrieval indexes without sacrificing the efficiency of state-of-the-art…
arXiv:2609.01913v2 Announce Type: replace Abstract: In product entity resolution, relationship definitions constantly evolve with business needs, yet adapting to each change traditionally requires slow, costly human…
arXiv:2510.18239v4 Announce Type: replace Abstract: Scaling large recommendation systems requires advancing three major frontiers: processing longer user histories, expanding candidate sets, and increasing model…
arXiv:2610.12243v1 Announce Type: new Abstract: Dense retrieval usually ranks text chunks by their semantic similarity to a question. This ignores structure that many data systems already store, including section…
arXiv:2610.11598v1 Announce Type: new Abstract: In this paper, we provide an overview of the NTCIR-19 Automatic Evaluation of LLMs 2 (AEOLLM-2) task. Building on the success of the NTCIR-18 core task AEOLLM, we proposed…
arXiv:2610.10556v1 Announce Type: new Abstract: Cascaded recommender systems use the same user history for retrieval and ranking, while the two stages have access to different information at different points of an…
arXiv:2610.11666v1 Announce Type: new Abstract: Universal multimodal retrieval typically encodes a query once and ranks independently indexed items by embedding similarity. This design supports efficient search, but…
arXiv:2610.11650v1 Announce Type: new Abstract: Similar agent skills can share instructions but differ in their conditions of use. Query-based text selection may retain shared instructions and omit these distinctions.…
arXiv:2610.11553v1 Announce Type: new Abstract: Accurate and scalable visual document retrieval (VDR) requires both fine-grained page understanding and efficient indexing, yet existing approaches struggle to achieve…
arXiv:2610.08077v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) turns agent experience into learning signals primarily through scalar outcome rewards after interaction.…
arXiv:2610.12256v1 Announce Type: cross Abstract: Omnimodal embeddings naturally involve both shared representations and modality-specific features across heterogeneous inputs. However, existing omnimodal embedding…
30 items available
